CN114239938A - State-based energy digital twin body construction method - Google Patents

State-based energy digital twin body construction method Download PDF

Info

Publication number
CN114239938A
CN114239938A CN202111488937.4A CN202111488937A CN114239938A CN 114239938 A CN114239938 A CN 114239938A CN 202111488937 A CN202111488937 A CN 202111488937A CN 114239938 A CN114239938 A CN 114239938A
Authority
CN
China
Prior art keywords
energy
energy consumption
state
learning machine
gaussian kernel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111488937.4A
Other languages
Chinese (zh)
Inventor
谷纪亭
徐晨博
吴赫君
张佳妮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Economic and Technological Research Institute of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Economic and Technological Research Institute of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Economic and Technological Research Institute of State Grid Zhejiang Electric Power Co Ltd filed Critical Economic and Technological Research Institute of State Grid Zhejiang Electric Power Co Ltd
Priority to CN202111488937.4A priority Critical patent/CN114239938A/en
Publication of CN114239938A publication Critical patent/CN114239938A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/901—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • 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
    • G06N3/045—Combinations of 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P80/00—Climate change mitigation technologies for sector-wide applications
    • Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/80—Management or planning
    • Y02P90/82—Energy audits or management systems therefor

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Educational Administration (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a construction method of a state-based energy digital twin body, wherein an energy digital twin model comprises a physical space and a digital space, the physical space comprises physical equipment and an edge database, and the digital space comprises a data fusion module, an energy model for simulating or predicting energy consumption behaviors, a data-driven hybrid Petri network, a Gaussian kernel limit learning machine and a digital twin database; according to the method, a Gaussian kernel extreme learning machine is adopted to fit the instantaneous emission speed of continuous energy consumption transition, meanwhile, the energy behavior of the physical equipment is predicted by combining with the data-driven hybrid Petri network, the distortion of the energy behavior of an energy model in simulation or prediction is corrected, and the effects of energy consumption calculation, abnormal energy consumption positioning, energy efficiency index evaluation, energy related parameter optimization and energy efficiency improvement are achieved.

Description

State-based energy digital twin body construction method
Technical Field
The invention relates to the technical field of digital twins, in particular to a construction method of a state-based energy digital twins.
Background
Energy management systems are useful tools to facilitate energy-related data collection, analysis, diagnosis, trend discovery, and decision-making. The energy management system integrates a plurality of support tools and methods, such as energy modeling and analysis, energy assessment, environmental emission calculation, energy benchmark test and the like. At present, energy management in the manufacturing industry is mainly based on measurement and application of energy related data of physical equipment by using technologies such as the internet of things.
The DT technology (Digital Twin) Digital Twin, also called Digital mapping, provides a new opportunity for improving the performance of energy consumption monitoring, analysis and energy efficiency optimization in manufacturing industry. Establishing an energy-saving manufacturing system through a physical, geometric, behavior and operation rule model; the energy consumption behavior model models real-time energy consumption characteristics at different states (i.e., idle and process states) and manufacturing levels (i.e., component, machine, unit/line, and shop levels), and the associated operating parameters (i.e., speed, force, and temperature) the energy consumption behavior model determines the reliability and effectiveness of DT-based manufacturing energy management services. Existing energy consumption behavior models can be classified into three types, namely theoretical models, empirical models and models based on operating states, wherein a state-based modeling technology is widely used for simulating or predicting energy consumption behaviors, and can simulate operating state-driven energy dynamics and a transition relationship from one operating state to another; however, the state-based energy model assumes constant power in the operating state and approximately adapts to the energy behavior regardless of uncertain operating environment, and in practice, the equipment operates in a complex dynamic production environment, production requirements are variable, material quality is inconsistent, equipment aging, tool wear, equipment failure, worker capability difference, and the like, the state-based energy modeling technique distorts the prediction result of the energy behavior compared to the real monitoring profile of the energy behavior, and distortion of the simulated or predicted energy behavior may further cause deviations in energy consumption calculation, abnormal energy consumption location, energy efficiency index evaluation, energy-related parameter optimization, energy efficiency improvement, and the like, and thus it can be seen that the distortion of the simulated energy behavior will prevent the application of DT in energy management.
Disclosure of Invention
The problem addressed by the present invention is how to improve the distortion of the energy behavior of state-based energy models in simulation or prediction.
In order to solve the above problems, the present invention provides a method for constructing a state-based energy digital twin, where the energy digital twin model includes a physical space and a digital space, the physical space includes a physical device and an edge database for collecting and storing multi-source data on the physical device, and the digital space includes a data fusion module for performing data fusion on the multi-source data in the edge database, an energy model for simulating or predicting energy consumption behavior, a data-driven hybrid Petri network for calculating power and corresponding duration of each state, a gaussian kernel limit learning machine, and a digital twin database for storing simulation results of the energy model.
The invention has the beneficial effects that: according to the method, a Gaussian kernel extreme learning machine is adopted to fit the instantaneous emission speed of continuous energy consumption transition, meanwhile, the energy behavior of the physical equipment is predicted by combining with the data-driven hybrid Petri network, the distortion of the energy behavior of an energy model in simulation or prediction is corrected, and the effects of energy consumption calculation, abnormal energy consumption positioning, energy efficiency index evaluation, energy related parameter optimization and energy efficiency improvement are achieved.
Preferably, the data-driven hybrid Petri network comprises discrete positions for simulating the operation states of the physical equipment, discrete conversion for controlling the operation state conversion of the physical equipment, an energy consumption continuous transition module for controlling each operation state, and a module for recording the instant of discrete conversion at each discrete positionA continuous location module of energy consumption state, said Gaussian kernel extreme learning machine for fitting the instantaneous firing speed v of the energy consumption continuous transition modulei(τ)。
Preferably, the energy consumption simulated by the energy module is as follows:
Figure BDA0003398415210000031
in the formula, Pk(τ) is the power of the kth operating state of time t, Δ τkThe time period of the kth operating state.
Preferably, the Gaussian kernel extreme learning machine fits the instantaneous ignition speed v of the energy consumption continuous transition modulei(τ) specifically includes a training sample set X, input layer nodes, hidden layer nodes, and output layer, where:
the training sample set is as follows:
X＝{(xi，vi|xi∈Rn，xi∈Rm，i＝1，2，…，N)}；
wherein x isi＝[xi，1，xi，2，…，xi，m]Representing the ith input vector; v. ofi＝[vi，1，vi，2，…，vi，m]∈RmIs the corresponding output vector, N is the number of samples;
the output of the gaussian kernel extreme learning machine is:
Figure BDA0003398415210000032
wherein alpha isj＝(αj1，αj2，…，αjN) Representing a weight vector connecting all input layer nodes to the jth hidden layer node, bjIs the jth neuron bias of the hidden layer, bjIs the output weight vector of the jth hidden layer node, L is the number of hidden layer nodes, h (-) is the activation function;
the learning goal of the gaussian kernel extreme learning machine is to minimize the output error, i.e.:
Figure BDA0003398415210000033
thus, it is possible to provide
Figure BDA0003398415210000034
Training a Gaussian kernel extreme learning machine by adopting a training sample set, specifically training weight vectors of input layer nodes:
Figure BDA0003398415210000041
drawings
FIG. 1 is a schematic structural diagram of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
The method for constructing the state-based energy digital twin body as shown in fig. 1 includes a physical space and a digital space, wherein the physical space includes a physical device and an edge database for collecting and storing multi-source data on the physical device, and the digital space includes a data fusion module for performing data fusion on the multi-source data in the edge database, an energy model for simulating or predicting energy consumption behavior, a data-driven hybrid Petri network for calculating power and corresponding duration of each state, a gaussian kernel limit learning machine, and a digital twin database for storing simulation results of the energy model.
The data fusion module in the embodiment performs data fusion on multi-source data by using principal component analysis, wavelet analysis single shot and a Kalman filter, and then takes the fused data as a basis for driving a data-driven hybrid Petri network to be transmitted to a Gaussian kernel extreme learning machine for simulating energy consumption behavior and energy consumption prediction;
the data-driven hybrid Petri network of the embodiment comprises a module for simulating the running states of physical equipment, including stop, standby, idle and processing, discrete positions for simulating the running states of the physical equipment comprise PS1, PS2, PS3 and PS4, discrete transitions for controlling the running state transitions of the physical equipment comprise ts1-ts2, ts2-ts3, ts3-ts4 and ts4-ts1, an energy consumption continuous transition module for controlling each running state, and a continuous position module for recording the instantaneous energy consumption state of discrete transition at each discrete position, and the Gaussian kernel limit learning machine is used for fitting the instantaneous ignition speed v of the energy consumption continuous transition modulei(τ)；
Wherein, the Gaussian kernel extreme learning machine is fitted with the instantaneous ignition speed v of the energy consumption continuous transition modulei(τ) specifically includes a training sample set X, input layer nodes, hidden layer nodes, and output layer, where:
the training sample set is stored in a digital twin database, and the training sample set is as follows:
X＝{(xi，vi|xi∈Rn，xi∈Rm，i＝1，2，…，N)}；
wherein x isi＝[xi，1，xi，2，…，xi，m]Representing the ith input vector; v. ofi＝[vi，1，vi，2，…，vi，m]∈RmIs the corresponding output vector, N is the number of samples;
the output of training the gaussian kernel extreme learning machine by using the training sample set is as follows:
Figure BDA0003398415210000051
wherein alpha isj＝(αj1，αj2，…，αjN) Representing a weight vector connecting all input layer nodes to the jth hidden layer node, bjIs the jth neuron bias of the hidden layer, bjIs the output weight vector of the jth hidden layer node, L is the number of hidden layer nodes, h (-) is the activation function;
the learning objective of the gaussian kernel limit learning machine of this embodiment is to minimize the output error, i.e.:
Figure BDA0003398415210000052
thus, it is possible to provide
Figure BDA0003398415210000053
Training a Gaussian kernel extreme learning machine by adopting a training sample set, specifically training weight vectors of input layer nodes:
Figure BDA0003398415210000061
then, the energy module calculates the energy consumption from the energy consumption behavior simulated by the data-driven hybrid Petri network by adopting optimization, preprocessing and simulation calculation, and comprises the following steps:
Figure BDA0003398415210000062
in the formula, Pk(τ) is the power of the kth operating state of time t, Δ τkFor the time period of the kth operating state, in order to simulate the dynamic behavior of the energy consumption.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present disclosure, and such changes and modifications will fall within the scope of the present invention.

Claims (4)

1. The energy digital twin body construction method based on the states is characterized in that the energy digital twin body model comprises a physical space and a digital space, the physical space comprises a physical device and an edge database used for collecting and storing multi-source data on the physical device, and the digital space comprises a data fusion module used for carrying out data fusion on the multi-source data in the edge database, an energy model used for simulating or predicting energy consumption behaviors, a data-driven hybrid Petri network used for calculating the power of each state and the corresponding duration, a Gaussian kernel limit learning machine and a digital twin database used for storing energy model simulation results.
2. The method as claimed in claim 1, wherein the data-driven hybrid Petri network comprises discrete positions for simulating the operation states of physical devices, discrete transitions for controlling the operation state transitions of the physical devices, a continuous transition module of energy consumption for controlling each operation state, and a continuous position module for recording the instantaneous energy consumption state of the discrete transitions at each discrete position, and the Gaussian kernel limit learning machine is used for fitting the instantaneous ignition speed v of the continuous transition module of energy consumptioni(τ)。
3. The method for constructing a state-based energy data twin according to claim 2, wherein the energy module simulates energy consumption as follows:
Figure FDA0003398415200000011
in the formula, Pk(τ) is the power of the kth operating state of time t, Δ τkThe time period of the kth operating state.
4. The method for constructing the state-based energy digital twin body according to claim 3, wherein the Gaussian kernel extreme learning machine is fitted to the instantaneous ignition speed v of the energy consumption continuous transition modulei(τ) specifically includes a training sample set X, input layer nodes, hidden layer nodes, and output layer, where: the training sample set is as follows:
X＝{(xi，vi|xi∈Rn，xi∈Rm，i＝1，2，…，N)}；
wherein x isi＝[xi，1，xi，2，…，xi，m]Representing the ith input vector; v. ofi＝[vi，1，vi，2，…，vi，m]∈RmIs the corresponding output vector, N is the number of samples;
the output of the gaussian kernel extreme learning machine is:
Figure FDA0003398415200000021
wherein alpha isj＝(αj1，αj2，…，αjN) Representing a weight vector connecting all input layer nodes to the jth hidden layer node, bjIs the jth neuron bias of the hidden layer, bjIs the output weight vector of the jth hidden layer node, L is the number of hidden layer nodes, h (-) is the activation function;
the learning goal of the gaussian kernel extreme learning machine is to minimize the output error, i.e.:
Figure FDA0003398415200000022
thus, it is possible to provide
Figure FDA0003398415200000023
Training a Gaussian kernel extreme learning machine by adopting a training sample set, specifically training weight vectors of input layer nodes:
Figure FDA0003398415200000024
CN202111488937.4A 2021-12-08 2021-12-08 State-based energy digital twin body construction method Pending CN114239938A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111488937.4A CN114239938A (en) 2021-12-08 2021-12-08 State-based energy digital twin body construction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111488937.4A CN114239938A (en) 2021-12-08 2021-12-08 State-based energy digital twin body construction method

Publications (1)

Publication Number Publication Date
CN114239938A true CN114239938A (en) 2022-03-25

Family

ID=80753811

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111488937.4A Pending CN114239938A (en) 2021-12-08 2021-12-08 State-based energy digital twin body construction method

Country Status (1)

Country Link
CN (1) CN114239938A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115494801A (en) * 2022-09-09 2022-12-20 广东鑫光智能***有限公司 Plate production line building method and terminal

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115494801A (en) * 2022-09-09 2022-12-20 广东鑫光智能***有限公司 Plate production line building method and terminal

Similar Documents

Publication Publication Date Title
CN111230887B (en) Industrial gluing robot running state monitoring method based on digital twin technology
Nasiri et al. Fracture mechanics and mechanical fault detection by artificial intelligence methods: A review
CN114048600A (en) Digital twin-driven multi-model fusion industrial system anomaly detection method
JP2021064370A (en) Method and system for semi-supervised deep abnormality detection for large-scale industrial monitoring system based on time-series data utilizing digital twin simulation data
CN103983453B (en) A kind of executing agency of aero-engine and the differentiating method of sensor fault diagnosis
CN103310051B (en) Board information terminal Failure Rate Forecasting Method in a kind of life cycle management
CN107644297B (en) Energy-saving calculation and verification method for motor system
CN111752151A (en) Adaptive tracking and compensating method and system for grinding and polishing industrial blade
CN111723440A (en) Thin-wall part machining precision prediction hybrid modeling method
CN114619292A (en) Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network
CN111190349A (en) Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment
WO2021195970A1 (en) Prediction model learning method, apparatus and system for an industrial system
CN115438726A (en) Device life and fault type prediction method and system based on digital twin technology
CN115081585B (en) Man-machine object cooperative abnormal state detection method for reinforced heterographic neural network
CN110757510A (en) Method and system for predicting remaining life of robot
CN112231966B (en) Cooperative robot assemblability prediction system and method based on digital twinning
CN114239938A (en) State-based energy digital twin body construction method
Wang et al. A graph neural network-based data cleaning method to prevent intelligent fault diagnosis from data contamination
Lu et al. Digital twin-based operation simulation system and application framework for electromechanical products
CN110108457B (en) Primary fan shaft temperature diagnosis method based on universal gravitation neural network
CN115034147B (en) Intelligent manufacturing system based on digital twins
Yao et al. Research on power modeling of the industrial robot based on ResNet
CN110188039A (en) The method and system of software test, software optimization
CN114609969A (en) Numerical control machine tool track error compensation method based on cloud computing
Zhang Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data

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