Numerical control machine tool intelligent maintenance decision-making method and system based on digital twinning

Abstract

The invention provides an intelligent maintenance decision-making method and system for a numerical control machine tool based on digital twinning, and relates to the technical field of equipment maintenance, and the method comprises the steps: obtaining the structural data and simulation precision requirements of the numerical control machine tool, determining the optimal grid size and distribution parameters of a finite element model, obtaining operation conditions, and adding the operation conditions to a multi-physics coupling modeling module, generating a machine tool digital twinborn model, fusing the machine tool digital twinborn model with the physical field, generating a machine tool operation degradation model, and optimizing to obtain a self-evolution digital twinborn model; obtaining machine tool operation parameters, performing preprocessing to obtain multi-modal perception data, extracting multi-view potential features, determining potential correlation features, and obtaining a machine tool health state evaluation result; the method comprises the following steps: generating a multi-level fault prediction result, determining a candidate maintenance scheme, adding the candidate maintenance scheme and the multi-level fault prediction result into a knowledge graph construction module, generating a semantic association network, and solving to obtain an optimal maintenance decision in combination with a multi-objective optimization algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and in particular to an intelligent maintenance decision method and system for CNC machine tools based on digital twins. Background Art

[0002] With the continuous development of the manufacturing industry, CNC machine tools have become one of the key equipment in modern manufacturing. The reliable operation of CNC machine tools directly affects production efficiency and product quality. However, due to factors such as the complex structure and harsh working environment of CNC machine tools, various faults and performance degradation problems are inevitable during operation.

[0003] Traditional CNC machine tool maintenance mainly relies on regular maintenance and post-repair. This passive maintenance model is difficult to adapt to the needs of modern manufacturing. Regular maintenance cycles are difficult to determine. Too frequent maintenance will increase maintenance costs, while too sparse maintenance will fail to detect potential faults in time. Post-repair will cause unexpected downtime, affecting production progress and product delivery. In addition, traditional maintenance methods rely heavily on the experience and skills of maintenance personnel, resulting in high labor costs and strong subjectivity in decision-making.

[0004] With the development of technologies such as the Internet of Things, big data, and artificial intelligence, intelligent maintenance decision-making methods have received widespread attention. However, most methods only focus on a single data source, which makes it difficult to fully reflect the health status of machine tools. At the same time, they are mainly based on data-driven modeling and lack consideration of the physical mechanism of machine tools. The interpretability and reliability of prediction results need to be improved.

[0005] Therefore, a solution is urgently needed to solve the problems existing in the prior art. Summary of the invention

[0006] The embodiments of the present invention provide a method and system for intelligent maintenance decision-making of CNC machine tools based on digital twins, which can at least solve some of the problems existing in the prior art.

[0007] A first aspect of an embodiment of the present invention provides a method for intelligent maintenance decision-making of a CNC machine tool based on digital twins, comprising:

[0008] Acquire the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and fuse it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model;

[0009] A sensor network is constructed based on the self-evolving digital twin model, the CNC machine tool is fully sensed and the machine tool operating parameters are obtained through distributed adaptive sampling, the machine tool operating parameters are preprocessed, multi-modal sensing data is obtained and added to the multi-view learning fusion model, multi-view potential features are extracted and potential correlation features between different modes are determined, and the machine tool health status assessment result is obtained in combination with the self-evolving digital twin model;

[0010] Based on the machine tool health status assessment result, a multi-level fault prediction result is generated in combination with a pre-set multi-time scale fault prediction model. Combined with historical maintenance cases, candidate maintenance plans are adaptively determined through a maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plans and the multi-level fault prediction results are added to the knowledge graph construction module. By associating the machine tool failure causes and failure mechanisms, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision.

[0011] In an optional embodiment,

[0012] The structural data and simulation accuracy requirements of the CNC machine tool are obtained, and the optimal mesh size and distribution parameters of the finite element model are determined by combining the adaptive meshing algorithm. The operating conditions of the CNC machine tool in the finite element model are obtained and added to the multi-physics field coupling modeling module. The machine tool digital twin model is generated and integrated with the physical field. The machine tool operation degradation model is generated by combining the mapping relationship. The self-evolving digital twin model is obtained by continuous optimization through the pre-acquired machine tool operation big data and the deep transfer learning model, including:

[0013] Acquire structural parameters of the CNC machine tool through three-dimensional scanning, wherein the structural parameters include the size, shape and assembly relationship of the parts of the CNC machine tool, and acquire the simulation accuracy requirements corresponding to the CNC machine tool based on the service condition and failure mode of the CNC machine tool;

[0014] Perform feature analysis on the CNC machine tool, extract structural stress and hot spots as key features, determine feature attributes and determine mesh scales in different areas in combination with simulation accuracy requirements, take areas with concentrated stress and sudden cross-section changes as weak areas, increase mesh density in the weak areas, combine high-order mesh units, improve approximation accuracy of field variables within the units, complete mesh division and obtain the optimal mesh size and distribution parameters, and build a multi-granularity finite element model of the current CNC machine tool through finite element software;

[0015] Based on the multi-granularity finite element model, the boundary conditions of the CNC machine tool under the processing conditions are obtained, and the boundary conditions are added to the multi-granularity finite element model as loads and constraints. Combined with the physical field corresponding to the CNC machine tool, a simulation numerical solution is performed in combination with a physical field coupling solution method to obtain the corresponding physical field behavior. Combined with sensor mapping technology, the state data of the CNC machine tool is collected and mapped to the corresponding nodes of the virtual model to obtain a multi-physical field digital twin model, the degradation process of the CNC machine tool is obtained, and the degradation precursor features are extracted in combination with the pre-acquired machine tool operation big data to construct a machine tool degradation model;

[0016] Through deep transfer learning technology, combined with the machine tool operation big data, common features under different working conditions are extracted through deep neural networks, degradation laws are determined, and the machine tool degradation model is adaptively adjusted under new working conditions combined with transfer learning to obtain the self-evolving digital twin model.

[0017] In an optional embodiment,

[0018] Combined with transfer learning, the machine tool degradation model is adaptively adjusted under new working conditions as shown in the following formula:

[0019] ;

[0020] Among them, θ t represents the network parameters under the target working condition, L t (θ) represents the loss function under the target working condition, dist(θ s , θ) represents the distance measure between the network parameters of the source and target conditions, λ 1 represents the distance metric weight factor, λ 2 represents the regularization term weight factor, and R(θ) represents the regularization term.

[0021] In an optional embodiment,

[0022] A sensor network is constructed based on the self-evolving digital twin model, the CNC machine tool is fully sensed and the machine tool operating parameters are obtained through distributed adaptive sampling, the machine tool operating parameters are preprocessed, multi-modal sensing data is obtained and added to the multi-view learning fusion model, multi-view potential features are extracted and potential correlation features between different modes are determined, and the machine tool health status assessment results obtained by combining the self-evolving digital twin model include:

[0023] Based on the self-evolving digital twin model, a sensor network covering all components and functional units of the CNC machine tool is constructed, wherein the sensor network includes multiple types of sensors corresponding to vibration, temperature, stress, displacement and current;

[0024] Based on the sensor network, the CNC machine tool is fully sensed, combined with the adaptive sampling trigger pre-set at the edge node, the sampling frequency of the sensor network is dynamically adjusted according to the real-time working condition and degradation state of the CNC machine tool, the machine tool operation parameters are obtained, and the machine tool operation parameters are pre-processed to obtain the multimodal perception data;

[0025] Based on the multimodal perception data, for each modality, a corresponding feature extraction subview is set, and based on the feature extraction subview, trend features and period features are extracted from the data in each modality as multi-view potential features, and based on the multi-view potential features, a multi-view fusion algorithm is combined to generate a cross-modal common representation by determining linear correlations and nonlinear correlations between different modalities, and a multi-view alignment strategy is combined to determine potential correlation features;

[0026] The potential correlation features are added to the self-evolving digital twin model, and combined with real-time monitoring data to generate the machine tool health status assessment result.

[0027] In an optional embodiment,

[0028] Based on the feature extraction subview, the trend features and period features of the data in each mode are extracted as shown in the following formula:

[0029] ;

[0030] Where WT(a, b) represents the periodic characteristics at scale a and position b, a represents the scale parameter, which is used to control the width of the function, b represents the translation parameter, which is used to determine the position of the function on the time axis, x(t) represents the original signal, and ψ() represents the mother wavelet function;

[0031] ;

[0032] Among them, y(t) represents the trend characteristics of the data in the current mode, w j represents the weight coefficient of the jth scale, M j represents the length of the sliding window of the jth scale, J represents the total number of scales, and i is an index variable used to represent the time step back relative to the current time point t.

[0033] In an optional embodiment,

[0034] Based on the machine tool health status assessment result, a multi-level fault prediction result is generated in combination with a pre-set multi-time scale fault prediction model. In combination with historical maintenance cases, a candidate maintenance plan is adaptively determined through a maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plan and the multi-level fault prediction result are added to the knowledge graph construction module. By associating the cause of the machine tool failure and the failure mechanism, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision, including:

[0035] Obtain the machine tool health status assessment result and add it to a pre-set multi-time scale fault prediction model, generate a short-term prediction result through a short-term prediction model based on a gated recurrent unit, determine a medium-term prediction result through a medium-term prediction model based on a convolutional long short-term memory network, generate a long-term prediction result through a long-term prediction model based on a deep survival model, and combine the prediction results to obtain the multi-level fault prediction result;

[0036] Based on the multi-level fault prediction results, a global decision layer and a subtask decision layer are set in combination with working conditions, wherein the global decision layer takes the health state of the CNC machine tool as the state, the candidate maintenance plan set as the action, and the maintenance performance index as the reward, and the subtask decision layer takes the subtask state as the state, the subtask execution plan as the action, and the subtask performance index as the reward;

[0037] Based on the global decision layer and the subtask decision layer, the global optimal decision and the local optimal decision are determined in combination with the active exploration mechanism, the global optimal decision is collaboratively optimized in combination with the Nash equilibrium strategy, and a global maintenance solution set is generated. The subtask decision layer is distributedly optimized through a multi-agent reinforcement learning algorithm to generate a subtask execution solution, and the subtask execution solution and the global maintenance solution set are integrated to obtain a candidate maintenance solution, and the integration is repeated to obtain a candidate maintenance solution set;

[0038] Design the CNC machine tool domain ontology, define core concepts and relationship types, extract entities and attribute information corresponding to the entities from structured data and unstructured data, perform knowledge fusion based on rule and graph embedding methods, generate a CNC machine tool knowledge graph, add the candidate maintenance plan and the multi-level fault prediction results to the CNC machine tool knowledge graph, determine the fault cause and failure mechanism through semantic association analysis and path reasoning and graph embedding reasoning algorithm, generate a semantic association network and the fault propagation path corresponding to the current fault;

[0039] With the goal of minimizing the failure recurrence rate and the maintenance cost, the objective function is set in combination with a multi-objective optimization algorithm and multiple elements are randomly selected from the candidate maintenance plan set to form an initial population. The initial population is subjected to crossover and mutation operations to generate a child population and perform non-dominated sorting. The congestion degree is calculated and the retained individuals are determined in combination with the dominance relationship. The operation is repeated to generate a Pareto frontier and sort them according to the Pareto solution set, and the individual ranked first is selected as the optimal maintenance decision.

[0040] In an optional embodiment,

[0041] The loss function corresponding to the long-term prediction model based on the deep survival model is shown in the following formula:

[0042] ;

[0043] Among them, L represents the loss value, δ g represents the indicative function, indicating whether the g-th sample is the time point when the event occurs. f(x, T) represents the prediction result of the model for the input feature x and time t. g represents the event occurrence of the g-th sample, μ represents the regularization coefficient, and W represents the network parameter.

[0044] A second aspect of an embodiment of the present invention provides an intelligent maintenance decision system for CNC machine tools based on digital twins, comprising:

[0045] The first unit is used to obtain the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and integrate it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model;

[0046] The second unit is used to build a sensor network based on the self-evolving digital twin model, comprehensively perceive the CNC machine tool and obtain the machine tool operating parameters through distributed adaptive sampling, pre-process the machine tool operating parameters, obtain multi-modal perception data and add it to the multi-view learning fusion model, extract multi-perspective potential features and determine the potential correlation features between different modes, and obtain the machine tool health status assessment result in combination with the self-evolving digital twin model;

[0047] The third unit is used to generate a multi-level fault prediction result based on the machine tool health status assessment result in combination with a pre-set multi-time scale fault prediction model, and in combination with historical maintenance cases, adaptively determine candidate maintenance plans through a maintenance strategy optimization algorithm based on deep reinforcement learning, add the candidate maintenance plans and the multi-level fault prediction results to the knowledge graph construction module, and generate a semantic association network by associating the cause of machine tool failure and the failure mechanism, and combine it with a multi-objective optimization algorithm to solve and obtain the optimal maintenance decision.

[0048] According to a third aspect of the embodiments of the present invention,

[0049] An electronic device is provided, comprising:

[0050] processor;

[0051] a memory for storing processor-executable instructions;

[0052] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0053] A fourth aspect of the embodiments of the present invention is:

[0054] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0055] In the present invention, the finite element model is optimized by an adaptive meshing algorithm, and a digital twin model of a machine tool is generated by combining multi-physics field coupling modeling. The machine tool operation big data is combined with the deep transfer learning model to realize continuous optimization and self-evolution of the digital twin model, which can accurately reflect the real-time operation status and degradation law of the machine tool, and provide a reliable digital foundation for subsequent health assessment and fault prediction. A multi-view learning fusion model is used to extract features and perform correlation analysis on multi-modal perception data to realize information fusion between different modes, which can comprehensively capture the multi-dimensional characteristics of the machine tool operation status, improve the accuracy and robustness of health status assessment, and introduce a multi-time scale fault prediction model to accurately predict the fault status of the machine tool from the short-term and medium-term. The machine tool failure can be predicted at three time scales: short-term and long-term, which can capture the dynamic characteristics of fault evolution, provide a comprehensive estimate of the time and severity of fault occurrence, and provide a basis for formulating targeted maintenance strategies. The maintenance strategy optimization algorithm based on deep reinforcement learning is adopted to adaptively determine candidate maintenance plans according to the machine tool health status and fault prediction results, so that maintenance decisions can be continuously improved over time, thereby improving the pertinence and effectiveness of maintenance. In summary, the present invention significantly improves the operation and maintenance efficiency and reliability of CNC machine tools, realizes the intelligence of machine tool health status assessment, fault prediction and maintenance decision-making, and provides an innovative solution for realizing intelligent operation and maintenance of CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flowchart of a method for intelligent maintenance decision-making of CNC machine tools based on digital twins according to an embodiment of the present invention;

[0057] Figure 2 It is a structural schematic diagram of an intelligent maintenance decision system for CNC machine tools based on digital twins according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0060] Figure 1 Schematic diagram of the process of intelligent maintenance decision-making method for CNC machine tools based on digital twins according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0061] S1. Obtain the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and integrate it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model;

[0062] The simulation accuracy requirement refers to the requirements for the accuracy and precision of the results during computer simulation and numerical simulation. The adaptive meshing algorithm is used to automatically adjust the meshing density according to the error or gradient change of the solution during the simulation process. The finite element model is a numerical calculation method that solves complex physical problems by dividing a continuous medium into discrete finite elements. The multi-physics field coupling modeling module is used to simulate the interaction between multiple physical fields (such as heat, structure, fluid, electromagnetic, etc.). The deep transfer learning model refers to using the knowledge of a deep learning model trained on a source task to help solve problems on a target task. The self-evolving digital twin model is a digital model that can continuously update and optimize itself as the physical system changes and data accumulates.

[0063] In an optional embodiment,

[0064] The structural data and simulation accuracy requirements of the CNC machine tool are obtained, and the optimal mesh size and distribution parameters of the finite element model are determined by combining the adaptive meshing algorithm. The operating conditions of the CNC machine tool in the finite element model are obtained and added to the multi-physics field coupling modeling module. The machine tool digital twin model is generated and integrated with the physical field. The machine tool operation degradation model is generated by combining the mapping relationship. The self-evolving digital twin model is obtained by continuous optimization through the pre-acquired machine tool operation big data and the deep transfer learning model, including:

[0065] Acquire structural parameters of the CNC machine tool through three-dimensional scanning, wherein the structural parameters include the size, shape and assembly relationship of the parts of the CNC machine tool, and acquire the simulation accuracy requirements corresponding to the CNC machine tool based on the service condition and failure mode of the CNC machine tool;

[0066] Perform feature analysis on the CNC machine tool, extract structural stress and hot spots as key features, determine feature attributes and determine mesh scales in different areas in combination with simulation accuracy requirements, take areas with concentrated stress and sudden cross-section changes as weak areas, increase mesh density in the weak areas, combine high-order mesh units, improve approximation accuracy of field variables within the units, complete mesh division and obtain the optimal mesh size and distribution parameters, and build a multi-granularity finite element model of the current CNC machine tool through finite element software;

[0067] Based on the multi-granularity finite element model, the boundary conditions of the CNC machine tool under the processing conditions are obtained, and the boundary conditions are added to the multi-granularity finite element model as loads and constraints. Combined with the physical field corresponding to the CNC machine tool, a simulation numerical solution is performed in combination with a physical field coupling solution method to obtain the corresponding physical field behavior. Combined with sensor mapping technology, the state data of the CNC machine tool is collected and mapped to the corresponding nodes of the virtual model to obtain a multi-physical field digital twin model, the degradation process of the CNC machine tool is obtained, and the degradation precursor features are extracted in combination with the pre-acquired machine tool operation big data to construct a machine tool degradation model;

[0068] Through deep transfer learning technology, combined with the machine tool operation big data, common features under different working conditions are extracted through deep neural networks, degradation laws are determined, and the machine tool degradation model is adaptively adjusted under new working conditions combined with transfer learning to obtain the self-evolving digital twin model.

[0069] The failure mode refers to the various types and manifestations of failures that may occur in the system or equipment, the structural stress refers to the internal stress generated by the structural parts under the action of external loads, the approximation accuracy refers to the degree of fit of the model to the actual system or data during the numerical simulation and modeling process, the degradation precursor characteristics refer to the early characteristics or signals exhibited by the system or equipment during the degradation process, and the degradation law refers to the regular changes in the performance of the system or equipment gradually declining over time during use.

[0070] The structural parameters of CNC machine tools are obtained through 3D scanning technology, including the size, shape and assembly relationship of CNC machine tool parts. Based on the service conditions and failure modes of CNC machine tools, the corresponding simulation accuracy requirements of CNC machine tools are determined;

[0071] Conduct feature analysis on CNC machine tools, extract structural stress and hot spots as key features, determine feature attributes, determine mesh scales in different areas in combination with simulation accuracy requirements, and consider areas with concentrated stress and sudden cross-section changes as weak areas. Increase mesh density in weak areas, combine high-order mesh units, improve approximation accuracy of field variables within the units, complete mesh division, obtain optimal mesh size and distribution parameters, and build a multi-granularity finite element model of the current CNC machine tool through finite element software;

[0072] The boundary conditions of the CNC machine tool under actual processing conditions, such as loads and constraints, are added to the multi-granular finite element model. The multi-physics field coupling of the machine tool, such as the mutual influence of structural stress and thermal field, is considered. The multi-granular finite element model is numerically simulated and solved using the physical field coupling solution method to obtain the physical field behavior of the CNC machine tool under actual working conditions, such as stress distribution, deformation, and temperature distribution. Combined with sensor mapping technology, the real-time collected CNC machine tool status data is mapped to the corresponding nodes of the virtual model to build a multi-physics field digital twin model to achieve real-time monitoring and prediction of the working status of the machine tool.

[0073] Using the pre-acquired machine tool operation big data, the degradation process and degradation precursor characteristics of the machine tool are extracted, including performance parameter changes, vibration spectrum anomalies, etc., which are used to build a machine tool degradation model. Based on deep transfer learning technology and combined with machine tool operation big data, the common features under different working conditions are extracted through deep neural networks to determine the degradation law. The machine tool degradation model is adaptively adjusted under the new working conditions using the transfer learning method to generate a self-evolving digital twin model.

[0074] In this embodiment, the geometric structure and assembly relationship of the CNC machine tool are accurately obtained through three-dimensional scanning technology to ensure the authenticity and accuracy of the model, improve the credibility and application value of the simulation results, and accurately capture the structural stress and hot spot areas of the machine tool through feature extraction algorithms and structural analysis tools. The weak areas are determined and the approximation accuracy of the stress field variables is improved by increasing the grid density and using high-order grid units. It can effectively predict possible structural problems. Based on deep neural networks and transfer learning methods, common features under different working conditions are extracted, the degradation law of the CNC machine tool is determined, and the adaptive adjustment of the machine tool degradation model is realized, so that the digital twin model can be continuously optimized and updated, and the prediction accuracy and fault diagnosis effect are improved. In summary, this embodiment can significantly improve the operating safety, stability and efficiency of the CNC machine tool, effectively extend the service life of the equipment, and reduce maintenance costs, thereby achieving the goals of intelligent manufacturing and service-oriented operations.

[0075] In an optional embodiment,

[0076] Combined with transfer learning, the machine tool degradation model is adaptively adjusted under new working conditions as shown in the following formula:

[0077] ;

[0078] Among them, θ t represents the network parameters under the target working condition, L t (θ) represents the loss function under the target working condition, dist(θ s , θ) represents the distance measure between the network parameters of the source and target conditions, λ 1represents the distance metric weight factor, λ 2 represents the regularization term weight factor, and R(θ) represents the regularization term.

[0079] In this embodiment, by introducing the model parameters trained under the source working condition to measure the difference between the network parameters of the source working condition and the target working condition, and controlling the intensity of the source working condition knowledge transfer through the weight factor, it is helpful to improve the generalization ability of the model under the target working condition, especially when the target working condition sample data is small. By introducing the regularization term, the network parameters under the target working condition are constrained and smoothed to avoid model overfitting. By controlling the distance measurement weight factor and the regularization term weight factor, the proportion of source working condition knowledge transfer and target working condition own feature learning can be balanced, which helps to improve the robustness of the model and enable it to better adapt to the data distribution and noise disturbance under the target working condition. In summary, this embodiment makes full use of the prior knowledge under the source working condition, improves the generalization ability, convergence speed and robustness of the model, realizes the adaptive optimization of the model under the new working condition, and provides strong support for the health management and predictive maintenance of CNC machine tools.

[0080] S2. Construct a sensor network based on the self-evolving digital twin model, comprehensively perceive the CNC machine tool and obtain the machine tool operating parameters through distributed adaptive sampling, pre-process the machine tool operating parameters, obtain multi-modal perception data and add them to the multi-view learning fusion model, extract multi-perspective potential features and determine the potential correlation features between different modes, and obtain the machine tool health status assessment result in combination with the self-evolving digital twin model;

[0081] The distributed adaptive sampling is a method for meeting the data collection needs in distributed systems. The adaptive sampling strategy can dynamically adjust the sampling frequency and sampling range of the sensor according to the real-time machine tool operation status and environmental conditions to ensure that the collected data is representative and high-quality, while reducing the cost of data transmission and processing. The machine tool operation parameters refer to various parameters that describe the key performance and status of the machine tool during operation, including but not limited to: cutting speed, feed speed, cutting force, temperature, vibration, machining accuracy, etc. The multi-view learning fusion model combines data features under different perspectives or modes to more comprehensively and accurately analyze the machine tool operation status and health status. The multi-view potential features refer to representative and highly correlated data features extracted from multiple perspectives or modes. The potential correlation features refer to correlations and patterns that may exist in the data but are not easily observed directly. The machine tool health status assessment result is a conclusion based on the multi-view learning fusion model and multi-view potential feature analysis, reflecting the overall operation health status of the machine tool at a specific moment or cycle.

[0082] In an optional embodiment,

[0083] A sensor network is constructed based on the self-evolving digital twin model, the CNC machine tool is fully sensed and the machine tool operating parameters are obtained through distributed adaptive sampling, the machine tool operating parameters are preprocessed, multi-modal sensing data is obtained and added to the multi-view learning fusion model, multi-view potential features are extracted and potential correlation features between different modes are determined, and the machine tool health status assessment results obtained by combining the self-evolving digital twin model include:

[0084] Based on the self-evolving digital twin model, a sensor network covering all components and functional units of the CNC machine tool is constructed, wherein the sensor network includes multiple types of sensors corresponding to vibration, temperature, stress, displacement and current;

[0085] Based on the sensor network, the CNC machine tool is fully sensed, combined with the adaptive sampling trigger pre-set at the edge node, the sampling frequency of the sensor network is dynamically adjusted according to the real-time working condition and degradation state of the CNC machine tool, the machine tool operation parameters are obtained, and the machine tool operation parameters are pre-processed to obtain the multimodal perception data;

[0086] Based on the multimodal perception data, for each modality, a corresponding feature extraction subview is set, and based on the feature extraction subview, trend features and period features are extracted from the data in each modality as multi-view potential features, and based on the multi-view potential features, a multi-view fusion algorithm is combined to generate a cross-modal common representation by determining linear correlations and nonlinear correlations between different modalities, and a multi-view alignment strategy is combined to determine potential correlation features;

[0087] The potential correlation features are added to the self-evolving digital twin model, and combined with real-time monitoring data to generate the machine tool health status assessment result.

[0088] The functional unit refers to the basic component in the system or model that completes a specific function or task. The adaptive sampling trigger is used to automatically trigger data collection according to the system state or specific conditions. The feature extraction subview is a module that extracts features of specific aspects or modalities from the data. The cross-modal common representation refers to mapping information of different modalities or data types into a shared representation space to facilitate comparison and fusion between different data sources. The multi-view alignment strategy refers to a method or technology used in multi-view learning to ensure the consistency and correlation of information between different views.

[0089] According to the structure and functional characteristics of CNC machine tools, multiple types of sensors are deployed, including vibration sensors, temperature sensors, stress sensors, displacement sensors, and current sensors. The layout and quantity of sensors should fully consider the key components and weak links of the machine tools to ensure comprehensive perception of the machine tool status;

[0090] An adaptive sampling trigger is set at the edge node to dynamically adjust the sampling frequency of the sensor network according to the real-time working condition and degradation state of the CNC machine tool. When the machine tool is in a stable working condition, the sampling frequency is reduced to reduce data redundancy. When the machine tool working condition changes or there are signs of degradation, the sampling frequency is increased to obtain more detailed status data. The collected machine tool operating parameters are preprocessed to obtain multimodal perception data.

[0091] For each data modality, a corresponding feature extraction subview is set. In each subview, the trend features and periodic features of the data are extracted as multi-view potential features. A multi-view fusion algorithm is used to generate a cross-modal common representation by analyzing the linear and nonlinear correlations between different modalities. Combined with the multi-view alignment strategy, the potential correlation features are determined to achieve effective fusion of multi-modal data.

[0092] The obtained potential correlation features are used as new inputs and added to the self-evolving digital twin model. Based on the updated model and combined with the real-time monitoring data collected by the sensor network, the current health status of the CNC machine tool is evaluated. The evaluation results may include the overall health of the machine tool, the health of key components, degradation trend prediction, etc., to obtain the health status evaluation results of the machine tool.

[0093] In this embodiment, by arranging multiple types of sensors in the key components and weak links of the CNC machine tool and building a sensor network covering all components and functional units, comprehensive perception of multiple state parameters of the machine tool, such as vibration, temperature, stress, displacement, and current, is achieved, providing a rich information basis for subsequent data analysis and health assessment. The multimodal data fusion method makes full use of the complementarity and correlation between different modal data, improves the richness and robustness of feature representation, and provides more comprehensive and accurate information for health status assessment. The digital twin model can dynamically adapt to the degradation process and working condition changes of the CNC machine tool through continuous learning and adaptive adjustment, thereby improving the accuracy and real-time performance of the health status assessment. In summary, this embodiment significantly improves the intelligence level of CNC machine tool health management, and provides strong support for predictive maintenance and optimization of operation and maintenance strategies.

[0094] In an optional embodiment,

[0095] Based on the feature extraction subview, the trend features and period features of the data in each mode are extracted as shown in the following formula:

[0096] ;

[0097] Where WT(a, b) represents the periodic characteristics at scale a and position b, a represents the scale parameter, which is used to control the width of the function, b represents the translation parameter, which is used to determine the position of the function on the time axis, x(t) represents the original signal, and ψ() represents the mother wavelet function;

[0098] ;

[0099] Among them, y(t) represents the trend characteristics of the data in the current mode, w j represents the weight coefficient of the jth scale, M j represents the length of the sliding window of the jth scale, J represents the total number of scales, and i is an index variable used to represent the time step back relative to the current time point t.

[0100] In this embodiment, wavelet transform is used to extract periodic features, which can effectively capture the periodic components of the signal at different scales. The sliding average method can effectively smooth short-term fluctuations and highlight long-term trends by performing weighted averaging on data in sliding windows of different scales. By combining periodic features and trend features at different scales, multi-scale feature fusion is achieved. By selecting a suitable mother wavelet function, high-frequency noise can be effectively suppressed and useful periodic components can be highlighted. In summary, this embodiment can effectively capture the periodic behavior and long-term trends in the operation of CNC machine tools, and has good noise reduction and feature enhancement capabilities, providing high-quality and high-reliability feature inputs for subsequent health status assessments.

[0101] S3. Based on the health status assessment result of the machine tool, combined with the pre-set multi-time scale fault prediction model, a multi-level fault prediction result is generated. Combined with historical maintenance cases, the candidate maintenance plan is adaptively determined through the maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plan and the multi-level fault prediction result are added to the knowledge graph construction module. By associating the cause of the machine tool failure and the failure mechanism, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision.

[0102] The multi-time scale fault prediction model considers the fault prediction of the system or equipment at different time scales. The multi-level fault prediction result refers to the multi-level prediction and analysis of different types of faults that may occur in the system or equipment. The historical maintenance case refers to the record and analysis of past cases and experiences of maintenance and repair of the system or equipment. The maintenance strategy optimization algorithm is aimed at the decision-making problem of equipment maintenance. Based on data analysis and model prediction, the optimal maintenance time, method and resource allocation are determined through optimization methods. The knowledge graph construction module is a module that uses knowledge graph technology to model and represent the key information, attributes, relationships and behaviors of the system or equipment in the form of a graph. The failure mechanism refers to the root cause or physical process that causes the failure of the equipment or system. The semantic association network is a network structure built based on semantic relationships, which is used to describe and analyze the association between entities.

[0103] In an optional embodiment,

[0104] Based on the machine tool health status assessment result, a multi-level fault prediction result is generated in combination with a pre-set multi-time scale fault prediction model. In combination with historical maintenance cases, a candidate maintenance plan is adaptively determined through a maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plan and the multi-level fault prediction result are added to the knowledge graph construction module. By associating the cause of the machine tool failure and the failure mechanism, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision, including:

[0105] Obtain the machine tool health status assessment result and add it to a pre-set multi-time scale fault prediction model, generate a short-term prediction result through a short-term prediction model based on a gated recurrent unit, determine a medium-term prediction result through a medium-term prediction model based on a convolutional long short-term memory network, generate a long-term prediction result through a long-term prediction model based on a deep survival model, and combine the prediction results to obtain the multi-level fault prediction result;

[0106] Based on the multi-level fault prediction results, a global decision layer and a subtask decision layer are set in combination with working conditions, wherein the global decision layer takes the health state of the CNC machine tool as the state, the candidate maintenance plan set as the action, and the maintenance performance index as the reward, and the subtask decision layer takes the subtask state as the state, the subtask execution plan as the action, and the subtask performance index as the reward;

[0107] Based on the global decision layer and the subtask decision layer, the global optimal decision and the local optimal decision are determined in combination with the active exploration mechanism, the global optimal decision is collaboratively optimized in combination with the Nash equilibrium strategy, and a global maintenance solution set is generated. The subtask decision layer is distributedly optimized through a multi-agent reinforcement learning algorithm to generate a subtask execution solution, and the subtask execution solution and the global maintenance solution set are integrated to obtain a candidate maintenance solution, and the integration is repeated to obtain a candidate maintenance solution set;

[0108] Design the CNC machine tool domain ontology, define core concepts and relationship types, extract entities and attribute information corresponding to the entities from structured data and unstructured data, perform knowledge fusion based on rule and graph embedding methods, generate a CNC machine tool knowledge graph, add the candidate maintenance plan and the multi-level fault prediction results to the CNC machine tool knowledge graph, determine the fault cause and failure mechanism through semantic association analysis and path reasoning and graph embedding reasoning algorithm, generate a semantic association network and the fault propagation path corresponding to the current fault;

[0109] With the goal of minimizing the failure recurrence rate and the maintenance cost, the objective function is set in combination with a multi-objective optimization algorithm and multiple elements are randomly selected from the candidate maintenance plan set to form an initial population. The initial population is subjected to crossover and mutation operations to generate a child population and perform non-dominated sorting. The congestion degree is calculated and the retained individuals are determined in combination with the dominance relationship. The operation is repeated to generate a Pareto frontier and sort them according to the Pareto solution set, and the individual ranked first is selected as the optimal maintenance decision.

[0110] The global decision layer refers to the level responsible for global task allocation and optimization decision-making in the entire system or multi-agent system. The subtask decision layer is the level responsible for executing specific tasks and local decisions in the multi-agent system. The Nash equilibrium strategy is an important concept in game theory, which means that among multiple decision makers, each decision maker chooses his own best strategy based on the strategy choices of other decision makers, so that each decision maker cannot improve his own utility by unilaterally changing the strategy. The multi-agent reinforcement learning algorithm is a type of algorithm designed for multi-agent systems. Combined with the idea of ​​reinforcement learning, multiple agents learn how to maximize cumulative rewards in interaction with the environment. The path reasoning refers to inferring possible event sequences or behavior paths based on historical data and models in complex systems. The graph embedding reasoning algorithm is a method of mapping entities and relationships in knowledge graphs to low-dimensional vector spaces for the convenience of reasoning and analysis. The fault propagation path describes how the fault propagates and affects various parts or components of the system after a fault occurs in the system. The non-dominated sorting is a method in multi-objective optimization problems for comparing and sorting solutions between multiple objective functions.

[0111] Obtain the machine tool health status assessment results and add them to the pre-set multi-time scale fault prediction model. Generate short-term prediction results through the short-term prediction model based on the gated recurrent unit. Determine the medium-term prediction results through the medium-term prediction model based on the convolutional long short-term memory network. Generate long-term prediction results through the long-term prediction model based on the deep survival model. Combine the short-term, medium-term and long-term prediction results to obtain multi-level fault prediction results.

[0112] Based on the multi-level fault prediction results, the global decision layer and sub-task decision layer are set in combination with the working conditions. The global decision layer takes the health status of the CNC machine tool as the state, the candidate maintenance plan set as the action, and the maintenance performance index as the reward. The sub-task decision layer takes the sub-task state as the state, the sub-task execution plan as the action, and the sub-task performance index as the reward. The Nash equilibrium strategy is used to collaboratively optimize the global optimal decision and generate a global maintenance plan set. The sub-task decision layer is distributedly optimized through the multi-agent reinforcement learning algorithm to generate sub-task execution plans. The sub-task execution plans and the global maintenance plan set are integrated to obtain candidate maintenance plans. Repeat the integration process to obtain a set of candidate maintenance plans;

[0113] Design the CNC machine tool domain ontology, define core concepts and relationship types, extract entities and corresponding attribute information from structured data and unstructured data, generate the CNC machine tool knowledge graph through knowledge fusion based on rule and graph embedding methods, add candidate maintenance plans and multi-level fault prediction results to the CNC machine tool knowledge graph, determine the fault cause and failure mechanism through semantic association analysis, path reasoning and graph embedding reasoning algorithm, generate semantic association network based on knowledge graph, and fault propagation path corresponding to the current fault, the semantic association network and fault propagation path are used to display the root cause and evolution process of the fault, and provide knowledge support for maintenance decision-making;

[0114] With the goal of minimizing the failure recurrence rate and the maintenance cost, a multi-objective optimization problem is set, and the objective function is set in combination with the multi-objective optimization algorithm. Multiple elements are randomly selected from the candidate maintenance solution set to form an initial population, and crossover and mutation operations are performed on the initial population to generate a child population. The child population is non-dominated and sorted, and the crowding degree of the individuals is calculated. The retained individuals are determined in combination with the dominance relationship to form a new generation of populations. The child population is repeatedly generated until the preset maximum number of iterations is reached, and finally the Pareto frontier is generated, which represents the optimal trade-off solution set between the failure recurrence rate and the maintenance cost.

[0115] The Pareto solutions are sorted and the first individual is selected as the optimal maintenance decision. The optimal maintenance decision comprehensively considers the fault prediction results, candidate maintenance plans, knowledge graph reasoning and multi-objective optimization, which can minimize the fault recurrence rate and maintenance cost while ensuring the feasibility and effectiveness of the maintenance plan.

[0116] In this embodiment, a multi-time scale fault prediction model is adopted to predict the faults of CNC machine tools from three levels: short-term, medium-term and long-term, which provides an important basis for maintenance decisions and helps to improve the foresight and pertinence of maintenance strategies. Through the coordinated optimization of the global decision layer and the subtask decision layer, a set of candidate maintenance solutions is generated, which can continuously learn and optimize in the interaction with the environment, adaptively adjust the maintenance strategy to adapt to the changes in the machine tool state, construct a knowledge graph of CNC machine tools, integrate structured and unstructured data, and form a comprehensive semantic representation of machine tool faults, which provides rich domain knowledge support for maintenance decisions and helps to improve the interpretability and credibility of decisions. With the goal of minimizing the fault recurrence rate and minimizing the maintenance cost, a multi-objective optimization problem is constructed, which can systematically consider the constraints and conflicts between different maintenance goals, generate the globally optimal maintenance decision, and achieve a balance between maintenance effect and maintenance cost. In summary, this embodiment realizes the intelligence and optimization of CNC machine tool maintenance decisions, provides a new solution for intelligent maintenance of CNC machine tools, and has significant technical advantages and application value.

[0117] In an optional embodiment,

[0118] The loss function corresponding to the long-term prediction model based on the deep survival model is shown in the following formula:

[0119] ;

[0120] Among them, L represents the loss value, δ g represents the indicative function, indicating whether the g-th sample is the time point when the event occurs. f(x, T) represents the prediction result of the model for the input feature x and time t. g represents the event occurrence of the g-th sample, μ represents the regularization coefficient, and W represents the network parameter.

[0121] In this embodiment, the time point of the event is included in the loss function, so that the model can learn the time characteristics of the event, make full use of the information of the event time, and improve the accuracy of long-term fault prediction. Through multi-layer nonlinear transformation, the model can capture the complex interactions and high-order relationships between features, and extract the most effective feature representation for long-term fault prediction. The survival probability estimation provides a quantitative risk assessment basis for formulating long-term maintenance strategies. The regularization constraint can improve the generalization ability of the model, so that it can make reliable long-term predictions even under unknown machine tool conditions. The deep survival model adopts an end-to-end training method and directly learns the prediction model from the input features and the event time through the back propagation algorithm, avoiding the need for manual feature engineering, simplifying the model building process, and automatically optimizing the entire process of feature extraction and survival probability estimation, thereby improving the overall performance of the model. In summary, this embodiment can effectively process machine tool status data, provide a probability estimate of long-term fault risks, and provide a quantitative decision-making basis for formulating long-term maintenance strategies.

[0122] Figure 2 Schematic diagram of the structure of the intelligent maintenance decision system for CNC machine tools based on digital twins according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0123] The first unit is used to obtain the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and integrate it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model;

[0124] The second unit is used to build a sensor network based on the self-evolving digital twin model, comprehensively perceive the CNC machine tool and obtain the machine tool operating parameters through distributed adaptive sampling, pre-process the machine tool operating parameters, obtain multi-modal perception data and add it to the multi-view learning fusion model, extract multi-perspective potential features and determine the potential correlation features between different modes, and obtain the machine tool health status assessment result in combination with the self-evolving digital twin model;

[0125] The third unit is used to generate a multi-level fault prediction result based on the machine tool health status assessment result in combination with a pre-set multi-time scale fault prediction model, and in combination with historical maintenance cases, adaptively determine candidate maintenance plans through a maintenance strategy optimization algorithm based on deep reinforcement learning, add the candidate maintenance plans and the multi-level fault prediction results to the knowledge graph construction module, and generate a semantic association network by associating the cause of machine tool failure and the failure mechanism, and combine it with a multi-objective optimization algorithm to solve and obtain the optimal maintenance decision.

[0126] According to a third aspect of the embodiments of the present invention,

[0127] An electronic device is provided, comprising:

[0128] processor;

[0129] a memory for storing processor-executable instructions;

[0130] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0131] A fourth aspect of the embodiments of the present invention is:

[0132] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0133] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. The intelligent maintenance decision-making method of CNC machine tools based on digital twins is characterized by: include: Acquire the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and fuse it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model; A sensor network is constructed based on the self-evolving digital twin model, the CNC machine tool is fully sensed and the machine tool operating parameters are obtained through distributed adaptive sampling, the machine tool operating parameters are preprocessed, multi-modal sensing data is obtained and added to the multi-view learning fusion model, multi-view potential features are extracted and potential correlation features between different modes are determined, and the machine tool health status assessment result is obtained in combination with the self-evolving digital twin model; Based on the machine tool health status assessment result, a multi-level fault prediction result is generated in combination with a pre-set multi-time scale fault prediction model. Combined with historical maintenance cases, candidate maintenance plans are adaptively determined through a maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plans and the multi-level fault prediction results are added to the knowledge graph construction module. By associating the machine tool failure causes and failure mechanisms, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision.

2. The method according to claim 1, characterized in that The structural data and simulation accuracy requirements of the CNC machine tool are obtained, and the optimal mesh size and distribution parameters of the finite element model are determined by combining the adaptive meshing algorithm. The operating conditions of the CNC machine tool in the finite element model are obtained and added to the multi-physics field coupling modeling module. The machine tool digital twin model is generated and integrated with the physical field. The machine tool operation degradation model is generated by combining the mapping relationship. The self-evolving digital twin model is obtained by continuous optimization through the pre-acquired machine tool operation big data and the deep transfer learning model, including: Acquire structural parameters of the CNC machine tool through three-dimensional scanning, wherein the structural parameters include the size, shape and assembly relationship of the parts of the CNC machine tool, and acquire the simulation accuracy requirements corresponding to the CNC machine tool based on the service condition and failure mode of the CNC machine tool; Perform feature analysis on the CNC machine tool, extract structural stress and hot spots as key features, determine feature attributes and determine mesh scales in different areas in combination with simulation accuracy requirements, take areas with concentrated stress and sudden cross-section changes as weak areas, increase mesh density in the weak areas, combine high-order mesh units, improve approximation accuracy of field variables within the units, complete mesh division and obtain the optimal mesh size and distribution parameters, and build a multi-granularity finite element model of the current CNC machine tool through finite element software; Based on the multi-granularity finite element model, the boundary conditions of the CNC machine tool under the processing conditions are obtained, and the boundary conditions are added to the multi-granularity finite element model as loads and constraints. Combined with the physical field corresponding to the CNC machine tool, a simulation numerical solution is performed in combination with a physical field coupling solution method to obtain the corresponding physical field behavior. Combined with sensor mapping technology, the state data of the CNC machine tool is collected and mapped to the corresponding nodes of the virtual model to obtain a multi-physical field digital twin model, the degradation process of the CNC machine tool is obtained, and the degradation precursor features are extracted in combination with the pre-acquired machine tool operation big data to construct a machine tool degradation model; Through deep transfer learning technology, combined with the machine tool operation big data, common features under different working conditions are extracted through deep neural networks, degradation laws are determined, and the machine tool degradation model is adaptively adjusted under new working conditions combined with transfer learning to obtain the self-evolving digital twin model.

3. The method according to claim 2, characterized in that Combined with transfer learning, the machine tool degradation model is adaptively adjusted under new working conditions as shown in the following formula: ； Among them, θ t represents the network parameters under the target working condition, L t (θ) represents the loss function under the target working condition, dist(θ s , θ) represents the distance measure between the network parameters of the source condition and the target condition, λ1 represents the distance measure weight factor, λ2 represents the regularization term weight factor, and R(θ) represents the regularization term.

4. The method according to claim 1, characterized in that: A sensor network is constructed based on the self-evolving digital twin model, the CNC machine tool is fully sensed and the machine tool operating parameters are obtained through distributed adaptive sampling, the machine tool operating parameters are preprocessed, multi-modal sensing data is obtained and added to the multi-view learning fusion model, multi-view potential features are extracted and potential correlation features between different modes are determined, and the machine tool health status assessment results obtained by combining the self-evolving digital twin model include: Based on the self-evolving digital twin model, a sensor network covering all components and functional units of the CNC machine tool is constructed, wherein the sensor network includes multiple types of sensors corresponding to vibration, temperature, stress, displacement and current; Based on the sensor network, the CNC machine tool is fully sensed, combined with the adaptive sampling trigger pre-set at the edge node, the sampling frequency of the sensor network is dynamically adjusted according to the real-time working condition and degradation state of the CNC machine tool, the machine tool operation parameters are obtained, and the machine tool operation parameters are pre-processed to obtain the multimodal perception data; Based on the multimodal perception data, for each modality, a corresponding feature extraction subview is set, and based on the feature extraction subview, trend features and period features are extracted from the data in each modality as multi-view potential features, and based on the multi-view potential features, a multi-view fusion algorithm is combined to generate a cross-modal common representation by determining linear correlations and nonlinear correlations between different modalities, and a multi-view alignment strategy is combined to determine potential correlation features; The potential correlation features are added to the self-evolving digital twin model, and combined with real-time monitoring data to generate the machine tool health status assessment result.

5. The method according to claim 4, characterized in that Based on the feature extraction subview, the trend features and period features of the data in each mode are extracted as shown in the following formula: ； Where WT(a, b) represents the periodic characteristics at scale a and position b, a represents the scale parameter, which is used to control the width of the function, b represents the translation parameter, which is used to determine the position of the function on the time axis, x(t) represents the original signal, and ψ() represents the mother wavelet function; ； Among them, y(t) represents the trend characteristics of the data in the current mode, w j represents the weight coefficient of the jth scale, M j represents the length of the sliding window of the jth scale, J represents the total number of scales, and i is an index variable used to represent the time step back relative to the current time point t.

6. The method according to claim 1, characterized in that Based on the machine tool health status assessment result, a multi-level fault prediction result is generated in combination with a pre-set multi-time scale fault prediction model. In combination with historical maintenance cases, a candidate maintenance plan is adaptively determined through a maintenance strategy optimization algorithm based on deep reinforcement learning. The candidate maintenance plan and the multi-level fault prediction result are added to the knowledge graph construction module. By associating the cause of the machine tool failure and the failure mechanism, a semantic association network is generated and combined with a multi-objective optimization algorithm to solve the optimal maintenance decision, including: Obtain the machine tool health status assessment result and add it to a pre-set multi-time scale fault prediction model, generate a short-term prediction result through a short-term prediction model based on a gated recurrent unit, determine a medium-term prediction result through a medium-term prediction model based on a convolutional long short-term memory network, generate a long-term prediction result through a long-term prediction model based on a deep survival model, and combine the prediction results to obtain the multi-level fault prediction result; Based on the multi-level fault prediction results, a global decision layer and a subtask decision layer are set in combination with working conditions, wherein the global decision layer takes the health state of the CNC machine tool as the state, the candidate maintenance plan set as the action, and the maintenance performance index as the reward, and the subtask decision layer takes the subtask state as the state, the subtask execution plan as the action, and the subtask performance index as the reward; Based on the global decision layer and the subtask decision layer, the global optimal decision and the local optimal decision are determined in combination with the active exploration mechanism, the global optimal decision is collaboratively optimized in combination with the Nash equilibrium strategy, and a global maintenance solution set is generated. The subtask decision layer is distributedly optimized through a multi-agent reinforcement learning algorithm to generate a subtask execution solution, and the subtask execution solution and the global maintenance solution set are integrated to obtain a candidate maintenance solution, and the integration is repeated to obtain a candidate maintenance solution set; Design the CNC machine tool domain ontology, define core concepts and relationship types, extract entities and attribute information corresponding to the entities from structured data and unstructured data, perform knowledge fusion based on rule and graph embedding methods, generate a CNC machine tool knowledge graph, add the candidate maintenance plan and the multi-level fault prediction results to the CNC machine tool knowledge graph, determine the fault cause and failure mechanism through semantic association analysis and path reasoning and graph embedding reasoning algorithm, generate a semantic association network and the fault propagation path corresponding to the current fault; With the goal of minimizing the failure recurrence rate and the maintenance cost, the objective function is set in combination with a multi-objective optimization algorithm and multiple elements are randomly selected from the candidate maintenance plan set to form an initial population. The initial population is subjected to crossover and mutation operations to generate a child population and perform non-dominated sorting. The congestion degree is calculated and the retained individuals are determined in combination with the dominance relationship. The operation is repeated to generate a Pareto frontier and sort them according to the Pareto solution set, and the individual ranked first is selected as the optimal maintenance decision.

7. The method according to claim 6, characterized in that The loss function corresponding to the long-term prediction model based on the deep survival model is shown in the following formula: ； Among them, L represents the loss value, δ g represents the indicative function, indicating whether the g-th sample is the time point when the event occurs. f(x, T) represents the prediction result of the model for the input feature x and time t. g represents the event occurrence of the g-th sample, μ represents the regularization coefficient, and W represents the network parameter.

8. An intelligent maintenance decision system for CNC machine tools based on digital twins, used to implement the method described in any one of claims 1 to 7, characterized in that: include: The first unit is used to obtain the structural data and simulation accuracy requirements of the CNC machine tool, determine the optimal mesh size and distribution parameters of the finite element model in combination with the adaptive meshing algorithm, obtain the operating conditions of the CNC machine tool in the finite element model and add them to the multi-physics field coupling modeling module, generate a machine tool digital twin model and integrate it with the physical field, generate a machine tool operation degradation model in combination with the mapping relationship, and continuously optimize through the pre-acquired machine tool operation big data and the deep transfer learning model to obtain a self-evolving digital twin model; The second unit is used to build a sensor network based on the self-evolving digital twin model, comprehensively perceive the CNC machine tool and obtain the machine tool operating parameters through distributed adaptive sampling, pre-process the machine tool operating parameters, obtain multi-modal perception data and add it to the multi-view learning fusion model, extract multi-perspective potential features and determine the potential correlation features between different modes, and obtain the machine tool health status assessment result in combination with the self-evolving digital twin model; The third unit is used to generate a multi-level fault prediction result based on the machine tool health status assessment result in combination with a pre-set multi-time scale fault prediction model, and in combination with historical maintenance cases, adaptively determine candidate maintenance plans through a maintenance strategy optimization algorithm based on deep reinforcement learning, add the candidate maintenance plans and the multi-level fault prediction results to the knowledge graph construction module, and generate a semantic association network by associating the cause of machine tool failure and the failure mechanism, and combine it with a multi-objective optimization algorithm to solve and obtain the optimal maintenance decision.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images