Health status evaluation method and system of hydropower units based on multi-source information fusion

Abstract

The present invention discloses a method and system for evaluating the health status of a through-flow hydropower unit based on multi-source information fusion, which specifically relates to the technical field of health status evaluation of hydropower units, including constructing a hierarchical analysis structure for unit health status evaluation; determining the weights of each layer and performing consistency checks; determining the thresholds for state division of each layer; constructing an indicator scoring standard by combining the fuzzy comprehensive evaluation method with industry standards; obtaining multi-source information of unit status through a data acquisition module; indicator layer score calculation and abnormal marking; project layer score calculation and abnormal marking; system layer score calculation and abnormal marking; unit overall status evaluation and operation and maintenance guidance and suggestions. The present invention extracts the upper-level equipment status layer by layer from the component equipment monitoring information based on the constructed unit health status evaluation model, and finally generates a consistent description of the health status of the hydropower unit, thereby improving the comprehensiveness and accuracy of the health status evaluation of the hydropower unit through the information combination advantage.

Description

Technical Field

[0001] The invention relates to a method and system for evaluating the health status of a tubular hydroelectric generator set based on multi-source information fusion, and belongs to the technical field of health status evaluation of hydroelectric generator sets. Background Art

[0002] At present, the maintenance mode of hydropower units in my country adopts the planned maintenance mode, which is based on reliability to formulate maintenance cycles, and then regularly inspect and repair the units according to the maintenance cycles. Since this maintenance mode fails to obtain the operating status of hydropower units in a timely manner, there are the following problems: some units with poor equipment status have reduced the stability of the units due to "insufficient maintenance", and even caused failures or accidents due to the deterioration of the operating status; some units with good equipment status have caused waste of manpower, material resources and other resources due to "excessive maintenance", and reduced the utilization rate of the units. In view of the shortcomings of the existing maintenance mode of hydropower units, experts and scholars have proposed a state maintenance mode that reasonably formulates maintenance plans according to the health status of hydropower units and performs maintenance and repair work on hydropower units accordingly, but the state maintenance mode is heavily dependent on the state evaluation technology of hydropower units. Since a hydropower unit is a complex nonlinear dynamic system coupled with multiple factors, it is impossible to directly draw an evaluation conclusion through a single monitoring indicator. Its health status evaluation process needs to be split into subsystems layer by layer according to the structural characteristics of the unit equipment, and the various types of data already available in the power station should be collected to evaluate the operating status of each subsystem equipment of the hydropower unit, and a systematic evaluation system should be constructed to comprehensively evaluate the evaluation results of the status of each subsystem to obtain the evaluation results of the hydropower unit operation status.

[0003] The analytic hierarchy process is a systematic decision analysis method. Based on the in-depth study of the nature, influencing factors and internal relationships of complex decision-making problems, it decomposes the elements related to the decision-making goals into goals, criteria, plans and other levels, so as to make the decision-making thinking process mathematical, thus providing a simple decision-making method for complex decision-making problems with multiple goals, multiple criteria or unstructured characteristics. The fuzzy comprehensive evaluation method is a comprehensive evaluation method based on fuzzy mathematics. It makes an overall evaluation of things or objects constrained by multiple factors based on the membership theory, and is suitable for solving fuzzy and difficult to quantify problems. The health status evaluation of hydropower units is a complex decision-making problem with multiple goals and multiple criteria. With the continuous development of hydropower technology, China has promulgated a number of industry standards, unit operation procedures and power station operation and maintenance procedures. There are clear qualitative or quantitative evaluation indicators for the status evaluation of various components of hydropower units. Therefore, the health status evaluation structure of hydropower units can be established according to the principle of analytic hierarchy process and the weight of each evaluation item can be determined. Then, the scoring standard of each evaluation item can be established through the fuzzy comprehensive evaluation method, and finally the health status evaluation model of hydropower units can be established. Summary of the invention

[0004] The present invention provides a method and system for evaluating the health status of a tubular hydropower unit based on multi-source information fusion, which solves the problems disclosed in the background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] Health status evaluation method of hydropower units based on multi-source information fusion:

[0007] Construct a target layer for evaluating the overall health status of hydropower units;

[0008] Construct the system layer according to the various systems of the hydropower unit;

[0009] Build project layers based on the status of each device in each system;

[0010] Construct an indicator layer based on various indicators of each device status;

[0011] The status of each device in the project layer uses the corresponding indicators in the indicator layer as evaluation indicators;

[0012] Each system in the system layer uses the status of each corresponding device in the project layer as an evaluation indicator;

[0013] Calculate the weight of each indicator at the indicator layer, and calculate the weight of each equipment status at the project layer;

[0014] Evaluation methods are divided into qualitative evaluation and quantitative evaluation;

[0015] The quantitative evaluation status score range is divided into excellent status: 90-100 points, good status: 75-90 points, qualified status: 60-75 points, abnormal status: 0-60 points;

[0016] The qualitative evaluation status scores are divided into: excellent: 100 points, good: 80 points, qualified: 60 points, abnormal: 40 points, fault: 0 points;

[0017] Establish quantitative evaluation scoring standards and evaluate the status based on the scores;

[0018] The qualitative evaluation is entered by the inspection personnel based on the actual situation;

[0019] The indicators of the indicator layer are divided into indicators for qualitative evaluation and indicators for quantitative evaluation, and the scores of the indicators are calculated respectively. When the indicators of the indicator layer are quantitatively evaluated, the measured values ​​of the indicators are collected, and the indicator scores of the indicator layer are calculated according to the quantitative evaluation score standard. The indicators whose indicator score status evaluation results are abnormal or faulty are marked;

[0020] The equipment states of the project layer are divided into equipment states for qualitative evaluation and equipment states for quantitative evaluation, and the scores of the equipment states are calculated respectively. When the equipment states of the project layer are quantitatively evaluated, the indicators are extracted according to the weights of the corresponding indicators in the indicator layer, and the scores of the extracted indicators are used to calculate the equipment state scores according to the quantitative evaluation score standards. The states are evaluated according to the scores, and the equipment states with abnormal or faulty state evaluation results are marked;

[0021] The systems at the system level are divided into qualitatively evaluated systems and quantitatively evaluated systems, and the scores of the systems are calculated respectively. When the systems at the system level are quantitatively evaluated, the device status is extracted according to the weight of the corresponding device status in the project level, and the extracted device status score is used to calculate the system score according to the quantitative evaluation score standard. The status is evaluated according to the obtained score, and the system with abnormal or faulty status evaluation results is marked;

[0022] The target layer evaluates the overall health status of the hydropower unit based on the status evaluation results of each system in the system layer.

[0023] Furthermore, the weight calculation process is as follows: using the paired comparison method and the 1-9 comparison scale table to construct the judgment matrix of the project layer and the indicator layer respectively; for each judgment matrix, calculate its maximum characteristic root λ max and the corresponding eigenvector E f ={e1, e2, ..., e n}, perform consistency test analysis, and calculate the consistency index CI based on the maximum characteristic root.

[0024]

[0025] Determine the random consistency comparison value CR according to the average consistency index table,

[0026]

[0027] Average consistency index table

[0028] nth order 1 2 3 4 5 6 7 8 9 10 RI value 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46 1.49

[0029] If CR < 0.1, it means that the judgment matrix is ​​consistent, otherwise the judgment matrix needs to be adjusted; after the consistency test passes, the weight vector corresponding to the judgment matrix is ​​feasible. f Normalize to get the weight vector W f ={w1, w, ..., w n}.

[0030] Furthermore, the process of dividing the quantitative evaluation status score interval is as follows:

[0031] The thresholds of evaluation indicators are set by combining industry standard values ​​with the healthy sample data of the unit. The standard values ​​are used as the qualified thresholds, and the normal distribution theory, i.e. the 3σ criterion, is used to set the excellent and good status thresholds based on the healthy sample data:

[0032]

[0033] In the formula, S h Represents healthy samples, represents the healthy sample baseline value, and σ represents the healthy sample standard deviation. The status evaluation table is as follows:

[0034]

[0035]

[0036] Furthermore, the calculation process of the quantitative evaluation score standard is:

[0037] The evaluation index threshold is divided into four corresponding intervals, namely:

[0038] excellent: good: qualified: Abnormal: non-standard value interval; when the monitoring value of the evaluation index is in the right section of a certain state interval, the index is a small trend index, and the degradation degree is calculated as formula 4:

[0039]

[0040] In the formula, l is the degradation degree of the indicator, m is the measured value of the indicator, u1 is the upper limit of the indicator, p1 is the best indicator, and p1<u1.

[0041] Otherwise, it is a large-scale indicator, and the degradation degree is calculated as shown in Formula 5:

[0042]

[0043] In the formula, d2 is the lower limit of the indicator, p2 is the optimal value of the indicator, and d2<p2;

[0044] The membership degree a is introduced to measure the degree of membership of the indicator in its state interval. The calculation formula is as follows:

[0045] a=1-l (6)

[0046] According to the index interval membership, the quantitative index score v can be calculated, as shown in Formula 7

[0047] v=a×(v u -v d )+v b (7)

[0048] In the formula, v is the index score, v u is the upper limit of the indicator status interval, v d is the lower limit of the indicator status interval, v b It is the lower limit of the score of the status interval to which the indicator belongs.

[0049] Accordingly, the health status evaluation system of tubular hydropower units based on multi-source information fusion includes:

[0050] Offline modeling system:

[0051] Construct a target layer for evaluating the overall health status of hydropower units;

[0052] Construct the system layer according to the various systems of the hydropower unit;

[0053] Build project layers based on the status of each device in each system;

[0054] Construct an indicator layer based on various indicators of each device status;

[0055] The status of each device in the project layer uses the corresponding indicators in the indicator layer as evaluation indicators;

[0056] Each system in the system layer uses the status of each corresponding device in the project layer as an evaluation indicator;

[0057] Calculate the weight of each indicator at the indicator layer, and calculate the weight of each equipment status at the project layer;

[0058] Evaluation methods are divided into qualitative evaluation and quantitative evaluation;

[0059] The quantitative evaluation status score range is divided into excellent status: 90-100 points, good status: 75-90 points, qualified status: 60-75 points, abnormal status: 0-60 points;

[0060] The qualitative evaluation status scores are divided into: excellent: 100 points, good: 80 points, qualified: 60 points, abnormal: 40 points, fault: 0 points;

[0061] Establish quantitative evaluation scoring standards and evaluate the status based on the scores;

[0062] Online evaluation system:

[0063] It includes a multi-source data acquisition module, which collects the measured values ​​of various evaluation indicators through various information subsystems, offline experiments and manual inspections.

[0064] The qualitative evaluation is entered by the inspection personnel based on the actual situation;

[0065] Collect monitoring values ​​of various indicators at the indicator layer, divide the indicators at the indicator layer into qualitative evaluation indicators and quantitative evaluation indicators, calculate the scores of each indicator respectively, and mark the indicators whose indicator score status evaluation results are abnormal or faulty;

[0066] The equipment states of the project layer are divided into qualitative evaluation states and quantitative evaluation states, and the scores of the equipment states are calculated respectively. When the equipment states of the project layer are quantitatively evaluated, the indicators are extracted according to the weights of the corresponding indicators in the indicator layer, and the scores of the extracted indicators are used to calculate the equipment state scores according to the quantitative evaluation score standards. The state is evaluated according to the scores, and the equipment states with abnormal or faulty state evaluation results are marked;

[0067] Each system in the system layer is divided into a qualitative evaluation system and a quantitative evaluation system, and the scores of each system are calculated respectively. When the system in the system layer is quantitatively evaluated, the device status is extracted according to the weight of the corresponding device status in the project layer, and the extracted device status score is used to calculate the system score according to the quantitative evaluation score standard. The status is evaluated according to the score, and the system with abnormal or faulty status evaluation results is marked;

[0068] The target layer evaluates the overall health status of the hydropower unit based on the status evaluation results of each system in the system layer.

[0069] Furthermore, the calculation process of the weights in the offline modeling system is as follows: using the paired comparison method and the 1-9 comparison scale table to construct the judgment matrices at the project level and the indicator level respectively; for each judgment matrix, calculate its maximum characteristic root λ max and the corresponding eigenvector E f ={e1, e2, ..., e n}, perform consistency test analysis, and calculate the consistency index CI based on the maximum characteristic root.

[0070]

[0071] Determine the random consistency comparison value CR according to the average consistency index table,

[0072]

[0073] Average consistency index table

[0074] nth order 1 2 3 4 5 6 7 8 9 10 RI value 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46 1.49

[0075] If CR < 0.1, it means that the judgment matrix has good consistency, otherwise the judgment matrix needs to be adjusted; after the consistency test passes, the weight vector corresponding to the judgment matrix is ​​feasible. f Normalize to get the weight vector W f ={w1, w, ..., wn}.

[0076] Furthermore, the process of dividing the quantitative evaluation status score interval in the offline modeling system is as follows:

[0077] The thresholds of evaluation indicators are set by combining industry standard values ​​with the healthy sample data of the unit. The standard values ​​are used as the qualified thresholds, and the normal distribution theory, i.e. the 3σ criterion, is used to set the excellent and good status thresholds based on the healthy sample data:

[0078]

[0079] In the formula, S h Represents healthy samples, represents the healthy sample baseline value, and σ represents the healthy sample standard deviation. The status evaluation table is as follows:

[0080]

[0081]

[0082] Furthermore, the calculation process of the quantitative evaluation score standard in the offline modeling system is:

[0083] The evaluation index threshold is divided into four corresponding intervals, namely:

[0084] excellent: good: qualified: Abnormal: non-standard value interval; when the monitoring value of the evaluation index is in the right section of a certain state interval, the index is a small trend index, and the degradation degree is calculated as formula 4:

[0085]

[0086] In the formula, l is the degradation degree of the indicator, m is the measured value of the indicator, u1 is the upper limit of the indicator, p1 is the best indicator, and p1<u1.

[0087] Otherwise, it is a large-scale indicator, and the degradation degree is calculated as shown in Formula 5:

[0088]

[0089] In the formula, d2 is the lower limit of the indicator, p2 is the optimal value of the indicator, and d2<p2;

[0090] The membership degree a is introduced to measure the degree of membership of the indicator in its state interval. The calculation formula is as follows:

[0091] a=1-l (6)

[0092] According to the index interval membership, the quantitative index score v can be calculated, as shown in Formula 7

[0093] v=a×(v u -v d )+v b (7)

[0094] In the formula, v is the index score, v u is the upper limit of the indicator status interval, v d is the lower limit of the indicator status interval, v b It is the lower limit of the score of the status interval to which the indicator belongs.

[0095] Accordingly, a computer-readable storage medium stores one or more programs: the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device performs any of the methods described above.

[0096] Accordingly, a computing device is characterized by comprising:

[0097] One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0098] The beneficial effects achieved by the present invention are as follows: the present invention comprehensively utilizes multi-source heterogeneous data such as online monitoring data of each information subsystem, offline test data and manual inspection results, and extracts the upper-level equipment status layer by layer from the component equipment monitoring information according to the constructed unit health status evaluation model, and finally generates a consistent description of the health status of the hydropower unit, thereby improving the comprehensiveness and accuracy of the health status evaluation of the hydropower unit through the advantages of information combination. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 It is a schematic diagram of the process of the present invention;

[0100] Figure 2 This is a hierarchical analysis system diagram for health status evaluation of hydropower units in the present invention. DETAILED DESCRIPTION

[0101] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0102] Refer to the instruction manual Figure 1 The health status evaluation method of tubular hydropower unit based on multi-source information fusion includes the following specific steps:

[0103] Step 1: Determine the four-level hierarchical analysis system of "target layer - system layer - project layer - indicator layer" according to the unit structure and the operation and maintenance procedures of the hydropower plant. Figure 2 It is a hierarchical analysis system for health status evaluation of tubular hydropower units.

[0104] Step 2: Construct a paired comparison matrix, calculate the weight vector and perform a consistency test. According to the analytic hierarchy structure of the health status evaluation of hydropower units constructed in step 1, the judgment matrix of the system layer, project layer and indicator layer is constructed using the paired comparison method and the 1-9 comparison scale table.

[0105] Table 1 Comparison scale table

[0106]

[0107] For each judgment matrix, calculate its maximum eigenvalue λ max and the corresponding eigenvector E f ={e1, e2, ..., e n In order to avoid logical errors in the judgment matrix, a consistency test analysis is required to calculate the consistency index CI based on the maximum characteristic root.

[0108]

[0109] The random consistency comparison value CR is determined according to the average consistency index table.

[0110]

[0111] Table 2 Average consistency index table

[0112] nth order 1 2 3 4 5 6 7 8 9 10 RI value 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46 1.49

[0113] If CR < 0.1, it means that the judgment matrix has good consistency, otherwise the judgment matrix needs to be adjusted. After the consistency test passes, the weight vector corresponding to the judgment matrix has strong feasibility. f Normalization can be performed to obtain the weight vector W f ={w1, w, ..., w n}.

[0114] Step 3: After obtaining the weight vector of each judgment matrix, it is necessary to confirm the status division threshold of each level of the hierarchical analysis system from bottom to top. According to the evaluation method classification, the evaluation items can be divided into qualitative evaluation and quantitative evaluation.

[0115] For quantitative evaluation items, the index thresholds are set by combining industry standard values ​​with unit health sample data. The standard values ​​are used as qualified thresholds, and the normal distribution theory, i.e., the 3σ criterion, is used to set the excellent and good status thresholds based on the health sample data:

[0116]

[0117] In the formula, S h Represents healthy samples, represents the healthy sample baseline value, and σ represents the healthy sample standard deviation. The status evaluation table is as follows:

[0118] Table 3 Quantitative status evaluation table

[0119]

[0120] For qualitative evaluation items, since the qualitative evaluation item data in the system comes from manual inspection entry, the inspection personnel can enter the status results of excellent, good, qualified, abnormal, and faulty according to the actual operating conditions.

[0121] Table 4 Qualitative status evaluation table

[0122] state Points Status description excellent 100 The operation status is normal and no action is required. good 80 The operating status is good, but there is a trend of approaching the operating limit, no action is required qualified 60 The operating status is normal, but close to the operating limit, need to pay more attention abnormal 40 In abnormal operation state, but no safety risk, measures need to be taken Fault 0 There is a safety risk if the equipment continues to work, and measures must be taken immediately

[0123] Step 4: Combine the Gaussian membership function of the fuzzy comprehensive evaluation method with industry standards and specifications to construct a quantitative indicator scoring standard.

[0124] In order to determine the scoring standard of quantitative indicators, the concept of degradation degree is introduced here to characterize the relative degradation degree of the current actual state compared with the fault state, and its value range is [0, 1]. Different values ​​reflect different degradation degrees of the evaluation indicators. According to the state classification, the indicator threshold is divided into four corresponding intervals, namely: Excellent:

[0125] good: qualified: Abnormal: non-standard value interval. When the indicator monitoring value is in the right section of a certain state interval, the indicator is a small trend indicator, and the degradation degree is calculated as formula 4:

[0126]

[0127] In the formula, l is the degradation degree of the indicator, m is the measured value of the indicator, u1 is the upper limit of the indicator, p1 is the best indicator, and p1<u1.

[0128] Otherwise, it is a large-scale indicator, and the degradation degree is calculated as shown in Formula 5:

[0129]

[0130] In the formula, d2 is the lower limit of the indicator, p2 is the optimal value of the indicator, and d2<p2.

[0131] The membership degree a is introduced to measure the degree of membership of the indicator in its state interval. The calculation formula is as follows:

[0132] a=1-l (6)

[0133] According to the index interval membership, the quantitative index score v can be calculated as shown in formula 7

[0134] v=a×(v u -v d )+v b (7)

[0135] In the formula, v is the index score, v u is the upper limit of the indicator status interval, v d is the lower limit of the indicator status interval, v b It is the lower limit of the score of the status interval to which the indicator belongs.

[0136] Step 5: Collect multi-source status data of the hydropower unit for online evaluation. The system obtains equipment status monitoring data from each information subsystem through the data acquisition module, collects the latest manual inspection data through the inspection system, and captures the latest offline test data from the document. The offline test data comes from the results entered into the formatted document template through the manual interface after each offline test; the data acquisition module performs data format conversion and data cleaning and then outputs the unit status information data to the next module.

[0137] Step 6: Classify according to the indicator layer scoring method, extract project characteristic indicators based on the unit status information data and scoring standards, and mark the indicators with abnormal or faulty status evaluation results.

[0138] Step 7: Calculate the project-level status evaluation score based on the indicator-level score and the corresponding weight, evaluate the operating status of each component sub-equipment of the unit, and mark the upper-level project with abnormal or faulty status evaluation results;

[0139] Step 8: Calculate the system-level status evaluation score based on the project-level score and the corresponding weight, evaluate the operating status of each component of the unit, and mark the upper-level system with abnormal or faulty status evaluation results;

[0140] Step 9: Calculate the unit status evaluation result based on the system level status evaluation score and the corresponding weight, evaluate the overall operating status of the unit, and provide guidance and suggestions for unit operation and maintenance.

[0141] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0142] A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes a hydropower unit health status evaluation method based on multi-source information fusion.

[0143] A computing device includes one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing a method for evaluating the health status of a hydropower unit based on multi-source information fusion.

[0144] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0148] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for evaluating the health status of a hydropower unit based on multi-source information fusion, characterized in that: Construct a target layer for evaluating the overall health status of hydropower units; Construct the system layer according to the various systems of the hydropower unit; Build project layers based on the status of each device in each system; Construct an indicator layer based on various indicators of each device status; The status of each device in the project layer uses the corresponding indicators in the indicator layer as evaluation indicators; Each system in the system layer uses the corresponding equipment status in the project layer as an evaluation indicator; Calculate the weight of each indicator at the indicator layer, and calculate the weight of each equipment status at the project layer; Evaluation methods are divided into qualitative evaluation and quantitative evaluation; The quantitative evaluation status score range is divided into excellent status: 90-100 points, good status: 75-90 points, qualified status: 60-75 points, abnormal status: 0-60 points; The qualitative evaluation status scores are divided into: excellent: 100 points, good: 80 points, qualified: 60 points, abnormal: 40 points, fault: 0 points; Establish quantitative evaluation scoring standards and evaluate the status based on the scores; The qualitative evaluation is entered by the inspection personnel based on the actual situation; The indicators of the indicator layer are divided into indicators for qualitative evaluation and indicators for quantitative evaluation, and the scores of the indicators are calculated respectively. When the indicators of the indicator layer are quantitatively evaluated, the measured values ​​of the indicators are collected, and the indicator scores of the indicator layer are calculated according to the quantitative evaluation score standard. The indicators whose indicator score status evaluation results are abnormal or faulty are marked; The equipment states of the project layer are divided into equipment states for qualitative evaluation and equipment states for quantitative evaluation, and the scores of the equipment states are calculated respectively. When the equipment states of the project layer are quantitatively evaluated, the indicators are extracted according to the weights of the corresponding indicators in the indicator layer, and the scores of the extracted indicators are used to calculate the equipment state scores according to the quantitative evaluation score standards. The states are evaluated according to the scores, and the equipment states with abnormal or faulty state evaluation results are marked; The systems at the system level are divided into qualitatively evaluated systems and quantitatively evaluated systems, and the scores of the systems are calculated respectively. When the systems at the system level are quantitatively evaluated, the device status is extracted according to the weight of the corresponding device status in the project level, and the extracted device status score is used to calculate the system score according to the quantitative evaluation score standard. The status is evaluated according to the obtained score, and the system with abnormal or faulty status evaluation results is marked; The target layer evaluates the overall health status of the hydropower unit based on the status evaluation results of each system in the system layer; the process of dividing the quantitative evaluation status score interval is as follows: The evaluation index thresholds are set by combining the industry standard values ​​and the unit health sample data. The standard values ​​are used as the qualified thresholds, and the normal distribution theory, i.e. the 3σ criterion, is used based on the health sample data to set the excellent and good status thresholds: In the formula, S h Represents healthy samples, represents the baseline value of healthy samples, σ represents the standard deviation of healthy samples; the status evaluation table is as follows: The calculation process of the quantitative evaluation score standard is as follows: The evaluation index threshold is divided into four corresponding intervals, namely: excellent: good: Qualified: [standard lower limit, Standard upper limit], abnormal: non-standard value interval; when the monitoring value of the evaluation index is in the right section of a certain state interval, the index is a small-scale index, and the degradation degree is calculated as formula 4: In the formula, l is the degradation degree of the indicator, m is the measured value of the indicator, u1 is the upper limit of the indicator, p1 is the best indicator, and p1 1； ​ Otherwise, it is a large-scale indicator, and the degradation degree is calculated as shown in Formula 5: In the formula, d2 is the lower limit of the indicator, p2 is the optimal value of the indicator, and d2 <p2; The membership degree a is introduced to measure the degree of membership of the indicator in its state interval. The calculation formula is as follows: a＝1-l ( 6 ) According to the index interval membership, the quantitative index score v can be calculated, as shown in Formula 7 v=a×(v u -v d )+v b (7) In the formula, v is the index score, v u is the upper limit of the indicator status interval, v d is the lower limit of the indicator status interval, v b It is the lower limit of the score of the status interval to which the indicator belongs.

2. The method for evaluating the health status of a hydropower unit based on multi-source information fusion according to claim 1 is characterized in that: The weight calculation process is as follows: Use the paired comparison method and the 1-9 comparison scale table to construct the judgment matrix of the project layer and the indicator layer respectively; for each judgment matrix, calculate its maximum characteristic root λ max and the corresponding eigenvector E f ={e1,e2,…,e n }, perform consistency test analysis, and calculate the consistency index CI based on the maximum characteristic root. Determine the random consistency comparison value CR according to the average consistency index table, Average consistency index table If CR<0.1, it means that the judgment matrix is ​​consistent, otherwise the judgment matrix needs to be adjusted; after the consistency test passes, the weight vector corresponding to the judgment matrix is ​​feasible. f Normalize to get the weight vector W f ={w1,w,…,w n }.

3. The hydropower unit health status evaluation system based on multi-source information fusion is characterized by: include: Offline modeling system: Construct a target layer for evaluating the overall health status of hydropower units; Construct the system layer according to the various systems of the hydropower unit; Build project layers based on the status of each device in each system; Construct an indicator layer based on various indicators of each device status; The status of each device in the project layer uses the corresponding indicators in the indicator layer as evaluation indicators; Each system in the system layer uses the corresponding equipment status in the project layer as an evaluation indicator; Calculate the weight of each indicator at the indicator layer, and calculate the weight of each equipment status at the project layer; Evaluation methods are divided into qualitative evaluation and quantitative evaluation; The quantitative evaluation status score range is divided into excellent status: 90-100 points, good status: 75-90 points, qualified status: 60-75 points, abnormal status: 0-60 points; The qualitative evaluation status scores are divided into: excellent: 100 points, good: 80 points, qualified: 60 points, abnormal: 40 points, fault: 0 points; Establish quantitative evaluation scoring standards and evaluate the status based on the scores; Online evaluation system: It includes a multi-source data acquisition module, which collects the measured values ​​of various evaluation indicators through various information subsystems, offline experiments and manual inspections. The qualitative evaluation is entered by the inspection personnel based on the actual situation; Collect monitoring values ​​of various indicators at the indicator layer, divide the indicators at the indicator layer into qualitative evaluation indicators and quantitative evaluation indicators, calculate the scores of each indicator respectively, and mark the indicators whose indicator score status evaluation results are abnormal or faulty; The equipment states of the project layer are divided into qualitative evaluation states and quantitative evaluation states, and the scores of the equipment states are calculated respectively. When the equipment states of the project layer are quantitatively evaluated, the indicators are extracted according to the weights of the corresponding indicators in the indicator layer, and the scores of the extracted indicators are used to calculate the equipment state scores according to the quantitative evaluation score standards. The state is evaluated according to the scores, and the equipment states with abnormal or faulty state evaluation results are marked; Each system in the system layer is divided into a qualitative evaluation system and a quantitative evaluation system, and the scores of each system are calculated respectively. When the system in the system layer is quantitatively evaluated, the device status is extracted according to the weight of the corresponding device status in the project layer, and the extracted device status score is used to calculate the system score according to the quantitative evaluation score standard. The status is evaluated according to the score, and the system with abnormal or faulty status evaluation results is marked; The target layer evaluates the overall health status of the hydropower unit based on the status evaluation results of each system in the system layer; The process of dividing the quantitative evaluation status score interval in the offline modeling system is as follows: The evaluation index thresholds are set by combining the industry standard values ​​and the unit health sample data. The standard values ​​are used as the qualified thresholds, and the normal distribution theory, i.e. the 3σ criterion, is used based on the health sample data to set the excellent and good status thresholds: In the formula, S h Represents healthy samples, represents the baseline value of the healthy sample, σ represents the standard deviation of the healthy sample, and the status evaluation table is as follows: The calculation process of the quantitative evaluation score standard in the offline modeling system is: The evaluation index threshold is divided into four corresponding intervals, namely: excellent: good: Qualified: [standard lower limit, Standard upper limit], abnormal: non-standard value interval; when the monitoring value of the evaluation index is in the right section of a certain state interval, the index is a small-scale index, and the degradation degree is calculated as formula 4: In the formula, l is the degradation degree of the indicator, m is the measured value of the indicator, u1 is the upper limit of the indicator, p1 is the best indicator, and p1 <u1; Otherwise, it is a large-scale indicator, and the degradation degree is calculated as shown in Formula 5: In the formula, d2 is the lower limit of the indicator, p2 is the optimal value of the indicator, and d2 <p2; The membership degree a is introduced to measure the degree of membership of the indicator in its state interval. The calculation formula is as follows: a＝1-l ( 6 ) According to the index interval membership, the quantitative index score v can be calculated, as shown in Formula 7 v=a×(v u -v d )+v b (7) In the formula, v is the index score, v u is the upper limit of the indicator status interval, v d is the lower limit of the indicator status interval, v b It is the lower limit of the score of the status interval to which the indicator belongs.

4. The hydropower unit health status evaluation system based on multi-source information fusion according to claim 3 is characterized by: The calculation process of weights in the offline modeling system is as follows: using the paired comparison method and the 1-9 comparison scale table to construct the judgment matrix of the project layer and the indicator layer respectively; for each judgment matrix, calculate its maximum characteristic root λ max and the corresponding eigenvector E f ={e1,e2,…,e n }, perform consistency test analysis, and calculate the consistency index CI based on the maximum characteristic root. Determine the random consistency comparison value CR according to the average consistency index table, Average consistency index table If CR<0.1, it means that the judgment matrix is ​​consistent, otherwise the judgment matrix needs to be adjusted; after the consistency test passes, the weight vector corresponding to the judgment matrix is ​​feasible. f Normalize to get the weight vector W f ={w1,w,…,w n }.

5. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions which, when executed by a computing device, cause the computing device to perform any one of the methods according to claims 1 to 2.

6. A computing device, characterized in that include: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods according to claims 1 to 2.

Images