CN118192479A - Factory workshop digital twin model correction method and system based on data acquisition - Google Patents
Factory workshop digital twin model correction method and system based on data acquisition Download PDFInfo
- Publication number
- CN118192479A CN118192479A CN202410615645.XA CN202410615645A CN118192479A CN 118192479 A CN118192479 A CN 118192479A CN 202410615645 A CN202410615645 A CN 202410615645A CN 118192479 A CN118192479 A CN 118192479A
- Authority
- CN
- China
- Prior art keywords
- digital twin
- twin model
- data
- workshop
- energy consumption
- 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.)
- Granted
Links
- 238000012937 correction Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004519 manufacturing process Methods 0.000 claims abstract description 194
- 238000005265 energy consumption Methods 0.000 claims abstract description 99
- 230000036541 health Effects 0.000 claims abstract description 83
- 239000002994 raw material Substances 0.000 claims description 52
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a factory workshop digital twin model correction method and a system based on data acquisition, and relates to the technical field of model correction; constructing a first digital twin model, predicting the state health value of production equipment, and constructing a second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop; calculating a mean square error function of the first digital twin model; calculating a mean square error function of the second digital twin model; and correcting the first digital twin model and the second digital twin model to obtain a corrected plant workshop digital twin model. The method and the device can improve the accuracy of the prediction of the production condition of the factory workshop and help a producer to better manage the factory workshop.
Description
Technical Field
The invention relates to the technical field of model correction, in particular to a factory workshop digital twin model correction method and system based on data acquisition.
Background
With the rapid development of information technology, intelligent manufacturing and industrial intellectualization have become major trends in the global manufacturing industry. Factory workshops have also evolved towards more and more intelligent. The production flow can be optimized by constructing a factory workshop digital twin model through a digitizing technology and a data driving method, and the production efficiency and the product quality are improved. The accuracy of the prediction of the production condition of the factory workshop can be improved by continuously correcting the digital twin model, and meanwhile, the correction of the digital twin model is also required to be analyzed by combining with the specific environment of the factory workshop, so that the real-time accuracy of the prediction process of the digital twin model is ensured.
The invention discloses a digital twin-based automobile assembly workshop monitoring simulation system, which comprises an assembly workshop static model building module, a bidirectional channel data acquisition module, an assembly workshop dynamic model building module, a production operation synchronous correction module and an assembly workshop entity control module, wherein the assembly workshop static model building module is used for initially building a static model of an assembly workshop entity, the bidirectional channel data acquisition module is used for acquiring real-time operation data of a static model sub-item through a bidirectional communication channel, the assembly workshop dynamic model building module is used for building a dynamic model of an assembly workshop by combining the assembly workshop static model and the acquired real-time operation data of the static model sub-item, the production operation synchronous correction module is used for monitoring the dynamic model of the assembly workshop, calculating and correcting the operation flow of the synchronous assembly workshop and outputting a correction synchronous signal, and the assembly workshop control module is used for controlling the assembly workshop entity through the correction synchronous signal.
The patent with publication number CN117495221A discloses a full-automatic intelligent loading control method based on digital twin scene establishment, which relates to the technical field of intelligent loading and comprises the following steps: building a twin plant virtual scene: the method comprises the steps of collecting environment information in a real-world express loading factory and action information and position information of mechanical equipment in the factory in real time through a sensor and a camera, cleaning, denoising and correcting the collected information, uploading the collected information to a cloud server, constructing a virtual scene model by utilizing Solidworks modeling software, optimizing the model by using an LOD technology, and importing the optimized three-dimensional model into a Unity3D virtual simulation platform. The invention provides a full-automatic intelligent loading control method based on digital twin scene establishment, which is convenient for scanning and identifying vehicles in the follow-up process by reminding the speed limit of the vehicles entering a factory, and avoids unclear captured images caused by the too high speed of the vehicles.
The problems presented in the background art exist in the above patents: analyzing without combining with the specific environment of the factory workshop, and optimizing the factory workshop digital twin model in real time according to the analysis result; in order to solve the problems, the invention provides a factory workshop digital twin model correction method and system based on data acquisition.
Disclosure of Invention
Aiming at the defects of the prior art, the main purpose of the invention is to provide a factory workshop digital twin model correction method and system based on data acquisition, which can effectively solve the problems in the background art. The specific technical scheme of the invention is as follows:
the factory workshop digital twin model correction method based on data acquisition comprises the following specific steps:
s1, collecting environmental data and production line data of a factory workshop at n moments, raw material data and yield data of each production line, and acquiring running state data of various production equipment at n moments;
S2, building a factory workshop digital twin model, wherein the factory workshop digital twin model comprises a first digital twin model and a second digital twin model;
S3, constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment;
S4, constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
S5, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a real-time production equipment state health value, collecting real-time raw material data and real-time yield data, and calculating a real-time factory workshop total energy consumption value;
S6, substituting the predicted production equipment state health value and the predicted production equipment real-time state health value into a first digital twin model correction formula to calculate a mean square error function of the first digital twin model;
S7, substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
s8, respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model.
Specifically, the environmental data includes: workshop temperature and workshop humidity measured by using a temperature and humidity sensor; the operating state data includes: device run time, device temperature, device noise measured using a sound level meter; the production line data includes: the number of production lines of a factory workshop and the number of production equipment on each production line; the raw material data includes: the number of kinds of raw materials, the weight of each raw material; the production data includes a production yield for each production line.
Specifically, the specific step of S3 is as follows:
S301, environment data and running state data at n moments are used as equipment state health feature data, and the equipment state health feature data are input into a first digital twin model to obtain a predicted production equipment state health value;
S302, training the first digital twin model based on a historical equipment state health sample set, wherein the historical equipment state health sample set comprises equipment state health characteristic data and corresponding production equipment state health values;
S303, the logic for acquiring the state health value of the production equipment is as follows:
Acquiring workshop temperature, workshop humidity, equipment running time, equipment temperature and equipment noise at n moments, substituting the workshop temperature, the workshop humidity, the equipment running time and the equipment temperature into a production equipment state health value calculation formula for calculating production equipment state health values at n moments, wherein the production equipment state health value calculation formula is as follows:
; wherein/> The production equipment state health value at the ith moment; /(I)Respectively the equipment running time, the equipment noise, the workshop humidity, the equipment temperature and the workshop temperature at the ith moment; Respectively, maximum acceptable noise level of production equipment, maximum humidity and minimum humidity for ensuring the operation of the production equipment, minimum value and maximum value of equipment temperature in n moments, workshop temperature at the moment corresponding to the minimum value of the equipment temperature, workshop temperature at the moment corresponding to the maximum value of the equipment temperature,/> Respectively an equipment operation time influence coefficient, an equipment noise influence coefficient, a humidity influence coefficient and a temperature influence coefficient, whereinAre all greater than 0 and add up to 1.
Specifically, the specific step of S4 is as follows:
S401, taking production line data, raw material data and yield data at n moments as production line energy consumption characteristic data, and inputting the production line energy consumption characteristic data into a second digital twin model to obtain a predicted total energy consumption value of a factory workshop;
S402, training the second digital twin model based on a historical line energy consumption sample set, wherein the historical line energy consumption sample set comprises line energy consumption characteristic data and corresponding factory workshop total energy consumption values;
s403, acquiring logic of the total energy consumption value of the factory workshop is as follows:
Acquiring the number of production lines of factory workshops at n moments and the number of production equipment on each production line; the method comprises the steps of substituting the types and the numbers of raw materials, the weight of each raw material and the product yield of each production line into a production line energy consumption value calculation formula to calculate the production line energy consumption values at n moments, wherein the production line energy consumption value calculation formula is as follows: Wherein/> The energy consumption value of the production line at the ith moment of the jth production line is used as the energy consumption value of the production line at the ith moment; /(I)For the energy consumption value of the q-th production equipment on the j-th production line at the i-th moment,The number of production equipment on the jth production line at the ith moment; /(I)For the energy consumption coefficient of the kth raw material on the jth production line at the ith moment,/>For the weight of the kth raw material on the jth line at the ith moment,/>Is the kind and the quantity of the raw materials on the jth production line at the ith moment.
Specifically, the step S403 further includes:
Calculating a total energy consumption value of the plant at the ith moment Where M is the line number at time i.
Specifically, the step S5 includes the following specific steps:
s501, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, and calculating to obtain a real-time production equipment state health value H according to the acquisition logic of the production equipment state health value;
S502, acquiring real-time raw material data and real-time yield data, and calculating to obtain a real-time total energy consumption value E of the factory workshop according to the acquisition logic of the total energy consumption value of the factory workshop.
Specifically, the first digital twin model correction formula is: Wherein/> A mean square error function for the first digital twin model; /(I)Producing a device state health value for an i-th moment predicted by the first digital twin model,/>And calculating the production equipment state health value at the ith moment according to the production equipment state health value calculation formula.
Specifically, the second digital twin model correction formula is: Wherein/> A mean square error function of a second digital twin model; /(I)Factory shop total energy consumption value at i-th moment predicted for second digital twin model,/>And calculating the total energy consumption value of the plant at the ith moment according to a total energy consumption value calculation formula of the plant.
Specifically, the step S8 specifically includes: and correcting the first digital twin model and the second digital twin model by using the minimized mean square error function of the first digital twin model and the minimized mean square error function of the second digital twin model as correction targets of the first digital twin model and the second digital twin model until the mean square error function of the first digital twin model and the mean square error function of the second digital twin model reach convergence respectively, and stopping correction to obtain the corrected factory workshop digital twin model.
Specifically, the factory workshop digital twin model correction system based on data acquisition is realized based on the factory workshop digital twin model correction method based on data acquisition, and comprises the following modules:
the data acquisition module is used for acquiring environment data and production line data of a factory workshop at n times, raw material data and yield data of each production line and acquiring running state data of various production equipment at n times;
The plant workshop digital twin model building module is used for building a plant workshop digital twin model, and the plant workshop digital twin model comprises a first digital twin model and a second digital twin model; constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment; constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
The real-time data analysis module is used for collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a state health value of the real-time production equipment, collecting real-time raw material data and real-time yield data, and calculating a total energy consumption value of the real-time factory workshop;
the correction processing module is used for substituting the predicted production equipment state health value and the real-time state health value of the production equipment into the first digital twin model correction formula to calculate a mean square error function of the first digital twin model; substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
The correction model acquisition module is used for respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model;
and the control module is used for controlling the operation of each module.
Compared with the prior art, the invention has the following beneficial effects:
The invention collects environmental data, production line data, raw material data, yield data and running state data of production equipment; constructing a first digital twin model, predicting the state health value of production equipment, and constructing a second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop; calculating a mean square error function of the first digital twin model; calculating a mean square error function of the second digital twin model; and correcting the first digital twin model and the second digital twin model to obtain a corrected plant workshop digital twin model. The method and the device can improve the accuracy of the prediction of the production condition of the factory workshop and help a producer to better manage the factory workshop.
Drawings
FIG. 1 is a workflow diagram of a method for correcting a digital twin model of a factory workshop based on data acquisition of the present invention;
FIG. 2 is a block diagram of a plant-to-plant digital twin model correction system based on data acquisition according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
The embodiment provides a correction method for a factory workshop digital twin model based on data acquisition, which specifically comprises the following specific steps as shown in fig. 1:
s1, collecting environmental data and production line data of a factory workshop at n moments, raw material data and yield data of each production line, and acquiring running state data of various production equipment at n moments;
S2, building a factory workshop digital twin model, wherein the factory workshop digital twin model comprises a first digital twin model and a second digital twin model;
S3, constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment;
S4, constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
S5, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a real-time production equipment state health value, collecting real-time raw material data and real-time yield data, and calculating a real-time factory workshop total energy consumption value;
S6, substituting the predicted production equipment state health value and the predicted production equipment real-time state health value into a first digital twin model correction formula to calculate a mean square error function of the first digital twin model;
S7, substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
s8, respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model.
In this embodiment, the environment data includes: workshop temperature and workshop humidity measured by using a temperature and humidity sensor; the operating state data includes: device run time, device temperature, device noise measured using a sound level meter; the production line data includes: the number of production lines of a factory workshop and the number of production equipment on each production line; the raw material data includes: the number of kinds of raw materials, the weight of each raw material; the production data includes a production yield for each production line.
In this embodiment, the specific steps of S3 are as follows:
S301, environment data and running state data at n moments are used as equipment state health feature data, and the equipment state health feature data are input into a first digital twin model to obtain a predicted production equipment state health value;
S302, training the first digital twin model based on a historical equipment state health sample set, wherein the historical equipment state health sample set comprises equipment state health characteristic data and corresponding production equipment state health values;
S303, the logic for acquiring the state health value of the production equipment is as follows:
Acquiring workshop temperature, workshop humidity, equipment running time, equipment temperature and equipment noise at n moments, substituting the workshop temperature, the workshop humidity, the equipment running time and the equipment temperature into a production equipment state health value calculation formula for calculating production equipment state health values at n moments, wherein the production equipment state health value calculation formula is as follows: ; wherein/> The production equipment state health value at the ith moment; /(I)Respectively the equipment running time, the equipment noise, the workshop humidity, the equipment temperature and the workshop temperature at the ith moment; /(I)Respectively, maximum acceptable noise level of production equipment, maximum humidity and minimum humidity for ensuring the operation of the production equipment, minimum value and maximum value of equipment temperature in n moments, workshop temperature at the moment corresponding to the minimum value of the equipment temperature, workshop temperature at the moment corresponding to the maximum value of the equipment temperature,/>Respectively an equipment operation time influence coefficient, an equipment noise influence coefficient, a humidity influence coefficient and a temperature influence coefficient, wherein/>All greater than 0 and the sum is 1, it is noted that/>Are set by the person skilled in the art according to the actual requirements and the specific circumstances.
In this embodiment, the specific steps of S4 are as follows:
S401, taking production line data, raw material data and yield data at n moments as production line energy consumption characteristic data, and inputting the production line energy consumption characteristic data into a second digital twin model to obtain a predicted total energy consumption value of a factory workshop;
S402, training the second digital twin model based on a historical line energy consumption sample set, wherein the historical line energy consumption sample set comprises line energy consumption characteristic data and corresponding factory workshop total energy consumption values;
s403, acquiring logic of the total energy consumption value of the factory workshop is as follows:
Acquiring the number of production lines of factory workshops at n moments and the number of production equipment on each production line; the method comprises the steps of substituting the types and the numbers of raw materials, the weight of each raw material and the product yield of each production line into a production line energy consumption value calculation formula to calculate the production line energy consumption values at n moments, wherein the production line energy consumption value calculation formula is as follows: Wherein/> The energy consumption value of the production line at the ith moment of the jth production line is used as the energy consumption value of the production line at the ith moment; /(I)For the energy consumption value of the q-th production equipment on the j-th production line at the i-th moment,The number of production equipment on the jth production line at the ith moment; /(I)For the energy consumption coefficient of the kth raw material on the jth production line at the ith moment,/>For the weight of the kth raw material on the jth line at the ith moment,/>Is the kind and the quantity of the raw materials on the jth production line at the ith moment. The energy consumption coefficient of the raw material is the energy consumed by the raw material per unit weight, and is usually expressed in a specific energy unit (for example, joules) and is used to evaluate the energy consumption of the raw material in the production process.
In this embodiment, the step S403 further includes:
Calculating a total energy consumption value of the plant at the ith moment Where M is the line number at time i.
In this embodiment, the step S5 includes the following specific steps:
s501, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, and calculating to obtain a real-time production equipment state health value H according to the acquisition logic of the production equipment state health value;
S502, acquiring real-time raw material data and real-time yield data, and calculating to obtain a real-time total energy consumption value E of the factory workshop according to the acquisition logic of the total energy consumption value of the factory workshop.
In this embodiment, the first digital twin model correction formula is: Wherein/> A mean square error function for the first digital twin model; /(I)Producing a device state health value for an i-th moment predicted by the first digital twin model,/>And calculating the production equipment state health value at the ith moment according to the production equipment state health value calculation formula.
In this embodiment, the second digital twin model correction formula is: Wherein/> A mean square error function of a second digital twin model; /(I)Factory shop total energy consumption value at i-th moment predicted for second digital twin model,/>And calculating the total energy consumption value of the plant at the ith moment according to a total energy consumption value calculation formula of the plant.
In this embodiment, the step S8 specifically includes: and correcting the first digital twin model and the second digital twin model by using the minimized mean square error function of the first digital twin model and the minimized mean square error function of the second digital twin model as correction targets of the first digital twin model and the second digital twin model until the mean square error function of the first digital twin model and the mean square error function of the second digital twin model reach convergence respectively, and stopping correction to obtain the corrected factory workshop digital twin model.
Example 2
The embodiment provides a factory workshop digital twin model correction system based on data acquisition, and specifically adopts a scheme that as shown in fig. 2, the factory workshop digital twin model correction system based on data acquisition is realized based on the factory workshop digital twin model correction method based on data acquisition described in embodiment 1, and the system comprises the following modules:
the data acquisition module is used for acquiring environment data and production line data of a factory workshop at n times, raw material data and yield data of each production line and acquiring running state data of various production equipment at n times;
The plant workshop digital twin model building module is used for building a plant workshop digital twin model, and the plant workshop digital twin model comprises a first digital twin model and a second digital twin model; constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment; constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
The real-time data analysis module is used for collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a state health value of the real-time production equipment, collecting real-time raw material data and real-time yield data, and calculating a total energy consumption value of the real-time factory workshop;
the correction processing module is used for substituting the predicted production equipment state health value and the real-time state health value of the production equipment into the first digital twin model correction formula to calculate a mean square error function of the first digital twin model; substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
The correction model acquisition module is used for respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model;
and the control module is used for controlling the operation of each module.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The method for correcting the digital twin model of the factory workshop based on data acquisition is characterized by comprising the following steps of: the method comprises the following specific steps:
s1, collecting environmental data and production line data of a factory workshop at n moments, raw material data and yield data of each production line, and acquiring running state data of various production equipment at n moments;
S2, building a factory workshop digital twin model, wherein the factory workshop digital twin model comprises a first digital twin model and a second digital twin model;
S3, constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment;
S4, constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
S5, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a real-time production equipment state health value, collecting real-time raw material data and real-time yield data, and calculating a real-time factory workshop total energy consumption value;
S6, substituting the predicted production equipment state health value and the predicted production equipment real-time state health value into a first digital twin model correction formula to calculate a mean square error function of the first digital twin model;
S7, substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
s8, respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model.
2. The method for correcting a digital twin model of a factory workshop based on data acquisition of claim 1, wherein: the environmental data includes: workshop temperature and workshop humidity measured by using a temperature and humidity sensor; the operating state data includes: device run time, device temperature, device noise measured using a sound level meter; the production line data includes: the number of production lines of a factory workshop and the number of production equipment on each production line; the raw material data includes: the number of kinds of raw materials, the weight of each raw material; the production data includes a production yield for each production line.
3. The method for correcting a digital twin model of a factory workshop based on data acquisition of claim 2, wherein: the specific steps of the S3 are as follows:
S301, environment data and running state data at n moments are used as equipment state health feature data, and the equipment state health feature data are input into a first digital twin model to obtain a predicted production equipment state health value;
S302, training the first digital twin model based on a historical equipment state health sample set, wherein the historical equipment state health sample set comprises equipment state health characteristic data and corresponding production equipment state health values;
S303, the logic for acquiring the state health value of the production equipment is as follows:
Acquiring workshop temperature, workshop humidity, equipment running time, equipment temperature and equipment noise at n moments, substituting the workshop temperature, the workshop humidity, the equipment running time and the equipment temperature into a production equipment state health value calculation formula for calculating production equipment state health values at n moments, wherein the production equipment state health value calculation formula is as follows: ; wherein/> The production equipment state health value at the ith moment; /(I)Respectively the equipment running time, the equipment noise, the workshop humidity, the equipment temperature and the workshop temperature at the ith moment; /(I)Respectively, maximum acceptable noise level of production equipment, maximum humidity and minimum humidity for ensuring the operation of the production equipment, minimum value and maximum value of equipment temperature in n moments, workshop temperature at the moment corresponding to the minimum value of the equipment temperature, workshop temperature at the moment corresponding to the maximum value of the equipment temperature,/>Respectively an equipment operation time influence coefficient, an equipment noise influence coefficient, a humidity influence coefficient and a temperature influence coefficient, wherein/>Are all greater than 0 and add up to 1.
4. A method of correcting a plant-to-plant digital twin model based on data acquisition as defined in claim 3, wherein: the specific steps of the S4 are as follows:
S401, taking production line data, raw material data and yield data at n moments as production line energy consumption characteristic data, and inputting the production line energy consumption characteristic data into a second digital twin model to obtain a predicted total energy consumption value of a factory workshop;
S402, training the second digital twin model based on a historical line energy consumption sample set, wherein the historical line energy consumption sample set comprises line energy consumption characteristic data and corresponding factory workshop total energy consumption values;
s403, acquiring logic of the total energy consumption value of the factory workshop is as follows:
Acquiring the number of production lines of factory workshops at n moments and the number of production equipment on each production line; the method comprises the steps of substituting the types and the numbers of raw materials, the weight of each raw material and the product yield of each production line into a production line energy consumption value calculation formula to calculate the production line energy consumption values at n moments, wherein the production line energy consumption value calculation formula is as follows: Wherein/> The energy consumption value of the production line at the ith moment of the jth production line is used as the energy consumption value of the production line at the ith moment; /(I)For the energy consumption value of the q-th production equipment on the j-th production line at the i-th moment,/>The number of production equipment on the jth production line at the ith moment; /(I)For the energy consumption coefficient of the kth raw material on the jth production line at the ith moment,/>For the weight of the kth raw material on the jth line at the ith moment,/>Is the kind and the quantity of the raw materials on the jth production line at the ith moment.
5. The method for correcting a digital twin model of a factory workshop based on data acquisition of claim 4, wherein: the S403 further includes:
Calculating a total energy consumption value of the plant at the ith moment Where M is the line number at time i.
6. The method for correcting a digital twin model of a factory workshop based on data acquisition of claim 5, wherein: s5, comprising the following specific steps:
s501, collecting real-time environment data of a factory workshop and real-time running state data of production equipment, and calculating to obtain a real-time production equipment state health value H according to the acquisition logic of the production equipment state health value;
S502, acquiring real-time raw material data and real-time yield data, and calculating to obtain a real-time total energy consumption value E of the factory workshop according to the acquisition logic of the total energy consumption value of the factory workshop.
7. The method for correcting a digital twin model of a plant workshop based on data acquisition of claim 6, wherein: the first digital twin model correction formula is: Wherein/> A mean square error function for the first digital twin model; /(I)Producing a device state health value for the i-th instant predicted by the first digital twin model,And calculating the production equipment state health value at the ith moment according to the production equipment state health value calculation formula.
8. The method for correcting a digital twin model of a plant workshop based on data acquisition of claim 7, wherein: the second digital twin model correction formula is: Wherein/> A mean square error function of a second digital twin model; /(I)Factory shop total energy consumption value at i-th moment predicted for second digital twin model,/>And calculating the total energy consumption value of the plant at the ith moment according to a total energy consumption value calculation formula of the plant.
9. The method for correcting a digital twin model of a plant workshop based on data acquisition of claim 8, wherein: the step S8 specifically comprises the following steps: and correcting the first digital twin model and the second digital twin model by using the minimized mean square error function of the first digital twin model and the minimized mean square error function of the second digital twin model as correction targets of the first digital twin model and the second digital twin model until the mean square error function of the first digital twin model and the mean square error function of the second digital twin model reach convergence respectively, and stopping correction to obtain the corrected factory workshop digital twin model.
10. A factory workshop digital twin model correction system based on data acquisition, which is realized based on the factory workshop digital twin model correction method based on data acquisition as claimed in any one of claims 1-9, and is characterized in that: the system comprises the following modules:
the data acquisition module is used for acquiring environment data and production line data of a factory workshop at n times, raw material data and yield data of each production line and acquiring running state data of various production equipment at n times;
The plant workshop digital twin model building module is used for building a plant workshop digital twin model, and the plant workshop digital twin model comprises a first digital twin model and a second digital twin model; constructing a first digital twin model, and importing environment data and running state data into the first digital twin model to predict the state health value of the production equipment to obtain a predicted state health value of the production equipment; constructing a second digital twin model, and importing production line data, raw material data and yield data into the second digital twin model to predict the total energy consumption value of the factory workshop to obtain a predicted total energy consumption value of the factory workshop;
The real-time data analysis module is used for collecting real-time environment data of a factory workshop and real-time running state data of production equipment, calculating a state health value of the real-time production equipment, collecting real-time raw material data and real-time yield data, and calculating a total energy consumption value of the real-time factory workshop;
the correction processing module is used for substituting the predicted production equipment state health value and the real-time state health value of the production equipment into the first digital twin model correction formula to calculate a mean square error function of the first digital twin model; substituting the predicted total energy consumption value of the factory workshop and the real-time total energy consumption value of the factory workshop into a second digital twin model correction formula to calculate a mean square error function of a second digital twin model;
The correction model acquisition module is used for respectively correcting the first digital twin model and the second digital twin model based on the mean square error function of the first digital twin model and the mean square error function of the second digital twin model to obtain a corrected factory workshop digital twin model;
and the control module is used for controlling the operation of each module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410615645.XA CN118192479B (en) | 2024-05-17 | 2024-05-17 | Factory workshop digital twin model correction method and system based on data acquisition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410615645.XA CN118192479B (en) | 2024-05-17 | 2024-05-17 | Factory workshop digital twin model correction method and system based on data acquisition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118192479A true CN118192479A (en) | 2024-06-14 |
| CN118192479B CN118192479B (en) | 2024-07-26 |
Family
ID=91399120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410615645.XA Active CN118192479B (en) | 2024-05-17 | 2024-05-17 | Factory workshop digital twin model correction method and system based on data acquisition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118192479B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111708332A (en) * | 2020-05-28 | 2020-09-25 | 上海航天精密机械研究所 | Digital twin system of production line |
| WO2022236064A2 (en) * | 2021-05-06 | 2022-11-10 | Strong Force Iot Portfolio 2016, Llc | Quantum, biological, computer vision, and neural network systems for industrial internet of things |
| CN115407735A (en) * | 2022-08-25 | 2022-11-29 | 扬州大学 | Plant factory management system based on digital twins |
| CN116051025A (en) * | 2022-12-22 | 2023-05-02 | 江苏杰瑞信息科技有限公司 | Digital twin foundation development platform oriented to energy consumption of park |
| CN116300736A (en) * | 2023-03-06 | 2023-06-23 | 广东长盈精密技术有限公司 | MES-based digital factory twin management system, platform and method |
| CN116880372A (en) * | 2023-06-15 | 2023-10-13 | 浙江链捷数字科技有限公司 | Operation optimization method and system of digital twin plant |
| CN117270482A (en) * | 2023-11-22 | 2023-12-22 | 博世汽车部件(苏州)有限公司 | Automobile factory control system based on digital twin |
| WO2024035405A1 (en) * | 2022-08-11 | 2024-02-15 | Siemens Corporation | Interpreting and categorizing traffic on industrial control networks |
| CN117857750A (en) * | 2024-01-09 | 2024-04-09 | 京东方科技集团股份有限公司 | Factory monitoring system based on digital twin technology |
| CN117952377A (en) * | 2024-02-06 | 2024-04-30 | 浪潮云洲工业互联网有限公司 | Digital twin discrete manufacturing workshop synchronous evolution method, device and medium |
-
2024
- 2024-05-17 CN CN202410615645.XA patent/CN118192479B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111708332A (en) * | 2020-05-28 | 2020-09-25 | 上海航天精密机械研究所 | Digital twin system of production line |
| WO2022236064A2 (en) * | 2021-05-06 | 2022-11-10 | Strong Force Iot Portfolio 2016, Llc | Quantum, biological, computer vision, and neural network systems for industrial internet of things |
| WO2024035405A1 (en) * | 2022-08-11 | 2024-02-15 | Siemens Corporation | Interpreting and categorizing traffic on industrial control networks |
| CN115407735A (en) * | 2022-08-25 | 2022-11-29 | 扬州大学 | Plant factory management system based on digital twins |
| CN116051025A (en) * | 2022-12-22 | 2023-05-02 | 江苏杰瑞信息科技有限公司 | Digital twin foundation development platform oriented to energy consumption of park |
| CN116300736A (en) * | 2023-03-06 | 2023-06-23 | 广东长盈精密技术有限公司 | MES-based digital factory twin management system, platform and method |
| CN116880372A (en) * | 2023-06-15 | 2023-10-13 | 浙江链捷数字科技有限公司 | Operation optimization method and system of digital twin plant |
| CN117270482A (en) * | 2023-11-22 | 2023-12-22 | 博世汽车部件(苏州)有限公司 | Automobile factory control system based on digital twin |
| CN117857750A (en) * | 2024-01-09 | 2024-04-09 | 京东方科技集团股份有限公司 | Factory monitoring system based on digital twin technology |
| CN117952377A (en) * | 2024-02-06 | 2024-04-30 | 浪潮云洲工业互联网有限公司 | Digital twin discrete manufacturing workshop synchronous evolution method, device and medium |
Non-Patent Citations (2)
| Title |
|---|
| 孙鑫: "基于数字孪生的数控铣削刀具磨损在线预测及节能工艺优化方法", 《中国优秀硕士学位论文全文数据库工程科技I辑》, 15 January 2023 (2023-01-15) * |
| 黄培;: "数字孪生在制造业的应用", 中国工业和信息化, no. 07, 15 July 2020 (2020-07-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118192479B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086999B (en) | Remote data acquisition and analysis system for filling production line and anomaly analysis method thereof | |
| WO2023193458A1 (en) | Digital twin-based production line optimization method and apparatus, electronic device, and medium | |
| CN110889091B (en) | Machine tool thermal error prediction method and system based on temperature sensitive interval segmentation | |
| CN106910144B (en) | Large building time-by-time energy consumption online prediction method based on time-division actual energy consumption coefficient | |
| CN109226282B (en) | Steel plate on-line solid solution post-rolling rapid cooling method based on Internet of things | |
| CN115936676A (en) | Equipment health management method and system based on digital twins | |
| CN111950577A (en) | Point inspection method and device | |
| CN115993856B (en) | Multi-region environmental condition management and control method and system for factory building | |
| CN117852896B (en) | Construction supervision risk control early warning system and method | |
| CN116629024A (en) | Method and system for predicting dust emission data of casting process | |
| CN117891644B (en) | Data acquisition system and method based on digital twin technology | |
| CN108470699B (en) | intelligent control system of semiconductor manufacturing equipment and process | |
| CN117649207A (en) | Building construction management system | |
| CN118192479B (en) | Factory workshop digital twin model correction method and system based on data acquisition | |
| CN117891223A (en) | Equipment management method, system, equipment and medium based on industrial Internet of things | |
| CN117993613A (en) | Artificial intelligence analysis method and system for operation data of digital factory | |
| CN117745945A (en) | AI-based boiler furnace water wall tube wall image acquisition and processing system | |
| CN113221452A (en) | Office space temperature prediction system based on distributed optical fiber | |
| CN117115115A (en) | Digital twinning-based continuous casting billet surface quality detection method and system | |
| CN116894172A (en) | Wind power short-term power prediction method based on hybrid prediction model | |
| CN115982555A (en) | Sedimentation prediction method based on fuzzy information granulation and dynamic neural network | |
| CN114800049A (en) | Grating ruler processing operation signal error compensation system | |
| CN114192583A (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN1719441A (en) | Date acquiring method realized by using object oriented data base development | |
| CN117474710B (en) | Hollow glass whole-process informationized management system |
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 |