CN111855219A - Diesel engine lubricating oil entering security parameter prediction method based on grey theory - Google Patents

Diesel engine lubricating oil entering security parameter prediction method based on grey theory Download PDF

Info

Publication number
CN111855219A
CN111855219A CN202010698450.8A CN202010698450A CN111855219A CN 111855219 A CN111855219 A CN 111855219A CN 202010698450 A CN202010698450 A CN 202010698450A CN 111855219 A CN111855219 A CN 111855219A
Authority
CN
China
Prior art keywords
diesel engine
lubricating oil
data
prediction
pressure
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.)
Pending
Application number
CN202010698450.8A
Other languages
Chinese (zh)
Inventor
王忠巍
李耀
徐荣
倪小明
张玉兴
周莉娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin Engineering University
Original Assignee
Harbin Engineering University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin Engineering University filed Critical Harbin Engineering University
Priority to CN202010698450.8A priority Critical patent/CN111855219A/en
Publication of CN111855219A publication Critical patent/CN111855219A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M15/00Testing of engines
    • G01M15/04Testing internal-combustion engines
    • G01M15/09Testing internal-combustion engines by monitoring pressure in fluid ducts, e.g. in lubrication or cooling parts
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M15/00Testing of engines
    • G01M15/04Testing internal-combustion engines
    • G01M15/05Testing internal-combustion engines by combined monitoring of two or more different engine parameters
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/11Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/13Differential equations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/16Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Combined Controls Of Internal Combustion Engines (AREA)

Abstract

The invention discloses a method for predicting the security parameters of diesel engine lubricating oil entering a machine based on a grey theory. The invention belongs to the technical field of diesel engine safety prediction, and the method comprises the steps of firstly collecting operating data of the pressure and the temperature of lubricating oil entering a diesel engine, and performing Kalman filtering processing on the operating data; then according to the modeling step of the grey prediction model, the prediction function of the diesel engine operation data is realized, and a prediction result is obtained; a relative error inspection method is used for inspecting the gray prediction model, if the four-level inspection index is not met, the gray model is optimized by a residual error method until the four-level and above-level indexes are met, and accurate prediction data are output; and on the basis of the qualified verification of the relative error of the predicted data, carrying out logic judgment on the predicted result and the alarm threshold value of the diesel engine, and outputting the predicted state result to an upper computer. The method can effectively predict the variation trend of the diesel engine lubricating oil feeding parameters and reasonably predict the future working state of the diesel engine lubricating oil system.

Description

Diesel engine lubricating oil entering security parameter prediction method based on grey theory
Technical Field
The invention relates to the technical field of diesel engine safety prediction, in particular to a method for predicting diesel engine lubricating oil entering security parameters based on a grey theory.
Background
With the rapid development of the current social industrialization level, the diesel engine is widely applied to the fields of petroleum mines, fixed power generation, railway traction, engineering machinery, special ships and the like as the most common power mechanical equipment, and the diesel engine is increasingly developed towards the large-scale, high-speed and precise directions, the working performance is continuously improved, and the automation degree is higher and higher. On one hand, the labor productivity is greatly improved, the product quality is improved, and the production cost and the energy consumption are reduced by utilizing the advanced diesel engine; on the other hand, the problem of safe operation of the diesel engine is increasingly severe, the risk degree of safety accidents of the diesel engine is further improved along with the development of high load and high rotation speed, once a certain part or a certain link of the diesel engine is continuously over-limited in operation and is not treated, equipment is often damaged, serious safety accidents are caused, and even personal safety is endangered. The research on the safety protection technology of the diesel engine can help people to prevent safety accidents, ensure the personal safety of workers and avoid potential huge economic loss and social loss.
The traditional diesel engine safety protection system has the tasks of monitoring important state parameters of a diesel engine, such as the pressure and the temperature of lubricating oil entering the diesel engine, judging whether the lubricating oil enters a set threshold value or not, further judging whether the diesel engine runs safely or not, and taking emergency shutdown measures before danger occurs to ensure the safety of personnel and equipment. Although the mode can avoid accidents to a certain extent, the defect is obvious, and when the diesel engine which normally runs under rated load suddenly stops (especially suddenly unloads from full load), stress impact can be caused to a moving part; in addition, in the process that the pressure of the lubricating oil gradually deviates from the normal range, the lubricating effect on the moving parts such as the engine body, the piston, the crankshaft and the like is greatly reduced, great irreversible damage is caused on equipment, and the service life of the equipment is seriously influenced.
Through the literature search of the prior art, the publication of a speed measuring and security system of a marine diesel engine provides a security system based on the rotating speed of the diesel engine, and the publication has the following self-description: the invention provides a speed measuring and security system of a marine diesel engine. A user sets an alarm threshold value according to the actual use condition through the industrial touch screen, the alarm threshold value is preset for each detection signal, and the alarm threshold value of each detection signal can be selectively set to be an analog quantity or a switching quantity. And the user sets the alarm threshold value of each detection signal as a switching value or an analog value through the industrial touch screen. The main control module judges the detection signal through the alarm threshold value, if the detection signal exceeds the alarm threshold value, the main control module sends a stop signal to the diesel engine, and alarms through the remote control box that the detection signal does not exceed the alarm threshold value, and no operation is adopted.
Disclosure of Invention
The invention relates to a method for predicting the feeding parameters of lubricating oil for realizing the safety protection of a diesel engine, which monitors the running state of the diesel engine by acquiring the running data of the feeding parameters of the lubricating oil of the diesel engine in real time, and further processes the data and predicts the change trend. The invention provides a method for predicting the security parameters of the lubricating oil entering the diesel engine based on the grey theory, which comprises the following steps of sending an alarm signal to an upper computer before a dangerous condition occurs, taking feedback measures in advance, avoiding the condition that equipment is over-limit to work, and improving the reliability and the safety of the equipment, wherein the method comprises the following steps:
a method for predicting the security parameters of diesel engine lubricating oil entering a machine based on a grey theory comprises the following steps:
step 1: acquiring pressure data of the diesel engine through a pressure sensor, wherein the pressure data is lubricating oil feeding pressure operation data of the diesel engine, acquiring the pressure data from the pressure sensor of a lubricating oil feeding inlet pipeline of the diesel engine through a data acquisition card, and storing the data into Excel;
step 2: carrying out data preprocessing on collected lubricating oil feeding pressure operation data of the diesel engine, and filtering out environmental noise influence;
And step 3: according to the data after noise filtering, the diesel engine lubricating oil enters the engine pressure gray prediction data to be processed, and a prediction result is obtained;
and 4, step 4: and comparing the prediction result with an alarm threshold value of the diesel engine safety protection system, judging the running state of the diesel engine, and giving an alarm according to the running state of the diesel engine.
Preferably, the step 2 specifically comprises:
step 2.1: initializing a diesel engine and determining an input signal wkObservation noise v of output signalk、QkAnd product specification error RkPreprocessing the collected pressure operation data of the lubricating oil of the diesel engine by adopting a Kalman filtering method, filtering the environmental noise influence, establishing a state equation and an output equation, and expressing a state equation x by the following formulak+1And output equation yk
xk+1=Akxk+wk
yk=Ckxk+vk
Wherein k is time, wkFor input signal, vkFor the observed noise of the output signal, A is the gain matrix between the state variables, xkC is a gain matrix between the state variable and the output signal;
determining an input signal wkAnd an outputObserved noise v of a signalk、QkAnd product specification error Rk
Step 2.2: setting the initial true temperature to x(0)=T0And covariance P of initial time(0)
Step 2.3: reading the optimal estimated value T at the k-1 time k-1Measured value t at time kkCalculating a gain factor, the gain factor being represented by:
Hk=P(k-1)/(P(k-1)+Rk)
Tk=Tk-1+Hk(tk-Tk-1)
the optimal to noise covariance at time k is represented by:
P(k)=(1-Hk)P(k-1)
step 2.4: reading the optimal estimated value T at the k-th momentkMeasured value t at time k +1k+1Calculating a gain factor Hk+1And Tk+1The optimum noise covariance P at time k +1(k+1)
Step 2.5: and (5) repeating the steps 2.3 to 2.4, estimating an optimal value, and obtaining effective data after the environmental noise is filtered.
Preferably, Q is measured when the true temperature of the diesel engine is constantk0; when the temperature of the diesel engine changes along with the running state, Qk=0.01。
Preferably, the step 3 specifically comprises:
step 3.1: establishing a gray prediction model GM (2,1), and expressing a differential equation of the gray prediction model GM (2,1) by the following formula:
Figure BDA0002592171360000031
wherein p is(1)The accumulated number sequence is generated through one accumulation operation; t is time; a is1,a2U is a parameter to be estimated, namely a developing ash coefficient and an endogenous control ash coefficient;
step 3.2: according to the number after filtering noiseAccordingly, a raw pressure data array is created, said array P being represented by(0)
P(0)=(p(0)(1),p(0)(2),p(0)(3)…p(0)(n))
Wherein p is(0)(i) Time series data of the pressure parameter of the lubricating oil inlet machine, i is 1, 2, … n;
step 3.3: according to P (0)Determining P(0)Step ratio of(0)(i) Is tested for the step ratio, and the step ratio σ is expressed by the following formula(0)(i):
Figure BDA0002592171360000032
Step 3.4: current class ratio sigma(0)(i) When the inspection standard is satisfied, for P(0)Performing 1-AGO accumulation operation and 1-IAGO accumulation subtraction to obtain generated P(1)And alpha(1)P(0)Array, P is represented by the formula(1)And alpha(1)P(0)The sequence of the numbers:
P(1)=(p(1)(1),p(1)(2),…p(1)(n))
α(1)P(0)=(α(1)p(0)(2),α(1)p(0)(3)…α(1)p(0)(n))
Figure BDA0002592171360000033
α(1)p(0)(i)=p(0)(i)-p(0)(i-1),i=2,3,…,n
step 3.5: test P(1)If the standard index rule exists, the standard index is calculated by the following formula(1)(i):
Figure BDA0002592171360000041
And 3, 6: when the quasi-index meets the inspection standard, P is aligned(1)Performing an immediate mean generation operation, wherein the immediate mean is represented by the following formula:
z(1)(i)=0.5p(1)(i)+0.5p(1)(i-1)(i=2,3…n)
Z(1)=(z(1)(2),z(1)(3),z(1)(4),z(1)(5))
step 3.7: for parameter column
Figure BDA0002592171360000042
Performing least square estimation to obtain a1,a2,u:
Figure BDA0002592171360000043
Figure BDA0002592171360000044
Step 3.8: solving a whitening equation for GM (2,1) to obtain a time response equation for GM (2,1), the time response equation being represented by:
Figure BDA0002592171360000045
solving for P(1)Is represented by the following formula(1)Analog value of (d):
Figure BDA0002592171360000046
determining P from analog value reduction(0)Is represented by the following formula(0)Analog value of (d):
Figure BDA0002592171360000047
Figure BDA0002592171360000048
will P(0)As a result of the prediction
Figure BDA0002592171360000049
Step 3.9: and carrying out error check on the model, and expressing the error detection value by the following formula:
Figure BDA00025921713600000410
the test indexes are as follows: first-stage: the index critical value is 0.01; and (2) second stage: the index critical value is 0.05; third-stage: the index critical value is 0.10; and (4) fourth stage: the index critical value is 0.20; and if the error detection value does not meet the critical value of the four-level index, adopting a residual error optimization gray prediction model GM (2, 1).
Preferably, the step ratio σ is determined(0)(i) The method specifically meets the inspection standard:
Figure BDA00025921713600000411
when the grade ratio is within the above formula check criteria, then it is satisfied.
Preferably, the specific steps for checking whether the quasi-index has the quasi-index rule are as follows:
(1)(i)∈(1,1.5)
the quasi-index is satisfied when it is within the above-described criteria.
Preferably, after the prediction result is compared with the alarm threshold of the diesel engine safety protection system, the pressure threshold of the safety protection system is lower than the pressure threshold of the safety protection system after 80min according to the predicted oil feeding pressure, then the future operation state of the diesel engine is judged to be that the lubricating oil feeding pressure is too low, at the moment, the safety protection system sends an alarm signal to an upper computer through a program, and the prediction data is sent to the upper computer in a charted form to be analyzed in the next step.
The invention has the following beneficial effects:
firstly, collecting pressure and temperature data of lubricating oil entering a diesel engine; processing the acquired data by a Kalman filtering technology to form an original parameter sequence of the pressure and the temperature of the lubricating oil entering the machine; according to the modeling step of a grey theoretical prediction model, carrying out accumulation operation on an original pressure sequence to generate an accumulated number sequence, then carrying out data quasi-smoothness inspection on the accumulated number sequence, establishing a grey prediction GM (2,1) model for prediction calculation under the condition of meeting the quasi-smoothness, carrying out model inspection by using a relative error inspection method, judging the model to be qualified when the model reaches four-level standard, outputting a prediction result if the model is qualified, establishing a model by using a residual sequence if the model is unqualified, correcting the original model until the model meets the inspection standard, and outputting the prediction result on the basis that the model meets the inspection standard so as to realize the trend prediction of the entering pressure and the temperature of the diesel engine lubricating oil; then, the prediction result is compared with a safety alarm threshold value of the diesel engine, and the state judgment of whether the pressure and the temperature of the lubricating oil entering the engine are normal is realized; and when the prediction result is in an abnormal state, namely the prediction result of the pressure of the lubricating oil entering the machine is lower than a specified threshold value or the temperature of the lubricating oil entering the machine is higher than the specified threshold value, outputting an alarm reminding signal to the upper computer so as to take a feedback measure in advance.
The method directly obtains the operating data of the lubricating oil feeding parameters from the diesel engine, meanwhile, the trend prediction is carried out on the lubricating oil feeding parameters by adopting a grey theory prediction method, and the future operating state of the diesel engine is judged according to the prediction result. If the diesel engine is judged to be in an abnormal operation state, the upper computer can be reminded to take feedback measures in advance, the conditions of overrun operation and sudden shutdown are avoided, and the purpose of diesel engine safety protection is achieved.
According to the prediction method provided by the invention, the future change of the pressure of the lubricating oil entering the engine can be effectively predicted, safety protection measures can be taken for the diesel engine as soon as possible, the reliability of equipment is improved, and the possibility of harm caused by sudden shutdown can be reduced as much as possible under the condition of ensuring the running safety of the diesel engine.
Drawings
FIG. 1 is a flow chart of a method for predicting security parameters of diesel engine lubricating oil entering a machine based on a grey theory;
fig. 2 is a graph showing the predicted result of the lubricating oil feed pressure during the operation of the diesel engine.
Detailed Description
The present invention will be described in detail with reference to specific examples.
The first embodiment is as follows:
according to the illustration in fig. 1, the invention provides a method for predicting the security parameters of the lubricating oil entering the diesel engine based on the gray theory, which specifically comprises the following steps:
A method for predicting the security parameters of diesel engine lubricating oil entering a machine based on a grey theory comprises the following steps:
step 1: acquiring pressure data of the diesel engine through a pressure sensor, wherein the pressure data is lubricating oil feeding pressure operation data of the diesel engine, acquiring the pressure data from the pressure sensor of a lubricating oil feeding inlet pipeline of the diesel engine through a data acquisition card, and storing the data into Excel;
step 2: carrying out data preprocessing on collected lubricating oil feeding pressure operation data of the diesel engine, and filtering out environmental noise influence;
the step 2 specifically comprises the following steps:
step 2.1: initializing a diesel engine and determining an input signal wkObservation noise v of output signalk、QkAnd product specification error RkPreprocessing the collected pressure operation data of the lubricating oil of the diesel engine by adopting a Kalman filtering method, filtering the environmental noise influence, establishing a state equation and an output equation, and expressing a state equation x by the following formulak+1And output equation yk
xk+1=Akxk+wk
yk=Ckxk+vk
Wherein k is time, wkFor input signal, vkFor the observed noise of the output signal, A is the gain matrix between the state variables, xkC is a gain matrix between the state variable and the output signal;
Determining an input signal wkObservation noise v of output signalk、QkAnd product specification errorRk
Step 2.2: setting the initial true temperature to x(0)=T0And covariance P of initial time(0)
Step 2.3: reading the optimal estimated value T at the k-1 timek-1Measured value t at time kkCalculating a gain factor, the gain factor being represented by:
Hk=P(k-1)/(P(k-1)+Rk)
Tk=Tk-1+Hk(tk-Tk-1)
the optimal to noise covariance at time k is represented by:
P(k)=(1-Hk)P(k-1)
step 2.4: reading the optimal estimated value T at the k-th momentkMeasured value t at time k +1k+1Calculating a gain factor Hk+1And Tk+1The optimum noise covariance P at time k +1(k+1)
Step 2.5: and (5) repeating the steps 2.3 to 2.4, estimating an optimal value, and obtaining effective data after the environmental noise is filtered.
Preferably, Q is measured when the true temperature of the diesel engine is constantk0; when the temperature of the diesel engine changes along with the running state, Qk=0.01。
And step 3: according to the data after noise filtering, the diesel engine lubricating oil enters the engine pressure gray prediction data to be processed, and a prediction result is obtained;
the step 3 specifically comprises the following steps:
step 3.1: establishing a gray prediction model GM (2,1), and expressing a differential equation of the gray prediction model GM (2,1) by the following formula:
Figure BDA0002592171360000071
wherein p is(1)The accumulated number sequence is generated through one accumulation operation; t is time; a is 1,a2U is a parameter to be estimated, namely a developing ash coefficient and an endogenous control ash coefficient;
step 3.2: establishing an original pressure data array according to the data after noise filtering, and expressing the array P by the following formula(0)
P(0)=(p(0)(1),p(0)(2),p(0)(3)…p(0)(n))
Wherein p is(0)(i) Time series data of the pressure parameter of the lubricating oil inlet machine, i is 1, 2, … n;
step 3.3: according to P(0)Determining P(0)Step ratio of(0)(i) Is tested for the step ratio, and the step ratio σ is expressed by the following formula(0)(i):
Figure BDA0002592171360000072
Step 3.4: current class ratio sigma(0)(i) When the inspection standard is satisfied, for P(0)Performing 1-AGO accumulation operation and 1-IAGO accumulation subtraction to obtain generated P(1)And alpha(1)P(0)Array, P is represented by the formula(1)And alpha(1)P(0)The sequence of the numbers:
P(1)=(p(1)(1),p(1)(2),…p(1)(n))
α(1)P(0)=(α(1)p(0)(2),α(1)p(0)(3)…α(1)p(0)(n))
Figure BDA0002592171360000073
α(1)p(0)(i)=p(0)(i)-p(0)(i-1),i=2,3,…,n
determination of the step ratio sigma(0)(i) The method specifically meets the inspection standard:
Figure BDA0002592171360000074
when the grade ratio is within the above formula check criteria, then it is satisfied.
Step 3.5: test P(1)If the standard index rule exists, the standard index is calculated by the following formula(1)(i):
Figure BDA0002592171360000075
The specific method for checking whether the quasi-index has the quasi-index rule is as follows:
(1)(i)∈(1,1.5)
the quasi-index is satisfied when it is within the above-described criteria.
Step 3.6: when the quasi-index meets the inspection standard, P is aligned(1)Performing an immediate mean generation operation, wherein the immediate mean is represented by the following formula:
z(1)(i)=0.5p(1)(i)+0.5p(1)(i-1)(i=2,3…n)
Z(1)=(z(1)(2),z(1)(3),z(1)(4),z(1)(5))
step 3.7: for parameter column
Figure BDA0002592171360000081
Performing least square estimation to obtain a1,a2,u:
Figure BDA0002592171360000082
Figure BDA0002592171360000083
Step 3.8: solving a whitening equation for GM (2,1) to obtain a time response equation for GM (2,1), the time response equation being represented by:
Figure BDA0002592171360000084
Solving for P(1)Is represented by the following formula(1)Analog value of (d):
Figure BDA0002592171360000085
determining P from analog value reduction(0)Is represented by the following formula(0)Analog value of (d):
Figure BDA0002592171360000086
Figure BDA0002592171360000087
will P(0)As a result of the prediction
Figure BDA0002592171360000088
Step 3.9: and carrying out error check on the model, and expressing the error detection value by the following formula:
Figure BDA0002592171360000089
the test indexes are as follows: first-stage: the index critical value is 0.01; and (2) second stage: the index critical value is 0.05; third-stage: the index critical value is 0.10; and (4) fourth stage: the index critical value is 0.20; and if the error detection value does not meet the critical value of the four-level index, adopting a residual error optimization gray prediction model GM (2, 1).
And 4, step 4: and comparing the prediction result with an alarm threshold value of the diesel engine safety protection system, judging the running state of the diesel engine, and giving an alarm according to the running state of the diesel engine.
And after the prediction result is compared with the alarm threshold of the diesel engine safety protection system, the pressure of the lubricating oil entering the engine is lower than the pressure threshold of the security system after 80min according to the predicted pressure, the future running state of the diesel engine is judged to be that the pressure of the lubricating oil entering the engine is too low, at the moment, the security system sends an alarm signal to an upper computer through a program, and the prediction data is sent to the upper computer in a chartification mode to be analyzed in the next step.
Firstly, collecting operating data of the pressure and the temperature of lubricating oil entering a diesel engine, and carrying out Kalman filtering processing on the operating data; then according to the modeling step of the grey prediction model, the prediction function of the diesel engine operation data is realized, and a prediction result is obtained; a relative error inspection method is used for inspecting the gray prediction model, if the four-level inspection index is not met, the gray model is optimized by a residual error method until the four-level and above-level indexes are met, and accurate prediction data are output; and on the basis of the qualified verification of the relative error of the predicted data, logically judging the predicted result and the alarm threshold value of the diesel engine, and then outputting the predicted state result to an upper computer. Through the steps, the variation trend of the diesel engine lubricating oil feeding parameters can be effectively predicted, and the future working state of the diesel engine lubricating oil system can be reasonably predicted. The method is based on the grey theory, predicts the change of the security parameters of the lubricating oil entering the diesel engine, can assist a control system, and adopts effective feedback measures before the equipment is over-limit operated, so that the safety and the reliability of the equipment are improved on the whole.
The second embodiment is as follows:
the invention comprises the following steps: the method comprises the steps of collecting the pressure of the lubricating oil entering the diesel engine, preprocessing the pressure of the lubricating oil entering the diesel engine, calculating the grey prediction data of the pressure of the lubricating oil entering the diesel engine, and judging the future working state of the diesel engine. The method comprises the following specific steps:
Step 1: collecting the pressure data of the lubricating oil entering the diesel engine: the pressure operation data of the lubricating oil feeding machine of the diesel engine is obtained from a pressure sensor of a pipeline at the inlet of the lubricating oil feeding machine of the diesel engine by a data acquisition card, and the operation data is stored in Excel so as to be read and used in the subsequent data preprocessing step and the gray prediction model building step.
Step 2: preprocessing the data of the pressure of the lubricating oil entering the diesel engine: the collected diesel engine operation data is preprocessed, so that noise influence caused by the sensor or the surrounding environment can be effectively filtered, and effective data of low interference signals are generated. The method selected here is a Kalman filtering method, which can be designed by setting an initial state and a variance, and carries out parameter estimation at the next moment; in the estimation and correction process, gain is calculated according to the statistical rule of external interference of the diesel engine and sensor noise; and finally, on the basis of the prediction state, correcting the predicted parameter value by using the gain. And obtaining the optimal parameter estimation value. The specific implementation steps are as follows:
first, the relevant definition of the kalman filter is given:
suppose the state variable at time k of the system is x kThe state equation and the output equation are then expressed as follows:
Xk+1=Akxk+wk#(1)
yk=Ckxk+vk#(2)
wherein k represents time, i.e. the kth iteration; input signal wkIs white noise, the observed noise v of the output signalkIs also white noise; a represents a gain matrix between state variables, varying with time k; c represents a gain matrix between the state variable and the output signal, varying with time k; suppose wkAnd vkAre all normal white noise with a mean of zero and variances of Q and R, respectively.
The first step is as follows: determining w by system initial conditionsk、vk、QkAnd Rk. When the real temperature of the measured system is constant, QkWhere Q is taken because the temperature of the diesel engine varies with the operating statek=0.01。vkFor measuring noise of the temperature measuring device, the factory instructions will mark the sensor error, RkThe product regulation error is taken.
The second step is that: and establishing a Kalman filtering model.
xk+1=Akxk+wk
yk=Ckxk+vk
In the formula, xkIs a one-dimensional temperature variable; a. thek=1;Ck=1;wkAnd vkHas a variance of QkAnd Rk
The third step: setting an initial true temperature value x(0)=T0And covariance P of initial time(0)
The fourth step: reading the optimal estimated value T at the k-1 timek-1Measured value t at time kkCalculating a gain factor
Hk=P(k-1)/(P(k-1)+Rk)#(3)
Then
Tk=Tk-1+Hk(tk-Tk-1)#(4)
Optimal noise covariance at time k
P(k)=(1-Hk)P(k-1)#(5)
The fifth step: reading the optimal estimated value T at the k-th moment kMeasured value t at time k +1k+1Calculating a gain factor Hk+1And Tk+1The optimum noise covariance P at time k +1(k+1)
And a sixth step: and repeating the fourth step and the fifth step to estimate the optimal temperature value.
And step 3: calculating the grey prediction data of the feeding pressure of the diesel engine lubricating oil: the diesel engine gray modeling trend prediction step is the core of the method, and the prediction calculation is carried out according to the construction steps of the gray prediction model through effective data obtained after the preprocessing step, so as to obtain a prediction result. Matlab software is adopted in the development environment of the step.
First, the relevant definition of the gray prediction model GM (2,1) is given:
the grey prediction model GM (2,1) reflects a second order differential function of a variable with respect to time, the corresponding differential equation of which can be expressed as
Figure BDA0002592171360000101
Wherein p is(1)The accumulated number sequence is generated through one accumulation operation; t is time; a is1,a2U is the parameter to be estimated, respectively the developing gray coefficient and the endogenous generationThe ash factor is controlled.
Establishing and calculating steps of gray GM (2,1) model
The first step is as follows: and establishing an original pressure data array according to the effective data obtained after preprocessing.
Let P(0)=(p(0)(1),p(0)(2),p(0)(3)…p(0)(n))
Wherein p is(0)(i) (i-1, 2, … n) is time series data of lubricant feed pressure parameters
The second step is that: for a given sequence P(0)Calculate P(0)Step ratio of(0)(i) And (4) performing a grade ratio test. The calculation formula of the grade ratio is
Figure BDA0002592171360000111
The inspection standard is
If the test criterion is met, the subsequent modeling step of GM (2,1) can be performed.
The third step: to P(0)Performing 1-AGO accumulation operation and 1-IAGO accumulation subtraction to obtain generated P(1)And alpha(1)P(0)Array of numbers
P(1)=(p(1)(1),p(1)(2),…p(1)(n))
α(1)P(0)=(α(1)p(0)(2),α(1)p(0)(3)…α(1)p(0)(n))
Wherein
Figure BDA0002592171360000112
α(1)p(0)(i)=p(0)(i)-p(0)(i-1),i=2,3,…,n#(10)
The fourth step: test P(1)Whether the method has quasi-exponential law. The quasi-exponential calculation formula is
Figure BDA0002592171360000113
The inspection standard is
(1)(i)∈(1,1.5)
If the test criterion is met, the subsequent modeling step of GM (2,1) can be performed.
The fifth step: to P(1)And performing an adjacent mean generation operation. Order to
z(1)(i)=0.5p(1)(i)+0.5p(1)(i-1)(i=2,3…n)#(12)
To obtain Z(1)=(z(1)(2),z(1)(3),z(1)(4),z(1)(5))
And a sixth step: for parameter column
Figure BDA0002592171360000114
A least squares estimation is performed. De a1,a2And the value of u.
Wherein
Figure BDA0002592171360000115
Figure BDA0002592171360000116
The seventh step: determining solutions to models and equations
Regarding the solution of the GM (2,1) whitening equation, if P(1)*Is that
Figure BDA0002592171360000121
The special solution of (a) is that,
Figure BDA0002592171360000122
is corresponding to a homogeneous equation
Figure BDA0002592171360000123
General solution of (1) then
Figure BDA0002592171360000124
Is a general solution to the GM (2,1) whitening equation.
General solution of whitening equation: when characteristic equation r2+a1r+a20 with unequal solid root r1,r2When the temperature of the water is higher than the set temperature,
Figure BDA0002592171360000125
when characteristic equation r2+a1r+a2When the same solid root r is present at 0,
Figure BDA0002592171360000126
when characteristic equation r2+a1r+a20 has a conjugate complex root r1=α+iβ,r2When the value is alpha-i beta, the reaction is carried out,
Figure BDA0002592171360000127
special solutions of the whitening equation: when zero is not the root of the characteristic equation, P(1)*=C;
When a single root of the characteristic equation is zero, P (1)*=Cp;
When the heavy root of the characteristic equation is zero, P(1)*=Cp2
For example: when a is1=-3,a2When u is 10, r is 22Two different real roots exist at-3 r +2 ═ 0, then the general solution to the homogeneous equation is
Figure BDA0002592171360000128
And since zero is not the heel of the characteristic equation, then P(1)*=C。
So whitening model
Figure BDA0002592171360000129
Is solved as p(1)(t)=c1et+c2e2t+C.
Reuse boundary condition P(1)=(p(1)(1),p(1)(2),…p(1)(n)) to give c1,c2And C. The time response formula of GM (2,1) can be obtained
Figure BDA00025921713600001210
Eighth step: calculating P(1)Analog value of
Figure BDA00025921713600001211
The ninth step: reduction to find P(0)The analog value of (1). By
Figure BDA00025921713600001212
To obtain
Figure BDA00025921713600001213
The tenth step: and (5) checking errors.
There are three methods of model checking: and (5) testing relative error, correlation degree and mean square error. In general, the most common is a relative error check:
Figure BDA0002592171360000131
the specific test indexes are as follows: first-stage: the index critical value is 0.01; and (2) second stage: the index critical value is 0.05; third-stage: the index critical value is 0.10; and (4) fourth stage: the index threshold was 0.20. And if the output result does not meet the critical value of the four-level index, adopting a residual error optimization gray prediction model.
And 4, step 4: judging the future working state of the diesel engine: and after the prediction result is compared with the alarm threshold value of the diesel engine safety protection system, the operation state of the diesel engine is logically judged, and the judgment result is fed back to the upper computer. Fig. 2 is a graph of the predicted lubricant feed pressure during operation of a diesel engine embodying the present invention. As shown in fig. 2, the pressure of the lubricating oil entering the diesel engine has a downward trend, and the pressure of the lubricating oil entering the diesel engine predicted according to the operation data is lower than the pressure threshold of the security system after 80min, so that it is determined that the pressure of the lubricating oil entering the diesel engine is too low in the future operation state of the diesel engine. At the moment, the security system sends an alarm signal to the upper computer through a program, and simultaneously sends the prediction data to the upper computer in a charting mode for further analysis.
The above description is only a preferred embodiment of the method for predicting the entering safety parameters of the diesel engine lubricating oil based on the grey theory, and the protection range of the method for predicting the entering safety parameters of the diesel engine lubricating oil based on the grey theory is not limited to the above embodiments, and all technical schemes belonging to the idea belong to the protection range of the invention. It should be noted that modifications and variations which do not depart from the gist of the invention will be those skilled in the art to which the invention pertains and which are intended to be within the scope of the invention.

Claims (7)

1. A method for predicting the security parameters of diesel engine lubricating oil entering a machine based on a grey theory is characterized by comprising the following steps: the method comprises the following steps:
step 1: acquiring pressure data of the diesel engine through a pressure sensor, wherein the pressure data is lubricating oil feeding pressure operation data of the diesel engine, acquiring the pressure data from the pressure sensor of a lubricating oil feeding inlet pipeline of the diesel engine through a data acquisition card, and storing the data into Excel;
step 2: carrying out data preprocessing on collected lubricating oil feeding pressure operation data of the diesel engine, and filtering out environmental noise influence;
and step 3: according to the data after noise filtering, the diesel engine lubricating oil enters the engine pressure gray prediction data to be processed, and a prediction result is obtained;
And 4, step 4: and comparing the prediction result with an alarm threshold value of the diesel engine safety protection system, judging the running state of the diesel engine, and giving an alarm according to the running state of the diesel engine.
2. The diesel engine lubricating oil inlet security parameter prediction method based on the gray theory as claimed in claim 1, characterized in that: the step 2 specifically comprises the following steps:
step 2.1: initializing filter parameters and determining input signal wkObservation noise v of output signalk、QkAnd product specification error RkPreprocessing the collected pressure operation data of the lubricating oil of the diesel engine by adopting a Kalman filtering method, filtering the environmental noise influence, establishing a state equation and an output equation, and expressing a state equation x by the following formulak+1And output equation yk
xk+1=Akxk+wk
yk=Ckxk+vk
Wherein k is time, wkFor input signal, vkFor the observed noise of the output signal, A is the gain matrix between the state variables, xkC is a gain matrix between the state variable and the output signal;
determining an input signal wkObservation noise v of output signalk、QkAnd product specification error Rk
Step 2.2: setting the initial true temperature to x(0)=T0And covariance P of initial time(0)
Step 2.3: reading the optimal estimated value T at the k-1 time k-1Measured value t at time kkCalculating a gain factor, the gain factor being represented by:
Hk=P(k-1)/(P(k-1)+Rk)
Tk=Tk-1+Hk(tk-Tk-1)
the optimal to noise covariance at time k is represented by:
P(k)=(1-Hk)P(k-1)
step 2.4: reading the optimal estimated value T at the k-th momentkAt time k +1Measured value tk+1Calculating a gain factor Hk+1And Tk+1The optimum noise covariance P at time k +1(k+1)
Step 2.5: and (5) repeating the steps 2.3 to 2.4, estimating an optimal value, and obtaining effective data after the environmental noise is filtered.
3. The diesel engine lubricating oil inlet security parameter prediction method based on the gray theory as claimed in claim 1, characterized in that: when the real temperature of the diesel engine is constant, Qk0; when the temperature of the diesel engine changes along with the running state, Qk=0.01。
4. The diesel engine lubricating oil inlet security parameter prediction method based on the gray theory as claimed in claim 1, characterized in that: the step 3 specifically comprises the following steps:
step 3.1: establishing a gray prediction model GM (2,1), and expressing a differential equation of the gray prediction model GM (2,1) by the following formula:
Figure FDA0002592171350000021
wherein p is(1)The accumulated number sequence is generated through one accumulation operation; t is time; a is1,a2U is a parameter to be estimated, namely a developing ash coefficient and an endogenous control ash coefficient;
step 3.2: establishing an original pressure data array according to the data after noise filtering, and expressing the array P by the following formula (0)
P(0)=(p(0)(1),p(0)(2),p(0)(3)…p(0)(n))
Wherein p is(0)(i) Time series data of the pressure parameter of the lubricating oil inlet machine, i is 1, 2, … n;
step 3.3: according to P(0)Determining P(0)Step ratio of(0)(i) Is tested for the step ratio, and the step ratio σ is expressed by the following formula(0)(i):
Figure FDA0002592171350000022
Step 3.4: current class ratio sigma(0)(i) When the inspection standard is satisfied, for P(0)Performing 1-AGO accumulation operation and 1-IAGO accumulation subtraction to obtain generated P(1)And alpha(1)P(0)Array, P is represented by the formula(1)And alpha(1)P(0)The sequence of the numbers:
P(1)=(p(1)(1),p(1)(2),…p(1)(n))
α(1)P(0)=(α(1)p(0)(2),α(1)p(0)(3)…α(1)p(0)(n))
Figure FDA0002592171350000023
α(1)p(0)(i)=p(0)(i)-p(0)(i-1),i=2,3,…,n
step 3.5: test P(1)If the standard index rule exists, the standard index is calculated by the following formula(1)(i):
Figure FDA0002592171350000024
Step 3.6: when the quasi-index meets the inspection standard, P is aligned(1)Performing an immediate mean generation operation, wherein the immediate mean is represented by the following formula:
z(1)(i)=0.5p(1)(i)+0.5p(1)(i-1)(i=2,3…n)
Z(1)=(z(1)(2),z(1)(3),z(1)(4),z(1)(5))
step 3.7: for parameter column
Figure FDA00025921713500000310
Performing least square estimation to obtain a1,a2,u:
Figure FDA0002592171350000031
Figure FDA0002592171350000032
Step 3.8: solving a whitening equation for GM (2,1) to obtain a time response equation for GM (2,1), the time response equation being represented by:
Figure FDA0002592171350000033
solving for P(1)Is represented by the following formula(1)Analog value of (d):
Figure FDA0002592171350000034
determining P from analog value reduction(0)Is represented by the following formula(0)Analog value of (d):
Figure FDA0002592171350000035
Figure FDA0002592171350000036
will P(0)As a result of the prediction
Figure FDA0002592171350000037
Step 3.9: and carrying out error check on the model, and expressing the error detection value by the following formula:
Figure FDA0002592171350000038
the test indexes are as follows: first-stage: the index critical value is 0.01; and (2) second stage: the index critical value is 0.05; third-stage: the index critical value is 0.10; and (4) fourth stage: the index critical value is 0.20; and if the error detection value does not meet the critical value of the four-level index, adopting a residual error optimization gray prediction model GM (2, 1).
5. The method for predicting the security parameters of the diesel engine lubricating oil inlet based on the gray theory as claimed in claim 4, wherein the method comprises the following steps: determination of the step ratio sigma(0)(i) The method specifically meets the inspection standard:
Figure FDA0002592171350000039
when the grade ratio is within the above formula check criteria, then it is satisfied.
6. The method for predicting the security parameters of the diesel engine lubricating oil inlet based on the gray theory as claimed in claim 4, wherein the method comprises the following steps: the specific method for checking whether the quasi-index has the quasi-index rule is as follows:
(1)(i)∈(1,1.5)
the quasi-index is satisfied when it is within the above-described criteria.
7. The diesel engine lubricating oil inlet security parameter prediction method based on the gray theory as claimed in claim 1, characterized in that: and after the prediction result is compared with the alarm threshold of the diesel engine safety protection system, the pressure threshold is lower than that of the security system after 80min according to the predicted oil feeding pressure, the future running state of the diesel engine is judged to be that the lubricating oil feeding pressure is too low, at the moment, the security system sends an alarm signal to the upper computer through a program, and the prediction data is simultaneously sent to the upper computer in a charted form for further analysis.
CN202010698450.8A 2020-07-20 2020-07-20 Diesel engine lubricating oil entering security parameter prediction method based on grey theory Pending CN111855219A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010698450.8A CN111855219A (en) 2020-07-20 2020-07-20 Diesel engine lubricating oil entering security parameter prediction method based on grey theory

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010698450.8A CN111855219A (en) 2020-07-20 2020-07-20 Diesel engine lubricating oil entering security parameter prediction method based on grey theory

Publications (1)

Publication Number Publication Date
CN111855219A true CN111855219A (en) 2020-10-30

Family

ID=73002079

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010698450.8A Pending CN111855219A (en) 2020-07-20 2020-07-20 Diesel engine lubricating oil entering security parameter prediction method based on grey theory

Country Status (1)

Country Link
CN (1) CN111855219A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113916843A (en) * 2021-10-26 2022-01-11 中国人民解放军91315部队 Grey model-based mechanical equipment lubricating oil performance prediction method
CN114295095A (en) * 2021-11-26 2022-04-08 广西科技大学 Method for determining optimal measuring point number of free-form surface detection
CN114577480A (en) * 2022-03-02 2022-06-03 中国船舶重工集团柴油机有限公司 Diesel engine state monitoring method and system based on sequence transformation
CN114638435A (en) * 2022-03-29 2022-06-17 中国船舶重工集团公司第七一一研究所 Diesel engine security parameter prediction method based on data driving

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1580003A1 (en) * 2003-02-05 2005-09-28 International United Technology Co., Ltd. Ink jet printhead identification circuit and method
CN102705078A (en) * 2012-04-19 2012-10-03 哈尔滨工程大学 Diesel engine fault prediction method based on gray model
CN105043593A (en) * 2015-06-30 2015-11-11 株洲南车时代电气股份有限公司 Locomotive temperature sensor fault diagnosis and fault tolerance estimation method
CN105466693A (en) * 2015-11-13 2016-04-06 哈尔滨工程大学 Diesel engine fuel oil fuel oil system fault pre-diagnosing method based on gray model
CN108008718A (en) * 2017-12-07 2018-05-08 上海海事大学 Study on intelligent based on model
CN109296457A (en) * 2018-10-30 2019-02-01 中船动力研究院有限公司 A kind of diesel generating set central control desk
CN110109162A (en) * 2019-03-26 2019-08-09 西安开阳微电子有限公司 A kind of Kalman filtering positioning calculation method that GNSS receiver is adaptive
CN110618313A (en) * 2019-09-09 2019-12-27 中车唐山机车车辆有限公司 Online energy consumption detection and prediction device and method for train power system
CN110738331A (en) * 2019-09-19 2020-01-31 智慧航海(青岛)科技有限公司 intelligent marine engine room system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1580003A1 (en) * 2003-02-05 2005-09-28 International United Technology Co., Ltd. Ink jet printhead identification circuit and method
CN102705078A (en) * 2012-04-19 2012-10-03 哈尔滨工程大学 Diesel engine fault prediction method based on gray model
CN105043593A (en) * 2015-06-30 2015-11-11 株洲南车时代电气股份有限公司 Locomotive temperature sensor fault diagnosis and fault tolerance estimation method
CN105466693A (en) * 2015-11-13 2016-04-06 哈尔滨工程大学 Diesel engine fuel oil fuel oil system fault pre-diagnosing method based on gray model
CN108008718A (en) * 2017-12-07 2018-05-08 上海海事大学 Study on intelligent based on model
CN109296457A (en) * 2018-10-30 2019-02-01 中船动力研究院有限公司 A kind of diesel generating set central control desk
CN110109162A (en) * 2019-03-26 2019-08-09 西安开阳微电子有限公司 A kind of Kalman filtering positioning calculation method that GNSS receiver is adaptive
CN110618313A (en) * 2019-09-09 2019-12-27 中车唐山机车车辆有限公司 Online energy consumption detection and prediction device and method for train power system
CN110738331A (en) * 2019-09-19 2020-01-31 智慧航海(青岛)科技有限公司 intelligent marine engine room system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
唐启义: "《实用统计分析及其计算机处理平台[M]》", 31 December 1997 *
杨丹: "卡尔曼滤波器设计及其应用研究", 《万方》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113916843A (en) * 2021-10-26 2022-01-11 中国人民解放军91315部队 Grey model-based mechanical equipment lubricating oil performance prediction method
CN114295095A (en) * 2021-11-26 2022-04-08 广西科技大学 Method for determining optimal measuring point number of free-form surface detection
CN114295095B (en) * 2021-11-26 2023-07-14 广西科技大学 Method for determining optimal number of measuring points for free-form surface detection
CN114577480A (en) * 2022-03-02 2022-06-03 中国船舶重工集团柴油机有限公司 Diesel engine state monitoring method and system based on sequence transformation
CN114577480B (en) * 2022-03-02 2023-11-10 中船发动机有限公司 Diesel engine state monitoring method and system based on sequence transformation
CN114638435A (en) * 2022-03-29 2022-06-17 中国船舶重工集团公司第七一一研究所 Diesel engine security parameter prediction method based on data driving

Similar Documents

Publication Publication Date Title
CN111855219A (en) Diesel engine lubricating oil entering security parameter prediction method based on grey theory
CN114813105B (en) Gear box fault early warning method and system based on working condition similarity evaluation
CN110298455B (en) Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction
Ahmed et al. Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor
Wegerich Similarity based modeling of time synchronous averaged vibration signals for machinery health monitoring
CN108508863A (en) A kind of electromechanical equipment method for diagnosing faults based on gray model
CN111648992B (en) Gas turbine compressor fault identification early warning method
Hansen et al. A new approach to the challenge of machinery prognostics
CN107710089B (en) Plant equipment diagnosis device and plant equipment diagnosis method
CN114934898B (en) Hydraulic pump fault diagnosis analysis system based on multi-mode parameters
CN111367253B (en) Chemical system multi-working-condition fault detection method based on local adaptive standardization
Ramezani et al. Prognostics and health management in machinery: A review of methodologies for RUL prediction and roadmap
CN112418306A (en) Gas turbine compressor fault early warning method based on LSTM-SVM
Jain et al. Dynamic optimization of process quality control and maintenance planning
CN112149953B (en) Electromechanical equipment operation safety assessment method based on multimode linkage and multistage cooperation
CN114088389A (en) Data processing method and related device for gearbox
CN114738132A (en) Supercharger speed sensor fault diagnosis method and system based on real ship data
Kobbacy et al. Condition monitoring of diesel engines
Mollazade et al. An intelligent model based on data mining and fuzzy logic for fault diagnosis of external gear hydraulic pumps
CN117312972A (en) Method for identifying health state of scraper conveyor speed reducer
KR102692731B1 (en) Method for diagnosing engine abnormalities, computer-readable storage medium recording engine abnormality diagnosis program, and engine abnormality diagnosis system
Sun et al. Anomaly detection of marine diesel engine valve system based on Mahalanobis distance
Byington et al. False alarm mitigation of vibration diagnostic systems
CN114118720A (en) Nuclear power plant circulating water pump operation state comprehensive evaluation method and device, electronic equipment and storage medium
CN114995338A (en) Industrial process micro-fault detection method based on normative variable analysis and JS divergence fusion

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20201030

RJ01 Rejection of invention patent application after publication