CN111008502B - Fault prediction method for complex equipment driven by digital twin - Google Patents
Fault prediction method for complex equipment driven by digital twin Download PDFInfo
- Publication number
- CN111008502B CN111008502B CN201911163211.6A CN201911163211A CN111008502B CN 111008502 B CN111008502 B CN 111008502B CN 201911163211 A CN201911163211 A CN 201911163211A CN 111008502 B CN111008502 B CN 111008502B
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- fault
- neural network
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a method and a device for predicting faults of complex equipment driven by digital twin, which comprises the following steps: a complex equipment digital twin establishing module capable of establishing and setting a geometric model, physical parameters, operation behaviors and restriction constraints; the digital twin body calibration module is used for calibrating by utilizing the deviation of data generated by the digital twin body and the data acquired by the entity equipment; the fault data generation module can generate fault data according to the set fault behavior; and the fault prediction model training and verification module can set training parameters and train a neural network. The method disclosed by the invention can solve the problems of high cost and incomplete data caused by the fact that the acquisition of the fault data of the complex equipment mainly depends on experiments, so that the cost of fault prediction of the complex equipment is reduced, and the accuracy of fault prediction is improved.
Description
Technical Field
The invention belongs to the field of electronic engineering and computer science, and particularly relates to a digital twin-driven complex equipment fault prediction method.
Background
In the manufacturing field, various complex equipment is provided, and the fault prediction of the complex equipment is always the key point of expert research in various countries due to the characteristics of multiple structures, high price of single equipment, complex process and the like of the complex equipment. Many failure prediction techniques have been studied, including linear correlation methods, but these methods have significant disadvantages, cannot predict the simultaneous occurrence of multiple failures, and also have problems in that the prediction result is insufficient when a single failure occurs, and therefore, it is necessary to train a neural network prediction model using a method with higher accuracy. However, training a neural network requires a large amount of data, and in the field of failure prediction, a large amount of failure data is required, and the acquisition of the failure data becomes a difficult problem: the experimental method is too high in cost and irrecoverable, time cost cannot be estimated when a historical database is established, and partial stable complex equipment cannot break down even for a long time.
Disclosure of Invention
Aiming at the problem that fault data are difficult to acquire due to the use of a neural network method, in order to solve the technical problem, the invention provides a method for acquiring fault data by establishing a complex equipment twin body matched with actual equipment by using a digital twin technology and performing simulation generation of the fault data on each fault and the combination of the faults of the equipment. The method can effectively generate the fault data of the complex equipment, thereby greatly reducing the cost for acquiring the fault prediction data of the complex equipment, and ensuring that the method has higher precision in the aspect of fault prediction by using the neural network prediction method. The method can solve the problems of difficult acquisition of the fault prediction data of the complex equipment and low prediction accuracy, and can realize the high-accuracy fault prediction of the complex equipment.
The technical problem to be solved by the invention is realized by adopting the following technical scheme: a digital twin driven complex equipment failure prediction method, comprising:
a digital twin driven complex equipment failure prediction method comprises the following steps:
step (1), establishing a complex equipment digital twin body, wherein the step is specifically realized as follows:
firstly, aiming at a complex device, according to the composition structure of the device, MATLAB software is used for establishing a geometric model of the device, and the model needs to reflect the structure and the assembly relation of the device;
adding physical attributes to each structure in the equipment geometric model by using an MATLAB software toolbox;
creating a production behavior according to the characteristics of the complex equipment, wherein the behavior comprises the response of each component of the equipment to the behavior and the characteristic of generating data;
setting production behavior constraints according to the specific field of the complex equipment, wherein the specific constraints with multiple dimensions and multiple ranges are required to be set;
fifthly, sorting, classifying and screening the parameters according to the structural characteristics of the equipment and the parameters collected in the production process, and establishing a parameter set of the equipment, wherein the parameter set is the parameter set collected under various fault conditions and input into a neural network;
step (2) and a digital twin calibration step, wherein the step is specifically realized as follows:
simulating the production process which is the same as the equipment entity according to the established complex equipment digital twin body and the actual production plan of the equipment; the twin body is established for simulating fault data of actual equipment through the twin body, and the twin body needs to be calibrated to be in line with the actual equipment, so that actual production process data is used for calibration;
generating simulation data of each parameter in the production process;
calculating the deviation value of the actual data and the simulated data, judging whether the twin model is matched with the equipment entity according to the deviation value, if so, turning to fifth, and if not, turning to fourth;
fourthly, calculating a gradient according to the deviation value, adjusting parameters of the twin model and converting;
fifthly, completing the construction of a digital twin body of complex equipment;
step (3), generating fault data, wherein the step is specifically realized as follows:
setting fault behaviors, namely actual fault conditions simulated by a twin body, including conditions of a single structure and a plurality of combined structures, and respectively generating corresponding fault data of different conditions;
simulating production behaviors containing faults according to the selected fault behaviors to generate simulation data;
calculating the deviation value of the set fault behavior according to the data reference value/expected value of the equipment production behavior;
fourthly, converting the deviation value into a characteristic vector to form a characteristic vector group;
step (4), training and verifying a fault prediction model, wherein the step is specifically realized as follows:
setting BP neural network training parameters;
secondly, training a neural network; obtaining a deviation value by training a twin of the equipment and setting corresponding fault behaviors, processing the deviation value, and converting the deviation value into a characteristic vector group, wherein the characteristic vector group is a data source for training a neural network;
using the actual data and the simulation data to calibrate and verify the neural network, and if the training requirements are not met, modifying the training parameters to continue training until the neural network meeting the fitting requirements is trained;
and fourthly, inputting the data acquired in the actual operation process of the complex equipment into the trained neural network, and outputting the prediction conditions of various faults and fault combinations by the neural network.
According to another aspect of the present invention, a digital twin driven complex equipment failure prediction apparatus is provided, including:
(1) the complex equipment digital twin establishing module is specifically realized as follows:
firstly, aiming at a complex device, according to the composition structure of the device, MATLAB software is used for establishing a geometric model of the device, and the model needs to reflect the structure and the assembly relation of the device;
adding physical attributes to each structure in the equipment geometric model by using an MATLAB software toolbox;
creating a production behavior according to the characteristics of the complex equipment, wherein the behavior comprises the response of each component of the equipment to the behavior and the characteristic of generating data;
setting production behavior constraints according to the specific field of the complex equipment, wherein the specific constraints with multiple dimensions and multiple ranges are required to be set;
fifthly, sorting, classifying and screening the parameters according to the structural characteristics of the equipment and the parameters collected in the production process, and establishing a parameter set of the equipment, wherein the parameter set is the parameter set collected under various fault conditions and input into a neural network;
(2) the digital twin body calibration module is implemented as follows:
simulating the production process which is the same as the equipment entity according to the established complex equipment digital twin body and the actual production plan of the equipment; the twin body is established for simulating fault data of actual equipment through the twin body, and the twin body needs to be calibrated to be in line with the actual equipment, so that actual production process data is used for calibration;
generating simulation data of each parameter in the production process;
calculating the deviation value of the actual data and the simulated data, judging whether the twin model is matched with the equipment entity according to the deviation value, if so, turning to fifth, and if not, turning to fourth;
fourthly, calculating a gradient according to the deviation value, adjusting parameters of the twin model and converting;
fifthly, completing the construction of a digital twin body of complex equipment;
(3) the fault data generation module is specifically implemented as follows:
setting fault behaviors, namely actual fault conditions simulated by a twin body, including conditions of a single structure and a plurality of combined structures, and respectively generating corresponding fault data of different conditions;
simulating production behaviors containing faults according to the selected fault behaviors to generate simulation data;
calculating the deviation value of the set fault behavior according to the data reference value/expected value of the equipment production behavior;
fourthly, converting the deviation value into a characteristic vector to form a characteristic vector group;
(4) the fault prediction model training and verifying module is specifically realized as follows:
setting BP neural network training parameters;
secondly, training a neural network; obtaining a deviation value by training a twin of the equipment and setting corresponding fault behaviors, processing the deviation value, and converting the deviation value into a characteristic vector group, wherein the characteristic vector group is a data source for training a neural network;
using the actual data and the simulation data to calibrate and verify the neural network, and if the training requirements are not met, modifying the training parameters to continue training until the neural network meeting the fitting requirements is trained;
and fourthly, inputting the data acquired in the actual operation process of the complex equipment into the trained neural network, and outputting the prediction conditions of various faults and fault combinations by the neural network.
Compared with the prior art, the invention has the advantages that:
(1) the invention uses the digital twin technology, and autonomously generates the fault data required by training the neural network by establishing a complex equipment digital twin body mode, thereby greatly reducing the time cost and the economic cost and solving the problem of difficulty in acquiring the fault data.
(2) Compared with the traditional linear deviation method and the like, the method has good prediction speed and higher accuracy by using the neural network method.
Drawings
FIG. 1 is a block diagram of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person skilled in the art without creative efforts based on the embodiments in the present invention belong to the protection scope of the present invention. .
The invention relates to a digital twin driven complex equipment fault prediction method. The method provides that a digital twinning technology is utilized to establish a complex equipment twinning body matched with actual equipment, and fault data is simulated and generated for each fault and the combination of the faults of the equipment, so that the fault data is acquired. The method can effectively generate the fault data of the complex equipment, thereby greatly reducing the cost for acquiring the fault prediction data of the complex equipment, and ensuring higher precision of the method in the aspect of fault prediction by using the neural network prediction method.
Fig. 1 shows a block diagram of a digital twin-driven complex equipment failure prediction device, and the specific implementation manner is as follows:
(1) fig. 1 shows a complex equipment digital twin establishment module, which is implemented as follows:
firstly, aiming at a certain specific complex equipment, establishing a geometric model of the equipment by using MATLAB software according to a composition structure of the equipment, wherein the model needs to embody the structure and the assembly relation of the equipment;
adding physical attributes to each structure in the equipment geometric model by using an MATLAB software toolbox;
creating a production behavior according to the characteristics of the complex equipment, wherein the behavior comprises the response of each component of the equipment to the behavior and the characteristic of generating data;
fourthly, according to the specific field of the complex equipment, setting production behavior constraint of the complex equipment, wherein the constraint has great influence on subsequently generated fault data, so that multi-dimensional and multi-range specific constraint is needed;
fifthly, sorting, classifying and screening the parameters according to the structural characteristics of the equipment and the parameters collected in the production process, and establishing a parameter set of the equipment, wherein the parameter set is the parameter set collected under various fault conditions and input into a neural network;
(2) fig. 1, 2 is a digital twin calibration module, which is implemented as follows:
simulating the production process which is the same as the equipment entity according to the established complex equipment digital twin body and the actual production plan of the equipment; the twin body is established for simulating the fault data of the actual equipment through the twin body, and the twin body needs to be calibrated to be as close to the actual equipment as possible, so that the actual production process data is used for calibration.
Generating simulation data of each parameter in the production process;
calculating the deviation value of the actual data and the simulated data, judging whether the twin model is matched with the equipment entity according to the deviation value, if so, turning to fifth, and if not, turning to fourth;
fourthly, calculating a gradient according to the deviation value, adjusting parameters of the twin model and converting;
fifthly, completing the construction of a digital twin body of complex equipment;
(3) fig. 1, 3 is a fault data generation module, which is implemented as follows:
setting fault behaviors, namely actual fault conditions simulated by a twin body, including conditions of a single structure and a plurality of combined structures, and respectively generating corresponding fault data of different conditions;
simulating production behaviors containing faults according to the selected fault behaviors to generate simulation data;
thirdly, calculating the deviation value of the fault behavior set in the first step according to the data reference value/expected value of the production behavior of the equipment; the parameter set established by the module 1, such as the heating rate, the holding temperature, the full pressure of the fan and the like, has reference/expected values under the condition of no fault, such as the holding temperature between 118 ℃ and 120 ℃, and the product quality/process is in accordance with the requirements. The step is to calculate the fault behavior deviation set in the step (i).
Fourthly, converting the deviation value into a characteristic vector to form a characteristic vector group;
(4) fig. 1, 4, is a fault prediction model training and verifying module, which is implemented as follows:
setting BP neural network training parameters;
secondly, training a neural network; one of the contributions of the invention is to solve the problem of the fault data source of the complex equipment, obtain the deviation value by training the twin of the equipment and setting the corresponding fault behavior, process the deviation value and convert the deviation value into a characteristic vector group, wherein the characteristic vector group is the data source for training the neural network.
Using the actual data and the simulation data to calibrate and verify the neural network, and if the training requirements are not met, modifying the training parameters to continue training until the neural network meeting the fitting requirements is trained;
and fourthly, inputting the data acquired in the actual operation process of the complex equipment into the trained neural network, and outputting the prediction conditions of various faults and fault combinations by the neural network.
In summary, the present invention discloses a method for predicting a failure of a complex device driven by a digital twin, including: the device comprises a complex equipment digital twin body establishing module, a digital twin body calibrating module, a fault data generating module and a fault prediction neural network training and verifying module. The method disclosed by the invention can solve the problems of high cost and incomplete data caused by the fact that the acquisition of the fault data of the complex equipment mainly depends on experiments, so that the cost of fault prediction of the complex equipment is reduced, and the accuracy of fault prediction is improved.
Those skilled in the art will appreciate that the invention may be practiced without these specific details.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (2)
1. A method for predicting faults of complex equipment driven by digital twins is characterized by comprising the following steps:
step (1), establishing a complex equipment digital twin body, wherein the step is specifically realized as follows:
firstly, aiming at a complex device, according to the composition structure of the device, MATLAB software is used for establishing a geometric model of the device, and the model needs to reflect the structure and the assembly relation of the device;
adding physical attributes to each structure in the equipment geometric model by using an MATLAB software toolbox;
creating a production behavior according to the characteristics of the complex equipment, wherein the behavior comprises the response of each component of the equipment to the behavior and the characteristics of generating data;
fourthly, setting production behavior constraints according to the specific field of the complex equipment, wherein the specific constraints with multiple dimensions and multiple ranges are required to be set;
according to the structural characteristics of the equipment and the parameters collected in the production process, sorting, classifying and screening the parameters, and establishing a parameter set of the equipment, wherein the parameter set is the parameter set which is collected under various fault conditions and input into a neural network;
step (2) and a digital twin calibration step, wherein the step is specifically realized as follows:
simulating the production process which is the same as the equipment entity according to the established complex equipment digital twin body and the actual production plan of the equipment; the twin body is established for simulating fault data of actual equipment through the twin body, and the twin body needs to be calibrated to be in line with the actual equipment, so that actual production process data is used for calibration;
generating simulation data of each parameter in the production process;
calculating the deviation value of the actual data and the simulated data, judging whether the twin model is matched with the equipment entity according to the deviation value, if so, turning to fifth, and if not, turning to fourth;
fourthly, calculating a gradient according to the deviation value, adjusting parameters of the twin model and converting;
fifthly, completing the construction of a digital twin body of complex equipment;
step (3), generating fault data, wherein the step is specifically realized as follows:
setting fault behaviors, namely actual fault conditions simulated by a twin body, including conditions of a single structure and a plurality of combined structures, and respectively generating corresponding fault data of different conditions;
simulating production behaviors containing faults according to the selected fault behaviors to generate simulation data;
calculating the deviation value of the set fault behavior according to the data reference value/expected value of the equipment production behavior;
fourthly, converting the deviation value into a characteristic vector to form a characteristic vector group;
step (4), training and verifying a fault prediction model, wherein the step is specifically realized as follows:
setting BP neural network training parameters;
secondly, training a neural network; obtaining a deviation value by training a twin of the equipment and setting corresponding fault behaviors, processing the deviation value, and converting the deviation value into a characteristic vector group, wherein the characteristic vector group is a data source for training a neural network;
using actual data and simulation data to calibrate and verify the neural network, and if the training requirement is not met, modifying the training parameters to continue training until the neural network meeting the fitting requirement is trained;
and fourthly, inputting the data acquired in the actual operation process of the complex equipment into the trained neural network, and outputting the prediction conditions of various faults and fault combinations by the neural network.
2. A digital twin driven complex equipment failure prediction device, comprising:
(1) the complex equipment digital twin establishing module is specifically realized as follows:
firstly, aiming at a complex device, according to the composition structure of the device, MATLAB software is used for establishing a geometric model of the device, and the model needs to reflect the structure and the assembly relation of the device;
adding physical attributes to each structure in the equipment geometric model by using an MATLAB software toolbox;
creating a production behavior according to the characteristics of the complex equipment, wherein the behavior comprises the response of each component of the equipment to the behavior and the characteristics of generating data;
fourthly, setting production behavior constraints according to the specific field of the complex equipment, wherein the specific constraints with multiple dimensions and multiple ranges are required to be set;
according to the structural characteristics of the equipment and the parameters collected in the production process, sorting, classifying and screening the parameters, and establishing a parameter set of the equipment, wherein the parameter set is the parameter set which is collected under various fault conditions and input into a neural network;
(2) the digital twin body calibration module is implemented as follows:
simulating the production process which is the same as the equipment entity according to the established complex equipment digital twin body and the actual production plan of the equipment; the twin body is established for simulating fault data of actual equipment through the twin body, and the twin body needs to be calibrated to be in line with the actual equipment, so that actual production process data is used for calibration;
generating simulation data of each parameter in the production process;
calculating the deviation value of the actual data and the simulated data, judging whether the twin model is matched with the equipment entity according to the deviation value, if so, turning to fifth, and if not, turning to fourth;
fourthly, calculating a gradient according to the deviation value, adjusting parameters of the twin model and converting;
fifthly, completing the construction of a digital twin body of complex equipment;
(3) the fault data generation module is specifically implemented as follows:
setting fault behaviors, namely actual fault conditions simulated by a twin body, including conditions of a single structure and a plurality of combined structures, and respectively generating corresponding fault data of different conditions;
simulating production behaviors containing faults according to the selected fault behaviors to generate simulation data;
calculating the deviation value of the set fault behavior according to the data reference value/expected value of the equipment production behavior;
fourthly, converting the deviation value into a characteristic vector to form a characteristic vector group;
(4) the fault prediction model training and verifying module is specifically realized as follows:
setting BP neural network training parameters;
secondly, training a neural network; obtaining a deviation value by training a twin of the equipment and setting corresponding fault behaviors, processing the deviation value, and converting the deviation value into a characteristic vector group, wherein the characteristic vector group is a data source for training a neural network;
using actual data and simulation data to calibrate and verify the neural network, and if the training requirement is not met, modifying the training parameters to continue training until the neural network meeting the fitting requirement is trained;
and fourthly, inputting the data acquired in the actual operation process of the complex equipment into the trained neural network, and outputting the prediction conditions of various faults and fault combinations by the neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911163211.6A CN111008502B (en) | 2019-11-25 | 2019-11-25 | Fault prediction method for complex equipment driven by digital twin |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911163211.6A CN111008502B (en) | 2019-11-25 | 2019-11-25 | Fault prediction method for complex equipment driven by digital twin |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111008502A CN111008502A (en) | 2020-04-14 |
CN111008502B true CN111008502B (en) | 2021-07-13 |
Family
ID=70113052
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911163211.6A Active CN111008502B (en) | 2019-11-25 | 2019-11-25 | Fault prediction method for complex equipment driven by digital twin |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111008502B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111859566B (en) * | 2020-07-17 | 2023-11-17 | 重庆大学 | Digital twinning-based surface roughness stabilization method |
CN112200493A (en) * | 2020-11-02 | 2021-01-08 | 傲林科技有限公司 | Digital twin model construction method and device |
CN112329183A (en) * | 2020-11-06 | 2021-02-05 | 北京三一智造科技有限公司 | Equipment state data acquisition method and device, electronic equipment and storage medium |
CN112199898B (en) * | 2020-11-11 | 2021-06-15 | 北京三维天地科技股份有限公司 | Instrument and equipment fault prediction and health management method based on big data |
CN112416531B (en) * | 2020-12-07 | 2021-11-26 | 深圳华制智能制造技术有限公司 | Digital twin system simulation method, system, computer device and storage medium |
CN112859789B (en) * | 2021-01-29 | 2024-02-06 | 重庆邮电大学 | CFD-based method and system for constructing digital twin body of data center |
CN113379123A (en) * | 2021-06-09 | 2021-09-10 | 中德(珠海)人工智能研究院有限公司 | Fault prediction method, device, server and storage medium based on digital twin |
CN113378939B (en) * | 2021-06-11 | 2022-08-09 | 福州大学 | Structure digital twin modeling and parameter identification method based on physical driving neural network |
CN113421008A (en) * | 2021-07-02 | 2021-09-21 | 北自所(北京)科技发展有限公司 | Health control method and system for digital twin textile complete equipment |
CN113642209B (en) * | 2021-07-16 | 2022-11-08 | 中国人民解放军总参谋部第六十研究所 | Structure implantation fault response data acquisition and evaluation method based on digital twinning |
CN113779785B (en) * | 2021-08-30 | 2023-06-09 | 国营芜湖机械厂 | Digital twin complex equipment deconstructing model system and deconstructing method thereof |
CN113792423B (en) * | 2021-09-04 | 2023-10-24 | 苏州特比姆智能科技有限公司 | Digital twin behavior constraint method and system for TPM equipment management |
CN114638160B (en) * | 2022-05-11 | 2023-04-07 | 西南交通大学 | Knowledge service method for complex equipment digital twin model |
CN114818388A (en) * | 2022-06-20 | 2022-07-29 | 北京航空航天大学 | Digital twin fault injection and equivalent simulation method and system for complex equipment |
CN114943185B (en) * | 2022-07-13 | 2022-09-30 | 北京航空航天大学 | Nondestructive acquisition method for twin data of complex equipment under extreme working conditions |
CN115292834B (en) * | 2022-07-20 | 2023-04-21 | 北自所(北京)科技发展股份有限公司 | Digital twin equipment fault diagnosis method, device and system |
CN116227010B (en) * | 2023-05-10 | 2023-07-25 | 中国公路工程咨询集团有限公司 | Construction method and system of highway maintenance digital twin application system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108107841A (en) * | 2017-12-26 | 2018-06-01 | 山东大学 | A kind of twin modeling method of numerically-controlled machine tool number |
WO2019005185A1 (en) * | 2017-06-28 | 2019-01-03 | General Electric Company | Methods and systems for improving care through post-operation feedback analysis |
CN110045608A (en) * | 2019-04-02 | 2019-07-23 | 太原理工大学 | Based on the twin mechanical equipment component structural dynamic state of parameters optimization method of number |
CN110135042A (en) * | 2019-05-08 | 2019-08-16 | 国网江苏省电力有限公司信息通信分公司 | A kind of visualization integrated management method of information machine room |
CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
WO2019211288A1 (en) * | 2018-05-02 | 2019-11-07 | Kongsberg Digital AS | A method and system for discovering and visualizing potential operational problems of processes running in equipment and systems in an installation |
CN110442936A (en) * | 2019-07-24 | 2019-11-12 | 中国石油大学(北京) | Equipment fault diagnosis method, apparatus and system based on the twin model of number |
CN110492186A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management method of the power battery module based on cloud control technology |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109785180A (en) * | 2019-02-19 | 2019-05-21 | 山东大学 | A kind of scene perception system and method towards the twin workshop of number |
-
2019
- 2019-11-25 CN CN201911163211.6A patent/CN111008502B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019005185A1 (en) * | 2017-06-28 | 2019-01-03 | General Electric Company | Methods and systems for improving care through post-operation feedback analysis |
CN108107841A (en) * | 2017-12-26 | 2018-06-01 | 山东大学 | A kind of twin modeling method of numerically-controlled machine tool number |
WO2019211288A1 (en) * | 2018-05-02 | 2019-11-07 | Kongsberg Digital AS | A method and system for discovering and visualizing potential operational problems of processes running in equipment and systems in an installation |
CN110045608A (en) * | 2019-04-02 | 2019-07-23 | 太原理工大学 | Based on the twin mechanical equipment component structural dynamic state of parameters optimization method of number |
CN110135042A (en) * | 2019-05-08 | 2019-08-16 | 国网江苏省电力有限公司信息通信分公司 | A kind of visualization integrated management method of information machine room |
CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
CN110492186A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management method of the power battery module based on cloud control technology |
CN110442936A (en) * | 2019-07-24 | 2019-11-12 | 中国石油大学(北京) | Equipment fault diagnosis method, apparatus and system based on the twin model of number |
Non-Patent Citations (2)
Title |
---|
Digital twin driven prognostics and health management for complex;陶飞等;《CIRP Annals - Manufacturing Technology》;20180524;全文 * |
Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in;Michael Grieves,John Vickers;《Transdisciplinary Perspectives on Complex Systems》;20160817;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111008502A (en) | 2020-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111008502B (en) | Fault prediction method for complex equipment driven by digital twin | |
CN107563067A (en) | Analysis of structural reliability method based on Adaptive proxy model | |
CN104517613A (en) | Method and device for evaluating speech quality | |
CN113011085A (en) | Equipment digital twin modeling method and system | |
WO2019160138A1 (en) | Causality estimation device, causality estimation method, and program | |
CN105005294A (en) | Real-time sensor fault diagnosis method based on uncertainty analysis | |
CN116305522A (en) | Digital twin-based aircraft structure reliability simulation test model calibration method, device and medium | |
KR102102685B1 (en) | A method for robotic facial expressions by learning human facial demonstrations | |
CN113111054A (en) | Industrial data balance processing algorithm based on combination of oversampling and undersampling | |
CN110648055A (en) | Electric power accident event and cause relation construction method based on convolutional neural network | |
CN110676852B (en) | Improved extreme learning machine rapid probability load flow calculation method considering load flow characteristics | |
CN113804997B (en) | Voltage sag source positioning method based on bidirectional WaveNet deep learning | |
CN113111573A (en) | Landslide displacement prediction method based on GRU | |
Andolfatto et al. | On neural networks’ ability to approximate geometrical variation propagation in assembly | |
CN111783283A (en) | Hierarchical fault transfer modeling and reasoning method based on fuzzy directed graph | |
CN101477582B (en) | Model modification method for a semiconductor device | |
Chu et al. | Fast multiple edge response method based on the design of experiment and machine learning | |
CN109325289B (en) | Method for estimating reliability parameters of electronic part | |
CN114980723A (en) | Fault prediction method and system for cross-working-condition chip mounter suction nozzle | |
US7360138B2 (en) | Verification of the design of an integrated circuit background | |
CN114266349A (en) | Load flow calculation method based on adaptive neural network | |
JP3139867B2 (en) | Semiconductor production system | |
CN111126659A (en) | Power load prediction method and system | |
Khorshidian et al. | Asymptotic behavior of multivariate reward processes with nonlinear reward functions | |
Acilan et al. | Novel Parameter Error Identification Method for Power Plant Dynamic Models |
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 |