Operation and maintenance mode analysis model generation method and system, medium and program product

Abstract

The invention discloses an operation and maintenance mode analysis model generation method and system, a medium and a program product, and relates to the field of electric digital data processing. Establishing an equipment basic life model based on the equipment fault time data and the non-fault working time data; calculating an environment correction coefficient according to the equipment operation environment parameter data and a preset environment influence factor, and combining the environment correction coefficient with the basic life model to obtain a corrected life prediction model; calculating the correlation degree of each equipment node based on the equipment topological structure, and constructing an equipment importance evaluation model; calculating equipment maintenance cost, replacement cost and shutdown loss according to a prediction result of the corrected life prediction model to obtain a cost loss model; and carrying out weighted fusion on an output result of the equipment importance evaluation model and a calculation result of the cost loss model to generate an operation and maintenance mode analysis model. The scientificity and accuracy of operation and maintenance mode analysis are improved.

Description

Technical Field

[0001] The present application belongs to the field of electronic digital data processing, and in particular, relates to a method, system, medium and program product for generating an operation and maintenance mode analysis model. Background Art

[0002] In the process of operation and maintenance, the operation and maintenance management of equipment systems faces huge challenges due to the multi-source heterogeneity, massive and complex nature of operation and maintenance data. The traditional operation and maintenance management model consumes a lot of manpower and financial resources, which not only causes energy waste and direct economic losses, but also has a relatively chaotic management model and poor security, and fails to achieve the overall analysis of energy stations, energy efficiency evaluation, and operation and maintenance coordination management functions.

[0003] In the relevant technology, the equipment failure time data and the actual working time data of non-faulty parts can be collected, the Weibull life distribution parameters can be calculated using the maximum estimation and failure rate function, and the operation and maintenance costs, parts replacement costs and indirect cost losses caused by downtime can be determined by combining the component failure cost model analysis, thereby realizing the prediction and management of equipment operation and maintenance costs.

[0004] However, due to the complexity and uncertainty of the equipment operating environment, there are limitations to relying solely on equipment life and cost factors to make operation and maintenance decisions. On the one hand, the operating status of the equipment will be affected by a variety of external factors, such as ambient temperature, load changes, etc., which will lead to deviations in equipment life prediction; on the other hand, the importance of different equipment in the system and the degree of impact on life safety also vary. Operation and maintenance decisions based on life and cost may ignore the timely maintenance of key equipment, increase system operation risks, and reduce the scientificity and accuracy of operation and maintenance model analysis. Summary of the invention

[0005] The present application provides a method, system, medium and program product for generating an operation and maintenance mode analysis model, which are used to address the limitations of related technologies when making operation and maintenance decisions and improve the scientificity and accuracy of operation and maintenance mode analysis.

[0006] In a first aspect, the present application provides a method for generating an operation and maintenance mode analysis model to obtain equipment operation data, the operation data including equipment failure time data, equipment non-failure working time data, and equipment operation environment parameter data; Based on the equipment failure time data and non-failure working time data, the basic equipment life model is established using Weibull distribution; Calculate the environmental correction coefficient based on the equipment operating environment parameter data and the preset environmental impact factors, and combine the environmental correction coefficient with the basic life model to obtain a corrected life prediction model; The correlation degree of each device node is calculated based on the device topology structure, and the device importance evaluation model is constructed based on the impact of device failure on system operation and personnel safety. The equipment maintenance cost, replacement cost and downtime loss are calculated according to the prediction results of the modified life prediction model to obtain a cost loss model; The output results of the equipment importance evaluation model are weighted and fused with the calculation results of the cost loss model to generate an operation and maintenance mode analysis model.

[0007] By adopting the above technical solution, by obtaining equipment operation data and establishing a basic life model of Weibull distribution, a more accurate life prediction model is obtained by combining the environmental correction coefficient, which can reflect the impact of the actual operating environment on the equipment life. The importance evaluation model constructed based on the equipment topology structure calculation correlation and considering the impact of equipment failure can comprehensively evaluate the importance of the equipment in the system. The cost loss model obtained by calculating maintenance costs, replacement costs and downtime losses can quantify the economic impact of equipment failure. The operation and maintenance mode analysis model generated by weighted fusion of the importance evaluation model and the cost loss model takes into account the system importance of the equipment, making the operation and maintenance decision more scientific and reasonable, and can achieve optimal cost configuration while ensuring system reliability, improving the scientificity and accuracy of the operation and maintenance mode analysis.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the environment correction coefficient according to the device operating environment parameter data and the preset environmental impact factor specifically includes: Segmenting the equipment operation environment parameter data according to the time series to obtain multiple environment parameter data segments; Calculating the deviation value from the preset standard environmental parameter for each environmental parameter data segment; Calculate the correction value corresponding to each environmental parameter based on the deviation value and the preset environmental impact factor; The environmental correction coefficient is obtained by weighted summing the correction values ​​corresponding to each environmental parameter.

[0009] By adopting the above technical solution, the equipment operating environment parameter data is segmented and processed according to the time series, which can reflect the dynamic change characteristics of the environmental parameters over time. By calculating the deviation value between the environmental parameters and the preset standard environmental parameters, the degree of difference between the actual operating environment and the standard environment can be quantified. The correction value corresponding to each environmental parameter is calculated based on the deviation value and the preset environmental impact factor, which can reflect the weight of the impact of different environmental parameters on the equipment life. The environmental correction coefficient obtained by weighted summing the correction values ​​corresponding to each environmental parameter comprehensively considers the coupling effect of multiple environmental factors, making the life prediction model closer to the actual operation situation, improving the prediction accuracy, and providing a more reliable basis for equipment management and maintenance decisions.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the association degree of each device node based on the device topology structure specifically includes: Construct a topological relationship diagram of the device system. The nodes in the topological relationship diagram represent the devices, and the edges represent the connection relationships between the devices. Calculate the degree centrality, betweenness centrality, and closeness centrality of each node; Construct node importance evaluation indicators based on degree centrality, betweenness centrality and closeness centrality; The correlation degree of each device node is calculated according to the node importance evaluation index.

[0011] By adopting the above technical solutions, a topological relationship diagram of the equipment system is constructed, which intuitively shows the connection relationship and system structure between the devices. By calculating the degree centrality, betweenness centrality and closeness centrality of the nodes, the status and role of the equipment in the network are quantified from different perspectives. The node importance evaluation index constructed based on multiple centrality indicators comprehensively reflects the structural importance of the equipment in the system. The device node correlation calculated according to the node importance evaluation index accurately reflects the propagation path and impact range of equipment failures, which helps to identify key equipment and weak links in the system.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after weighted fusion of the output result of the equipment importance evaluation model and the calculation result of the cost loss model to generate the operation and maintenance mode analysis model, the method further includes: Based on the equipment life cycle, the operation phase is divided into the following three phases: running-in phase, stabilization phase and aging phase. Calculate the equipment state transfer matrix in each operation stage. The state transfer matrix represents the transition probability between different states. Identify the dominant failure mode in each operation stage based on the state transition matrix; The operation and maintenance mode analysis model is modified segment by segment based on the dominant failure mode to obtain a modified operation and maintenance mode analysis model.

[0013] By adopting the above technical solution, the operation stage is divided based on the equipment life cycle, and the dividing points of the running-in period, stabilization period and aging period are identified, reflecting the evolution of equipment performance over time. The state transfer matrix in each operation stage is calculated to quantify the probability of equipment transition between different states, reflecting the dynamic change characteristics of the equipment state. The dominant failure mode of each operation stage is identified through the state transfer matrix, revealing the typical failure forms of different stages. The operation and maintenance mode analysis model is segmented and corrected based on the dominant failure mode, so that the model can better adapt to the characteristics of the equipment at different life cycle stages, improve the pertinence and effectiveness of operation and maintenance decisions, and realize the rational allocation of operation and maintenance resources.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, dividing the operation phases based on the device life cycle specifically includes: Obtain historical fault data and operating parameter data of the equipment; Construct the phase space of equipment operation trajectory. The dimensions of the phase space include fault interval time, operation parameter deviation and maintenance response time. Calculate the trajectory attractor in the phase space, the trajectory attractor represents the stable state set of the device operation; The phase demarcation points are identified based on the morphological changes of trajectory attractors, and the operation phases are divided according to the phase demarcation points.

[0015] By adopting the above technical solution, the technical solution of dividing the operation stage by constructing the phase space of the equipment operation trajectory and calculating the trajectory attractor can describe the dynamic evolution law of the equipment operation state from the mathematical essence. The trajectory attractor in the phase space reflects the stable operation mode of the equipment in different stages. By analyzing the morphological changes of the trajectory attractor, the position of the stage boundary point can be accurately identified. Taking the fault interval time, operation parameter deviation and maintenance response time as the phase space dimensions improves the accuracy and reliability of the stage division. It provides a more effective time scale for state transition analysis and failure mode identification, making the entire operation and maintenance mode analysis closer to the actual operation characteristics of the equipment.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the operation and maintenance mode analysis model is segmentedly corrected based on the dominant failure mode to obtain the corrected operation and maintenance mode analysis model, the method further includes: Construct a high-dimensional feature space based on equipment operation data; Calculate the distribution of singular points in high-dimensional feature space, where singular points represent the mutation locations of the system state; Analyze the topological structure of singular points and identify critical paths; Construct mutation warning mechanism based on critical paths.

[0017] By adopting the above technical solution, the technical solution of constructing a mutation warning mechanism by analyzing the distribution characteristics of singular points in a high-dimensional feature space can achieve early warning of potential equipment failures. The high-dimensional feature space contains multi-dimensional information of equipment operation and can more comprehensively characterize the system state. As the location where the system state mutates, the distribution law of singular points reflects the critical state where the equipment may fail. By analyzing the topological structure of these singular points and identifying the critical path, the main laws of the system state evolution can be mastered. The mutation warning mechanism constructed based on the critical path has a strong theoretical basis and can issue a warning signal in time when the system is close to the critical state, reducing the probability of accidental equipment failure.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, analyzing the topological structure of the singularity point and identifying the critical path specifically includes: Construct the homotopy group of singular points, which describes the connectivity between singular points; Based on the homotopy group, the fundamental group is calculated, and the fundamental group represents the topological invariant of the connectivity relationship; Map the fundamental group to an algebraic torus, which preserves the topological invariant properties; Calculate the genus of an algebraic torus, which represents the complexity of the topological structure; The path with the smallest complexity is selected as the critical path according to the genus number.

[0019] By adopting the above technical solution, the optimality of the identified path is guaranteed by constructing the homotopy group of singular points and using algebraic topology theory to identify the critical path. The homotopy group describes the connectivity relationship between singular points, and the fundamental group extracts the topological invariant characteristics in this connectivity relationship. Mapping the fundamental group to the algebraic torus not only maintains the topological invariant characteristics, but also simplifies the computational complexity. The complexity of the topological structure is characterized by calculating the genus number of the algebraic torus, and the path with the minimum complexity is selected as the critical path, which ensures that the selected path has the simplest topological structure and improves the accuracy and interpretability of mutation warning.

[0020] In the second aspect, an embodiment of the present application provides an operation and maintenance mode analysis model generation system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a system, causes the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application provides a method for generating an operation and maintenance mode analysis model. By acquiring equipment operation data and establishing a basic life model of the Weibull distribution, a more accurate life prediction model is obtained by combining the environmental correction coefficient, which can reflect the impact of the actual operating environment on the equipment life. The importance evaluation model constructed based on the equipment topology structure calculates the correlation and considers the impact of equipment failure, which can comprehensively evaluate the importance of the equipment in the system. The cost loss model obtained by calculating the maintenance cost, replacement cost and downtime loss can quantify the economic impact of equipment failure. The operation and maintenance mode analysis model generated by weighted fusion of the importance evaluation model and the cost loss model takes into account the system importance of the equipment, making the operation and maintenance decision more scientific and reasonable, and can achieve optimal cost configuration while ensuring system reliability, thereby improving the scientificity and accuracy of the operation and maintenance mode analysis.

[0024] 2. This application provides a method for generating an operation and maintenance mode analysis model, which divides the operation stages based on the equipment life cycle, identifies the dividing points of the running-in period, stabilization period and aging period, and reflects the evolution of equipment performance over time. The state transfer matrix in each operation stage is calculated to quantify the probability of the equipment's transition between different states, reflecting the dynamic change characteristics of the equipment state. The dominant failure mode of each operation stage is identified through the state transition matrix, revealing the typical failure forms of different stages. The operation and maintenance mode analysis model is segmented and corrected based on the dominant failure mode, so that the model can better adapt to the characteristics of the equipment at different life cycle stages, improve the pertinence and effectiveness of operation and maintenance decisions, and achieve the rational allocation of operation and maintenance resources.

[0025] 3. The present application provides a method for generating an operation and maintenance mode analysis model, which constructs a technical solution for a mutation warning mechanism by analyzing the distribution characteristics of singular points in a high-dimensional feature space, thereby realizing early warning of potential equipment failures. The high-dimensional feature space contains multi-dimensional information about the operation of the equipment and can characterize the system state more comprehensively. As the location where the system state mutates, the distribution pattern of the singular point reflects the critical state where the equipment may fail. By analyzing the topological structure of these singular points and identifying the critical path, the main laws of the system state evolution can be mastered. The mutation warning mechanism constructed based on the critical path has a strong theoretical basis, and can issue a warning signal in time when the system approaches a critical state, thereby reducing the probability of unexpected equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for generating an operation and maintenance mode analysis model in an embodiment of the present application.

[0027] Figure 2 It is a flow chart of a method for improving an operation and maintenance mode analysis model in an embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the physical device structure of an operation and maintenance mode analysis model generation system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0031] The following uses an embodiment and combines Figure 1 , a method for generating an operation and maintenance mode analysis model in an embodiment of the present application is described: See also Figure 1 , which is a flow chart of a method for generating an operation and maintenance mode analysis model in an embodiment of the present application.

[0032] S101, obtaining equipment operation data; The system obtains equipment operation data, which includes equipment failure time data, equipment non-failure working time data, and equipment operation environment parameter data.

[0033] In this step, the system obtains the operation data of the equipment through various data collection methods. These data include equipment failure time data, equipment non-fault working time data, and equipment operation environment parameter data. Equipment failure time data records the specific time point when the equipment fails, which can be used to analyze the failure pattern and life characteristics of the equipment. Equipment non-fault working time data records the operating time of the equipment under normal working conditions, which can be used to evaluate the reliability and stability of the equipment. Equipment operation environment parameter data records various parameters of the environment in which the equipment is located, such as temperature, humidity, vibration, etc. These parameters may affect the operation of the equipment.

[0034] The system can obtain equipment operation data in a variety of ways. One way is to install various sensors and monitoring devices on the equipment to collect the equipment's operating parameters and status information in real time, and transmit the data to the data center for storage and analysis. Another way is to obtain operation data through the equipment's own diagnostic system and log system. Many modern devices have built-in special diagnostic modules and log recording modules that can record the equipment's operating status and fault information in detail. In addition, the system can also obtain equipment operation data through manual inspection and recording. For example, maintenance personnel regularly inspect the equipment and record the equipment's operating status and fault occurrence time.

[0035] S102. Based on the equipment failure time data and non-failure working time data, a basic equipment life model is established using Weibull distribution; In this step, the system uses the equipment failure time data and non-failure working time data to establish the basic life model of the equipment using Weibull distribution. Weibull distribution is a commonly used life distribution model that can well describe the failure law and life characteristics of the equipment. By analyzing the equipment failure time data and non-failure working time data, the system can estimate the parameters of the Weibull distribution, including shape parameters and scale parameters. The shape parameter determines the changing trend of the equipment failure rate, and the scale parameter determines the average life of the equipment. Based on the estimated parameters, the system can establish a basic life model for the equipment to predict the remaining life and failure probability of the equipment.

[0036] In order to establish the Weibull distribution life model, the system needs to process and analyze the equipment's failure time data and non-failure working time data. First, the system needs to screen and clean the data according to the integrity and reliability of the data, and remove incomplete or erroneous data records. Then, the system needs to perform statistical analysis on the data to calculate statistics such as the number of failures, failure intervals, and failure rates of the equipment. Based on these statistics, the system can use methods such as maximum likelihood estimation or least squares estimation to estimate the shape parameters and scale parameters of the Weibull distribution. After obtaining the parameter estimates, the system can establish a Weibull distribution life model for equipment life prediction and reliability analysis.

[0037] In the process of establishing the Weibull distribution life model, some technical problems may be encountered, such as the accuracy of parameter estimation and the applicability of the model. In order to solve these problems, the system can use a variety of estimation methods when performing parameter estimation, such as Bayesian estimation, Bootstrap estimation, etc., to improve the accuracy and robustness of parameter estimation. When selecting a model, the system can select an appropriate life distribution model, such as exponential distribution, lognormal distribution, etc., according to the failure mechanism and data characteristics of the equipment. In addition, the system can also use a hierarchical modeling method for life data to establish a hierarchical life model according to the different operating conditions and environmental conditions of the equipment, thereby improving the applicability and prediction accuracy of the model. Through the optimization of parameter estimation methods and the rationalization of model selection, the system can establish a more accurate and reliable basic life model.

[0038] S103, calculating an environmental correction coefficient according to equipment operating environment parameter data and preset environmental impact factors, and combining the environmental correction coefficient with a basic life model to obtain a corrected life prediction model; The system calculates the environmental correction coefficient based on the equipment operating environment parameter data and the preset environmental impact factors, specifically including: segmenting the equipment operating environment parameter data according to the time series to obtain multiple environmental parameter data segments; calculating the deviation value from the preset standard environmental parameters for each environmental parameter data segment; calculating the correction value corresponding to each environmental parameter based on the deviation value and the preset environmental impact factor; performing weighted summation on the correction value corresponding to each environmental parameter to obtain the environmental correction coefficient; and combining the environmental correction coefficient with the basic life model to obtain a corrected life prediction model.

[0039] In this step, the system considers the impact of the equipment operating environment on the equipment life, and corrects the basic life model by introducing an environmental correction coefficient to obtain a more accurate life prediction model. The equipment operating environment parameter data reflects the various characteristics of the environment in which the equipment is located, such as temperature, humidity, vibration, etc. These environmental factors may accelerate or slow down the aging and failure process of the equipment, thereby affecting the actual life of the equipment. The preset environmental impact factor is a pre-set weight of the impact of various environmental factors on the equipment life based on prior knowledge and historical experience. The system calculates the environmental correction coefficient based on the equipment operating environment parameter data and the preset environmental impact factor to quantify the degree of impact of environmental factors on the equipment life. Combining the environmental correction coefficient with the basic life model can obtain a revised life prediction model, which not only takes into account the reliability characteristics of the equipment itself, but also takes into account the impact of environmental factors, and can more accurately predict the actual life of the equipment.

[0040] When calculating the environmental correction coefficient, the system first segments the equipment operating environment parameter data according to the time series to obtain multiple environmental parameter data segments. Each segment corresponds to a time window, reflecting the average state of the environment in which the equipment is located within the time window. Then, the system calculates the deviation value from the preset standard environmental parameter for each environmental parameter data segment. The larger the deviation value, the greater the difference between the environment in which the equipment is located and the standard environment. Based on the deviation value and the preset environmental impact factor, the system calculates the correction value of each environmental parameter for the equipment life. Finally, the correction value of each environmental parameter is weighted and summed to obtain a comprehensive environmental correction coefficient. If the environmental correction coefficient is greater than 1, it means that the environmental factors have accelerated the aging and failure of the equipment, and if it is less than 1, it means that the aging and failure have been slowed down. By multiplying the environmental correction coefficient with the basic life model, a corrected life prediction model can be obtained.

[0041] In the process of introducing environmental correction coefficients, some technical problems may be encountered, such as the rationality of environmental parameter selection and the accuracy of environmental impact factor settings. In order to solve these problems, the system can use feature selection and dimensionality reduction methods when selecting environmental parameters to screen out the subset of environmental parameters that have the most significant impact on equipment life. When setting environmental impact factors, the system can use a data-driven approach to automatically learn and optimize the impact weights of each environmental parameter from historical data through machine learning algorithms to improve the accuracy of preset environmental impact factors.

[0042] S104, calculating the correlation of each device node based on the device topology structure, and building a device importance evaluation model based on the impact of device failure on system operation and on personnel safety; The system calculates the correlation of each device node based on the device topology structure, specifically including: constructing a topological relationship diagram of the device system, in which nodes represent devices and edges represent connection relationships between devices; calculating the degree centrality, betweenness centrality and closeness centrality of each node; constructing node importance evaluation indicators based on degree centrality, betweenness centrality and closeness centrality; calculating the correlation of each device node based on the node importance evaluation indicators; and constructing an equipment importance evaluation model based on the impact of equipment failures on system operation and on personnel safety.

[0043] In this step, the system constructs an equipment importance evaluation model by analyzing the equipment topology and the impact of failures, which is used to evaluate the importance of each equipment node to the system operation and personnel safety. The equipment topology reflects the connection relationship and dependency relationship between each equipment node in the equipment system. By calculating the correlation of equipment nodes, the importance of each node in the system can be quantitatively evaluated. The higher the correlation of the node, the more critical its role in the system and the greater its impact on the system operation. At the same time, the system also considers the impact of equipment failure on system operation and the impact on personnel safety. Equipment failure may cause system malfunction, performance degradation or even paralysis, affecting the normal operation of the system. The failure of key equipment may also endanger personnel safety. Therefore, the severity of the impact of equipment failure is also an important basis for evaluating the importance of equipment. The system constructs an equipment importance evaluation model by comprehensively considering the correlation of equipment nodes, the impact of failures on system operation and the impact on personnel safety.

[0044] In order to calculate the relevance of device nodes, the system first constructs a topological relationship diagram of the device system. The nodes in the diagram represent devices, and the edges represent the connection relationship between devices. Based on the topological relationship diagram, the system can calculate the centrality indicators of each node, such as degree centrality, betweenness centrality, and closeness centrality. Degree centrality reflects the number of direct connections of a node. The higher the degree centrality, the more important the node is in the local scope. Betweenness centrality reflects the intermediary role of a node in the network. The higher the betweenness centrality, the more important the node is in the global scope. Closeness centrality reflects the distance between a node and other nodes. The higher the closeness centrality, the higher the accessibility of the node in the network. The system constructs node importance evaluation indicators based on these centrality indicators and calculates the comprehensive relevance of each device node through a certain weighted combination method. When quantifying the impact of equipment failure, the system can classify and quantify the severity of equipment failure based on historical data and expert experience, considering the impact on system operation and the threat to personnel safety respectively. The node relevance, fault impact score and safety score are weighted and summed to obtain the comprehensive importance evaluation value of the equipment.

[0045] In the process of building a model for evaluating the importance of equipment, some technical problems may be encountered, such as the problem of dynamic changes in topology and the subjectivity of fault impact assessment. In order to solve the problem of dynamic changes in topology, the system can introduce an incremental calculation method. When the equipment topology changes, only the association of the affected nodes is updated instead of recalculating the association of the entire network to improve the calculation efficiency. In response to the subjective problem of fault impact assessment, the system can use methods such as hierarchical analysis and Delphi method to integrate the opinions of multiple experts and reduce the subjective bias of the evaluation results. In addition, the system can also introduce a dynamic weight adjustment mechanism to dynamically adjust the weights of the fault impact score and the node association according to the real-time information of the equipment operation status and the occurrence of the fault, so that the importance evaluation results can adapt to the dynamic changes of the equipment system.

[0046] S105, calculating equipment maintenance cost, replacement cost and downtime loss according to the prediction results of the revised life prediction model to obtain a cost loss model; In this step, the system uses the revised life prediction model obtained earlier to predict the remaining life of the equipment, and calculates the maintenance cost, replacement cost and loss caused by equipment downtime under different maintenance plans based on the prediction results, and finally obtains a cost loss model that comprehensively considers various cost factors. This model can quantify the economic benefits of different operation and maintenance strategies and provide a basis for the subsequent optimization of the operation and maintenance model.

[0047] The system can use a variety of methods to implement this step. First, the system can use machine learning algorithms (such as neural networks, support vector machines, etc.) based on the historical maintenance data and downtime data of the equipment to establish an equipment maintenance cost model and downtime loss model, and then combine it with the life prediction results to obtain a complete cost loss model. Second, the system can also introduce market price information for equipment maintenance and replacement, combine factors such as the importance and failure rate of the equipment, and estimate the expected cost loss under different scenarios through methods such as Monte Carlo simulation, thereby generating a cost loss model.

[0048] A new technical problem that may arise in this step is how to reasonably weigh the relationship between short-term maintenance costs and long-term replacement costs and downtime losses in the cost loss model. To this end, the system can design a multi-objective optimization model, introduce a discount factor to balance short-term and long-term costs, and consider factors such as the importance of equipment and the impact of failures on production. By solving the optimization model, the optimal cost loss weight distribution scheme is obtained to guide the generation of the cost loss model.

[0049] S106. Perform weighted fusion on the output result of the equipment importance evaluation model and the calculation result of the cost loss model to generate an operation and maintenance mode analysis model.

[0050] The purpose of this step is to comprehensively consider the importance of the equipment and the economic cost-effectiveness, and generate an analysis model to guide equipment operation and maintenance decisions. The system first standardizes the output results of the equipment importance evaluation model and the calculation results of the cost loss model to make them consistent in dimension and within a similar numerical range. Then, the system linearly weights and fuses the two with a certain weight ratio to obtain a comprehensive score for each device or equipment combination. The weight parameters can be adjusted according to the company's maintenance strategy and risk preference to optimize resource allocation by balancing importance and cost-benefit.

[0051] The key to this step is how to design a reasonable weighted fusion mechanism. The system can use commonly used multi-attribute decision-making methods such as the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation to determine the weight coefficients of the two in the decision-making according to the importance of the equipment and the strength of the impact of cost loss. In addition, the system can also introduce the idea of ​​game theory, regard the equipment operation and maintenance decision as a game process of multiple stakeholders, and determine a balanced and robust weight distribution plan by solving Nash equilibrium or minimum and maximum regret value, which takes into account both equipment reliability and maximizes cost-effectiveness.

[0052] One technical problem that may be encountered during the fusion process is how to deal with inconsistent or even contradictory results in importance and cost loss assessment. For example, a device is very important but has a high maintenance cost, or a device is not important but has considerable maintenance benefits. In this regard, the system can introduce nonlinear functions during fusion, giving higher weight coefficients to devices with large differences in importance and cost benefits, highlighting their special status in maintenance decisions; and for those devices with moderate indicators, give them medium weights to avoid their scores being dominated by extreme values.

[0053] In the above embodiment, by obtaining equipment operation data and establishing a basic life model of Weibull distribution, a more accurate life prediction model is obtained by combining the environmental correction coefficient, which can reflect the impact of the actual operating environment on the equipment life. The importance evaluation model constructed based on the equipment topology structure calculates the correlation and considers the impact of equipment failure, which can comprehensively evaluate the importance of the equipment in the system. The cost loss model obtained by calculating the maintenance cost, replacement cost and downtime loss can quantify the economic impact of equipment failure. The operation and maintenance mode analysis model generated by weighted fusion of the importance evaluation model and the cost loss model takes into account the system importance of the equipment, making the operation and maintenance decision more scientific and reasonable, and can achieve optimal cost configuration while ensuring system reliability, thereby improving the scientificity and accuracy of the operation and maintenance mode analysis.

[0054] In the above embodiment, after the operation and maintenance mode analysis model is generated, the equipment often exhibits different performance characteristics and failure patterns at different operation stages. In order to more accurately characterize the dynamic characteristics of the equipment at different life cycle stages and further improve the accuracy of the operation and maintenance mode analysis, the following is combined with Figure 2 , a method for improving an operation and maintenance mode analysis model in an embodiment of the present application is described: See also Figure 2 , which is a flow chart of a method for improving an operation and maintenance mode analysis model in an embodiment of the present application.

[0055] S201, dividing the operation phases based on the equipment life cycle to obtain the demarcation points of the three phases: the running-in phase, the stabilization phase, and the aging phase; The system divides the operation phases based on the equipment life cycle and obtains the demarcation points of the three phases: running-in period, stabilization period and aging period. Specifically: historical fault data and operation parameter data of the equipment are obtained; Construct the phase space of equipment operation trajectory. The dimensions of the phase space include fault interval time, operation parameter deviation and maintenance response time. Calculate the trajectory attractor in the phase space, the trajectory attractor represents the stable state set of the device operation; The phase demarcation points are identified based on the morphological changes of trajectory attractors, and the operation phases are divided according to the phase demarcation points.

[0056] In this step, the system analyzes the operating characteristics of the equipment throughout its life cycle and divides it into three typical stages: running-in period, stabilization period, and aging period. The running-in period refers to a period when the equipment is first put into use, its performance and reliability are not stable, and the failure rate is relatively high; the stabilization period refers to a period when the equipment performance tends to be stable and the failure rate remains at a relatively low level; the aging period refers to a period when the equipment has been running for a long time, the various components begin to age and degrade, and the failure rate gradually increases. By identifying the dividing points of these three stages, the system can more finely characterize the dynamic behavior of the equipment and optimize the operation and maintenance strategy in a targeted manner.

[0057] To achieve this step, the system first obtains the historical fault data and operating parameter data of the equipment, such as vibration, temperature, current, etc. Then, the system can construct a multi-dimensional phase space of the equipment operation trajectory, using key indicators such as fault interval time, operating parameter deviation and maintenance response time as the coordinate axes of the phase space. In this phase space, the operation trajectory of the equipment will form an attractor, reflecting its dynamic characteristics. By analyzing the morphological changes of the attractor, such as the size of the attraction domain and the distribution density, the system can identify the time point when the equipment state changes significantly, and then determine the dividing point of the running-in period, stable period and aging period. When dividing the stage, the system can also use data mining techniques such as cluster analysis and principal component analysis to comprehensively consider the influence of multiple indicators and improve the accuracy of the division.

[0058] A potential technical problem in this step is how to deal with the differences in operating characteristics between different devices. To this end, when constructing the phase space, the system can select appropriate indicator systems and data normalization methods for different types and models of equipment to ensure that the phase space can objectively reflect the actual status of the equipment. In addition, the system can also introduce adaptive thresholds and dynamic update mechanisms to timely adjust the stage division model based on the historical performance and current operating parameters of the equipment, and use incremental learning algorithms to optimize the identification rules of the demarcation points, thereby realizing a continuously evolving and self-improving stage division framework to meet the needs of equipment life cycle management.

[0059] S202, calculating the equipment state transfer matrix in each operation stage; The system calculates the equipment state transfer matrix in each operation stage, and the state transfer matrix represents the transition probability between different states.

[0060] The purpose of this step is to characterize the dynamic reliability characteristics of the equipment by analyzing the state transition rules of the equipment in different operating stages. The system first discretizes the operating state of the equipment, for example, it can be divided into several typical states such as normal, deceleration, shutdown, and maintenance. Then, the system statistically analyzes the transition frequency and transition probability between each state to generate a state transition matrix. Each element in the matrix represents the probability of transitioning from one state to another. Through calculation, the system can grasp the state distribution law and evolution trend of the equipment at different stages, which is of great guiding significance for optimizing operation and maintenance decisions and formulating maintenance plans.

[0061] To achieve this step, the system can use the Markov chain model to describe the device state transition process. Markov chain is a typical random process model, which assumes that the state at the next moment is only related to the current state, but not to the past state. This memoryless feature is consistent with the actual operation of the device. The system can use methods such as maximum likelihood estimation and Bayesian estimation to learn the state transition probability based on the historical state sequence of the device. When estimating parameters, the system can also consider introducing smoothing technology to alleviate the impact of data sparsity. In addition, in order to characterize the temporal dynamics of state transition, the system can also use more complex sequence models such as hidden Markov models (HMM) to capture the internal mechanisms of equipment degradation and failure through hidden states.

[0062] S203, identifying the dominant failure mode of each operation stage according to the state transfer matrix; In this step, the system uses the state transition matrix obtained in the previous step to further analyze the dominant failure mode of the equipment in each operation stage. The dominant failure mode refers to the main reason that leads to the final failure of the equipment. By identifying the dominant failure mode in different stages, the system can formulate operation and maintenance strategies more targetedly, inhibit the occurrence of failure or delay the process of failure, thereby improving the reliability and availability of the equipment.

[0063] The system can use a variety of technologies to implement this step. First, the system can calculate the transition probability from the normal state to the failure state based on the state transition matrix, sort the transfer paths, identify the state transition sequence that is most likely to cause failure, and then infer the dominant failure mode. Second, the system can introduce Markov Chain Monte Carlo (MCMC) simulation technology to simulate the random process of equipment state evolution, statistically analyze the triggering factors and transfer paths of the failure state, and judge the dominant failure mode accordingly. Third, the system can also use reliability modeling methods such as fault tree analysis (FTA) and event tree analysis (ETA), comprehensively consider the quantitative information provided by the state transition matrix and the qualitative knowledge provided by expert experience, infer the propagation mechanism and influencing factors of failure, and thus comprehensively characterize the failure behavior of the equipment.

[0064] When identifying the dominant failure mode, the system may face the challenges of complex failure mechanisms and diverse influencing factors. Some failure modes may be caused by the combination of multiple states, showing certain correlation and timing. To address this problem, the system can use data-driven methods such as association rule mining and temporal pattern recognition to discover frequent patterns and dependencies in the state transition matrix, and combine them with physical mechanism knowledge to construct a multi-state failure mechanism map. In addition, the system can also apply sensitivity analysis technology to calculate the influence weight of state transition probability on failure and identify the weak links that contribute the most to failure. The system can also introduce a competitive failure model to consider the competition and coupling effects between different failure mechanisms to improve the accuracy of failure prediction. By adopting the above strategies, the system can summarize and extract the key failure modes of each stage from massive operation data, and use them to guide subsequent operation and maintenance decision optimization.

[0065] S204, performing segmented correction on the operation and maintenance mode analysis model based on the dominant failure mode to obtain a corrected operation and maintenance mode analysis model.

[0066] The core of this step is to adjust and optimize the operation and maintenance mode analysis model locally for the dominant failure modes at different stages, so that it can more accurately guide stage-by-stage operation and maintenance decisions. Since the failure patterns and influencing factors of equipment at different life cycle stages are different, it is difficult to achieve satisfactory results using a unified analysis model. Through segmented correction, the system can make full use of the unique prior knowledge of each stage to improve the accuracy of local predictions while ensuring the consistency and continuity of the global model.

[0067] To achieve segmented correction, the system first divides the original operation and maintenance mode analysis model into several sub-models, each of which corresponds to an operation stage. Then, the system makes targeted corrections to the corresponding sub-models based on the dominant failure modes identified in each stage. This correction can be reflected in many aspects: first, adjust the structure and parameters of the model so that it can more sensitively capture the characteristics of the dominant failure mode; second, introduce new influencing factors and constraints to embed failure mechanism knowledge into the model; third, optimize the model's objective function and solution algorithm to improve the efficiency and accuracy of local search. During the correction process, the system can also use technologies such as transfer learning and incremental learning to draw on experience and knowledge between different stages to achieve collaborative optimization between sub-models.

[0068] In the above embodiment, the operation stage is divided based on the equipment life cycle, and the dividing points of the running-in period, the stabilization period and the aging period are identified, reflecting the evolution of equipment performance over time. The state transition matrix in each operation stage is calculated to quantify the probability of the equipment transitioning between different states, reflecting the dynamic change characteristics of the equipment state. The dominant failure mode of each operation stage is identified through the state transition matrix, revealing the typical failure forms of different stages. The operation and maintenance mode analysis model is segmented and corrected based on the dominant failure mode, so that the model can better adapt to the characteristics of the equipment at different life cycle stages, improve the pertinence and effectiveness of operation and maintenance decisions, and realize the rational allocation of operation and maintenance resources.

[0069] Furthermore, in another embodiment, after the system performs segmented correction on the operation and maintenance mode analysis model based on the dominant failure mode to obtain the corrected operation and maintenance mode analysis model, it can also construct a high-dimensional feature space based on the equipment operation data; Calculate the distribution of singular points in high-dimensional feature space, where singular points represent the mutation locations of the system state; Analyze the topological structure of singular points and identify key paths. Specifically: construct homology groups of singular points, which describe the connectivity between singular points. Based on the homotopy group, the fundamental group is calculated, and the fundamental group represents the topological invariant of the connectivity relationship; Map the fundamental group to an algebraic torus, which preserves the topological invariant properties; Calculate the genus of an algebraic torus, which represents the complexity of the topological structure; Select the path with the minimum complexity as the critical path according to the genus number; Construct mutation warning mechanism based on critical paths.

[0070] In this embodiment, after obtaining the revised operation and maintenance mode analysis model, the system further mines the deep information contained in the equipment operation data and constructs a high-dimensional feature space to characterize the complex dynamic behavior of the equipment state. In this feature space, the system focuses on the distribution pattern of singular points. Singular points refer to the locations where the system state changes dramatically or suddenly, usually corresponding to key events such as equipment failure and performance degradation.

[0071] To realize the topological analysis of singular points, the system first constructs the homotopy group between singular points. The homotopy group is an algebraic structure that describes connectivity, which characterizes the equivalence relationship between singular points that can be continuously transformed. Through the homotopy group, the system can classify the scattered singular points into several connected branches. Then, the system calculates the fundamental group based on the homotopy group. The fundamental group is an invariant that can reflect the topological relationship between connected branches, which reveals the skeleton structure of the distribution of singular points. In order to facilitate the analysis and comparison of the complexity of different topological structures, the system further maps the fundamental group to the algebraic torus. The algebraic torus is a plane expansion form that maintains topological characteristics. By calculating the genus number of the algebraic torus, the system can quantitatively evaluate the complexity of the topological structure. Finally, the system selects the connected path with the smallest genus number as the critical path, and constructs a mutation warning mechanism based on it. The critical path corresponds to a track that the device state evolution is most likely to pass through. The singular points occurring along this path are most likely to cause system mutations, so they are the focus of the warning.

[0072] In the above embodiment, a technical solution for constructing a mutation warning mechanism by analyzing the distribution characteristics of singular points in a high-dimensional feature space achieves early warning of potential equipment failures. The high-dimensional feature space contains multi-dimensional information about the operation of the equipment and can more comprehensively characterize the system state. As the location where the system state mutates, the distribution law of the singular point reflects the critical state where the equipment may fail. By analyzing the topological structure of these singular points and identifying the critical path, the main laws of the system state evolution can be mastered. The mutation warning mechanism constructed based on the critical path has a strong theoretical basis and can issue a warning signal in time when the system approaches a critical state, thereby reducing the probability of unexpected equipment failures.

[0073] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of an operation and maintenance mode analysis model generation system provided in an embodiment of the present application.

[0074] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0075] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0076] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0077] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0078] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiment; or may exist independently without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiment.

[0081] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 make equivalent replacements for some of the technical features therein. 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 application.

[0082] As used in the above embodiments, the term "when..." may be interpreted as "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted as "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0083] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0084] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for generating an operation and maintenance mode analysis model, characterized in that: include: Acquire equipment operation data, the operation data including equipment failure time data, equipment non-failure working time data and equipment operation environment parameter data; Based on the equipment failure time data and the non-failure working time data, a basic equipment life model is established using Weibull distribution; Calculating an environmental correction coefficient based on the equipment operating environment parameter data and a preset environmental impact factor, and combining the environmental correction coefficient with the basic life model to obtain a corrected life prediction model; The correlation degree of each device node is calculated based on the device topology structure, and the device importance evaluation model is constructed based on the impact of device failure on system operation and personnel safety. Calculating equipment maintenance cost, replacement cost and downtime loss according to the prediction results of the modified life prediction model to obtain a cost loss model; The output result of the equipment importance evaluation model is weightedly integrated with the calculation result of the cost loss model to generate an operation and maintenance mode analysis model.

2. The method according to claim 1, characterized in that The calculating of the environmental correction coefficient according to the equipment operating environment parameter data and the preset environmental impact factor specifically includes: Segmenting the equipment operation environment parameter data according to time series to obtain multiple environment parameter data segments; Calculating a deviation value from a preset standard environmental parameter for each environmental parameter data segment; Calculate the correction value corresponding to each environmental parameter based on the deviation value and the preset environmental impact factor; The correction values ​​corresponding to the environmental parameters are weighted and summed to obtain the environmental correction coefficient.

3. The method according to claim 1, characterized in that The calculation of the association degree of each device node based on the device topology structure specifically includes: Constructing a topological relationship diagram of the device system, wherein nodes in the topological relationship diagram represent devices, and edges represent connection relationships between the devices; Calculating the degree centrality, betweenness centrality and closeness centrality of each of the nodes; Constructing a node importance evaluation index based on the degree centrality, the betweenness centrality, and the closeness centrality; The relevance of each device node is calculated according to the node importance evaluation index.

4. The method according to claim 1, characterized in that After weighted fusion of the output result of the equipment importance evaluation model and the calculation result of the cost loss model to generate an operation and maintenance mode analysis model, the method further includes: Based on the equipment life cycle, the operation phase is divided into the following three phases: running-in phase, stabilization phase and aging phase. Calculating a state transfer matrix of the device in each of the operation stages, wherein the state transfer matrix represents the probability of transition between different states; Identify the dominant failure mode of each of the operation stages according to the state transition matrix; The operation and maintenance mode analysis model is modified in sections based on the dominant failure mode to obtain a modified operation and maintenance mode analysis model.

5. The method according to claim 4, characterized in that The division of operation phases based on the equipment life cycle specifically includes: Obtain historical fault data and operating parameter data of the equipment; Constructing a phase space of equipment operation trajectories, wherein the dimensions of the phase space include fault interval time, operation parameter deviation, and maintenance response time; calculating a trajectory attractor in the phase space, the trajectory attractor representing a set of stable states of operation of the device; The phase demarcation points are identified based on the morphological changes of the trajectory attractor, and the operation phases are divided according to the phase demarcation points.

6. The method according to claim 4, characterized in that After the operation and maintenance mode analysis model is corrected in sections based on the dominant failure mode to obtain a corrected operation and maintenance mode analysis model, the method further includes: Construct a high-dimensional feature space based on equipment operation data; Calculating the distribution of singular points in the high-dimensional feature space, wherein the singular points represent the mutation positions of the system state; Analyzing the topological structure of the singular points and identifying the critical path; A mutation early warning mechanism is constructed based on the key path.

7. The method according to claim 6, characterized in that The analyzing the topological structure of the singular point and identifying the critical path specifically includes: Constructing a homotopy group of singular points, wherein the homotopy group describes a connectivity relationship between the singular points; Calculate a fundamental group based on the homotopy group, where the fundamental group represents a topological invariant of the connectivity relationship; mapping the fundamental group to an algebraic torus, the algebraic torus preserving the topological invariant property; Calculating the genus of the algebraic torus, where the genus represents the complexity of the topological structure; A path with the minimum complexity is selected as a critical path according to the genus number.

8. A system for generating an operation and maintenance mode analysis model, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Images