CN118565827B - Gas turbine generator set state monitoring and fault diagnosis method and system - Google Patents
Gas turbine generator set state monitoring and fault diagnosis method and system Download PDFInfo
- Publication number
- CN118565827B CN118565827B CN202411050827.3A CN202411050827A CN118565827B CN 118565827 B CN118565827 B CN 118565827B CN 202411050827 A CN202411050827 A CN 202411050827A CN 118565827 B CN118565827 B CN 118565827B
- Authority
- CN
- China
- Prior art keywords
- generator set
- gas turbine
- turbine generator
- oil
- oil sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000003745 diagnosis Methods 0.000 title claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 136
- 230000008859 change Effects 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 239000007789 gas Substances 0.000 claims description 150
- 238000005299 abrasion Methods 0.000 claims description 31
- 230000015556 catabolic process Effects 0.000 claims description 31
- 238000006731 degradation reaction Methods 0.000 claims description 31
- 239000007788 liquid Substances 0.000 claims description 26
- 239000002245 particle Substances 0.000 claims description 24
- 239000000126 substance Substances 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 13
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 12
- 239000001301 oxygen Substances 0.000 claims description 12
- 229910052760 oxygen Inorganic materials 0.000 claims description 12
- 239000002923 metal particle Substances 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000006866 deterioration Effects 0.000 claims description 2
- 238000012854 evaluation process Methods 0.000 claims description 2
- 230000036541 health Effects 0.000 abstract description 2
- 238000005461 lubrication Methods 0.000 description 4
- 238000007792 addition Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002585 base Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007254 oxidation reaction Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- MYMOFIZGZYHOMD-UHFFFAOYSA-N Dioxygen Chemical compound O=O MYMOFIZGZYHOMD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/26—Oils; Viscous liquids; Paints; Inks
- G01N33/28—Oils, i.e. hydrocarbon liquids
- G01N33/2888—Lubricating oil characteristics, e.g. deterioration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
Landscapes
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- General Chemical & Material Sciences (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to the technical field of generator set fault diagnosis, in particular to a method and a system for monitoring the state of a gas turbine generator set and diagnosing faults, which are characterized in that oil samples of the gas turbine generator set under normal operation conditions are collected and used as reference oil samples, the oil samples are collected periodically in the operation process of the gas turbine generator set according to a preset date interval in a preset period, the oil samples are compared with the reference oil samples, analyzing the physicochemical property change evaluation coefficients of all the oil samples, further evaluating the state information of the gas turbine generator set, if the state information of the gas turbine generator set is evaluated to be an early warning state, carrying out deep detection analysis on all the oil samples, judging the fault type of the gas turbine generator set, and providing information of the bearing running state through monitoring indexes in the oil during oil collection analysis, so that the real-time monitoring and evaluation of the bearing health condition are realized, and early warning is realized.
Description
Technical Field
The invention belongs to the technical field of generator set fault diagnosis, and relates to a gas turbine generator set state monitoring and fault diagnosis method and system.
Background
Offshore platforms are widely used for offshore oil and gas drilling and production, and play an extremely important role in economic production. Due to the distance from the coast, the power is generated from the power generator to the whole offshore platform equipment. This makes the generator set the most important equipment on the platform. For platforms that produce natural gas, gas turbine power generation units typically become the primary generator on the platform.
The generator in the generator set is a large generator, the bearings at the two ends of the generator set are sliding bearings, and the lubrication mode is hydrodynamic lubrication. Once the bearing bush lubrication of the generator bearing is abnormal, the risk of shutdown of the generator set is caused, and the production and life of the whole offshore platform are seriously affected. Therefore, it is highly necessary to perform diagnostic analysis on lubrication failure of the offshore platform generator.
The prior art mainly aims at bearing fault diagnosis of a gas turbine generator set by arranging a sensor, but early signals of bearing faults are difficult to accurately capture under complex working conditions, so that faults are often found when the severity is high, and the reliability and safety of equipment are affected.
Disclosure of Invention
In view of the above problems in the prior art, the present invention provides a method and a system for monitoring the status and diagnosing faults of a gas turbine generator set, which are used for solving the above technical problems.
In order to achieve the above and other objects, the present invention adopts the following technical scheme:
In one aspect, the present invention provides a method for monitoring the condition and diagnosing faults of a gas turbine generator set, comprising the steps of:
Step S1, collecting an oil sample of the gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
S2, simply recording the oil samples collected in each sampling date as each oil sample, comparing each oil sample with a reference oil sample, and analyzing the physicochemical property change evaluation coefficients of each oil sample;
step S3, evaluating the state information of the gas turbine generator set, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, further executing step S4, otherwise, jumping out of the step circulation;
And S4, carrying out deep detection analysis on each oil sample, judging the bearing wear evaluation index of the gas turbine generator set, and further obtaining the fault reason of the corresponding bearing of the gas turbine generator set.
The physical and chemical property change evaluation coefficients of each oil sample are analyzed by the following specific analysis processes:
Extracting all physical and chemical indexes corresponding to the detection of the oil liquid sample from a unit database, and screening out all key physical and chemical indexes corresponding to the detection of the oil liquid sample from the physical and chemical indexes;
Respectively obtaining index values of the oil samples and the reference oil samples corresponding to the key physicochemical indexes according to the detection instrument;
analyzing to obtain the change rate of each oil sample and each key physicochemical index corresponding to the reference oil sample ，Is the index value of the kth oil sample corresponding to the q key physicochemical index,The index value of the q-th key physicochemical index corresponding to the reference oil sample is k, k is the number of each oil sample, k=1, 2,..i, q is the number of each key physicochemical index, q=1, 2,..j;
finally analyzing to obtain the physicochemical property change evaluation coefficient of each oil sample ，The q is the weight value of the q-th key physical and chemical index, and j is the total number of the key physical and chemical indexes.
Exemplary, each key physicochemical index of the oil liquid sample corresponding detection is screened out, and the specific screening process is as follows:
obtaining fault duration time of gas turbine generator set corresponding to each historical fault frequency from a set database And synchronously collecting index values corresponding to physical and chemical indexes corresponding to each historical failure frequency of the gas turbine generator setP is the number of each historical failure number, p=1, 2,..m, c is the number of each physicochemical index, c=1, 2,..n;
calculating to obtain the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set M and n respectively represent the total times of historical faults and the total number of physical and chemical indexes;
And comparing the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set with a predefined linear correlation coefficient reference set, and if the correlation coefficient of a physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set is within the predefined linear correlation coefficient reference set, marking the physicochemical index as a key physicochemical index, and screening out each key physicochemical index detected correspondingly by the oil liquid sample in an analysis mode.
The weight value of each key physicochemical index is exemplified, and the specific acquisition process is as follows:
acquiring index values of each oil sample corresponding to each key physicochemical index And subjecting it to standardization treatment;
calculating the calculated specific gravity value of each key physicochemical index in each oil sample Thereby further calculating the calculated entropy value of each key physicochemical index in the oil sampleWherein；
Finally, calculating the weight value of each key physicochemical index。
Illustratively, the state information of the gas turbine generator set is evaluated by:
s3-1, comparing the physicochemical property change evaluation coefficient of each oil sample with a predefined physicochemical property change evaluation threshold coefficient, if the physicochemical property change evaluation coefficient of a certain oil sample is larger than the predefined physicochemical property change evaluation threshold coefficient, judging the state information of the gas turbine generator set as an early warning state, and if the physicochemical property change evaluation coefficient of each oil sample is smaller than or equal to the predefined physicochemical property change evaluation threshold coefficient, executing the step S3-2;
Step S3-2, through analysis formula Analyzing to obtain average change rate of the oil sample corresponding to the physicochemical property change evaluation coefficientT is a preset date interval,Representing the physicochemical property change evaluation coefficient of the i-1 th oil sample;
step S3-3, calculating to obtain physicochemical property change evaluation coefficients corresponding to oil samples in the next acquisition date after a preset period ，And (3) for arranging the physicochemical property change evaluation coefficient of the last oil sample in the acquisition date in the preset period, comparing the physicochemical property change evaluation coefficient of the oil sample in the next acquisition date after the preset period with a predefined physicochemical property change evaluation threshold coefficient, and judging the state information of the gas turbine generator set as an early warning state in the same way if the physicochemical property change evaluation coefficient of the oil sample in the next acquisition date is larger than the predefined physicochemical property change evaluation threshold coefficient, otherwise judging the state information of the gas turbine generator set as a normal state.
Illustratively, the bearing wear rating index of the gas turbine generator set is determined by:
Testing each oil sample by using an automatic particle counter to further determine the number of metal particles in each oil sample ；
Obtaining the corresponding ISO grade of each oil sample；
Extracting a base line ISO grade from a unit database, and calculating a first assessment index of bearing wear of a gas turbine generator unit，For a predefined rating index correction value;
identifying abrasion particles in each oil sample by using a scanning electron microscope, further processing abrasion particle images captured in each oil sample by using image analysis software, and acquiring size factors and shape factors of each oil sample corresponding to each abrasion particle;
According to the size factor and the shape factor of each abrasion particle corresponding to each oil sample, the abrasion type screening is carried out on each abrasion particle in each oil sample, so that the number, the size factor and the shape factor of the abrasion particles corresponding to each abrasion type in each oil sample are obtained;
Calculating a second assessment index of bearing wear of a gas turbine generator set S is the number of each wear type,For the volume of the kth oil sample,The number, the size factor and the shape factor of the abrasion particles corresponding to the s abrasion type in the kth oil sample are respectively;
And adding the first bearing wear evaluation index and the second bearing wear evaluation index of the gas turbine generator set, and calculating the addition result by the term number 2 to obtain the bearing wear evaluation index of the gas turbine generator set.
Illustratively, the failure causes of the corresponding bearings of the gas turbine generator set are specifically classified into oil degradation causes, external pollution causes, and equipment friction causes.
The fault cause of the corresponding bearing of the gas turbine generator set is obtained by an exemplary method, and the specific acquisition process is as follows:
Testing each oil sample to obtain a rotary oxygen bomb test value of each oil sample, and further calculating to obtain an oil product degradation evaluation grade of the oil sample in a preset period corresponding to the gas turbine generator set;
testing each oil sample to obtain the moisture content and oil film strength value of each oil sample, and further calculating to obtain the external pollution evaluation grade of the oil sample in the corresponding preset period of the gas turbine generator set;
Comparing the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set oil quality degradation evaluation reference grade of the generator set, simultaneously comparing the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set external pollution evaluation reference grade of the generator set, and if the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set oil quality degradation evaluation reference grade of the generator set and the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set external pollution evaluation reference grade of the generator set, marking the fault cause of the bearing corresponding to the gas turbine generator set as both the oil quality degradation cause and the external pollution cause, otherwise marking the fault cause of the bearing corresponding to the gas turbine generator set as the equipment friction cause;
If the oil product degradation evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is larger than the set oil product degradation evaluation reference level of the generator set and the external pollution evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is smaller than or equal to the set external pollution evaluation reference level of the generator set, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the oil product degradation reason, otherwise, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the external pollution reason.
In another aspect, the present invention provides a gas turbine generator set condition monitoring and fault diagnosis system comprising:
The oil liquid sample collection module: the method comprises the steps of collecting an oil sample of a gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
sample comparison analysis module: the oil samples collected in each sampling date are simply recorded as oil samples, the oil samples are compared with a reference oil sample, and the physicochemical property change evaluation coefficients of the oil samples are analyzed;
The unit state evaluation module: the state information of the gas turbine generator set is evaluated, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, a fault type judging module is further executed;
A fault type judging module: and carrying out deep detection analysis on each oil sample so as to judge the bearing wear evaluation index of the gas turbine generator set, and further obtaining the fault reason of the corresponding bearing of the gas turbine generator set.
As described above, the method and system for monitoring the state and diagnosing the fault of the gas turbine generator set provided by the invention have the following beneficial effects:
According to the method and the system for monitoring the state of the gas turbine generator set and diagnosing faults, the oil samples of the gas turbine generator set under the normal operation condition are collected to be used as reference oil samples, the oil samples are periodically collected in the operation process of the gas turbine generator set according to the preset date interval in the preset period, the sampling date is recorded, the oil samples and the reference oil samples are compared, the physicochemical property change evaluation coefficient of the oil samples is analyzed, the state information of the gas turbine generator set is further evaluated, if the state information of the gas turbine generator set is obtained through evaluation, the state information of the gas turbine generator set is in an early warning state, the oil samples are subjected to deep detection analysis to judge the fault type of the gas turbine generator set, and the oil collection analysis is carried out on the gas turbine generator set to help find the signs of bearing faults in advance, so that important benefits and necessity are achieved. Firstly, oil liquid collection and analysis can provide information of the running state of the bearing by monitoring indexes such as metal particles, oxidation products, moisture and the like in the oil liquid, so that the real-time monitoring and evaluation of the health condition of the bearing are realized. The method is favorable for timely finding out the symptoms of the bearing faults, early warning is carried out in advance, and equipment damage and shutdown loss caused by further development of the faults are avoided. And secondly, the oil liquid collection analysis can help to determine the specific cause of the bearing fault, can judge the nature and the severity of the bearing fault more accurately, provides an important reference basis for subsequent maintenance and repair, can realize early monitoring and diagnosis of the bearing fault, determine the cause of the fault, optimize the maintenance strategy, improve the reliability of equipment, reduce the running cost and have important benefits and necessity.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram showing the connection of the steps of the method of the present invention.
FIG. 2 is a schematic diagram of the connection of the modules of the system of the present invention.
Detailed Description
The foregoing is merely illustrative of the principles of the invention, and various modifications, additions and substitutions for those skilled in the art will be apparent to those having ordinary skill in the art without departing from the principles of the invention or from the scope of the invention as defined in the accompanying claims.
Example 1
Referring to FIG. 1, a method for monitoring the condition and diagnosing faults in a gas turbine generator set, the method comprising the steps of:
Step S1, collecting an oil sample of the gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
S2, simply recording the oil samples collected in each sampling date as each oil sample, comparing each oil sample with a reference oil sample, and analyzing the physicochemical property change evaluation coefficients of each oil sample;
the specific numbers of the oil samples collected in each sampling date are sequentially numbered according to the sequence of the sampling dates.
In the preferred technical scheme of the application, the physicochemical property change evaluation coefficients of each oil sample are analyzed, and the specific analysis process is as follows:
Extracting all physical and chemical indexes corresponding to the detection of the oil liquid sample from a unit database, and screening out all key physical and chemical indexes corresponding to the detection of the oil liquid sample from the physical and chemical indexes;
Respectively obtaining index values of the oil samples and the reference oil samples corresponding to the key physicochemical indexes according to the detection instrument;
analyzing to obtain the change rate of each oil sample and each key physicochemical index corresponding to the reference oil sample ，Is the index value of the kth oil sample corresponding to the q key physicochemical index,The index value of the q-th key physicochemical index corresponding to the reference oil sample is k, k is the number of each oil sample, k=1, 2,..i, q is the number of each key physicochemical index, q=1, 2,..j;
finally analyzing to obtain the physicochemical property change evaluation coefficient of each oil sample ，The q is the weight value of the q-th key physical and chemical index, and j is the total number of the key physical and chemical indexes.
In the preferred technical scheme of the application, each key physicochemical index of the oil liquid sample corresponding detection is screened out, and the specific screening process is as follows:
the physical and chemical indexes of the oil liquid sample corresponding detection include but are not limited to viscosity, density, flash point, acid value, alkali value and moisture content;
obtaining fault duration time of gas turbine generator set corresponding to each historical fault frequency from a set database And synchronously collecting index values corresponding to physical and chemical indexes corresponding to each historical failure frequency of the gas turbine generator setP is the number of each historical failure number, p=1, 2,..m, c is the number of each physicochemical index, c=1, 2,..n;
calculating to obtain the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set M and n respectively represent the total times of historical faults and the total number of physical and chemical indexes;
And comparing the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set with a predefined linear correlation coefficient reference set, and if the correlation coefficient of a physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set is within the predefined linear correlation coefficient reference set, marking the physicochemical index as a key physicochemical index, and screening out each key physicochemical index detected correspondingly by the oil liquid sample in an analysis mode.
If it isApproaching 1 or-1 indicates that there is a strong positive or negative correlation. If the number of the pins is not equal,Approaching 0, no linear correlation is indicated. In general, the number of the devices used in the system,Values greater than 0.5 or less than-0.5 indicate a strong correlation, so the predefined set of linear correlation coefficient references is specifically expressed as。
In the preferred technical scheme of the application, the weight value of each key physicochemical index is obtained by the following steps:
acquiring index values of each oil sample corresponding to each key physicochemical index And subjecting it to standardization treatment;
calculating the calculated specific gravity value of each key physicochemical index in each oil sample Thereby further calculating the calculated entropy value of each key physicochemical index in the oil sampleWherein；
Finally, calculating the weight value of each key physicochemical index。
The function of (1) is to normalize the entropy values to the [0,1] interval so that the entropy values of different indexes are comparable and the difference between indexes can be reflected.
Step S3, evaluating the state information of the gas turbine generator set, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, further executing step S4, otherwise, jumping out of the step circulation;
In the preferred technical scheme of the application, the state information of the gas turbine generator set is evaluated, and the evaluation process is as follows:
s3-1, comparing the physicochemical property change evaluation coefficient of each oil sample with a predefined physicochemical property change evaluation threshold coefficient, if the physicochemical property change evaluation coefficient of a certain oil sample is larger than the predefined physicochemical property change evaluation threshold coefficient, judging the state information of the gas turbine generator set as an early warning state, and if the physicochemical property change evaluation coefficient of each oil sample is smaller than or equal to the predefined physicochemical property change evaluation threshold coefficient, executing the step S3-2;
Step S3-2, through analysis formula Analyzing to obtain average change rate of the oil sample corresponding to the physicochemical property change evaluation coefficientT is a preset date interval,Representing the physicochemical property change evaluation coefficient of the i-1 th oil sample;
step S3-3, calculating to obtain physicochemical property change evaluation coefficients corresponding to oil samples in the next acquisition date after a preset period ，And (3) for arranging the physicochemical property change evaluation coefficient of the last oil sample in the acquisition date in the preset period, comparing the physicochemical property change evaluation coefficient of the oil sample in the next acquisition date after the preset period with a predefined physicochemical property change evaluation threshold coefficient, and judging the state information of the gas turbine generator set as an early warning state in the same way if the physicochemical property change evaluation coefficient of the oil sample in the next acquisition date is larger than the predefined physicochemical property change evaluation threshold coefficient, otherwise judging the state information of the gas turbine generator set as a normal state.
And S4, carrying out deep detection analysis on each oil sample, judging the bearing wear evaluation index of the gas turbine generator set, and further obtaining the fault reason of the corresponding bearing of the gas turbine generator set.
In the preferred technical scheme of the application, the bearing wear evaluation index of the gas turbine generator set is judged, and the specific judging process is as follows:
Testing each oil sample by using an automatic particle counter to further determine the number of metal particles in each oil sample ；
Obtaining the corresponding ISO grade of each oil sample；
Extracting a base line ISO grade from a unit database, and calculating a first assessment index of bearing wear of a gas turbine generator unit，For a predefined rating index correction value;
The ISO level change interval value is the maximum change range estimated from the device history data for normalizing the rating index, and can be regarded as an ISO level change interval value if the history data shows ISO levels of 15/13/10 and 22/20/18 in the best and worst cases, respectively; the baseline ISO class is the ISO class of the device under known normal operating conditions.
Identifying abrasion particles in each oil sample by using a scanning electron microscope, further processing abrasion particle images captured in each oil sample by using image analysis software, and acquiring size factors and shape factors of each oil sample corresponding to each abrasion particle;
wherein,
According to the size factor and the shape factor of each abrasion particle corresponding to each oil sample, the abrasion type screening is carried out on each abrasion particle in each oil sample, so that the number, the size factor and the shape factor of the abrasion particles corresponding to each abrasion type in each oil sample are obtained;
Wherein the wear type includes, but is not limited to, fatigue wear, abrasion wear, and erosion wear;
Calculating a second assessment index of bearing wear of a gas turbine generator set S is the number of each wear type,For the volume of the kth oil sample,The number, the size factor and the shape factor of the abrasion particles corresponding to the s abrasion type in the kth oil sample are respectively;
And adding the first bearing wear evaluation index and the second bearing wear evaluation index of the gas turbine generator set, and calculating the addition result by the term number 2 to obtain the bearing wear evaluation index of the gas turbine generator set.
In the preferred technical scheme of the application, the failure reasons of the corresponding bearings of the gas turbine generator set are specifically classified into oil deterioration reasons, external pollution reasons and equipment friction reasons.
In the preferred technical scheme of the application, the fault cause of the corresponding bearing of the gas turbine generator set is obtained, and the specific acquisition process is as follows:
Testing each oil sample to obtain a rotary oxygen bomb test value of each oil sample, and further calculating to obtain an oil product degradation evaluation grade of the oil sample in a preset period corresponding to the gas turbine generator set;
the specific test process is as follows:
1. Sample preparation: placing each oil liquid sample into an oxygen bomb;
2. Oxygenation and sealing: filling pure oxygen into the oxygen bomb to a certain pressure, and then sealing the oxygen bomb;
3. Heating and rotating: the oxygen bomb was placed in a thermostatic water bath, typically set at a temperature of about 150 ℃, and rotated to ensure adequate contact mixing of the oil sample and oxygen.
4. Monitoring and recording: in the testing process, the change of each oil sample is monitored until the oil sample has obvious oxidation reaction, such as pressure drop, and the time point of the pressure drop is recorded, namely the rotary oxygen bomb test value of each oil sample.
Rotational oxygen bomb test value of each oil sample = test end time of each oil sample-test start time of each oil sample;
And comparing the rotating oxygen bomb test value of each oil sample with the rotating oxygen bomb test interval value corresponding to each oil degradation evaluation level stored in the unit database to obtain the oil degradation evaluation level of each oil sample corresponding to the gas turbine generator unit, and carrying out average calculation to obtain the oil degradation evaluation level of the oil sample in the preset period corresponding to the gas turbine generator unit.
Testing each oil sample to obtain the moisture content and oil film strength value of each oil sample, and further calculating to obtain the external pollution evaluation grade of the oil sample in the corresponding preset period of the gas turbine generator set;
；
；
w1 and w2 are respectively calculated weight values corresponding to the moisture content and the oil film strength value;
Comparing the external pollution evaluation index of the oil samples in the preset period corresponding to the gas turbine generator set with the external pollution evaluation index interval value corresponding to each external pollution evaluation level stored in the set database to obtain the external pollution evaluation level of each oil sample corresponding to the gas turbine generator set, and calculating the average value of the external pollution evaluation index to obtain the external pollution evaluation level of the oil samples in the preset period corresponding to the gas turbine generator set;
Comparing the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set oil quality degradation evaluation reference grade of the generator set, simultaneously comparing the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set external pollution evaluation reference grade of the generator set, and if the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set oil quality degradation evaluation reference grade of the generator set and the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set external pollution evaluation reference grade of the generator set, marking the fault cause of the bearing corresponding to the gas turbine generator set as both the oil quality degradation cause and the external pollution cause, otherwise marking the fault cause of the bearing corresponding to the gas turbine generator set as the equipment friction cause;
If the oil product degradation evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is larger than the set oil product degradation evaluation reference level of the generator set and the external pollution evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is smaller than or equal to the set external pollution evaluation reference level of the generator set, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the oil product degradation reason, otherwise, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the external pollution reason.
Example 2
Referring to FIG. 2, a gas turbine generator set condition monitoring and fault diagnosis system comprising:
The oil liquid sample collection module: the method comprises the steps of collecting an oil sample of a gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
sample comparison analysis module: the oil samples collected in each sampling date are simply recorded as oil samples, the oil samples are compared with a reference oil sample, and the physicochemical property change evaluation coefficients of the oil samples are analyzed;
The unit state evaluation module: the state information of the gas turbine generator set is evaluated, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, a fault type judging module is further executed;
A fault type judging module: and carrying out deep detection analysis on each oil sample so as to judge the bearing wear evaluation index of the gas turbine generator set, and further obtaining the fault reason of the corresponding bearing of the gas turbine generator set.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A method for condition monitoring and fault diagnosis of a gas turbine generator set, comprising:
Step S1, collecting an oil sample of the gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
S2, simply recording the oil samples collected in each sampling date as each oil sample, comparing each oil sample with a reference oil sample, and analyzing the physicochemical property change evaluation coefficients of each oil sample;
step S3, evaluating the state information of the gas turbine generator set, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, further executing step S4, otherwise, jumping out of the step circulation;
The state information of the gas turbine generator set is evaluated, and the evaluation process is as follows:
s3-1, comparing the physicochemical property change evaluation coefficient of each oil sample with a predefined physicochemical property change evaluation threshold coefficient, if the physicochemical property change evaluation coefficient of a certain oil sample is larger than the predefined physicochemical property change evaluation threshold coefficient, judging the state information of the gas turbine generator set as an early warning state, and if the physicochemical property change evaluation coefficient of each oil sample is smaller than or equal to the predefined physicochemical property change evaluation threshold coefficient, executing the step S3-2;
Step S3-2, through analysis formula Analyzing to obtain average change rate of the oil sample corresponding to the physicochemical property change evaluation coefficientT is a preset date interval,Representing the physicochemical property change evaluation coefficient of the i-1 th oil sample;
step S3-3, calculating to obtain physicochemical property change evaluation coefficients corresponding to oil samples in the next acquisition date after a preset period ，Arranging the physicochemical property change evaluation coefficient of the last oil sample for the acquisition date in the preset period, comparing the physicochemical property change evaluation coefficient of the oil sample corresponding to the next acquisition date after the preset period with a predefined physicochemical property change evaluation threshold coefficient, and judging the state information of the gas turbine generator set as an early warning state in the same way if the physicochemical property change evaluation coefficient of the oil sample is larger than the predefined physicochemical property change evaluation threshold coefficient, otherwise judging the state information of the gas turbine generator set as a normal state;
S4, carrying out deep detection analysis on each oil sample, judging a bearing wear evaluation index of the gas turbine generator set, and further obtaining a fault reason of a corresponding bearing of the gas turbine generator set;
Judging the bearing wear evaluation index of the gas turbine generator set, wherein the specific judging process comprises the following steps of:
Testing each oil sample by using an automatic particle counter to further determine the number of metal particles in each oil sample ；
Obtaining the corresponding ISO grade of each oil sample；
Extracting a base line ISO grade from a unit database, and calculating a first assessment index of bearing wear of a gas turbine generator unit，For a predefined rating index correction value;
identifying abrasion particles in each oil sample by using a scanning electron microscope, further processing abrasion particle images captured in each oil sample by using image analysis software, and acquiring size factors and shape factors of each oil sample corresponding to each abrasion particle;
According to the size factor and the shape factor of each abrasion particle corresponding to each oil sample, the abrasion type screening is carried out on each abrasion particle in each oil sample, so that the number, the size factor and the shape factor of the abrasion particles corresponding to each abrasion type in each oil sample are obtained;
Calculating a second assessment index of bearing wear of a gas turbine generator set S is the number of each wear type,For the volume of the kth oil sample,The number, the size factor and the shape factor of the abrasion particles corresponding to the s abrasion type in the kth oil sample are respectively;
adding the first evaluation index of the bearing wear of the gas turbine generator set with the second evaluation index of the bearing wear, and calculating the addition result by the term number 2 to obtain the evaluation index of the bearing wear of the gas turbine generator set;
the failure reasons of the corresponding bearings of the gas turbine generator set are specifically classified into oil deterioration reasons, external pollution reasons and equipment friction reasons;
The fault cause of the corresponding bearing of the gas turbine generator set is obtained, and the specific acquisition process is as follows:
Testing each oil sample to obtain a rotary oxygen bomb test value of each oil sample, and further calculating to obtain an oil product degradation evaluation grade of the oil sample in a preset period corresponding to the gas turbine generator set;
testing each oil sample to obtain the moisture content and oil film strength value of each oil sample, and further calculating to obtain the external pollution evaluation grade of the oil sample in the corresponding preset period of the gas turbine generator set;
Comparing the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set oil quality degradation evaluation reference grade of the generator set, simultaneously comparing the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set with the set external pollution evaluation reference grade of the generator set, and if the oil quality degradation evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set oil quality degradation evaluation reference grade of the generator set and the external pollution evaluation grade of the oil sample in the preset period corresponding to the gas turbine generator set is greater than the set external pollution evaluation reference grade of the generator set, marking the fault cause of the bearing corresponding to the gas turbine generator set as both the oil quality degradation cause and the external pollution cause, otherwise marking the fault cause of the bearing corresponding to the gas turbine generator set as the equipment friction cause;
If the oil product degradation evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is larger than the set oil product degradation evaluation reference level of the generator set and the external pollution evaluation level of the oil liquid sample in the preset period corresponding to the gas turbine generator set is smaller than or equal to the set external pollution evaluation reference level of the generator set, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the oil product degradation reason, otherwise, the failure reason of the bearing corresponding to the gas turbine generator set is marked as the external pollution reason.
2. The method for monitoring the state of a gas turbine generator set and diagnosing faults according to claim 1, wherein the physical and chemical property change evaluation coefficients of each oil sample are analyzed, and the specific analysis process is as follows:
Extracting all physical and chemical indexes corresponding to the detection of the oil liquid sample from a unit database, and screening out all key physical and chemical indexes corresponding to the detection of the oil liquid sample from the physical and chemical indexes;
Respectively obtaining index values of the oil samples and the reference oil samples corresponding to the key physicochemical indexes according to the detection instrument;
analyzing to obtain the change rate of each oil sample and each key physicochemical index corresponding to the reference oil sample ，Is the index value of the kth oil sample corresponding to the q key physicochemical index,The index value of the q-th key physicochemical index corresponding to the reference oil sample is k, k is the number of each oil sample, k=1, 2,..i, q is the number of each key physicochemical index, q=1, 2,..j;
finally analyzing to obtain the physicochemical property change evaluation coefficient of each oil sample ，The q is the weight value of the q-th key physical and chemical index, and j is the total number of the key physical and chemical indexes.
3. The method for monitoring the state and diagnosing faults of the gas turbine generator set according to claim 2, wherein the screening of each key physicochemical index of the oil liquid sample corresponding detection is carried out, and the specific screening process is as follows:
obtaining fault duration time of gas turbine generator set corresponding to each historical fault frequency from a set database And synchronously collecting index values corresponding to physical and chemical indexes corresponding to each historical failure frequency of the gas turbine generator setP is the number of each historical failure number, p=1, 2,..m, c is the number of each physicochemical index, c=1, 2,..n;
calculating to obtain the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set M and n respectively represent the total times of historical faults and the total number of physical and chemical indexes;
And comparing the correlation coefficient of each physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set with a predefined linear correlation coefficient reference set, and if the correlation coefficient of a physicochemical index corresponding to the historical fault corresponding to the gas turbine generator set is within the predefined linear correlation coefficient reference set, marking the physicochemical index as a key physicochemical index, and screening out each key physicochemical index detected correspondingly by the oil liquid sample in an analysis mode.
4. The method for monitoring the state of a gas turbine generator set and diagnosing faults according to claim 2, wherein the specific obtaining process of the weight value of each key physicochemical index is as follows:
acquiring index values of each oil sample corresponding to each key physicochemical index And subjecting it to standardization treatment;
calculating the calculated specific gravity value of each key physicochemical index in each oil sample Thereby further calculating the calculated entropy value of each key physicochemical index in the oil sampleWherein；
Finally, calculating the weight value of each key physicochemical index。
5. A gas turbine generator set condition monitoring and fault diagnosis system, characterized in that it is implemented based on a gas turbine generator set condition monitoring and fault diagnosis method according to any one of claims 1-4, comprising:
The oil liquid sample collection module: the method comprises the steps of collecting an oil sample of a gas turbine generator set under normal operation conditions, taking the oil sample as a reference oil sample, periodically collecting the oil sample in the operation process of the gas turbine generator set according to a preset date interval in a preset period, and recording the sampling date;
sample comparison analysis module: the oil samples collected in each sampling date are simply recorded as oil samples, the oil samples are compared with a reference oil sample, and the physicochemical property change evaluation coefficients of the oil samples are analyzed;
The unit state evaluation module: the state information of the gas turbine generator set is evaluated, wherein the state information is divided into a normal state and an early warning state, and if the state information of the gas turbine generator set obtained by evaluation is the early warning state, a fault type judging module is further executed;
A fault type judging module: and carrying out deep detection analysis on each oil sample so as to judge the bearing wear evaluation index of the gas turbine generator set, and further obtaining the fault reason of the corresponding bearing of the gas turbine generator set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411050827.3A CN118565827B (en) | 2024-08-01 | 2024-08-01 | Gas turbine generator set state monitoring and fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411050827.3A CN118565827B (en) | 2024-08-01 | 2024-08-01 | Gas turbine generator set state monitoring and fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118565827A CN118565827A (en) | 2024-08-30 |
| CN118565827B true CN118565827B (en) | 2024-10-22 |
Family
ID=92473400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411050827.3A Active CN118565827B (en) | 2024-08-01 | 2024-08-01 | Gas turbine generator set state monitoring and fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118565827B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102692449A (en) * | 2012-04-12 | 2012-09-26 | 北京工业大学 | Fault diagnosis method of blast furnace top gearbox through comprehensive analysis |
| CN102840882A (en) * | 2012-09-04 | 2012-12-26 | 中国海洋石油总公司 | State monitoring and fault diagnosis system of gas turbine generating unit and use method of state monitoring and fault diagnosis system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4504065B2 (en) * | 2004-03-31 | 2010-07-14 | 中国電力株式会社 | Rolling bearing remaining life diagnosis method |
| CN102707037B (en) * | 2012-06-01 | 2014-10-08 | 广州机械科学研究院有限公司 | On-line monitoring system for diesel lubrication oil |
| US9897582B2 (en) * | 2012-10-26 | 2018-02-20 | Pratt & Whitney Canada Corp. | Method and system for failure prediction using lubricating fluid analysis |
| CN110455546A (en) * | 2019-07-19 | 2019-11-15 | 广西大学 | Engine state monitor and method for diagnosing faults based on vibration and oil liquid information |
| CN113987205A (en) * | 2021-10-27 | 2022-01-28 | 中国华能集团清洁能源技术研究院有限公司 | Gas turbine fault diagnosis method and system |
-
2024
- 2024-08-01 CN CN202411050827.3A patent/CN118565827B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102692449A (en) * | 2012-04-12 | 2012-09-26 | 北京工业大学 | Fault diagnosis method of blast furnace top gearbox through comprehensive analysis |
| CN102840882A (en) * | 2012-09-04 | 2012-12-26 | 中国海洋石油总公司 | State monitoring and fault diagnosis system of gas turbine generating unit and use method of state monitoring and fault diagnosis system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118565827A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109469896B (en) | Industrial boiler fault diagnosis method and system based on time series analysis | |
| CN112179691B (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
| CN111353482A (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| CN105976578B (en) | A kind of bullet train axle temperature dynamic alert threshold setting method based on monitoring data | |
| CN113757093B (en) | Flash steam compressor unit fault diagnosis method | |
| WO2011049667A1 (en) | System and method for selecting a maintenance operation | |
| CN113916531A (en) | Fault diagnosis and prediction system for on-line monitoring of vibration and oil of nuclear power gearbox | |
| CN117741517A (en) | Capacitor equipment online monitoring method and system based on artificial intelligence | |
| CN113131019A (en) | New energy electric automobile battery module operation safety real-time supervision early warning system based on cloud calculates and thing networking | |
| CN118565827B (en) | Gas turbine generator set state monitoring and fault diagnosis method and system | |
| CN114878172B (en) | Ship host cylinder temperature signal feature extraction method and system | |
| Koukoura et al. | On the use of AI based vibration condition monitoring of wind turbine gearboxes | |
| CN118243200B (en) | Gas turbine flowmeter fault diagnosis method and system | |
| CN117649123B (en) | Wisdom garden management system | |
| CN112326246A (en) | Bearing safety state online monitoring method based on periodic data and nuclear density estimation | |
| CN114577470A (en) | Fault diagnosis method and system for fan main bearing | |
| CN118468175A (en) | Ball mill fault diagnosis method and system based on hybrid neural network | |
| CN117786461A (en) | Water pump fault diagnosis method, control device and storage medium thereof | |
| CN114112390B (en) | Nonlinear complex system early fault diagnosis method | |
| CN115758066A (en) | Method for counting carbon emission in whole life cycle of transformer | |
| Byington et al. | False alarm mitigation of vibration diagnostic systems | |
| CN115167364A (en) | Early fault detection method based on probability transformation and statistical characteristic analysis | |
| CN113283375A (en) | Early fault real-time early warning method for mine hydraulic support system | |
| Ding et al. | Adaptive angle-weighted cumulative sum for interpretable machine condition monitoring | |
| Oddan | Multivariate statistical condition monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |