Power equipment full life cycle management system based on digital twinning technology

Abstract

The invention relates to the technical field of electric power asset management, and discloses an electric power equipment full life cycle management system based on a digital twinning technology, and the system comprises a causal knowledge graph construction unit, a strategy rule learning unit, a decision option value quantification unit, a combined decision optimization unit, and a maintenance decision voucher management unit. The method comprises the following steps: constructing a knowledge graph containing a causal relationship among equipment, environment and management activities; carrying out anti-fact deduction based on the atlas to dynamically learn strategy rules; quantizing the value of the potential maintenance decision by adopting a physical option model; performing combination optimization under resource constraints of budget, spare parts and the like to generate an optimal decision combination; and finally, generating a standardized maintenance decision voucher for the decision in the combination. According to the method, decision-making flexibility and environment uncertainty can be quantified into specific economic values, future-oriented and globally optimal resource allocation is realized, and a decision-making process and a decision-making result are solidified into traceable and manageable digital assets.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power asset management, in particular to a power equipment whole life cycle management system based on digital twin technology. BACKGROUND

[0002] As the core asset of the power grid, the health management and cost control of the whole life cycle of power equipment are crucial to the safe and stable operation of the power system. With the development of digital technology, digital twin, big data analysis and other technologies have been gradually applied to the management of power equipment, aiming to improve the scientific nature of operation and maintenance decisions through data-driven methods.

[0003] However, the existing technology still has some limitations in practice. The analysis of massive operation data in the existing technology mostly stays at the level of state monitoring and correlation analysis, and fails to deeply mine the deep causal relationship between equipment state, external environment and operation and maintenance activities, resulting in insufficient basis for decision-making. Therefore, the development of maintenance strategies often relies on fixed threshold rules or personal experience, and lacks a closed-loop learning mechanism that can dynamically evolve and self-optimize according to actual results.

[0004] In terms of economic evaluation of decision-making, traditional cost-benefit analysis methods are difficult to quantify the value of future uncertainty and management decision flexibility, such as the option value of delayed maintenance and phased investment, which makes the real economic benefits of decision-making underestimated. In addition, the decision-making process is often decentralized and isolated, lacking a mechanism for systematic combination optimization under global resource (such as budget, spare parts, manpower) constraints, making it difficult to maximize overall benefits, and the formation process and value basis of decision-making also lack standardized recording and management means, which is not conducive to the accumulation and reuse of knowledge.

[0005] Therefore, the present application proposes a power equipment whole life cycle management system based on digital twin technology to solve the deficiencies of the prior art. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a power equipment whole life cycle management system based on digital twin technology, which solves the problem that in the management of power equipment, the decision-making process lacks the mining of deep causal logic, the quantification of the value of future uncertainty, and the optimization ability of global resources, resulting in the economic value of maintenance decisions cannot be maximized and the process is not transparent.

[0007] To achieve the above purpose, the present application realizes the following technical scheme: a power equipment whole life cycle management system based on digital twin technology, the system comprises: The causal knowledge graph construction unit is configured to obtain design data, operation data, maintenance data and external environment data of the power equipment to form a full life cycle dataset, and construct a causal knowledge graph containing causal relationships between equipment entities, environmental factors and management activities based on the full life cycle dataset. The strategy rule learning unit is configured to perform counterfactual reasoning on historical maintenance events based on the causal knowledge graph to determine utility gains of alternative decisions, generate new strategy rules, and inject the new strategy rules into the causal knowledge graph for dynamic updating. The decision option value quantification unit is configured to identify potential maintenance decision options based on the dynamically updated causal knowledge graph, and calculate a real option value of each potential maintenance decision option using a real option model. The combined decision optimization unit is configured to receive the potential maintenance decision options and the real option values, and perform combined optimization under preset resource constraints to generate an optimal decision combination that maximizes the total real option value. The maintenance decision voucher management unit is configured to generate a standardized maintenance decision voucher containing task obligations, opportunity values and traceability information for selected maintenance decision options based on the optimal decision combination.

[0008] Preferably, the causal knowledge graph construction unit is specifically configured to: adopt a constraint-based causal discovery algorithm to learn and determine a preliminary causal structure between data variables by performing a series of conditional independence tests on the operation data in the full life cycle dataset; convert verified equipment failure analysis patterns and domain expert knowledge into formalized causal rules, and use the formalized causal rules to verify, correct or complete the preliminary causal structure.

[0009] Preferably, the strategy rule learning unit is specifically configured to: adopt a potential outcomes framework to simulate and calculate actual outcomes caused by actual decisions taken in the historical maintenance events, and counterfactual outcomes that could have occurred if alternative decisions had been taken; determine the utility gains by calculating the difference between the utility of the counterfactual outcomes and the utility of the actual outcomes, and refine and generate new strategy rules based on the utility gains.

[0010] Preferably, the decision option value quantification unit is specifically configured to: model each potential maintenance decision option as a real option; And the predicted avoidable loss present value is taken as the present value of the target asset, the maintenance execution cost is taken as the execution price, the effective decision-making time window, the risk-free interest rate and the quantified uncertainty are combined, and the physical option pricing model is substituted to determine the physical option value. The expected present value of future economic benefits and the quantified uncertainty are calculated according to the dynamically updated causal knowledge graph.

[0011] Preferably, the calculation of the quantified uncertainty is specifically to take the dynamically updated causal knowledge graph as input, and to obtain by comprehensively quantifying at least two uncertainty sources: The uncertainty of the deterioration rate of the equipment health state determined by the physical characteristics and historical operation data of the equipment itself; The uncertainty of the external economic environment determined by the electricity market price and the future load forecast.

[0012] Preferably, the combined decision optimization unit is specifically used for: Constructing multiple potential maintenance decision options into a decision portfolio; Defining the budget, spare parts inventory and professional human resources as resource constraints of the decision portfolio; Solving the optimal decision combination that maximizes the total physical option value of the decision portfolio under the resource constraints by using an integer programming algorithm.

[0013] Preferably, the maintenance decision voucher includes: An obligation module for describing the specific content and technical quality standards of the maintenance task according to the diagnosis results of the causal knowledge graph; An opportunity value module for recording the physical option value associated with the maintenance task calculated by the decision option value quantification unit; A traceability hash module for storing a hash value calculated according to an analysis snapshot used to generate the maintenance decision voucher, to establish an unalterable link between the maintenance decision voucher and the analysis snapshot.

[0014] Preferably, the maintenance decision voucher management unit is further used for: Based on the maintenance decision voucher, a two-layer transaction platform including an internal market layer and an external market layer is constructed and managed; The internal market layer provides a voucher value query and internal resource transfer interface to support resource replacement between different departments within the enterprise based on the value of the maintenance decision voucher; The external market layer provides a voucher listing, bidding and contract generation function to support market procurement of maintenance tasks between pre-authenticated third-party service providers.

[0015] Preferably, the system further comprises: a fault diagnosis unit configured to perform Bayesian reverse probability reasoning along the causal relationship from the monitored abnormal state node in the causal knowledge graph to calculate and output a probability ranking of root cause nodes leading to the abnormal state.

[0016] The application also provides a power equipment life cycle management method based on digital twin technology, which comprises the following steps: S1, obtaining design data, operation data, maintenance data and external environment data of the power equipment to form a life cycle data set, and constructing a causal knowledge graph comprising causal relationships between equipment entities, environmental factors and management activities based on the life cycle data set; S2, based on the causal knowledge graph, determining the utility gain of alternative decisions by counterfactual reasoning on historical maintenance events, generating new strategy rules, and injecting the new strategy rules into the causal knowledge graph for dynamic updating; S3, identifying potential maintenance decision options based on the dynamically updated causal knowledge graph, and calculating the real option value of each potential maintenance decision option using a real option model; S4, receiving the potential maintenance decision options and real option values, and performing combinatorial optimization under preset resource constraints to generate an optimal decision combination that maximizes the total real option value; S5, generating a standardized maintenance decision certificate comprising task obligations, opportunity values and traceability information for the selected maintenance decision options according to the optimal decision combination.

[0017] The application provides a power equipment life cycle management system based on digital twin technology. It has the following advantages: 1. The application constructs a causal knowledge graph that reveals deep causal relationships, and dynamically updates strategy rules using counterfactual reasoning, which goes beyond surface correlation-based state monitoring, enabling more accurate fault tracing and forward-looking decision-making, and improving the depth and accuracy of power equipment life cycle state assessment and decision-making.

[0018] 2. By introducing a real option model to quantify the value of potential maintenance decisions, the application scientifically converts technical and market uncertainties into option values for decision-making, enabling dynamic evaluation of decision-making economic benefits. This provides a scientific basis for selecting the best investment opportunity in an uncertain environment, avoiding economic losses caused by premature or late decision-making.

[0019] 3、The present application can output the optimal decision combination at the system level under the constraints of budget, manpower and other actual resources by constructing all potential maintenance decision options as a decision portfolio and optimizing the solution with the goal of maximizing the total real option value. It realizes the transition from handling isolated events to global resource optimization configuration, and improves the overall use efficiency of limited resources.

[0020] 4、By generating the optimized maintenance decision as a standardized maintenance decision voucher, the present application converts intangible management behavior into tangible, traceable and transferable digital assets. This provides a technical basis for subsequent value discovery and resource transactions of maintenance tasks in internal or external markets, and promotes more efficient allocation of operation and maintenance resources within the whole industry chain. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 The functional module architecture diagram of the power equipment whole life cycle management system based on digital twin technology of the present application; Figure 2 The workflow schematic diagram of the causal knowledge graph construction unit of the present application; Figure 3 The principle schematic diagram of the counterfactual reasoning of the strategy rule learning unit of the present application; Figure 4 The principle schematic diagram of the value calculation of the decision option value quantification unit of the present application; Figure 5 The data structure schematic diagram of the standardized maintenance decision voucher of the present application; Figure 6 The flowchart of the power equipment whole life cycle management method based on digital twin technology of the present application.

[0022] Among them, 10, the causal knowledge graph construction unit; 20, the strategy rule learning unit; 30, the decision option value quantification unit; 40, the combined decision optimization unit; 50, the maintenance decision voucher management unit; 60, the fault diagnosis unit. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the specification of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0024] Referring to the drawings Figure 1 , Figure 1is a functional module architecture diagram of a power equipment life cycle management system based on digital twin technology according to an embodiment of the present application. The system provided by the present application can comprise: a causal knowledge graph construction unit 10, a strategy rule learning unit 20, a decision option value quantification unit 30, a combined decision optimization unit 40 and a maintenance decision voucher management unit 50.

[0025] The causal knowledge graph construction unit 10 is configured to obtain a full life cycle data set of the power equipment, the data set comprising design data, operation data, maintenance data and external environment data, and construct a causal knowledge graph comprising causal relationships between equipment entities, environmental factors and management activities based on the data set.

[0026] The strategy rule learning unit 20 is connected to the data output end of the causal knowledge graph construction unit 10. The strategy rule learning unit 20 receives the causal knowledge graph and performs counterfactual reasoning on historical maintenance events based on the causal knowledge graph to generate new strategy rules. The strategy rule learning unit 20 simultaneously outputs the new strategy rules generated by it to the causal knowledge graph construction unit 10 for dynamic updating of the causal knowledge graph.

[0027] The decision option value quantification unit 30 is connected to the output end of the strategy rule learning unit 20. The decision option value quantification unit 30 receives the dynamically updated causal knowledge graph, identifies potential maintenance decision options based on the dynamically updated causal knowledge graph, and calculates the real option value of each potential maintenance decision option using a real option model.

[0028] The combined decision optimization unit 40 is connected to the output end of the decision option value quantification unit 30. The combined decision optimization unit 40 receives the potential maintenance decision options and the corresponding real option values, and performs combined optimization under preset resource constraints to generate an optimal decision combination.

[0029] The maintenance decision voucher management unit 50 is connected to the output end of the combined decision optimization unit 40. The maintenance decision voucher management unit 50 receives the optimal decision combination and generates standardized maintenance decision vouchers for the selected maintenance decision options in the combination.

[0030] In an optional embodiment, the system can further comprise a fault diagnosis unit 60 connected to the output end of the causal knowledge graph construction unit 10, configured to perform reverse probability reasoning in the causal knowledge graph to calculate and output a probability ranking of root cause nodes.

[0031] Referring to the accompanying drawings Figure 6 , Figure 6 is a flowchart of a power equipment life cycle management method based on digital twin technology according to an embodiment of the present application. The method is applied to the system described above and comprises the following steps: Step S1, obtain the full life cycle dataset of the power equipment, and construct a causal knowledge graph based on the dataset. This step is performed by the causal knowledge graph construction unit 10.

[0032] Step S2, based on the causal knowledge graph generated in step S1, the historical maintenance events are counterfactual deduced, new strategy rules are generated, and the rules are injected into the causal knowledge graph for dynamic updating. This step is performed by the strategy rule learning unit 20.

[0033] Step S3, based on the dynamically updated causal knowledge graph in step S2, identify potential maintenance decision options, and calculate the real option value of each potential maintenance decision option. This step is performed by the decision option value quantification unit 30.

[0034] Step S4, receive the potential maintenance decision options and their real option values generated in step S3, and perform combinatorial optimization under the preset resource constraints to generate the optimal decision combination. This step is performed by the combinatorial decision optimization unit 40.

[0035] Step S5, according to the optimal decision combination generated in step S4, generate standardized maintenance decision credentials for the selected maintenance decision options. This step is performed by the maintenance decision credential management unit 50.

[0036] The internal implementation of each core unit in the system will be described in detail below.

[0037] Referring to the accompanying drawings Figure 2 , Figure 2 is a workflow schematic diagram of the causal knowledge graph construction unit 10 according to an embodiment of the present application. The causal knowledge graph construction unit 10 is used to provide a knowledge base containing deep causal logic for subsequent analysis, learning and decision making. The first operation performed by the unit 10 is to obtain and integrate the full life cycle dataset. The dataset includes but is not limited to: design data of power equipment, such as material specifications, rated voltage, insulation level and design drawings; operation data, such as current, voltage, temperature, vibration, oil dissolved gas, partial discharge signal and other time series monitoring data; maintenance data, such as historical repair records, component replacement dates, inspection reports and other event data; and external environmental data, such as environmental temperature, humidity, altitude and air pressure of the equipment operating site.

[0038] After obtaining the full life cycle dataset, the causal knowledge graph construction unit 10 constructs the graph by combining data-driven and knowledge-driven methods.

[0039] In the data-driven path, the causal knowledge graph construction unit 10 adopts a constraint-based causal discovery algorithm. The core of this type of algorithm is to perform a series of conditional independence tests on the operating data in the full life cycle data set. The conditional independence test is used to determine whether there is a direct statistical dependency relationship between two variables given one or more other variables. For example, the test variable and variables In a given set of variables Independence under the condition of can be expressed as judging whether the following equation is true: ; Where, represents probability; Indicates in variables and variable collections Simultaneous variable Conditional probability of occurrence; Indicates in the variable set Occurrence variable The conditional probability of occurrence. If the equation is established, the variable and In a given By systematically performing such tests on each variable pair in the full life cycle dataset, the causal knowledge graph construction unit 10 can learn and determine the causal structure between data variables and form a preliminary causal relationship network.

[0040] In a specific embodiment, the constraint-based causal discovery algorithm can adopt the PC algorithm (Peter-Clark-Algorithm). The execution process of the algorithm is as follows: First, construct an undirected complete graph containing all data variables as nodes, that is, assume that there is an edge between any two variables. Second, perform a zero-order conditional independence test, that is, for any two variables in the graph, , perform an unconditional independence test, if , then remove the edges between them. Then, iteratively perform higher-order conditional independence tests. For example, in the first-order test, for the variable pairs that are still connected by edges, , traverse all its adjacent nodes , to For the conditional independence test, if it is found that Under the conditions and If the conditional independence holds, the edges between them are removed. This iteration process continues until all conditional independence tests of all orders are completed. Finally, the causal directions on the remaining edges are determined using known causal rules (e.g. temporal precedence) and V-structure (Collider) identification rules, and the preliminary causal relationship network is output. For the conditional independence test in the test process, when dealing with discrete data, G-test or Chi-square test can be used; when dealing with continuous data, a test method based on partial correlation can be used.

[0041] In the knowledge-driven path, the causal knowledge graph construction unit 10 formalizes the verified expert knowledge and equipment failure analysis patterns in the field. These knowledge comes from equipment operation manuals, failure mode and effects analysis (FMEA) reports, and the diagnosis experience of senior operation and maintenance engineers. The formalization process converts unstructured natural language descriptions, such as "damp insulation causes the dielectric loss tangent value to increase", into structured causal rules. This conversion process can be represented in the form of triples (damp insulation, causes, dielectric loss tangent value increases) or IF-THEN rules.

[0042] Finally, the causal knowledge graph construction unit 10 fuses the preliminary causal structure generated by the data-driven path with the formalized causal rules generated by the knowledge-driven path. In this process, the formalized causal rules are injected as prior knowledge to verify, correct or complete the causal relationships learned by data-driven learning, thereby constructing the final causal knowledge graph containing the causal relationships between equipment entities, environmental factors and management activities. The knowledge graph is stored in the form of a graph structure, where nodes represent equipment entities, state variables or events, and edges represent the causal relationships between them.

[0043] Referring to the accompanying drawings Figure 3 , Figure 3 is a schematic diagram of the principle of counterfactual reasoning of the strategy rule learning unit 20 according to an embodiment of the present application. The strategy rule learning unit 20 is used to enable the system to evolve and optimize the decision logic by analyzing historical events in depth. The input of the unit 20 is the causal knowledge graph constructed and dynamically maintained by the causal knowledge graph construction unit 10.

[0044] The working process of the strategy rule learning unit 20 adopts the potential outcome framework. First, the unit 20 selects an already completed maintenance event from the historical maintenance data for analysis. The historical event contains the actual decision taken under a specific equipment state and environmental condition, and the actual result caused by the decision.

[0045] Subsequently, the policy rule learning unit 20 performs counterfactual reasoning based on the causal knowledge graph. Specifically, while maintaining all preconditions in the historical event, except for the decision variables, the policy rule learning unit 20 replaces the actual decision with one or more alternative decisions. Leveraging the causal relationships defined in the causal knowledge graph, the system simulates and calculates how the equipment status and related economic indicators would evolve if these alternative decisions were taken, thereby generating a series of possible counterfactual outcomes. The essence of this reasoning process is to perform intervention calculations on the established causal model to predict the consequences of different decision-making behaviors.

[0046] After obtaining the actual outcome and the counterfactual outcome, the policy rule learning unit 20 needs to quantitatively compare the pros and cons of the two outcomes. This comparison is achieved by calculating the counterfactual utility gain. First, a utility function is defined. This function is used to map a specific event outcome to a scalar value to represent the overall benefit of the outcome. Based on this utility function, the following counterfactual utility gain calculation model can be used: ; Where: is the counterfactual utility gain, which represents the change in benefits that can be brought about by taking the alternative decision relative to the actual decision; is a utility function that combines various indicators of an event outcome into a single utility value. In a specific embodiment, the function can be defined as a weighted sum of multiple key performance indicators, and its specific form is: ; in, Represents a specific event result; For the results The corresponding total maintenance cost; For the results The corresponding device availability time; For the results The remaining life of the corresponding equipment; , , They are the preset weight coefficients for total maintenance cost, equipment availability and equipment remaining life.

[0047] The counterfactual result is the comprehensive result of simulating alternative decisions in historical events; It is the actual result, which is the comprehensive result of what actually occurred and was recorded in historical events.

[0048] When the calculated counterfactual utility gain When the difference is greater than a pre-set threshold, it indicates that the analyzed alternative decision has a higher application value in similar scenarios. Based on this judgment, the policy rule learning unit 20 abstracts and generates a new policy rule. The form of the rule can be: IF [specific device state and environmental conditions] THEN [execute the alternative decision]. Finally, the new policy rule is injected back into the causal knowledge graph construction unit 10 for updating or enhancing the relationship between the management activities and the results in the causal knowledge graph.

[0049] Referring to the drawings Figure 4 , Figure 4 is a schematic diagram of the principle of value calculation by the decision option value quantification unit 30 according to an embodiment of the present application. The function of the decision option value quantification unit 30 is to quantify the flexibility and uncertainty in management decisions, thereby providing an economic value scale for decisions beyond traditional cost-benefit analysis.

[0050] The decision option value quantification unit 30 first identifies potential maintenance decision options based on the dynamically updated causal knowledge graph. This identification process is achieved by querying nodes representing the health status of the equipment in the causal knowledge graph and filtering out those nodes that have shown a deterioration trend but have not yet reached a pre-set intervention threshold. For each filtered state node, the system matches one or more maintenance activities that can prevent or delay its deterioration path. The combination of each potential problem to be solved and the corresponding maintenance activity constitutes a potential maintenance decision option.

[0051] After identifying potential maintenance decision options, the decision option value quantification unit 30 models each option as a real option, specifically as an European call option. The logical basis of this modeling is that holding a maintenance decision option is equivalent to having the right, but not the obligation, to obtain an asset (avoid future greater losses due to equipment failure) at a certain cost (the cost of executing maintenance) within a certain time window in the future.

[0052] In order to calculate the value of this real option, several core input parameters of the model need to be determined. The calculation of these parameters is based on the dynamically updated causal knowledge graph as data and logical basis.

[0053] First, by performing forward reasoning on the causal knowledge graph, the expected present value of the possible failure modes, failure probabilities and economic losses (including repair costs, downtime losses, penalties, etc.) that may occur in the future of the equipment without executing the maintenance decision option is simulated, and this expected present value is defined as the underlying asset present value of the real option model .

[0054] Secondly, the direct cost required to execute the maintenance decision option, including labor, spare parts and planned downtime cost, is defined as the strike price of the real option model .

[0055] Thirdly, the time span between the current time and the critical point when action must be taken, which is defined as the expiration time of the option, is determined according to the deterioration rate of the equipment health state predicted by the causal knowledge graph .

[0056] Meanwhile, an external input risk-free interest rate is introduced to represent the time value of capital .

[0057] Finally, the most critical parameter, the volatility of the underlying asset value , is quantified. This volatility quantifies the uncertainty faced by the decision, and its calculation combines at least two sources: First, the uncertainty of the deterioration rate of the equipment health state, which is derived by analyzing historical operation data and the physical model of the equipment; Second, the uncertainty of the future economic environment, which is derived by analyzing external environmental data (such as electricity market prices, load forecasts, etc.).

[0058] After all the above parameters are determined, the decision option value quantification unit 30 uses the following real option value calculation model to calculate the real option value of each potential maintenance decision option: ; Where: ; ; In the formula: is the real option value of the potential maintenance decision option; is the present value of the underlying asset, which is the expected present value of the avoidable future loss predicted; is the execution price, which is the cost of executing the maintenance decision; is the expiration time, which is the effective time window for executing the decision; is the risk-free interest rate; is the volatility of the underlying asset value, which quantifies the uncertainty of the decision environment; is the cumulative distribution function of the standard normal distribution; is the natural logarithm function; and are intermediate variables in the model calculation process.

[0059] By the above steps, the decision option value quantification unit 30 assigns a quantified economic value to each potential maintenance decision option, taking into account the future uncertainty , and outputs these options together with their values to the portfolio decision optimization unit 40.

[0060] The portfolio decision optimization unit 40 is responsible for systematically integrating the multiple independent potential maintenance decision options and their corresponding real option values output by the decision option value quantification unit 30, to achieve the maximum overall value under the limited resource condition. This unit 40 receives the set of potential maintenance decision options, as well as the real option value and execution cost of each option.

[0061] First, the portfolio decision optimization unit 40 constructs all the received potential maintenance decision options into a decision portfolio. In this model, each potential maintenance decision option is treated as an investment project. A binary decision variable is introduced for each project, to indicate whether the project is selected for execution.

[0062] Next, the portfolio decision optimization unit 40 defines the resources required to execute the decisions in the portfolio, and formalizes them as a series of resource constraints. These constraints reflect the limitations faced in actual operations. In a specific embodiment, the defined resource constraints include: budget constraint, i.e., the total cost of all selected decisions cannot exceed the pre-set total budget; spare parts constraint, i.e., the total amount of each specific type of spare part consumed by all selected decisions cannot exceed the current inventory of that type of spare part; human resource constraint, i.e., the total working hours of each specific skill required by all selected decisions cannot exceed the available total working hours of that skill.

[0063] After completing the portfolio modeling and constraint definition, the portfolio decision optimization unit 40 constructs and solves a portfolio decision optimization objective function. The goal of this optimization is to maximize the total real option value of the selected decision portfolio, subject to all defined resource constraints. This portfolio optimization problem can be formalized as the following mathematical model: Objective function: ; Constraints: : ; ; ; ; wherein: is a binary decision variable, when the th potential maintenance decision option is selected, otherwise ; is the real option value of the th potential maintenance decision option, which is calculated by the decision option value quantification unit 30; is the total number of potential maintenance decision options; is the cost of implementing the th potential maintenance decision option; is the preset total budget upper limit; is the number of the th type of spare parts consumed for implementing the th decision option; is the total available inventory of the th type of spare parts; is the total number of spare part types; is the number of man-hours of the th skill type consumed for implementing the th decision option; is the total available man-hours of the th skill type; is the total number of skill types of manpower.

[0064] The combined decision optimization unit 40 solves the above model using an integer programming solver or other algorithms to obtain a set of optimal values of the decision variables . The corresponding set of potential maintenance decision options of all constitutes the final optimal decision combination with the maximum value under the current resource conditions. The optimal decision combination is then output to the maintenance decision voucher management unit 50.

[0065] In a specific embodiment, the solver used to solve the integer programming problem can use a Branch-and-Bound based algorithm. This method finds the global optimal solution by systematically decomposing the original problem into a series of sub-problems and using the boundaries of the solutions of the sub-problems to prune the search space that does not contain the optimal solution. In engineering implementation, a commercial optimization solver (such as Gurobi, CPLEX) or an open source optimization solver (such as SCIP, GLPK) can be called to perform the solving process.

[0066] Referring to the accompanying Figure 5 , Figure 5is a data structure diagram of a standardized maintenance decision credential according to an embodiment of the present application. The maintenance decision credential management unit 50 functions to transform the abstract, optimized decision results into a specific, standardized data credential for subsequent management, execution and circulation.

[0067] The maintenance decision credential management unit 50 receives the optimal decision combination output by the combined decision optimization unit 40. For each selected maintenance decision option (i.e. decision variable in the combination, the maintenance decision credential management unit 50 generates a standardized maintenance decision credential for it. The credential is a structured data object, the data structure of which is shown in the following figure: Figure 5 The obligation module is used to clearly define the maintenance task to be performed. The data fields it contains include: task unique identifier, target device code, specific maintenance task content description generated according to the causal knowledge graph diagnosis result, and technical quality standards and acceptance procedures to be followed for the execution of the task.

[0068] The opportunity value module is used to record the economic value information associated with the maintenance task. The data fields it contains include: the real option value associated with this maintenance decision calculated by the decision option value quantification unit 30 , and the core parameters used to calculate the value, such as the underlying asset present value , execution price , expiration time and volatility .

[0069] The traceability hash module is used to ensure the traceability and non-tamperability of the decision-making process. When the credential is generated, the system will record the analysis snapshot of the causal knowledge graph used to generate the decision, which contains all the relevant node states, causal relationships and parameters at that time. Subsequently, the system uses a preset hash algorithm (e.g. SHA-256) to operate on the complete data of the analysis snapshot, generating a unique hash value. The hash value is stored in the traceability hash module, providing an unalterable verification path pointing to the original analysis basis.

[0070] ​In an optional embodiment, to further enhance the non-tamperability, transparency and transferability of the credential, the standardized maintenance decision credential can be minted as a Non-Fungible Token (NFT) and recorded on a blockchain (e.g. consortium chain or private chain). At this time, the data structure of the credential is stored as the metadata of the NFT, while the hash value in the provenance hash module can point to the detailed analysis snapshot stored in a distributed file system (such as IPFS), thereby realizing the on-chain management of the credential asset.

[0071] In an optional embodiment, the function of the maintenance decision credential management unit 50 can be further extended to build and manage a two-layer transaction platform. The platform takes the generated maintenance decision credentials as the transaction object.

[0072] The internal market layer of the platform is for different departments within the enterprise. In this layer, each department can view the generated maintenance decision credentials and their opportunity value. A department can perform resource substitution with another department through internal processes based on the value of the credential, for example, using a high-value maintenance decision credential to apply for additional budget or transferring task execution rights to a department that has more corresponding resources.

[0073] The external market layer of the platform is for pre-authorized third-party service providers outside the enterprise. The enterprise can list specific maintenance decision credentials on this layer. Third-party service providers can bid for the execution contract of the task according to the task content defined in the obligation module and the economic importance shown in the opportunity value module of the credential. This process realizes the market procurement of maintenance services using standardized credentials.

[0074] In an optional embodiment, referring to the attached Figure 1 The system of the present application can also include a fault diagnosis unit 60. The input end of the fault diagnosis unit 60 is connected to the output end of the causal knowledge graph construction unit 10. The function of this unit is to reason according to the causal knowledge graph when an abnormal state of the equipment is monitored, to calculate and output the probability ranking of the root cause of the abnormality.

[0075] When the monitored abnormal state node is taken as input, the fault diagnosis unit 60 first traces back along the defined causal relationship in the causal knowledge graph from the abnormal state node to determine the set of all potential root cause nodes that can cause this abnormality.

[0076] For each potential root cause node in the set, the fault diagnosis unit 60 employs a Bayesian inference method to calculate its posterior probability as the true cause. This process utilizes the prior knowledge and conditional probability information stored in the causal knowledge graph. Specifically, the posterior probability of a certain potential root cause node as the true cause can be calculated using the following Bayesian inference model: ; In the formula: is the posterior probability, representing the probability of the i-th potential root cause being the true cause given that the abnormal state has been observed; is the abnormal state node that has been monitored, such as the excessive concentration of dissolved gas acetylene in oil; is the i-th potential root cause node, such as local overheating or high-energy discharge; is the conditional probability or likelihood, representing the probability of observing the abnormal state if the root cause occurs. This value is determined based on the causal relationship strength along the path from to in the causal knowledge graph; is the prior probability, representing the probability of the root cause occurring on its own without any observation information. This value can be set based on historical fault statistics of the equipment or expert experience and stored in the knowledge graph; is the marginal probability of the evidence, which is the total probability of observing the abnormal state as a normalization factor. It is calculated by summing the probability of each cause causing the abnormality for all i potential root causes; is the total number of potential root cause nodes determined in this diagnosis. The fault diagnosis unit 60 repeats the above calculation for each candidate root cause node, thereby obtaining the posterior probability value of each candidate cause. Finally, the fault diagnosis unit 60 ranks all candidate root cause nodes in descending order according to their calculated posterior probability values and outputs the probability ranking list. This list provides a data-supported diagnostic direction for the root cause of the fault for subsequent maintenance decisions. In summary, the embodiments of the present application provide a power equipment life cycle management system and method based on digital twin technology. Through the collaborative work of each unit, the full-process transformation and closed-loop management from multi-source heterogeneous data to standardized value certificates are realized.

[0077] In summary, the embodiments of the present application provide a power equipment life cycle management system and method based on digital twin technology. Through the collaborative work of each unit, the full-process transformation and closed-loop management from multi-source heterogeneous data to standardized value certificates are realized.

[0078] In summary, the embodiments of the present application provide a power equipment life cycle management system and method based on digital twin technology. Through the collaborative work of each unit, the full-process transformation and closed-loop management from multi-source heterogeneous data to standardized value certificates are realized.

[0079] ​​The operation of the system starts from the causal knowledge graph construction unit 10, which integrates the design, operation, maintenance and external environment data of the equipment, and constructs a knowledge graph describing the internal causal logic between equipment entities, environmental factors and management activities through the combination of data-driven causal discovery and knowledge-driven rule injection. This graph provides the basis for all subsequent advanced analysis.

[0080] On this basis, the strategy rule learning unit 20 takes historical maintenance events as samples, uses the latent outcome framework and counterfactual reasoning to quantitatively evaluate the utility gain of alternative decisions relative to actual decisions, thereby refining new and better strategy rules and feeding them back to the causal knowledge graph, enabling the system's decision logic to evolve and continuously optimize itself.

[0081] Subsequently, the decision option value quantification unit 30 uses the dynamically updated causal knowledge graph to identify potential maintenance decision options in the future, and by introducing a real option value calculation model, quantifies the future uncertainty (such as equipment health deterioration rate, market price fluctuations) contained in each decision option as the option value of the decision. This process upgrades traditional cost analysis to dynamic value assessment for the future.

[0082] Next, the combined decision optimization unit 40 constructs all the value-quantified potential decision options into a decision portfolio, and takes budget, spare parts, manpower, etc. as resource constraints, and by solving the combined decision optimization objective function, outputs an optimal decision combination that maximizes the total real option value, realizing the transition from single decision to global resource optimal allocation.

[0083] Finally, the maintenance decision voucher management unit 50 solidifies each selected item in the optimal decision combination into a standardized maintenance decision voucher. The voucher, through its obligation module, opportunity value module and traceability hash module, converts an abstract decision into a specific, value-measurable and process-traceable digital asset, providing a solid technical carrier for subsequent fine management, task allocation and even market transactions.

[0084] Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A power equipment life cycle management system based on digital twin technology, characterized in that, The system comprises: a causal knowledge graph construction unit, configured to acquire design data, operation data, maintenance data and external environment data of power equipment to form a full life cycle dataset, and construct a causal knowledge graph containing causal relationships between equipment entities, environmental factors and management activities based on the full life cycle dataset; a strategy rule learning unit, configured to perform counterfactual reasoning on historical maintenance events based on the causal knowledge graph to determine utility gains of alternative decisions, generate new strategy rules, and inject the new strategy rules into the causal knowledge graph for dynamic updating; a decision option value quantification unit, configured to identify potential maintenance decision options based on the dynamically updated causal knowledge graph, and calculate a real option value of each potential maintenance decision option by using a real option model; a combined decision optimization unit, configured to receive the potential maintenance decision options and the real option values, and perform combined optimization under preset resource constraints to generate an optimal decision combination that maximizes the total real option value; a maintenance decision voucher management unit, configured to generate a standardized maintenance decision voucher containing task obligations, opportunity values and traceability information for the selected maintenance decision options according to the optimal decision combination. 2.The power equipment life cycle management system based on digital twin technology according to claim 1, characterized in that, The causal knowledge graph construction unit is specifically configured to: use a constraint-based causal discovery algorithm to learn and determine a preliminary causal structure between data variables by performing a series of conditional independence tests on the operation data in the full life cycle dataset; convert verified equipment failure analysis patterns and domain expert knowledge into formalized causal rules, and use the formalized causal rules to verify, correct or complete the preliminary causal structure. 3.The power equipment life cycle management system based on digital twin technology according to claim 1, characterized in that, The strategy rule learning unit is specifically configured to: use a potential outcomes framework to simulate and calculate actual outcomes caused by actually taken decisions in the historical maintenance events, and counterfactual outcomes that may occur if alternative decisions are taken, respectively; determine the utility gains by calculating the difference between the utility of the counterfactual outcomes and the utility of the actual outcomes, and refine and generate new strategy rules based on the utility gains. 4.The power equipment life cycle management system based on digital twin technology of claim 1, wherein, The decision option value quantification unit is specifically configured to: model each potential maintenance decision option as a real option; determine the real option value by substituting a predicted avoidable loss present value as an underlying asset present value, a maintenance execution cost as an execution price, and an effective decision time window, a risk-free rate and quantified uncertainty into a preset real option pricing model; wherein the expected present value of future economic benefits and the quantified uncertainty are both calculated based on the dynamically updated causal knowledge graph.

5. The power equipment life cycle management system based on digital twin technology according to claim 4, characterized in that, The quantified uncertainty is specifically calculated by taking the dynamically updated causal knowledge graph as input, and quantifying at least two sources of uncertainty, including: uncertainty in the deterioration rate of the equipment health state determined by the physical characteristics of the equipment and historical operation data; uncertainty in the external economic environment determined by power market prices and future load forecasts. 6.The power equipment life cycle management system based on digital twin technology according to claim 1, wherein, The combined decision optimization unit is specifically configured to: construct multiple potential maintenance decision options into a decision portfolio; budget, spare parts inventory and professional human resources are defined as resource constraints of the decision portfolio; an integer programming algorithm is used to solve the optimal decision combination which maximizes the total real option value of the decision portfolio under the resource constraints. 7.The power equipment life cycle management system based on digital twin technology according to claim 1, characterized in that, The maintenance decision voucher includes: an obligation module for describing the specific content and technical quality standards of the maintenance task according to the diagnosis result of the causal knowledge graph; an opportunity value module for recording the real option value associated with the maintenance task calculated by the decision option value quantification unit; a traceability hash module for storing a hash value calculated according to the analysis snapshot used to generate the maintenance decision voucher, to establish an unalterable link between the maintenance decision voucher and the analysis snapshot. 8.The power equipment life cycle management system based on digital twin technology of claim 1, wherein, The maintenance decision voucher management unit is also used to: based on the maintenance decision voucher, build and manage a two-layer trading platform including an internal market layer and an external market layer; The internal market layer provides a voucher value query and internal resource transfer interface to support resource replacement between different departments within the enterprise based on the value of the maintenance decision voucher; The external market layer provides voucher listing, bidding and contract generation functions to support market procurement of maintenance tasks between pre-authenticated third-party service providers. 9.The power equipment life cycle management system based on digital twin technology of claim 1, wherein, The system further includes: a fault diagnosis unit for performing Bayesian reverse probability reasoning along the causal relationship in the causal knowledge graph from the monitored abnormal state node to calculate and output the probability ranking of the root cause node causing the abnormal state.

10. The power equipment life cycle management method based on digital twin technology, applied to the system of any one of claims 1-9, characterized in that, The method includes the following steps: S1, obtaining design data, operation data, maintenance data and external environment data of the power equipment to form a full life cycle data set, and building a causal knowledge graph containing the causal relationship between equipment entities, environmental factors and management activities based on the full life cycle data set; S2, based on the causal knowledge graph, determine the utility gain of the alternative decision by counterfactual reasoning on the historical maintenance event, generate new strategy rules, and inject the new strategy rules into the causal knowledge graph for dynamic updating; S3, based on the dynamically updated causal knowledge graph, identify potential maintenance decision options, and calculate the real option value of each potential maintenance decision option using a real option model; S4, receive the potential maintenance decision options and real option values, and perform combination optimization under the preset resource constraints to generate an optimal decision combination that maximizes the total real option value; S5, according to the optimal decision combination, generate a standardized maintenance decision voucher including task obligations, opportunity values and traceability information for the selected maintenance decision options.

Images