Power plant electrical secondary aid decision collaborative method and system

Abstract

The invention discloses a power plant electrical secondary aid decision collaborative method and system, and the method comprises the steps: collecting a power plant measurement data sample set to calculate an equipment index, and synthesizing an equipment health index through an entropy weight fusion evaluation algorithm; establishing a multi-objective optimization model based on the power plant electrical knowledge base, solving a Pareto optimal solution of the multi-objective optimization model, and converting the equipment health index into an execution operation sequence; establishing an execution operation sequence exception handling mechanism, if the execution operation fails, recording failure operation and reasons and triggering collaborative retry, and if the retry fails, switching a standby execution operation sequence and recording an execution log; and constructing a feature vector based on the health index, the execution operation sequence and the execution log, and generating incremental power plant electrical knowledge base update based on similarity matching. According to the invention, the problems of low monitoring and decision-making efficiency, low accuracy, poor fault tolerance and the like of the existing power plant electrical secondary system are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system automation, and in particular relates to a method and system for coordinating electrical secondary auxiliary decision-making in a power plant. Background Art

[0002] As power plant electrical systems continue to grow in complexity, equipment operation and maintenance face increasing challenges. Existing secondary decision-making support systems, which mostly rely on manual judgment and simple rule engines, struggle to achieve efficient and accurate decision-making in complex environments. This often leads to delays, inefficiencies, and unsafe conditions in electrical equipment maintenance, troubleshooting, and operational optimization.

[0003] The Chinese patent publication number CN119722043A discloses a method, device, medium and equipment for equipment maintenance decision-making in thermal power plants, which can improve decision-making quality and work efficiency. The method includes: obtaining a multi-source data set of a target device in a thermal power plant, the multi-source data set including component data, historical maintenance data and real-time data of equipment sensors of the target device; constructing a target device knowledge graph based on the multi-source data set; in response to a user input instruction for the target device, determining the user intention information corresponding to the input instruction, and obtaining a target Mermaid graph based on the user intention information and the target device knowledge graph; and determining the maintenance strategy of the target device based on the target Mermaid graph. This invention relies too much on static knowledge graph construction and user instruction drive, lacks dynamic quantitative evaluation, and lacks a closed-loop evolution mechanism, and cannot adapt to fluctuating operating conditions of the electrical system. Summary of the Invention

[0004] The purpose of the present invention is to provide a collaborative method and system for auxiliary decision-making of electrical secondary systems in power plants, which solves the problems of low efficiency, low accuracy and poor fault tolerance in monitoring and decision-making of electrical secondary systems in existing power plants through accurate equipment health assessment, multi-objective optimization decision-making, exception handling mechanism and adaptive knowledge base update.

[0005] The technical solutions of the present invention are as follows: In one aspect, the present invention provides a collaborative method for secondary auxiliary decision-making of a power plant, comprising the following steps: Collect power plant measurement data sample sets to calculate equipment indicators including health deviation, fixed value maladaptation and state penalty items, and synthesize the equipment health index through entropy weight fusion evaluation algorithm; Based on the power plant electrical knowledge base, a multi-objective optimization model is established with the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence. Establish an exception handling mechanism for the execution operation sequence. If an execution operation fails, record the failed operation and reason and trigger a collaborative retry. If the retry fails, switch to the backup execution operation sequence in the Pareto frontier solution set and record the execution log. A feature vector is constructed based on the health index, execution operation sequence and execution log, and an incremental power plant electrical knowledge base update is generated based on similarity matching.

[0006] Preferably, a sample set of power plant measurement data is collected to calculate equipment indicators including health deviation, fixed value inadaptability and state penalty items, and the equipment health index is synthesized by an entropy weight fusion evaluation algorithm, specifically: Collect power plant measurement data including electrical quantities and calculate the health deviation of electrical quantities:

[0007] Where, is the healthy deviation of electrical quantity data, ,in, is the measured current, is the measured voltage; is the measured value of the electrical quantity; is the rated value of the electrical quantity; Calculate the fixed value maladjustment:

[0008] Where, is the fixed value maladaptability; is the current constant; is the theoretical optimal value of current; The state penalty item is calculated by dividing the number of device switch abnormalities in the collection times by the total collection times.

[0009] Preferably, the information entropy of the healthy deviation of the electrical quantity, the fixed value inadaptability, and the state penalty term in the collected power plant measurement data samples is calculated, and the weight of each equipment indicator is calculated based on the information entropy:

[0010] Where, For the Weights of device-type indicators; For the Information entropy of device-like indicators; For the Information entropy of device-like indicators; The device health index is synthesized based on the calculated device indicator weights:

[0011] Where, is the equipment health index; is the weight of the current health deviation index; is the healthy deviation of the current; is the weight of the voltage health deviation index; is the healthy deviation of voltage; is the weight of the fixed-value unfitness indicator; is the weight of the state penalty indicator; is the state penalty term.

[0012] Preferably, based on the electrical knowledge base of the power plant, a multi-objective optimization model based on the objective function of minimizing time cost and operation risk is established. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence as follows: Selecting an operation template in a power plant electrical knowledge base based on the equipment health index to obtain an operation set in the operation template; The objective function of constructing the multi-objective optimization model is:

[0013]

[0014] Where, is the objective function; is the estimated total operation time; Score operational risk; 、 is the risk weight coefficient; is the equipment health index; is the inherent risk level of the operation; Based on electrical topology constraints and safety constraints, the operation set is sequentially adjusted to obtain an operation sequence set, the objective function value of each operation sequence in the operation sequence set is solved, and the Pareto frontier solution set is generated through non-dominated sorting. Select the Pareto optimal solution based on the numerical range of the equipment health index and output the execution operation sequence.

[0015] Preferably, the Pareto frontier solution set generated by non-dominated sorting is specifically: Compare the dominance relationship of each operation sequence in the operation sequence set, and the dominance relationship determination rule is: operation sequence Governing operation sequence If and only if both satisfy: Operation sequence of Less than or equal to sequence of operations of ;Operation sequence of Less than or equal to sequence of operations of ; At least one strict inequality holds; Collect all operation sequences that are not dominated by any operation sequence as the Pareto front solution set.

[0016] Preferably, a feature vector is constructed based on the health index, the execution operation sequence, and the execution log, and an incremental power plant electrical knowledge base update is generated based on similarity matching as follows: Extract the operation device type in the execution operation sequence; Extract the operation time from the execution log, and extract the failed operations, number of retries, and exception types from the execution log to calculate the actual risk value of the execution operation sequence; Construct a feature vector based on the equipment health index, operating equipment type, operating time and actual risk value; In the power plant electrical knowledge base, a set of operation templates with the same operating equipment type is selected. Preliminary filtering is performed based on the equipment health index range. The similarity between the filtered operation templates and the feature vector is calculated:

[0017] Where, is similarity; is the health index difference; is the operation time difference; is the actual risk difference; 、 、 are the weight factors corresponding to the three types of differences; If the similarity between the feature vector and the filtered job template set exceeds the set threshold, and the operation time and actual risk value of the executed operation sequence are better than the job template, the job template is merged, otherwise a new job template is executed.

[0018] On the other hand, the present invention provides a power plant electrical secondary auxiliary decision-making collaborative system, comprising a data acquisition and fusion evaluation module, a collaborative decision-making module, a fault-tolerant execution module, and a knowledge base evolution and update module; The data acquisition and fusion evaluation module is used to collect power plant measurement data sample sets to calculate equipment indicators including health deviation, fixed value maladaptation and state penalty items, and synthesize the equipment health index through the entropy weight fusion evaluation algorithm; The collaborative decision-making module is used to establish a multi-objective optimization model based on the power plant electrical knowledge base, with the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence; The fault-tolerant execution module is used to establish an exception handling mechanism for the execution operation sequence. If the execution operation fails, the failed operation and reason are recorded and a collaborative retry is triggered. If the retry fails, the backup execution operation sequence in the Pareto frontier solution set is switched and the execution log is recorded. The knowledge base evolution and update module is used to construct feature vectors based on health index, execution operation sequence and execution log, and generate incremental power plant electrical knowledge base updates based on similarity matching.

[0019] On the other hand, the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the power plant electrical secondary auxiliary decision-making collaborative method as described in any embodiment of the present invention is implemented.

[0020] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the power plant electrical secondary auxiliary decision-making collaborative method as described in any embodiment of the present invention.

[0021] Compared with the prior art, the present invention has the following technical effects: The method described in this paper integrates multi-source data and fusion assessments to achieve equipment health assessment and multi-objective decision optimization. Based on this, it also performs exception handling and adaptive adjustments, effectively addressing the inaccurate decisions, slow response, and poor fault tolerance inherent in traditional systems. Furthermore, through a "data-knowledge-decision" approach, the method drives the closed-loop evolution of the electrical knowledge base, improving not only the intelligence level of the power plant's electrical system but also the operational efficiency and decision-making accuracy of the electrical secondary system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is an overall flow chart of the power plant electrical secondary auxiliary decision-making collaborative method described in the present invention. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in combination with specific embodiments of the present application and with reference to the accompanying drawings.

[0024] Example 1 This embodiment provides a power plant electrical secondary auxiliary decision-making collaborative method, see Figure 1 As shown, the following steps are included: A sample set of power plant measurement data is collected to calculate equipment indicators including health deviation, fixed value maladaptation and state penalty items, and the equipment health index is synthesized through an entropy weight fusion evaluation algorithm; specifically, this embodiment preferably builds a network based on the IEC61850 standardized communication protocol, integrates the power plant DCS, NCS, protection devices, automatic devices and other systems to build a unified data acquisition platform to collect various electrical data of the power plant secondary system.

[0025] As a preferred implementation of this embodiment, a sample set of power plant measurement data is collected to calculate equipment indicators including health deviation, fixed value unfitness and state penalty items, and the equipment health index is synthesized through the entropy weight fusion evaluation algorithm. Specifically, it is: Based on the IEC 61850 MMS protocol, power plant measurement data, including electrical quantities, is collected from protection devices / measurement and control devices to calculate the health deviation of the electrical quantities:

[0026] Where, is the healthy deviation of electrical quantity data, ,in, is the measured current, is the measured voltage; is the measured value of the electrical quantity; It is the electrical quantity rating.

[0027] Calculate the fixed value maladjustment:

[0028] Where, is the fixed value maladaptability; is the current constant, which can be read based on the protection device; It is the theoretical optimal value of current and can be calculated based on the short-circuit current.

[0029] Based on the device status collected by the DCS system, the number of device switch abnormalities in the collection times is calculated and divided by the total collection times as the status penalty item.

[0030] As a preferred implementation of this embodiment, the collected The information entropy of the healthy deviation of electrical quantities, the unsuitability of fixed values ​​and the state penalty items in the measurement data samples of power plants is:

[0031]

[0032] Where, For device indicators Information entropy of For device indicators In the data sample The value in ; For device indicators In the data sample The probability distribution in ; .

[0033] Calculate the weight of each device indicator based on information entropy:

[0034] Where, For the Weights of device-type indicators; For the Information entropy of device-like indicators; For the The information entropy of device-type indicators.

[0035] The device health index is synthesized based on the calculated device indicator weights, providing a quantitative status basis for subsequent operational decision-making:

[0036] Where, is the equipment health index; is the weight of the current health deviation index; is the healthy deviation of the current; is the weight of the voltage health deviation index; is the healthy deviation of voltage; is the weight of the fixed-value unfitness indicator; is the weight of the state penalty indicator; is the state penalty term.

[0037] Based on the power plant electrical knowledge base, a multi-objective optimization model is established based on the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence. Furthermore, the electrical topology constraints can be constructed by parsing the CAD format electrical wiring diagram to construct a node relationship table, extracting the logical connection diagram by parsing the IEC 61850 SCL file, and dynamically generating a connection matrix by obtaining the circuit breaker / disconnector status through the SCADA system to obtain the topology constraint adjacency matrix; safety constraints can be extracted based on national mandatory standards, equipment manufacturer specifications, or historical accident cases to generate a safety rule constraint library.

[0038] As a preferred implementation of this embodiment, based on the power plant electrical knowledge base, a multi-objective optimization model is established based on the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence as follows: Based on the equipment health index, an operation template in the power plant electrical knowledge base is selected. For example, a risk level threshold range is set, and the equipment health index in the corresponding range is mapped to an operation template of the corresponding level to obtain an operation set in the operation template.

[0039] The objective function of constructing the multi-objective optimization model is:

[0040]

[0041] Where, is the objective function; is the estimated total operation time; Score operational risk; 、 is the risk weight coefficient, ; is the equipment health index; The inherent risk level of the operation.

[0042] Based on electrical topology constraints and safety constraints, the operation set is sequentially adjusted to obtain an operation sequence set. The objective function value of each operation sequence in the operation sequence set is solved, and the Pareto frontier solution set is generated through non-dominated sorting.

[0043] Select the Pareto optimal solution based on the numerical range of the device health index and output the execution operation sequence. Specifically, set the corresponding threshold range based on the device health index and select the corresponding shortest, Minimum or and The Pareto optimal solution of equilibrium.

[0044] As a preferred implementation of this embodiment, generating a Pareto frontier solution set through non-dominated sorting is specifically as follows: Compare the dominance relationship of each operation sequence in the operation sequence set, and the dominance relationship determination rule is: operation sequence Governing operation sequence If and only if both satisfy: Operation sequence of Less than or equal to sequence of operations of ;Operation sequence of Less than or equal to sequence of operations of ; At least one strict inequality holds.

[0045] Collect all operation sequences that are not dominated by any other operation sequence and sort them into the first level as the Pareto front solution set. Remove the stratified operation sequences and repeat the above comparison steps until all operation sequences are stratified, completing the stratified sorting.

[0046] Establish an exception handling mechanism for the execution operation sequence. If the execution operation fails, record the failed operation and the reason and trigger a collaborative retry (the upper limit of the collaborative retry is generally no more than 5 times, and the preferred upper limit in practical applications is 3). If the retry fails, switch to the backup execution operation sequence in the Pareto frontier solution set, and record the execution log (which may include timestamp, operation content, execution results, etc.) to ensure the safe execution of the execution operation sequence in the real physical environment and realize dynamic cross-system linkage of the power plant.

[0047] A feature vector is constructed based on the health index, execution operation sequence and execution log, and an incremental power plant electrical knowledge base update is generated based on similarity matching.

[0048] As a preferred implementation of this embodiment, a feature vector is constructed based on the health index, the execution operation sequence, and the execution log, and an incremental power plant electrical knowledge base update is generated based on similarity matching as follows: Extracts the type of device that performs the operation in the sequence.

[0049] Extract the operation time from the execution log, and extract the failed operations, number of retries, and exception types from the execution log to calculate the actual risk value of the execution operation sequence.

[0050] A feature vector is constructed based on the equipment health index, operating equipment type, operating time and actual risk value.

[0051] In the power plant electrical knowledge base, a set of operation templates with the same operating equipment type is selected. Preliminary filtering is performed based on the equipment health index range. The similarity between the filtered operation templates and the feature vector is calculated:

[0052] Where, is similarity; is the health index difference; is the operation time difference; is the actual risk difference; 、 、 are the weight factors corresponding to the three types of differences, .

[0053] If the similarity between the feature vector and the filtered job template set exceeds the set threshold, and the operation time and actual risk value of the executed operation sequence are better than the job template, the job template is merged, otherwise a new job template is executed.

[0054] The following is a simple example of generating an incremental power plant electrical knowledge base update: Feature extraction: The health index is 0.082, the operating device type is "01" (circuit breaker), the operation time is 3 minutes, and the actual risk value is 0.3*1 (failure) + 0.1*1 (retry) = 0.4.

[0055] Similarity matching: 127 job templates of equipment type 01 are retrieved from the power plant electrical knowledge base, and the health index is filtered: (0.07, 0.09) -> 23 remain, and the best similarity match is calculated. =0.68<Set threshold 0.7, execute the new job template.

[0056] Example 2 Accordingly, this embodiment provides a power plant electrical secondary auxiliary decision-making collaborative system, which is used to execute the power plant electrical secondary auxiliary decision-making collaborative method as described in Example 1, including a data acquisition and fusion evaluation module, a collaborative decision-making module, a fault-tolerant execution module, and a knowledge base evolution and update module.

[0057] The data acquisition and fusion evaluation module is used to collect the power plant measurement data sample set to calculate the equipment indicators including health deviation, fixed value maladaptation and state penalty items, and synthesize the equipment health index through the entropy weight fusion evaluation algorithm.

[0058] The collaborative decision-making module is used to establish a multi-objective optimization model based on the electrical knowledge base of the power plant, with the objective function of minimizing time cost and operation risk. Under the premise of satisfying electrical topology constraints and safety constraints, it solves the Pareto optimal solution of the objective function in the multi-objective optimization model and converts the equipment health index into an execution operation sequence.

[0059] The fault-tolerant execution module is used to establish an exception handling mechanism for the execution operation sequence. If the execution operation fails, the failed operation and reason are recorded and a collaborative retry is triggered. If the retry fails, the backup execution operation sequence in the Pareto frontier solution set is switched and the execution log is recorded.

[0060] The knowledge base evolution and update module is used to construct feature vectors based on health index, execution operation sequence and execution log, and generate incremental power plant electrical knowledge base updates based on similarity matching.

[0061] Example 3 This embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the power plant electrical secondary auxiliary decision-making collaborative method as described in the first embodiment of the present invention is implemented.

[0062] Example 4 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the power plant electrical secondary auxiliary decision-making collaborative method as described in the first embodiment of the present invention is implemented.

[0063] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0064] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0065] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0066] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0067] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A collaborative method for secondary auxiliary decision-making in power plants, characterized in that: The following steps are involved: Collect power plant measurement data sample sets to calculate equipment indicators including health deviation, fixed value maladaptation and state penalty items, and synthesize the equipment health index through entropy weight fusion evaluation algorithm; Based on the power plant electrical knowledge base, a multi-objective optimization model is established with the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence. Establish an exception handling mechanism for the execution operation sequence. If an execution operation fails, record the failed operation and reason and trigger a collaborative retry. If the retry fails, switch to the backup execution operation sequence in the Pareto frontier solution set and record the execution log. A feature vector is constructed based on the health index, execution operation sequence and execution log, and an incremental power plant electrical knowledge base update is generated based on similarity matching.

2. The power plant electrical secondary auxiliary decision-making collaborative method according to claim 1, characterized in that: A sample set of power plant measurement data is collected to calculate equipment indicators including health deviation, fixed value inadaptability and state penalty items, and the entropy weight fusion evaluation algorithm is used to synthesize the equipment health index: Collect power plant measurement data including electrical quantities and calculate the health deviation of electrical quantities: Where, is the healthy deviation of electrical quantity data, ,in, is the measured current, is the measured voltage; is the measured value of the electrical quantity; is the rated value of the electrical quantity; Calculate the fixed value maladjustment: Where, is the fixed value maladaptability; is the current constant; is the theoretical optimal value of current; The state penalty item is calculated by dividing the number of device switch abnormalities in the collection times by the total collection times.

3. The power plant electrical secondary auxiliary decision-making collaborative method according to claim 2, characterized in that: Calculate the information entropy of the health deviation, fixed value inadaptability and state penalty items of the electrical quantity in the collected power plant measurement data samples, and calculate the weight of each equipment indicator based on the information entropy: Where, For the Weights of device-type indicators; For the Information entropy of device-like indicators; For the Information entropy of device-like indicators; The device health index is synthesized based on the calculated device indicator weights: Where, is the equipment health index; is the weight of the current health deviation index; is the healthy deviation of the current; is the weight of the voltage health deviation index; is the healthy deviation of voltage; is the weight of the fixed-value unfitness indicator; is the weight of the state penalty indicator; is the state penalty term.

4. The power plant electrical secondary auxiliary decision-making collaborative method according to claim 1, characterized in that: Based on the electrical knowledge base of the power plant, a multi-objective optimization model is established based on the objective function of minimizing time cost and operation risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence as follows: Selecting an operation template in a power plant electrical knowledge base based on the equipment health index to obtain an operation set in the operation template; The objective function of constructing the multi-objective optimization model is: Where, is the objective function; is the estimated total operation time; Score operational risk; 、 is the risk weight coefficient; is the equipment health index; is the inherent risk level of the operation; Based on electrical topology constraints and safety constraints, the operation set is sequentially adjusted to obtain an operation sequence set, the objective function value of each operation sequence in the operation sequence set is solved, and the Pareto frontier solution set is generated through non-dominated sorting. Select the Pareto optimal solution based on the numerical range of the equipment health index and output the execution operation sequence.

5. The power plant electrical secondary auxiliary decision-making collaborative method according to claim 4, characterized in that: The Pareto frontier solution set generated by non-dominated sorting is specifically: Compare the dominance relationship of each operation sequence in the operation sequence set, and the dominance relationship determination rule is: operation sequence Governing operation sequence If and only if both satisfy: Operation sequence of Less than or equal to sequence of operations of ;Operation sequence of Less than or equal to sequence of operations of ; At least one strict inequality holds; Collect all operation sequences that are not dominated by any operation sequence as the Pareto front solution set.

6. The power plant electrical secondary auxiliary decision-making collaborative method according to claim 1, characterized in that: Based on the health index, execution operation sequence and execution log, a feature vector is constructed. Based on similarity matching, an incremental power plant electrical knowledge base update is generated as follows: Extract the operation device type in the execution operation sequence; Extract the operation time from the execution log, and extract the failed operations, number of retries, and exception types from the execution log to calculate the actual risk value of the execution operation sequence; Construct a feature vector based on the equipment health index, operating equipment type, operating time and actual risk value; In the power plant electrical knowledge base, a set of operation templates with the same operating equipment type is selected. Preliminary filtering is performed based on the equipment health index range. The similarity between the filtered operation templates and the feature vector is calculated: Where, is similarity; is the health index difference; is the operation time difference; is the actual risk difference; 、 、 are the weight factors corresponding to the three types of differences; If the similarity between the feature vector and the filtered job template set exceeds the set threshold, and the operation time and actual risk value of the executed operation sequence are better than the job template, the job template is merged, otherwise a new job template is executed.

7. A power plant electrical secondary auxiliary decision-making collaborative system, characterized in that: The system is used to implement the collaborative method for auxiliary decision-making of electrical secondary power plants according to any one of claims 1 to 6, comprising a data acquisition and fusion evaluation module, a collaborative decision-making module, a fault-tolerant execution module, and a knowledge base evolution and update module; The data acquisition and fusion evaluation module is used to collect power plant measurement data sample sets to calculate equipment indicators including health deviation, fixed value maladaptation and state penalty items, and synthesize the equipment health index through the entropy weight fusion evaluation algorithm; The collaborative decision-making module is used to establish a multi-objective optimization model based on the power plant electrical knowledge base, with the objective function of minimizing time cost and operational risk. Under the premise of satisfying electrical topology constraints and safety constraints, the Pareto optimal solution of the objective function in the multi-objective optimization model is solved, and the equipment health index is converted into an execution operation sequence; The fault-tolerant execution module is used to establish an exception handling mechanism for the execution operation sequence. If the execution operation fails, the failed operation and reason are recorded and a collaborative retry is triggered. If the retry fails, the backup execution operation sequence in the Pareto frontier solution set is switched and the execution log is recorded. The knowledge base evolution and update module is used to construct feature vectors based on health index, execution operation sequence and execution log, and generate incremental power plant electrical knowledge base updates based on similarity matching.

8. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the power plant electrical secondary auxiliary decision-making collaborative method as described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the power plant electrical secondary auxiliary decision-making collaborative method according to any one of claims 1 to 6 is implemented.

Images