Method for constructing vulnerability evaluation model based on G1 method-CRITIC method combined weighting

Abstract

The invention provides a vulnerability evaluation model construction method based on G1 method-CRITIC method combined weighting, which comprises the following steps: acquiring data information in four aspects of personnel, equipment, environment and management of a hydropower station, determining vulnerability factors of the hydropower station based on the data information, establishing a vulnerability evaluation index system based on the vulnerability factors, and establishing a vulnerability evaluation model of the hydropower station based on the vulnerability evaluation index system. According to the method, a comprehensive and accurate index basis is provided for vulnerability evaluation of the hydropower station, based on a vulnerability evaluation index system, a G1 method and a CRITIC method are used for combined weighting to obtain a combined weight of an evaluation index, based on evaluation grade division, a standard cloud evaluation model is constructed in combination with the combined weight of the evaluation index, and real-time data are evaluated. The vulnerability of the hydropower station is evaluated, and timely prevention is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station evaluation, and particularly relates to a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method and the CRITIC method. Background Art

[0002] Analyze the definition of the vulnerability concept in small and medium-sized hydropower stations, and conduct a vulnerability analysis of hydropower stations from four aspects: personnel, equipment and facilities, environment, and management, as follows:

[0003] In terms of personnel: The vulnerability of a hydropower station is closely related to factors such as the educational level of personnel, personnel density, and the age structure of personnel. If the overall educational level of the employees in the hydropower station is low and they lack necessary skills training and emergency drills, they may not be able to effectively respond to emergencies when faced with them, thus leading to the occurrence of accidents. In addition, human factors are also important reasons for the vulnerability of hydropower stations. Behaviors such as human negligence and dereliction of duty may exacerbate the vulnerability of hydropower stations;

[0004] In terms of equipment: The vulnerability of a hydropower station is closely related to factors such as facility density, facility location, and facility classification level. The equipment of a hydropower station is the basis for its normal operation. Aging of equipment, improper maintenance, lack of standby equipment, etc. will all increase the vulnerability of the hydropower station. Once an important piece of equipment fails, it may lead to the shutdown of the hydropower station, causing serious economic losses and safety hazards;

[0005] In terms of environment: The environment around the hydropower station cannot be ignored. For example, factors such as environmental exposure, geographical location, and environmental recovery ability are closely related to the vulnerability of the hydropower station. It also includes whether the natural environment around the hydropower station is easily affected by natural disasters; whether it is easily damaged by humans, etc. If the environment of the hydropower station is easily disturbed externally, its vulnerability will increase accordingly;

[0006] In terms of management: The vulnerability of a hydropower station is closely related to factors such as emergency management, safety education and training, operation safety management, personnel management, equipment management, and environmental management. Lack of an emergency plan or failure to conduct regular emergency drills, and employees being unfamiliar with the emergency procedures may lead to missing the opportunity to respond. Insufficient employee training, especially in the operation and safety management of new equipment and technologies, may lead to operation errors; failure to formulate an effective equipment maintenance and inspection plan, resulting in an increase in the failure rate of key equipment;

[0007] To sum up, the vulnerability of a hydropower station is defined as the degree to which it is easily damaged or its normal operation is affected when facing various influences such as personnel, equipment, and environmental factors. Therefore, it is necessary to evaluate the vulnerability of the hydropower station for timely prevention. Summary of the Invention

[0008] The present invention provides a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method and the CRITIC method to solve the problems raised in the background art.

[0009] A method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method and the CRITIC method includes:

[0010] S1: Collect data information on four aspects of personnel, equipment, environment, and management of the hydropower station. Based on the data information, determine the vulnerability factors of the hydropower station;

[0011] S2: Establish a vulnerability evaluation index system based on the vulnerability factors;

[0012] S3: Based on the vulnerability evaluation index system, use the G1 method - CRITIC method for combined weighting to obtain the combined weights of the evaluation indexes;

[0013] S4: Based on the evaluation grade division, combine the combined weights of the evaluation indexes to construct a standard cloud evaluation model and evaluate the real-time data.

[0014] Preferably, collect data information on four aspects of personnel, equipment, environment, and management of the hydropower station,

[0015] including:

[0016] Obtain the personnel work type information, work equipment information, hydropower station environment information, and management system information of the hydropower station;

[0017] Extract the key information that affects the vulnerability of the hydropower station from the personnel work type information, work equipment information, hydropower station environment information, and management system information as the data information.

[0018] Preferably, in S1, based on the data information, determine the vulnerability factors of the hydropower station, including:

[0019] Obtain the direct causes of vulnerability in the four aspects of personnel, equipment, environment, and management;

[0020] Obtain the target information related to the direct cause from the data information;

[0021] Based on the target information, determine the vulnerability factors of the hydropower station.

[0022] Preferably, in S2, based on the vulnerability factors, establish a vulnerability evaluation index system, including:

[0023] Perform semantic standardization on the vulnerability factors to obtain standard factors;

[0024] Based on the standard factors, establish a vulnerability evaluation index system.

[0025] Preferably, in S3, based on the vulnerability evaluation index system, the G1 method - CRITIC method is used for combined weighting to obtain the combined weight of the evaluation indexes, including:

[0026] Determine the first weight of each evaluation index in the vulnerability evaluation index system based on the G1 method;

[0027] Determine the second weight of each evaluation index in the vulnerability evaluation index system based on the CRITIC method;

[0028] Perform combined weighting processing on the first weight and the second weight to obtain the combined weight of the evaluation indexes.

[0029] Preferably, the determination of the first weight vector of each evaluation index in the vulnerability evaluation index system based on the G1 method includes:

[0030] Based on the vulnerability evaluation index system, establish an index set, sort and set weights for each evaluation index in the index set from largest to smallest importance to obtain an index weight sequence;

[0031] Based on the index characteristics, determine the importance of the previous evaluation index and the next evaluation index adjacent to each other in the index weight sequence;

[0032] Based on the importance, and calculate the first weight of the hth evaluation index according to the following formula;

[0033]

[0034] where A n represents the first weight of the hth evaluation index, and r i represents the importance between the (ω - 1)th evaluation index and the ωth evaluation index.

[0035] Preferably, the determination of the second weight of each evaluation index in the vulnerability evaluation index system based on the CRITIC method includes:

[0036] Obtain the number m of the vulnerability evaluation objects of the hydropower station, obtain the number n of the evaluation indexes in the evaluation index system, construct an m - row and n - column hydropower station vulnerability evaluation matrix, and perform normalization processing on the hydropower station vulnerability evaluation matrix to obtain a standardized matrix;

[0037] Calculate the standard deviation of each evaluation index of the standardized matrix according to the following formula;

[0038]

[0039] where S j represents the standard deviation of the jth evaluation index, and x ijRepresents the value at the i-th row and j-th column in the standardized matrix, represents the mean of the j-th column;

[0040] Determine the correlation coefficient between any two indicators based on the standard deviation of the evaluation indicators;

[0041] Based on the correlation coefficient, calculate the conflict A of the j1-th evaluation indicator according to the following formula j1 ;

[0042]

[0043] where ρ j1j2 represents the correlation coefficient between the j1-th evaluation indicator and the j2-th evaluation indicator;

[0044] Based on the conflict and standard deviation of the evaluation indicators, calculate the second weight w of the evaluation indicators according to the following formula j ;

[0045] C j =S j ×A j (j = 1, 2, 3…, n)

[0046]

[0047] where C j represents the information content of the j-th evaluation indicator.

[0048] Preferably, perform combined weighting processing on the first weight and the second weight to obtain the combined weight of the evaluation indicators, including:

[0049] Set the ideal value of the indicator attribute and the ideal weighting scheme for each evaluation indicator;

[0050] Based on the ideal value of the indicator attribute, construct a Lagrangian function to determine the weighting algorithm for combining the first weight and the second weight with the principle of the minimum distance from the actual weighting scheme to the ideal weighting scheme, and obtain the combined weight of the evaluation indicators based on the weighting algorithm.

[0051] Preferably, before S4, it further includes: setting the vulnerability evaluation level based on the historical evaluation data of the power station:

[0052] From the corresponding relationship between the historical rating results and the historical actual vulnerability hazards in the historical evaluation data of the power station, determine the matching degree between the historical rating results and the historical actual vulnerability hazards based on the corresponding relationship;

[0053] Select the alternative historical rating results with a matching degree greater than the preset matching degree, and determine the range of the number of levels and the historical evaluation index system based on all the alternative historical rating results;

[0054] Determine the current number of levels from the range of the number of levels based on the similarity between the historical evaluation index system and the current vulnerability evaluation index system;

[0055] Obtain the target historical rating result that matches the current number of levels from the alternative historical rating results, and select the target historical rating result with the highest similarity between the historical evaluation index system and the current vulnerability evaluation index system in the target historical rating results as the initial rating result;

[0056] Obtain the old evaluation indicators in the initial historical rating result, and determine the first influence level and the first influence weight of the old evaluation indicators on the rating result;

[0057] When the first influence weight is less than the preset influence weight, determine that there is no need to perform the first rating correction on the initial rating result. Otherwise, based on the first influence level and the second influence weight, combined with the preset correction model, perform the first rating correction on the first influence level in the initial historical rating result to obtain the first corrected rating result;

[0058] Based on the current vulnerability evaluation index system, determine the new evaluation indicators, and based on human experience, determine the second influence level and the second influence weight of the new evaluation indicators on the rating result;

[0059] Based on the second influence level and the second influence weight, combined with the preset correction model, perform the second rating correction on the second influence level in the first corrected rating result to obtain the second corrected rating result;

[0060] Based on the second corrected rating result, determine the level division of the vulnerability evaluation index system under the combined weight, and the rating criteria for each level.

[0061] Preferably, in S4, based on the evaluation level division, combined with the combined weight of the evaluation indicators, construct a standard cloud evaluation model and evaluate the real-time data, including:

[0062] Based on the evaluation level division, combined with the combined weight of the evaluation indicators, determine the expected value, entropy, and hyperentropy of the evaluation level pair;

[0063] Based on the expected value, entropy, and hyperentropy, input them into MATLAB software for programming to obtain the standard cloud evaluation model corresponding to the expected value, entropy, and hyperentropy;

[0064] Based on the real-time data, combined with MATLAB software, obtain the actual cloud map;

[0065] Compare the difference between the actual cloud map and the standard cloud evaluation model, and determine the vulnerability evaluation result of the real-time data according to the comparison result.

[0066] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0067] By collecting data information on four aspects of personnel, equipment, environment and management of a hydropower station, based on the data information, determining the vulnerability factors of the hydropower station, establishing a vulnerability evaluation index system based on the vulnerability factors, providing a comprehensive and accurate index basis for the vulnerability evaluation of the hydropower station, based on the vulnerability evaluation index system, using the G1 method - CRITIC method for combined weighting to obtain the combined weight of the evaluation indexes, based on the evaluation grade division, constructing a standard cloud evaluation model in combination with the combined weight of the evaluation indexes and evaluating the real-time data, realizing the evaluation of the vulnerability of the hydropower station, and facilitating timely prevention.

[0068] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structure specifically pointed out in this application document.

[0069] The following will further describe the technical solutions of the present invention in detail through the drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0071] Figure 1 is a flowchart of a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method - CRITIC method in an embodiment of the present invention;

[0072] Figure 2 is a flowchart of collecting data information in an embodiment of the present invention;

[0073] Figure 3 is a flowchart of obtaining the combined weight of the evaluation indexes in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] The following will describe the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not used to limit the present invention.

[0075] Embodiment 1:

[0076] An embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method - CRITIC method, as Figure 1 shown, including:

[0077] S1: Collect data information on personnel, equipment, environment and management of the hydropower station, and determine the vulnerability factors of the hydropower station based on the data information;

[0078] S2: Establish a vulnerability assessment index system based on the vulnerability factors;

[0079] S3: Based on the vulnerability assessment index system, the G1 method-CRITIC method is used to perform combined weighting to obtain the combined weight of the assessment index;

[0080] S4: Based on the evaluation level classification, the standard cloud evaluation model is constructed in combination with the combined weights of the evaluation indicators and the real-time data is evaluated.

[0081] In this embodiment, the human vulnerability factors include operating efficiency, safety personnel quality, safety personnel staffing, personnel physical fitness, personnel three violations rate, personnel emergency response capabilities and other factors; the equipment vulnerability factors include mainly the rationality of equipment layout, equipment failure, equipment service life, equipment status, equipment informatization level, equipment redundancy, implementation of industry standards and specifications, reliability of safety devices and other factors; environmental factors include natural environment conditions, accessibility of the working environment, disaster resistance of structures, rationality of structure layout, rationality of layout of emergency equipment and facilities and other factors; management factors include the standardization of personnel, equipment, and environmental management; risk management standardization; work site management standardization; safety education and training quality; emergency organization system operation capability and rationality of emergency plans and other factors.

[0082] In this embodiment, the vulnerability assessment index system consists of four parts: personnel, equipment, environment, and management, and each part has several indicators.

[0083] In this embodiment, the G1 method is an improved subjective weighting method that makes up for the disadvantage of strong subjectivity of expert scoring in the hierarchical analysis method, which can avoid unreasonable evaluation results due to too many influencing factors. It can save cumbersome calculation steps and does not require repetitive matrix construction; it deletes the consistency check and is easy to apply.

[0084] In this embodiment, the CRITIC method performs objective weight assignment, which takes into account the correlation between indicators and makes up for the shortcomings of the entropy weight method. According to the characteristics that the vulnerability evaluation indicators of the hydropower station operation system are difficult to quantify, the improved CRITIC method is used to replace the standard deviation with the coefficient of variation to measure the difference within the indicator and calculate the indicator weight, which takes into account both the difference of the indicator and its correlation, making the calculation of the weight more reasonable.

[0085] In this embodiment, the standard cloud evaluation model is a data model used to represent uncertainty and ambiguity, and is widely applied in fields such as artificial intelligence, data mining, and decision support. The cloud model combines fuzziness and randomness, and can effectively handle the uncertainty in complex systems, especially suitable for quantitatively describing concepts. The cloud model is mainly used to handle uncertainty problems and is a model for converting qualitative concepts and quantitative data with uncertainty, representing the uncertainty of the probability of things occurring and the knowledge boundary. This model is an extension of probability theory and fuzzy set theory. It can reflect both the randomness of qualitative descriptions and the uncertainty of samples.

[0086] The beneficial effects of the above design scheme are as follows: By collecting data information on four aspects of personnel, equipment, environment, and management of the hydropower station, based on the data information, determining the vulnerability factors of the hydropower station, establishing a vulnerability evaluation index system based on the vulnerability factors, providing a comprehensive and accurate index basis for the vulnerability evaluation of the hydropower station, based on the vulnerability evaluation index system, using the G1 method - CRITIC method for combined weighting to obtain the combined weight of the evaluation index, based on the evaluation grade division, constructing a standard cloud evaluation model in combination with the combined weight of the evaluation index and evaluating the real-time data, realizing the evaluation of the vulnerability of the hydropower station, and facilitating timely prevention.

[0087] Embodiment 2:

[0088] Based on Embodiment 1, the embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method - CRITIC method, as Figure 2 shown. In S1, collect data information on four aspects of personnel, equipment, environment, and management of the hydropower station, including:

[0089] Obtain the personnel work type information, work equipment information, hydropower station environment information, and management system information of the hydropower station;

[0090] Extract the key information that affects the vulnerability of the hydropower station from the personnel work type information, work equipment information, hydropower station environment information, and management system information as the data information.

[0091] The beneficial effects of the above design scheme are as follows: By obtaining the personnel work type information, work equipment information, hydropower station environment information, and management system information of the hydropower station, and extracting the key information that affects the vulnerability of the hydropower station from the personnel work type information, work equipment information, hydropower station environment information, and management system information as the data information, it provides a basis for constructing the vulnerability evaluation model.

[0092] Embodiment 3:

[0093] Based on Embodiment 1, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weighting of the G1 method and the CRITIC method. In S1, based on the data information, the vulnerability factors of the hydropower station are determined, including:

[0094] Obtain the direct causes of vulnerability caused by personnel, equipment, environment, and management;

[0095] Obtain the target information related to the direct cause from the data information;

[0096] Based on the target information, determine the vulnerability factors of the hydropower station.

[0097] The beneficial effect of the above design is that by obtaining the direct causes of vulnerability caused by personnel, equipment, environment, and management, obtaining the target information related to the direct cause from the data information, and determining the vulnerability factors of the hydropower station based on the target information, a comprehensive and accurate index basis is provided for the vulnerability evaluation of the hydropower station.

[0098] Embodiment 4:

[0099] Based on Embodiment 1, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weighting of the G1 method and the CRITIC method. In S2, based on the vulnerability factors, a vulnerability evaluation index system is established, including:

[0100] Perform semantic standardization on the vulnerability factors to obtain standard factors;

[0101] Based on the standard factors, establish a vulnerability evaluation index system.

[0102] The beneficial effect of the above design is that by performing semantic standardization on the vulnerability factors to obtain standard factors and establishing a vulnerability evaluation index system based on the standard factors, a comprehensive and accurate index basis is provided for the vulnerability evaluation of the hydropower station.

[0103] Embodiment 5:

[0104] Based on Embodiment 1, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weighting of the G1 method and the CRITIC method. As Figure 3 shown, in S3, based on the vulnerability evaluation index system, use the G1 method - CRITIC method for combined weighting to obtain the combined weight of the evaluation index, including:

[0105] Based on the G1 method, determine the first weight of each evaluation index in the vulnerability evaluation index system;

[0106] Based on the CRITIC method, determine the second weight of each evaluation index in the vulnerability evaluation index system;

[0107] Combine the first weight and the second weight to obtain the combined weight of the evaluation index.

[0108] The beneficial effect of the above design solution is as follows: By determining the first weight of each evaluation index in the vulnerability evaluation index system based on the G1 method, determining the second weight of each evaluation index in the vulnerability evaluation index system based on the CRITIC method, and combining and weighting the first weight and the second weight to obtain the combined weight of the evaluation index, targeted analysis of the evaluation index is realized, providing a basis for the construction of the vulnerability evaluation model and data analysis.

[0109] Example 6:

[0110] Based on Example 5, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weighting of the G1 method - CRITIC method. Determining the first weight vector of each evaluation index in the vulnerability evaluation index system based on the G1 method includes:

[0111] Based on the vulnerability evaluation index system, establish an index set, sort and set weights for each evaluation index in the index set from largest to smallest importance to obtain an index weight sequence;

[0112] Based on the index characteristics, determine the importance between the previous adjacent evaluation index and the subsequent evaluation index in the index weight sequence;

[0113] Based on the importance, calculate the first weight of the h-th evaluation index according to the following formula;

[0114]

[0115] where A n represents the first weight of the h-th evaluation index, and r i represents the importance between the (ω - 1)-th evaluation index and the ω-th evaluation index.

[0116] The beneficial effect of the above design solution is as follows: By establishing an index set based on the vulnerability evaluation index system, sorting and setting weights for each evaluation index in the index set from largest to smallest importance to obtain an index weight sequence, determining the importance between the previous adjacent evaluation index and the subsequent evaluation index in the index weight sequence based on the index characteristics, and calculating the first weight of the evaluation index based on the importance, the cumbersome calculation steps are omitted, and there is no need to repeatedly construct matrices; the consistency test is deleted, which is convenient for application.

[0117] Example 7:

[0118] Based on Example 5, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on the combination of G1 method and CRITIC method. Determining the second weight of each evaluation index in the vulnerability evaluation index system based on the CRITIC method includes:

[0119] Obtain the number m of vulnerability evaluation objects of the hydropower station, obtain the number n of evaluation indexes in the evaluation index system, construct a vulnerability evaluation matrix of the hydropower station with m rows and n columns, and normalize the vulnerability evaluation matrix of the hydropower station to obtain a standardized matrix;

[0120] Calculate the standard deviation of each evaluation index of the standardized matrix according to the following formula;

[0121]

[0122] where S j represents the standard deviation of the j-th evaluation index, x ij represents the value of the i-th row and j-th column in the standardized matrix, represents the mean value of the j-th column;

[0123] Determine the correlation coefficient between any two indexes based on the standard deviation of the evaluation indexes;

[0124] Based on the correlation coefficient, calculate the conflict A j1 of the j1-th evaluation index according to the following formula;

[0125]

[0126] where ρ j1j2 represents the correlation coefficient between the j1-th evaluation index and the j2-th evaluation index;

[0127] Based on the conflict and standard deviation of the evaluation indexes, calculate the second weight w j of the evaluation index according to the following formula;

[0128] C j =S j ×A j (j = 1, 2, 3…, n)

[0129]

[0130] where C j represents the information amount of the j-th evaluation index.

[0131] The beneficial effects of the above design are as follows: By using the improved CRITIC method for objective weight assignment, this method takes into account the correlation between indicators and makes up for the shortcomings of the entropy weight method. According to the characteristics that the vulnerability evaluation indicators of the hydropower station operation system are difficult to quantify, the improved CRITIC method is applied to replace the standard deviation with the coefficient of variation to measure the internal difference of indicators and calculate the indicator weights, which not only considers the difference of indicators but also their correlation, making the calculation of weights more reasonable.

[0132] Embodiment 8:

[0133] Based on Embodiment 5, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weight assignment of the G1 method - CRITIC method. The combined weight assignment process is performed on the first weight and the second weight to obtain the combined weight of the evaluation indicators, including:

[0134] Set the ideal value of the indicator attribute and the ideal weight assignment scheme for each evaluation indicator;

[0135] Based on the ideal value of the indicator attribute, with the principle of minimizing the distance from the actual weight assignment scheme to the ideal weight assignment scheme, construct a Lagrangian function to determine the weight assignment algorithm for combined weight assignment of the first weight and the second weight, and obtain the combined weight of the evaluation indicators based on the weight assignment algorithm.

[0136] The beneficial effects of the above design are as follows: By setting the ideal value of the indicator attribute and the ideal weight assignment scheme for each evaluation indicator; based on the ideal value of the indicator attribute, with the principle of minimizing the distance from the actual weight assignment scheme to the ideal weight assignment scheme, construct a Lagrangian function to determine the weight assignment algorithm for combined weight assignment of the first weight and the second weight, and obtain the combined weight of the evaluation indicators. Through the combined weight processing of the G1 method - CRITIC method, it is ensured that the obtained combined weight can more accurately play the role of the evaluation indicator in vulnerability judgment and provide a basis for constructing the vulnerability evaluation model.

[0137] Embodiment 9:

[0138] Based on Embodiment 1, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on combined weight assignment of the G1 method - CRITIC method. Before S4, it further includes: setting the vulnerability evaluation level based on the historical evaluation data of the power station:

[0139] From the correspondence between the historical rating results and the historical actual vulnerability hazards in the historical evaluation data of the power station, determine the matching degree between the historical rating results and the historical actual vulnerability hazards based on the correspondence;

[0140] Select the alternative historical rating results with a matching degree greater than the preset matching degree, and determine the range of the number of levels and the historical evaluation index system based on all the alternative historical rating results;

[0141] Determine the current number of levels from the range of the number of levels based on the similarity between the historical evaluation index system and the current vulnerability evaluation index system;

[0142] Obtain the target historical rating result that matches the current number of levels from the alternative historical rating results, and select the target historical rating result with the highest similarity between the historical evaluation index system and the current vulnerability evaluation index system from the target historical rating results as the initial rating result;

[0143] Obtain the old evaluation indicators in the initial historical rating result, and determine the first influence level and the first influence weight of the old evaluation indicators on the rating result;

[0144] When the first influence weight is less than the preset influence weight, determine that no first rating correction is required for the initial rating result; otherwise, based on the first influence level and the second influence weight, and in combination with the preset correction model, perform a first rating correction on the first influence level in the initial historical rating result to obtain the first corrected rating result;

[0145] Based on the current vulnerability evaluation index system, determine new evaluation indicators, and based on human experience, determine the second influence level and the second influence weight of the new evaluation indicators on the rating result;

[0146] Based on the second influence level and the second influence weight, and in combination with the preset correction model, perform a second rating correction on the second influence level in the first corrected rating result to obtain the second corrected rating result;

[0147] Based on the second corrected rating result, determine the level division of the vulnerability evaluation index system under the combined weight, and the rating criteria for each level.

[0148] In this embodiment, the current number of levels is, for example, 5, specifically high vulnerability, relatively high vulnerability, medium vulnerability, relatively low vulnerability, and low vulnerability.

[0149] In this embodiment, the old evaluation indicators in the historical rating result are the evaluation indicators that the current vulnerability evaluation index system does not have and belong to the eliminated indicators.

[0150] In this embodiment, the new evaluation indicators are the indicators that do not exist in the historical rating result but exist in the vulnerability evaluation index system and belong to the newly added indicators.

[0151] In this embodiment, the preset correction model is pre-designed based on machine learning according to historical experience and actual situations in advance.

[0152] The beneficial effects of the above design solution are as follows: By determining the number of levels based on the historical evaluation data of the power station, an accurate level basis for the classification of rating levels is provided. Then, based on the index differences between the historical rating results and the vulnerability evaluation index system, the formulation and correction of the rating criteria are carried out. Finally, the level classification under the combined weight and the rating criteria for each level are obtained, providing an accurate data basis for the construction of the vulnerability evaluation model.

[0153] Embodiment 10:

[0154] Based on Embodiment 1, an embodiment of the present invention provides a method for constructing a vulnerability evaluation model based on the combined weighting of the G1 method and the CRITIC method. In S4, based on the evaluation level classification, a standard cloud evaluation model is constructed by combining the combined weights of the evaluation indicators and the real-time data is evaluated, including:

[0155] Based on the evaluation level classification, combined with the combined weights of the evaluation indicators, the expected value, entropy, and hyperentropy of the evaluation level pair are determined;

[0156] Based on the expected value, entropy, and hyperentropy, input into MATLAB software for programming to obtain the standard cloud evaluation model corresponding to the expected value, entropy, and hyperentropy;

[0157] Based on the real-time data, combined with MATLAB software, an actual cloud map is obtained;

[0158] The actual cloud map is compared with the standard cloud evaluation model for differences, and the vulnerability evaluation result of the real-time data is determined according to the comparison result.

[0159] The beneficial effects of the above design solution are as follows: By based on the evaluation level classification, combined with the combined weights of the evaluation indicators, the expected value, entropy, and hyperentropy of the evaluation level pair are determined; based on the expected value, entropy, and hyperentropy, input into MATLAB software for programming to obtain the standard cloud evaluation model corresponding to the expected value, entropy, and hyperentropy; based on the real-time data, combined with MATLAB software, an actual cloud map is obtained; the actual cloud map is compared with the standard cloud evaluation model for differences, and the vulnerability evaluation result of the real-time data is determined according to the comparison result, realizing the construction of the vulnerability evaluation model, ensuring the efficiency and accuracy of actual detection, and realizing the intuitive display of the results, realizing the evaluation of the vulnerability of the hydropower station, and facilitating timely prevention.

[0160] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of this application document and its equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A vulnerability assessment model construction method based on the combined weighting of the G1 method and the CRITIC method, characterized in that: include: S1: Collect data information on personnel, equipment, environment and management of the hydropower station, and determine the vulnerability factors of the hydropower station based on the data information; S2: Establish a vulnerability assessment index system based on the vulnerability factors; S3: Based on the vulnerability assessment index system, the G1 method-CRITIC method is used to perform combined weighting to obtain the combined weight of the assessment index; S4: Based on the evaluation level classification, the standard cloud evaluation model is constructed in combination with the combined weights of the evaluation indicators and the real-time data is evaluated.

2. According to claim 1, a vulnerability assessment model construction method based on G1 method-CRITIC method combined weighting is characterized in that: In S1, data and information on personnel, equipment, environment and management of the hydropower station are collected, including: Obtain information on the work type of personnel at the hydropower station, work equipment, environmental information of the hydropower station, and management system information; The key information that affects the vulnerability of the hydropower station is extracted from the personnel's work type information, work equipment information, hydropower station environment information and management system information as data information.

3. According to the method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 1, it is characterized in that: In S1, based on the data information, determining the vulnerability factors of the hydropower station includes: Obtain the direct causes of vulnerability in four aspects: personnel, equipment, environment and management; Acquire target information related to the direct cause from the data information; A vulnerability factor of the hydropower station is determined based on the target information.

4. According to the method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 1, it is characterized in that: In S2, a vulnerability assessment index system is established based on the vulnerability factors, including: Performing semantic standardization on the vulnerability factors to obtain standard factors; A vulnerability assessment index system is established based on the standard factors.

5. According to the method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 1, it is characterized in that: In S3, based on the vulnerability evaluation index system, the G1 method-CRITIC method is used to perform combined weighting to obtain the combined weights of the evaluation indicators, including: Determine the first weight of each evaluation index in the vulnerability evaluation index system based on the G1 method; Determine the second weight of each evaluation indicator in the vulnerability evaluation index system based on the CRITIC method; The first weight and the second weight are combined and weighted to obtain a combined weight of the evaluation index.

6. According to claim 5, a vulnerability assessment model construction method based on G1 method-CRITIC method combined weighting is characterized in that: The method of determining the first weight vector of each evaluation index in the vulnerability evaluation index system based on the G1 method includes: Based on the vulnerability assessment index system, an index set is established, and the importance of each assessment index in the index set is sorted from large to small and the weight is set to obtain an index weight sequence; Based on the indicator characteristics, determine the importance of the adjacent previous evaluation indicator and the next evaluation indicator in the indicator weight sequence; Based on the importance, the first weight of the hth evaluation indicator is calculated according to the following formula; Among them, A n represents the first weight of the hth evaluation index, r i It indicates the importance between the ω-1th evaluation index and the ωth evaluation index.

7. The method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 5 is characterized in that: The second weight of each evaluation indicator in the vulnerability evaluation indicator system is determined based on the CRITIC method, including: The number m of vulnerability assessment objects of the hydropower station is obtained, the number n of evaluation indicators in the evaluation indicator system is obtained, a hydropower station vulnerability assessment matrix with m rows and n columns is constructed, and the hydropower station vulnerability assessment matrix is ​​normalized to obtain a standardized matrix; The standard deviation of each evaluation indicator of the standardized matrix is ​​calculated according to the following formula; Among them, S j represents the standard deviation of the jth evaluation index, x ij represents the value of the i-th row and j-th column in the standardized matrix, represents the mean of the jth column; Determine the correlation coefficient between any two indicators based on the standard deviation of the evaluation indicators; Based on the correlation coefficient, the conflict A of the j1th evaluation index is calculated according to the following formula: j1 ; Among them, ρ j1j2 represents the correlation coefficient between the j1th evaluation index and the j2th evaluation index; Based on the conflict and standard deviation of the evaluation index, the second weight w of the evaluation index is calculated according to the following formula j ; C j =S j ×A j (j=1,2,3…,n) Among them, C j Represents the information amount of the jth evaluation index.

8. The method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 5 is characterized in that: The first weight and the second weight are combined and weighted to obtain a combined weight of the evaluation index, including: Set the ideal value of the indicator attribute and the ideal weighting scheme for each evaluation indicator; Based on the ideal value of the indicator attribute and the principle of minimizing the distance between the actual weighting scheme and the ideal weighting scheme, a Lagrangian function is constructed to determine a weighting algorithm for combining the first weight and the second weight, and the combined weight of the evaluation indicator is obtained based on the weighting algorithm.

9. The method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 1 is characterized in that: The step before S4 also includes: setting a vulnerability assessment level based on historical assessment data of the power plant: Determine the matching degree between the historical rating results and the historical actual vulnerability hazards based on the corresponding relationship between the historical rating results and the historical actual vulnerability hazards in the historical evaluation data of the power station; Select alternative historical rating results with a matching degree greater than the preset matching degree, and determine the grade quantity range and historical evaluation indicator system based on all alternative historical rating results; Determining a current level number from the level number range based on the similarity between the historical evaluation index system and the current vulnerability evaluation index system; Obtain the target historical rating results that match the current rating quantity from the candidate historical rating results, and select the target historical rating results with the highest similarity between the historical evaluation index system and the current vulnerability evaluation index system as the initial rating result from the target historical rating results; Obtain old evaluation indicators in the initial historical rating results, and determine the first impact level and first impact weight of the old evaluation indicators on the rating results; When the first impact weight is less than the preset impact weight, it is determined that there is no need to perform a first rating revision on the initial rating result; otherwise, based on the first impact level and the second impact weight, combined with a preset revision model, a first rating revision is performed on the first impact level in the initial historical rating result to obtain a first revised rating result; Based on the current vulnerability assessment indicator system, determine new assessment indicators, and determine the second impact level and second impact weight of the new assessment indicators on the rating results based on human experience; Based on the second impact level and the second impact weight, in combination with a preset correction model, a second rating correction is performed on the second impact level in the first corrected rating result to obtain a second corrected rating result; Based on the second revised rating result, the grade division of the vulnerability assessment index system under the combined weight and the rating criteria under each grade are determined.

10. The method for constructing a vulnerability assessment model based on the combined weighting of the G1 method and the CRITIC method according to claim 1 is characterized in that: In S4, based on the evaluation level classification, a standard cloud evaluation model is constructed in combination with the combined weights of the evaluation indicators and the real-time data is evaluated, including: Based on the evaluation level division, combined with the combined weights of the evaluation indicators, the expected value, entropy and super entropy of the evaluation level pair are determined; Based on the expected value, entropy and hyperentropy, input the MATLAB software for programming and obtain the standard cloud evaluation model corresponding to the expected value, entropy and hyperentropy; Based on real-time data and combined with MATLAB software, the actual cloud map is obtained; The actual cloud image is compared with the standard cloud evaluation model for differences, and a vulnerability evaluation result for the real-time data is determined according to the comparison result.

Images