Hydraulic gate safety evaluation method and device, processor and storage medium

Abstract

The invention provides a hydraulic gate safety evaluation method and device, a processor and a storage medium, and relates to the technical field of gates, and the method comprises the steps: obtaining a historical index value set of a target risk index; determining an uncertainty interval and a feasible weight space corresponding to the target risk index according to the historical index value set of the target risk index; based on the feasible weight space corresponding to the target risk index, determining a comprehensive weight value corresponding to the target risk index; inputting the product of each historical index value in the historical index value set of the target risk index and the comprehensive weight value corresponding to the target risk index into a safety evaluation risk analysis model; and based on the uncertainty interval corresponding to the target risk index, outputting a risk probability corresponding to the target risk index through a safety evaluation risk analysis model. By determining the risk probability corresponding to each target risk index, the comprehensiveness and reliability of the safety evaluation of the hydraulic gate are improved.

Description

Technical Field

[0001] The present application relates to the field of gate technology, and in particular to a hydraulic gate safety evaluation method, a hydraulic gate safety evaluation device, a processor, and a storage medium. Background Art

[0002] Through the safety evaluation of hydraulic gates, potential safety hazards can be discovered in time, the use efficiency and life of hydraulic gates can be improved, and the normal operation of water conservancy projects can be guaranteed. At the same time, the safety evaluation of hydraulic gates can also provide a basis for the management and maintenance of hydraulic gates, effectively prevent accidents, and ensure the rational use of water resources and people's safety.

[0003] In related technologies, the safety of hydraulic gates is affected by many factors. In actual practice, when conducting safety evaluation of hydraulic gates, the data involved in the evaluation indicators are often not completely certain. Usually, the specific values ​​of the evaluation indicators collected at a certain moment are used to carry out safety evaluation. There is a lack of effective methods to accurately describe and deal with the uncertainty of the evaluation indicators, which may lead to uncertainty and unreliability in the evaluation results. In addition, there are many methods for weighting the various evaluation indicators of hydraulic gates, such as subjective weighting method and objective weighting method. The selection of different weighting methods may also lead to inconsistency in the evaluation results, further increasing the uncertainty of the evaluation results. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a hydraulic gate safety evaluation method, a hydraulic gate safety evaluation device, a processor and a storage medium to solve the problem that when performing safety evaluation on hydraulic gates, the reliability of the evaluation results and the comprehensiveness of the safety evaluation are reduced due to the uncertainty of the evaluation indicators.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a hydraulic gate safety evaluation method, the method comprising:

[0006] Get the historical indicator value set of the target risk indicator;

[0007] According to the historical indicator value set of the target risk indicator, determine the uncertainty interval and feasible weight space corresponding to the target risk indicator;

[0008] Based on the feasible weight space corresponding to the target risk indicator, determine the comprehensive weight value corresponding to the target risk indicator;

[0009] The product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator is input into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

[0010] In the embodiment of the present application, the uncertainty interval corresponding to the target risk indicator is determined according to the historical indicator value set of the target risk indicator, including:

[0011] Using the first n historical indicator values ​​in the historical indicator value set to train the preset initial indicator value prediction model, to obtain an intermediate indicator value prediction model;

[0012] For each historical indicator value in the historical indicator value set except the first n historical indicator values ​​and the last historical indicator value, the following steps are performed on each historical indicator value in sequence according to the order of the position in the historical indicator value set: all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value are input into the current intermediate indicator value prediction model to obtain the predicted indicator value corresponding to the historical indicator value; all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value and the historical indicator value are input into the current intermediate indicator value prediction model for model training to obtain a new intermediate indicator value prediction model; the new intermediate indicator value prediction model is used as the current intermediate indicator value prediction model to finally obtain the target indicator value prediction model;

[0013] Input all historical indicator values ​​in the historical indicator value set into the target indicator value prediction model to obtain the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set;

[0014] Determine the variance corresponding to the target risk indicator according to each historical indicator value except the first n historical indicator values ​​in the historical indicator value set and its corresponding predicted indicator value;

[0015] Determine the expectation corresponding to the target risk indicator according to the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set;

[0016] According to the variance and expectation corresponding to the target risk indicator, the uncertainty interval corresponding to the target risk indicator is determined.

[0017] In the embodiment of the present application, according to the historical indicator value set of the target risk indicator, the feasible weight space corresponding to the target risk indicator is determined, including:

[0018] Set the probability density function;

[0019] The historical indicator value set of the target risk indicator is input into the probability density function to obtain the feasible weight space corresponding to the target risk indicator.

[0020] In the embodiment of the present application, based on the feasible weight space corresponding to the target risk indicator, determining the comprehensive weight value corresponding to the target risk indicator includes:

[0021] Using the analytic hierarchy process, the subjective weight value corresponding to the target risk indicator is determined in the feasible weight space corresponding to the target risk indicator;

[0022] In the feasible weight space corresponding to the target risk indicator, the entropy weight method, the indicator conflict method and the principal component analysis method are used to determine the first objective weight value, the second objective weight value and the third objective weight value corresponding to the target risk indicator; the objective weight value corresponding to the target risk indicator is determined according to the first objective weight value, the second objective weight value and the third objective weight value;

[0023] According to the subjective weight value and objective weight value corresponding to the target risk indicator, the comprehensive weight value corresponding to the target risk indicator is determined using the game theory method based on the Nash equilibrium criterion.

[0024] In the embodiment of the present application, according to the subjective weight value and the objective weight value corresponding to the target risk indicator, a game theory method based on the Nash equilibrium criterion is used to determine the comprehensive weight value corresponding to the target risk indicator, including:

[0025] According to the subjective weight value and objective weight value corresponding to the target risk indicator, the coordination weight corresponding to the target risk indicator is determined with Nash equilibrium as the coordination target;

[0026] The particle swarm algorithm is used to solve the coordination weights corresponding to the target risk indicators, obtain the optimal linear combination, and extract the coordination weight vector of the optimal linear combination;

[0027] The coordination weight vectors are secondary fused using game theory methods to define the feasible weight space corresponding to the target risk indicator as a subspace that expands outward from the coordination weight point as the center, and the comprehensive weight value corresponding to the target risk indicator is obtained.

[0028] In an embodiment of the present application, before inputting the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model, the method further includes:

[0029] Construct a safety assessment risk analysis model based on the second-order moment method;

[0030] Based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model, including:

[0031] Based on the uncertainty interval corresponding to the target risk indicator, a first reliability index value corresponding to the target risk indicator is determined through a safety assessment risk analysis model, and according to the first reliability index value, the risk probability corresponding to the target risk indicator is determined.

[0032] In an embodiment of the present application, the method further includes:

[0033] According to the risk probability corresponding to each risk indicator of each target, determine the risk contribution rate corresponding to each risk indicator of each target.

[0034] A second aspect of the present application provides a hydraulic gate safety evaluation device, the device comprising:

[0035] A historical indicator value acquisition module is used to obtain a set of historical indicator values ​​of a target risk indicator;

[0036] A relevant data determination module is used to determine the uncertainty interval and feasible weight space corresponding to the target risk indicator based on the historical indicator value set of the target risk indicator;

[0037] A comprehensive weight determination module is used to determine the comprehensive weight value corresponding to the target risk indicator based on the feasible weight space corresponding to the target risk indicator;

[0038] The risk probability determination module is used to input the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

[0039] A third aspect of the present application provides a processor configured to execute the above-mentioned hydraulic gate safety assessment method.

[0040] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned hydraulic gate safety assessment method.

[0041] The hydraulic gate safety evaluation method, device, processor and storage medium provided by the present application quantify the uncertainty interval and feasible weight space corresponding to each of the target risk indicators, and further determine the comprehensive weight value corresponding to each of the target risk indicators. Under the constraint of defining the risk of the hydraulic gate safety evaluation as the probability of not reaching the specified level and the corresponding uncertainty interval, the risk probability corresponding to each of the target risk indicators is solved through the model, and the risk probability can more accurately reflect the safety of the hydraulic gate. The present application improves the comprehensiveness and reliability of the hydraulic gate safety evaluation by determining the risk probability corresponding to each of the target risk indicators that have a significant impact on the safety of the hydraulic gate, and effectively solves the problem that when conducting the safety evaluation of the hydraulic gate, the reliability of the evaluation results and the comprehensiveness of the safety evaluation are reduced due to the uncertainty of the evaluation indicators.

[0042] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0044] Figure 1 The flowchart of the hydraulic gate safety evaluation method according to the embodiment of the present application is schematically shown;

[0045] Figure 2 A structural block diagram of a hydraulic gate safety evaluation device according to an embodiment of the present application is schematically shown;

[0046] Figure 3 The internal structure diagram of the computer device according to the embodiment of the present application is schematically shown.

[0047] Description of Reference Numerals

[0048] A01-processor; A02-network interface; A03-internal memory; A04-display screen; A05-input device; A06-non-volatile storage medium; B01-operating system; B02-computer program. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0050] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0051] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0052] In view of the problem that when conducting safety evaluation on hydraulic gates in the related art, the reliability of the evaluation results and the comprehensiveness of the safety evaluation are reduced due to the uncertainty of the evaluation indicators, the present application provides a hydraulic gate safety evaluation method, device, processor and storage medium. The hydraulic gate safety evaluation method, device, processor and storage medium provided by the present application are described in detail through specific embodiments and implementation methods in conjunction with the accompanying drawings.

[0053] Figure 1 The schematic diagram of the process flow of the hydraulic gate safety evaluation method of the embodiment of the present application is shown schematically. Figure 1 As shown, in one embodiment of the present application, a hydraulic gate safety evaluation method is provided, the method comprising:

[0054] Step 200, obtaining a set of historical indicator values ​​of a target risk indicator.

[0055] The historical indicator value set of the target risk indicator is obtained based on the historical data of the hydraulic gate, and each historical indicator value in the historical indicator value set is arranged in the historical indicator value set in the order of generation time.

[0056] Specifically, the safety of hydraulic gates is affected by a variety of factors, and different factors have different degrees of influence on the safety of hydraulic gates. In order to improve the efficiency of the safety evaluation of hydraulic gates, before step 200, the method further includes:

[0057] Step 110, obtaining historical data of the hydraulic gate, determining all risk indicators that affect the safety of the hydraulic gate based on the historical data; and determining all target risk indicators of the hydraulic gate based on the sensitivity values ​​corresponding to each risk indicator.

[0058] Among them, the risk index represents the evaluation index that affects the safety of hydraulic gates. In this embodiment, based on the historical data of hydraulic gates, all risk indicators that affect the safety of hydraulic gates can be extracted through risk assessment tools or other methods to ensure that all risk indicators that affect the safety of hydraulic gates can be fully extracted.

[0059] In a specific implementation, the step 110 specifically includes:

[0060] Step 111: for each risk indicator, determine the sensitivity value corresponding to the risk indicator by using a perturbation-response method.

[0061] Among them, the perturbation-response method is used to determine the response of the hydraulic gate to external perturbations (disturbance). Specifically, for the determined risk index, while keeping other conditions unchanged, the value of the risk index is changed, and the change of the hydraulic gate safety index determined by the relevant mathematical model and / or engineering analysis method is the sensitivity value corresponding to the risk index.

[0062] Step 112: determine the risk indicators whose corresponding sensitivity values ​​among all risk indicators are greater than a preset sensitivity threshold as target risk indicators of the hydraulic gate.

[0063] Among them, the preset sensitivity threshold can be set according to the actual environment and historical experience. The target risk index screened based on the preset sensitivity threshold is the sensitive risk index of the hydraulic gate. Its change has a significant impact on the safety of the hydraulic gate. All target risk indicators can be combined into a risk indicator set for the hydraulic gate. In one example, the target risk indicators of the hydraulic gate include water level, flow, gate opening speed, and gate closing speed.

[0064] In this embodiment, for each target risk indicator determined in step 112, subsequent steps 400 to 800 are executed to comprehensively evaluate the safety of the hydraulic gate.

[0065] In this embodiment, step 200 obtains the historical index values ​​of the target risk index of the hydraulic gate so as to determine the data input into the safety evaluation risk analysis model later, thereby obtaining the safety evaluation result of the hydraulic gate, that is, the risk probability corresponding to each target risk index.

[0066] Step 400, determining the uncertainty interval and feasible weight space corresponding to the target risk indicator according to the historical indicator value set of the target risk indicator.

[0067] In a specific implementation, in step 400, determining the uncertainty interval corresponding to the target risk indicator according to the historical indicator value set of the target risk indicator specifically includes:

[0068] Step 411, using the first n historical indicator values ​​in the historical indicator value set to perform model training on a preset initial indicator value prediction model to obtain an intermediate indicator value prediction model.

[0069] The number of historical indicator values ​​in the historical indicator value set is m, the value of m is greater than 10, and n is greater than 0 and less than m.

[0070] Among them, the preset initial indicator value prediction model adopts a long short-term memory network (Long Short-Term Memory, LSTM) model suitable for processing and predicting time series data. Specifically, the LSTM model can learn the intrinsic pattern of time series data and make predictions of future values; the LSTM model has the characteristics of long-term memory, can effectively process long-term dependencies in time series data, and is suitable for predicting indicator values ​​with long-term trends and periodicity; the LSTM model can learn nonlinear relationships in time series data, and has good performance for complex indicator value prediction problems. Based on this, this embodiment uses the LSTM model to describe the uncertainty of the target risk indicator to predict the uncertainty interval corresponding to the target risk indicator. Of course, it can be understood that the preset initial indicator value prediction model in this embodiment can also adopt other network models suitable for predicting time series data.

[0071] Step 412, for each historical indicator value in the historical indicator value set except the first n historical indicator values ​​and the last historical indicator value, perform the following steps in sequence for each historical indicator value in the order of their positions in the historical indicator value set: input all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value into the current intermediate indicator value prediction model to obtain a predicted indicator value corresponding to the historical indicator value; input all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value and the historical indicator value into the current intermediate indicator value prediction model for model training to obtain a new intermediate indicator value prediction model; use the new intermediate indicator value prediction model as the current intermediate indicator value prediction model to finally obtain a target indicator value prediction model.

[0072] It is understandable that when the n+1th historical indicator value in the historical indicator value set is input into the current intermediate indicator value prediction model, the current intermediate indicator value prediction model at this time is the intermediate indicator value prediction model obtained in step 411. Of course, it is understandable that after all historical indicator values ​​except the last historical indicator value in the historical indicator value set are input into the model and the model is trained, the new intermediate indicator value prediction model / current intermediate indicator value prediction model obtained is the target indicator value prediction model.

[0073] Step 413: input all historical indicator values ​​in the historical indicator value set into the target indicator value prediction model to obtain the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set.

[0074] Step 414, determining the variance corresponding to the target risk indicator according to each historical indicator value except the first n historical indicator values ​​in the historical indicator value set and its corresponding predicted indicator value.

[0075] Wherein, the step 414 specifically includes:

[0076] Step 4141: for each historical indicator value in the historical indicator value set except the first n historical indicator values, a difference obtained by subtracting the historical indicator value from the predicted indicator value corresponding to the historical indicator value is determined as the prediction error corresponding to the historical indicator value.

[0077] Taking the last historical indicator value in the historical indicator value set (its serial number in the historical indicator value set is m) as an example, the relationship between the historical indicator value and its corresponding predicted indicator value and the prediction error can be expressed as:

[0078]

[0079] Among them, t represents the risk index of the tth item, R t Indicates the last historical indicator value in the historical indicator value set. Indicates the predicted index value corresponding to the last historical index value in the historical index value set, ε t Represents the prediction error corresponding to the last historical indicator value in the historical indicator value set.

[0080] Step 4142, according to each prediction error follows a normal distribution Determine the standard deviation corresponding to the target risk indicator. The calculation formula for the standard deviation is:

[0081]

[0082] Among them, ε j,t Represents the prediction error corresponding to the n+jth historical indicator value in the historical indicator value set.

[0083] Step 4143, determining the variance corresponding to the target risk indicator based on the standard deviation corresponding to the target risk indicator.

[0084] In this embodiment, the variance corresponding to the target risk indicator is the square of the standard deviation corresponding to the target risk indicator, and its calculation formula can be expressed as:

[0085]

[0086] Among them, D(R t ) represents the variance corresponding to the risk indicator of the tth item.

[0087] Step 415, determining the expectation corresponding to the target risk indicator according to the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set.

[0088] In this embodiment, the expectation corresponding to the target risk indicator is the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set, and its calculation formula can be expressed as:

[0089]

[0090] Among them, E(R t ) represents the expectation corresponding to the risk indicator of the tth item.

[0091] Step 416, determining the uncertainty interval corresponding to the target risk indicator according to the variance and expectation corresponding to the target risk indicator.

[0092] In this embodiment, the uncertainty interval corresponding to the target risk indicator is the variance and expectation corresponding to the target risk indicator, which is expressed in the form of a matrix.

[0093] In a specific implementation, in step 400, determining the feasible weight space corresponding to the target risk indicator according to the historical indicator value set of the target risk indicator specifically includes:

[0094] Step 421, setting the probability density function.

[0095] Specifically, in order to flexibly handle the uncertainty of the weight of the indicator (specifically the target risk indicator) in the process of hydraulic gate safety evaluation, this embodiment introduces the concept of feasible weight space. Among them, the feasible weight space can be represented by a probability density function, which has four possibilities, namely, the indicator weight value is uniquely determined, the indicator weight value obeys a uniform distribution in the specified space, the indicator weight value obeys any type of distribution in the specified space, and the indicator weight information is completely unknown. The following is a specific description of these four possibilities.

[0096] For the unique determination of the indicator weight value, when the indicator weight value is a deterministic value, the feasible weight space will be uniquely determined. Taking three-dimensional space as an example, when the indicator weight value is uniquely determined, the feasible weight space can be a point W (w1, w2, w3) in the three-dimensional space, where w1, w2 and w3 represent the indicator weights respectively.

[0097] For the indicator weight values ​​to be uniformly distributed in the specified space, in the safety evaluation of hydraulic gates, due to the complexity of the indicators and the differences between different methods, it is difficult to reach a consensus on the weights in the evaluation process under incomplete and uncertain information conditions. At this time, if the corresponding weights are expressed by simply determined numerical information, it may not cover the differences in the information of the indicators themselves and the methods. The spatial estimation based on weights can well express this information and avoid the loss of corresponding information. Taking three-dimensional space as an example, when the specified indicator weight values ​​are uniformly distributed in the weight space, the feasible weight space can be a hexagonal plane.

[0098] For the indicator weight values ​​to obey any type of distribution in the specified space, in addition to the above indicator weight values ​​obeying uniform distribution in the specified space, the indicator weight values ​​can also be described in a more general form, that is, the indicator weight values ​​obey any type of distribution in the specified space. Taking three-dimensional space as an example, when the indicator weight values ​​obey any type of distribution in the specified space, the feasible weight space can be an elliptical plane.

[0099] When the indicator weight information is completely unknown, it is difficult to accurately give the corresponding weight information of the indicator in the early stage of evaluation due to the influence of various factors such as its own internal knowledge and evaluation environment. At this time, the feasible weight space of the entire weight space can be searched through the idea of ​​reverse weight analysis. Taking three-dimensional space as an example, when the indicator weight information is completely unknown, the feasible weight space can be a triangular area formed by three points in three-dimensional space.

[0100] In this embodiment, for each target risk indicator, when the feasible weight space has the above four possibilities, a corresponding probability density function can be selected and set according to actual conditions.

[0101] Step 422, input the historical indicator value set of the target risk indicator into the probability density function to obtain the feasible weight space corresponding to the target risk indicator.

[0102] This embodiment determines the feasible weight space corresponding to each item of the risk index of each target, so that the comprehensive weight value corresponding to each item of the risk index of each target can be determined later.

[0103] Step 600, based on the feasible weight space corresponding to the target risk indicator, determine the comprehensive weight value corresponding to the target risk indicator.

[0104] In a specific implementation, the step 600 specifically includes:

[0105] Step 610, using the analytic hierarchy process, determine the subjective weight value corresponding to the target risk indicator in the feasible weight space corresponding to the target risk indicator.

[0106] When determining the subjective weight value corresponding to the target risk indicator, this embodiment uses the feasible weight space to impose constraints, so as to increase the rationality of the distribution of the subjective weight value.

[0107] Step 620, in the feasible weight space corresponding to the target risk indicator, use the entropy weight method, the indicator conflict method, and the principal component analysis method to determine the first objective weight value, the second objective weight value, and the third objective weight value corresponding to the target risk indicator; determine the objective weight value corresponding to the target risk indicator based on the first objective weight value, the second objective weight value, and the third objective weight value.

[0108] Among them, the first objective weight value represents the weight value corresponding to the target risk indicator determined based on the entropy weight method, the second objective weight value represents the weight value corresponding to the target risk indicator determined based on the indicator conflict method, and the third objective weight value represents the weight value corresponding to the target risk indicator determined based on the principal component analysis method.

[0109] Specifically, the second objective weight value corresponding to the target risk indicator is determined by the indicator conflict method, which specifically includes: constructing a comparison matrix for the target risk indicator, according to the comparison matrix, using the judgment analysis method to obtain the relative importance between the target risk indicator and other target risk indicators, and using the indicator conflict method to obtain the conflict between the target risk indicator and other target risk indicators, based on the relative importance and conflict between the target risk indicator and other target risk indicators, determining the second objective weight value corresponding to the target risk indicator.

[0110] Specifically, the third objective weight value corresponding to the target risk indicator is determined using the principal component analysis method, which specifically includes: using the principal component analysis method to reduce the dimension and calculate the weight of the historical indicator value set of the target risk indicator to obtain the third objective weight value corresponding to the target risk indicator.

[0111] In this embodiment, for each target risk indicator, based on the first objective weight value, the second objective weight value and the third objective weight value corresponding to the target risk indicator, the arithmetic average method or the weighted average method can be used to determine the objective weight value corresponding to the target risk indicator.

[0112] Step 630, according to the subjective weight value and the objective weight value corresponding to the target risk indicator, a game theory method based on the Nash equilibrium criterion is used to determine the comprehensive weight value corresponding to the target risk indicator.

[0113] In a specific implementation, step 630 specifically includes:

[0114] Step 631, according to the subjective weight value and the objective weight value corresponding to the target risk indicator, with Nash equilibrium as the coordination target, determine the coordination weight corresponding to the target risk indicator.

[0115] Step 632, using the particle swarm algorithm to solve the coordination weight corresponding to the target risk indicator, obtain the optimal linear combination, and extract the coordination weight vector of the optimal linear combination.

[0116] Step 633, using game theory methods to perform secondary fusion on the coordination weight vectors, so as to define the feasible weight space corresponding to the target risk indicator as a subspace that expands outward from the coordination weight point as the center, and obtain the comprehensive weight value corresponding to the target risk indicator.

[0117] Among them, in the process of hydraulic gate safety evaluation, the basic weights (i.e., subjective weight value, first objective weight value, second objective weight value and third objective weight value) obtained by different weighting methods often have certain conflicts. This embodiment introduces game theory and performs secondary fusion and aggregation of conflicting coordination weight vectors based on the Nash equilibrium criterion, thereby achieving the purpose of conflict resolution and further improving the reliability of the hydraulic gate safety evaluation results.

[0118] In one example, the basic weight set obtained by the above methods is defined as the basic weight vector Among them, w k represents the basic weight vector, k=1,2,...,L, L represents the number of weighting methods, n represents the total number of target risk indicators, It represents the weight value of the i-th target risk indicator under the k-th weighting method. Any linear combination of the basic weight vectors can be expressed as:

[0119]

[0120] Among them, α k is the linear combination coefficient and α k >0,

[0121] Taking Nash equilibrium as the coordination goal, we seek equilibrium or compromise among the basic weights obtained by different weighting methods, and finally determine the coordination weight to minimize the total deviation between it and each basic weight. In the process of determining the coordination weight, the objective function expression used is:

[0122]

[0123] Among them, α i represents the weight value of the i-th basic weight, w i represents the i-th basic weight.

[0124] The particle swarm algorithm is used to solve the coordination weight and obtain the optimal linear combination coefficient, which is (Right now Where k = 1, 2, ..., L).

[0125] Then the following formula is used to further obtain the coordination weight vector after conflict resolution:

[0126]

[0127] in,

[0128] The coordination weight vectors are secondary fused using the game theory method and aggregated into comprehensive weight values. The feasible weight space FWS can be defined as a subspace that expands outward from the coordination weight point (i.e., the position point corresponding to the coordination weight in space) as the center, which can be expressed by the formula:

[0129]

[0130] Among them, λ represents the weight uncertainty level, and its value is related to the degree of conflict between different weighting methods. w represents the weight vector, R n represents n-dimensional space, w j represents the jth weight, Indicates w j When the conflict between different weighting methods is relatively small and the coordination weights obtained by the optimization calculation are close, λ can take a smaller value; when the conflict between different weighting methods is large, λ should take a larger value to obtain a wider coverage FWS.

[0131] Step 800, input the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, output the risk probability corresponding to the target risk indicator through the safety assessment risk analysis model.

[0132] In this embodiment, according to the characteristics of hydraulic gates, the risk of hydraulic gate safety evaluation is defined as the probability that the actual safety level of the hydraulic gate cannot reach the specified safety level due to the uncertainty of the evaluation index (specifically the target risk index) and its weight. Based on this definition, for the tth evaluation index, the risk of hydraulic gate safety evaluation can be expressed as:

[0133] P ft =Prob[S t <C t ]=Prob[R t ·w t <C t ] (9)

[0134] Among them, P ft represents the risk of the t-th evaluation indicator, the Prob function represents the probability, S tDenote the score of the t-th evaluation index as C t Denote the preset safety value (i.e., the specified safety value) corresponding to the t-th evaluation index as R t Denote the index value of the t-th evaluation index as w t Denote the weight of the t-th evaluation index.

[0135] Since the First Order Second Moment (FOSM) method only requires the first two moments (i.e., the mathematical expectation and variance) of random variables to calculate reliability and risk, it is an effective risk assessment method and is applicable to complex systems. Therefore, before inputting the product of each historical index value in the historical index value set of the target risk index and the comprehensive weight value corresponding to the target risk index into the safety evaluation risk analysis model, based on the definition of the risk of the safety evaluation of hydraulic gates, this embodiment constructs a safety evaluation risk analysis model based on the FOSM method to perform risk calculation.

[0136] To better understand the application of the FOSM method in the safety evaluation of hydraulic gates, the main principle of this method is briefly introduced below.

[0137] The failure risk P of a system f is defined as:

[0138] P f = Prob(Capacity < Load) (10)

[0139] where Capacity represents the bearing capacity of the system, Load represents the load acting on the system, and Prob(Capacity < Load) represents the probability that the load acting on the system exceeds the bearing capacity.

[0140] Define the function G = Capacity - Load, then the risk can be written as P f = Prob(G < 0). The function G is a function of x1, x2,..., x n where x1, x2,..., x n are independent uncertain factors applied to the system, n represents the total number of uncertain factors, that is, G = G(x1, x2,..., x n ).

[0141] Perform Taylor expansion on the function G at the mean point and ignore the quadratic and higher-order terms, then the function G can be expressed as:

[0142]

[0143] where, represent x1,x2,...,x respectively n The mean point of .

[0144] The expectation E(G) and variance D(G) of the performance function G can be further written as:

[0145]

[0146]

[0147] Among them, E(·) means to find the expectation of ·, and D(·) means to find the variance of ·.

[0148] After obtaining the expectation and variance through the above formula, the reliability index value β can be calculated as follows:

[0149]

[0150] Assuming that the performance function G follows a normal distribution, then the risk P f It can be calculated as follows:

[0151]

[0152] Among them, f G (G) is the probability density function of the normal variable G.

[0153] Defining variables Then the performance function G can be expressed as: Risk P f It can be further calculated as follows:

[0154]

[0155] Where F(·) represents the Cumulative Distribution Function (CDF) of the standard normal variable.

[0156] Based on the principle of FOSM method, the formula of safety assessment risk analysis model is derived as follows:

[0157] The function Y t Defined as:

[0158] Y t =Y t (R t ,w t )=R t ·w t -C t (17)

[0159] Among them, R t represents the index value of the risk index of the tth item, wt represents the weight of the risk indicator of the tth item (i.e., the comprehensive weight value), C t Represents the preset safety value of the risk indicator of the tth item.

[0160] At this point, the safety assessment risk of hydraulic gates (i.e., the safety assessment risk analysis model) can be expressed as:

[0161] P f =Prob(Y t <0) (18)

[0162] Since the FOSM method is used to calculate risk, it is necessary to know the index value R of the target risk index. t and its weight w t Therefore, for the t-th target risk indicator, the risk calculation can be carried out as follows:

[0163] For simplicity, each variable is abbreviated in the derivation, specifically: y = Yt, R * =E(R t ), w * =E(w t ). Among them, E(R t )、E(w t ) represent R t 、w t At this time, the functional function Y constructed by using the FOSM method to calculate the risk t You can write:

[0164] y=y(R,w)=R·wC t (19)

[0165] Where R represents R t The corresponding vector, w represents w t The corresponding vector.

[0166] For y=y(R,w) at the mean point (R * ,w * ) and ignoring the quadratic and higher order terms, y can be written as:

[0167]

[0168] The expectation E(y) and variance D(y) of the utility function y can be further written as:

[0169]

[0170]

[0171] Among them, E(·) and E[·] both represent the expectation of ·, and D(·) and D[·] both represent the variance of ·.

[0172] Restore the abbreviated symbols y and R * and w * , functional function Y t Expected E(Y t ) and variance D(Y t ) can be written as:

[0173] E(Y t )=E(R t )·E(w t )-C t (twenty three)

[0174] D(Y t )=[E(w t )] 2 ·D(R t )+[E(R t )] 2 ·D(w t ) (twenty four)

[0175] For the t-th target risk index, its corresponding reliability index value β t and risk probability P ft It can be calculated as follows:

[0176]

[0177] P ft =F(-β t )=1-F(β t ) (26)

[0178] Optionally, after step 800, the method further includes:

[0179] Step 900, determining the risk contribution rate corresponding to each of the risk indicators of each item of the objective according to the risk probability corresponding to each of the risk indicators of each item of the objective.

[0180] In a specific implementation, step 900 specifically includes:

[0181] Step 910: Determine the sum of the risk probabilities as the total risk probability.

[0182] Step 920: For each target risk indicator, the ratio between the risk probability corresponding to the target risk indicator and the total risk probability is determined as the risk contribution rate corresponding to the target risk indicator.

[0183] This embodiment determines the risk contribution rate corresponding to each of the risk indicators of each target, so as to formulate more targeted risk management strategies and measures to reduce potential risks.

[0184] It is not difficult to see that the hydraulic gate safety evaluation method provided in this embodiment first introduces a neural network model for each target risk indicator to quantify the uncertainty interval corresponding to the target risk indicator, and then determines the feasible weight space corresponding to the target risk indicator based on the concept of feasible weight space and its four common weight forms, and then adopts a variety of weighting methods to weight the target risk indicator, combines game theory to resolve the multi-method weighting conflict and estimate the weight feasible domain, and adopts a probability distribution with spatial constraints (specifically, feasible weight space) to quantify the weight uncertainty to obtain the comprehensive weight value corresponding to the target risk indicator, and then defines the hydraulic gate safety evaluation risk as the probability of not being able to reach the specified level, and gives the corresponding model and solution method, and finally solves the risk probability corresponding to the target risk indicator under the constraint of the uncertainty interval corresponding to the target risk indicator. The calculated risk probability can more accurately reflect the safety of the hydraulic gate. This embodiment improves the comprehensiveness, reliability and scientificity of the hydraulic gate safety evaluation by determining the risk probability corresponding to each target risk indicator.

[0185] Figure 1 FIG. 1 is a flow chart of a hydraulic gate safety evaluation method in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0186] Figure 2 The structural block diagram of the hydraulic gate safety evaluation device according to the embodiment of the present application is schematically shown. Figure 2 As shown, in one embodiment of the present application, a hydraulic gate safety evaluation device is provided, the hydraulic gate safety evaluation device includes a historical index value acquisition module, a related data determination module, a comprehensive weight determination module and a risk probability determination module, wherein:

[0187] The historical indicator value acquisition module is used to obtain a set of historical indicator values ​​of a target risk indicator.

[0188] The relevant data determination module is used to determine the uncertainty interval and feasible weight space corresponding to the target risk indicator based on the historical indicator value set of the target risk indicator.

[0189] The comprehensive weight determination module is used to determine the comprehensive weight value corresponding to the target risk indicator based on the feasible weight space corresponding to the target risk indicator;

[0190] The risk probability determination module is used to input the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

[0191] In this embodiment, the relevant data determination module includes:

[0192] The model training unit is used to use the first n historical indicator values ​​in the historical indicator value set to perform model training on a preset initial indicator value prediction model to obtain an intermediate indicator value prediction model.

[0193] The model training and prediction unit is used to perform the following steps on each historical indicator value in the historical indicator value set except the first n historical indicator values ​​and the last historical indicator value in the historical indicator value set, in order of the positions in the historical indicator value set: input all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value into the current intermediate indicator value prediction model to obtain the predicted indicator value corresponding to the historical indicator value; input all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value and the historical indicator value into the current intermediate indicator value prediction model for model training to obtain a new intermediate indicator value prediction model; use the new intermediate indicator value prediction model as the current intermediate indicator value prediction model to finally obtain the target indicator value prediction model.

[0194] The model prediction unit is used to input all historical indicator values ​​in the historical indicator value set into the target indicator value prediction model to obtain the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set.

[0195] The variance determination unit is used to determine the variance corresponding to the target risk indicator according to each historical indicator value except the first n historical indicator values ​​in the historical indicator value set and its corresponding prediction indicator value.

[0196] The expectation determination unit is used to determine the expectation corresponding to the target risk indicator according to the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set.

[0197] The uncertainty interval determination unit is used to determine the uncertainty interval corresponding to the target risk indicator according to the variance and expectation corresponding to the target risk indicator.

[0198] In this embodiment, the relevant data determination module further includes:

[0199] A function determination unit, used to set a probability density function;

[0200] The feasible weight space determination unit is used to input the historical indicator value set of the target risk indicator into the probability density function to obtain the feasible weight space corresponding to the target risk indicator.

[0201] In this embodiment, the comprehensive weight determination module includes:

[0202] The subjective weight value determination unit is used to determine the subjective weight value corresponding to the target risk indicator within the feasible weight space corresponding to the target risk indicator by using the hierarchical analysis method.

[0203] The objective weight value determination unit is used to determine the first objective weight value, the second objective weight value and the third objective weight value corresponding to the target risk indicator in the feasible weight space corresponding to the target risk indicator by using the entropy weight method, the indicator conflict method and the principal component analysis method respectively; and determine the objective weight value corresponding to the target risk indicator according to the first objective weight value, the second objective weight value and the third objective weight value.

[0204] The comprehensive weight value determination unit is used to determine the comprehensive weight value corresponding to the target risk indicator according to the subjective weight value and the objective weight value corresponding to the target risk indicator, using a game theory method based on the Nash equilibrium criterion.

[0205] In this embodiment, the comprehensive weight value determining unit specifically includes:

[0206] The coordination weight determination subunit is used to determine the coordination weight corresponding to the target risk indicator based on the subjective weight value and the objective weight value corresponding to the target risk indicator, taking Nash equilibrium as the coordination target.

[0207] The coordination weight vector determination subunit is used to solve the coordination weight corresponding to the target risk indicator using the particle swarm algorithm, obtain the optimal linear combination, and extract the coordination weight vector of the optimal linear combination.

[0208] The comprehensive weight value determination subunit is used to perform secondary fusion of the coordination weight vector using the game theory method, so as to define the feasible weight space corresponding to the target risk indicator as a subspace expanding outward from the coordination weight point as the center, and obtain the comprehensive weight value corresponding to the target risk indicator.

[0209] In this embodiment, the risk probability determination module includes:

[0210] The risk probability determination unit is used to determine the first reliability index value corresponding to the target risk index through the safety assessment risk analysis model based on the uncertainty interval corresponding to the target risk index, and determine the risk probability corresponding to the target risk index according to the first reliability index value.

[0211] In this embodiment, the device further includes:

[0212] The model building module is used to build a safety assessment risk analysis model based on the second-order moment method.

[0213] In this embodiment, the device further includes:

[0214] The risk contribution rate determination module is used to determine the risk contribution rate corresponding to each of the risk indicators of each target according to the risk probability corresponding to each of the risk indicators of each target.

[0215] In this embodiment, the hydraulic gate safety evaluation device includes a processor and a memory. The historical indicator value acquisition module, the relevant data determination module, the comprehensive weight determination module and the risk probability determination module are all stored in the memory as program units, and the processor executes the above program modules stored in the memory to implement corresponding functions.

[0216] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the above hydraulic gate safety evaluation method is implemented by adjusting kernel parameters.

[0217] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0218] An embodiment of the present application provides a processor configured to execute the above-mentioned hydraulic gate safety assessment method.

[0219] An embodiment of the present application provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned hydraulic gate safety assessment method.

[0220] Figure 3 The internal structure diagram of the computer device of the embodiment of the present application is schematically shown. Figure 3As shown, in one embodiment of the present application, a computer device is provided, which may be a terminal. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a hydraulic gate safety evaluation method is implemented. The display screen A04 of the computer device may be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0221] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0222] In one embodiment, the hydraulic gate safety evaluation device provided in the present application can be implemented in the form of a computer program. The computer program can be Figure 3 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the hydraulic gate safety evaluation device, for example, Figure 2 The historical index value acquisition module, the relevant data determination module, the comprehensive weight determination module and the risk probability determination module shown in the figure. The computer program composed of each program module enables the processor to execute the steps of the hydraulic gate safety evaluation method of each embodiment of the present application described in this specification.

[0223] Figure 3 The computer device shown can be Figure 2 The historical index value acquisition module in the hydraulic gate safety evaluation device shown executes step 200, the relevant data determination module executes step 400, the comprehensive weight determination module executes step 600 and the risk probability determination module executes step 800.

[0224] The present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0225] Get the historical indicator value set of the target risk indicator;

[0226] According to the historical indicator value set of the target risk indicator, determine the uncertainty interval and feasible weight space corresponding to the target risk indicator;

[0227] Based on the feasible weight space corresponding to the target risk indicator, determine the comprehensive weight value corresponding to the target risk indicator;

[0228] The product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator is input into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

[0229] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0230] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0231] 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 comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0232] 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.

[0233] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0234] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0235] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0236] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0237] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A hydraulic gate safety assessment method, characterized in that: The method comprises: Get the historical indicator value set of the target risk indicator; According to the historical indicator value set of the target risk indicator, determine the uncertainty interval and feasible weight space corresponding to the target risk indicator; Based on the feasible weight space corresponding to the target risk indicator, determine the comprehensive weight value corresponding to the target risk indicator; The product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator is input into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

2. The method according to claim 1, characterized in that According to the historical indicator value set of the target risk indicator, the uncertainty interval corresponding to the target risk indicator is determined, including: Using the first n historical indicator values ​​in the historical indicator value set to train the preset initial indicator value prediction model, to obtain an intermediate indicator value prediction model; For each historical indicator value in the historical indicator value set except the first n historical indicator values ​​and the last historical indicator value, the following steps are performed on each historical indicator value in sequence according to the order of the position in the historical indicator value set: all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value are input into the current intermediate indicator value prediction model to obtain the predicted indicator value corresponding to the historical indicator value; all historical indicator values ​​in the historical indicator value set that are located before the historical indicator value and the historical indicator value are input into the current intermediate indicator value prediction model for model training to obtain a new intermediate indicator value prediction model; the new intermediate indicator value prediction model is used as the current intermediate indicator value prediction model to finally obtain the target indicator value prediction model; Input all historical indicator values ​​in the historical indicator value set into the target indicator value prediction model to obtain the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set; Determine the variance corresponding to the target risk indicator according to each historical indicator value except the first n historical indicator values ​​in the historical indicator value set and its corresponding predicted indicator value; Determine the expectation corresponding to the target risk indicator according to the predicted indicator value corresponding to the last historical indicator value in the historical indicator value set; According to the variance and expectation corresponding to the target risk indicator, the uncertainty interval corresponding to the target risk indicator is determined.

3. The method according to claim 1, characterized in that: According to the historical indicator value set of the target risk indicator, the feasible weight space corresponding to the target risk indicator is determined, including: Set the probability density function; The historical indicator value set of the target risk indicator is input into the probability density function to obtain the feasible weight space corresponding to the target risk indicator.

4. The method according to claim 1, characterized in that Based on the feasible weight space corresponding to the target risk indicator, determine the comprehensive weight value corresponding to the target risk indicator, including: Using the analytic hierarchy process, the subjective weight value corresponding to the target risk indicator is determined in the feasible weight space corresponding to the target risk indicator; In the feasible weight space corresponding to the target risk indicator, the entropy weight method, the indicator conflict method and the principal component analysis method are used to determine the first objective weight value, the second objective weight value and the third objective weight value corresponding to the target risk indicator; the objective weight value corresponding to the target risk indicator is determined according to the first objective weight value, the second objective weight value and the third objective weight value; According to the subjective weight value and objective weight value corresponding to the target risk indicator, the comprehensive weight value corresponding to the target risk indicator is determined using the game theory method based on the Nash equilibrium criterion.

5. The method according to claim 4, characterized in that According to the subjective weight value and objective weight value corresponding to the target risk indicator, the game theory method based on the Nash equilibrium criterion is used to determine the comprehensive weight value corresponding to the target risk indicator, including: According to the subjective weight value and objective weight value corresponding to the target risk indicator, the coordination weight corresponding to the target risk indicator is determined with Nash equilibrium as the coordination target; The particle swarm algorithm is used to solve the coordination weights corresponding to the target risk indicators, obtain the optimal linear combination, and extract the coordination weight vector of the optimal linear combination; The coordination weight vectors are secondary fused using game theory methods to define the feasible weight space corresponding to the target risk indicator as a subspace that expands outward from the coordination weight point as the center, and the comprehensive weight value corresponding to the target risk indicator is obtained.

6. The method according to claim 1, characterized in that Before inputting the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model, the method further includes: Construct a safety assessment risk analysis model based on the second-order moment method; Based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model, including: Based on the uncertainty interval corresponding to the target risk indicator, a first reliability index value corresponding to the target risk indicator is determined through a safety assessment risk analysis model, and according to the first reliability index value, the risk probability corresponding to the target risk indicator is determined.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: According to the risk probability corresponding to each risk indicator of each target, determine the risk contribution rate corresponding to each risk indicator of each target.

8. A hydraulic gate safety evaluation device, characterized in that: The device comprises: A historical indicator value acquisition module is used to obtain a set of historical indicator values ​​of a target risk indicator; A relevant data determination module is used to determine the uncertainty interval and feasible weight space corresponding to the target risk indicator based on the historical indicator value set of the target risk indicator; A comprehensive weight determination module is used to determine the comprehensive weight value corresponding to the target risk indicator based on the feasible weight space corresponding to the target risk indicator; The risk probability determination module is used to input the product of each historical indicator value in the historical indicator value set of the target risk indicator and the comprehensive weight value corresponding to the target risk indicator into the safety assessment risk analysis model; based on the uncertainty interval corresponding to the target risk indicator, the risk probability corresponding to the target risk indicator is output through the safety assessment risk analysis model.

9. A processor, characterized in that: The method is configured to execute the hydraulic gate safety assessment method according to any one of claims 1 to 7.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the hydraulic gate safety assessment method according to any one of claims 1 to 7.

Images