Water conservancy project service performance improvement effect evaluation method, device and equipment

Abstract

The invention discloses a water conservancy project service performance improvement effect evaluation method, device and equipment, relates to the technical field of water conservancy projects, and is beneficial to determining water conservancy project service performance improvement effect evaluation so as to determine the effectiveness of project reinforcement and maintenance measures. Comprising the steps of constructing an evaluation index of a water conservancy project service performance improvement effect; determining importance values of the evaluation indexes based on a projection pursuit method optimized by a genetic algorithm; and evaluating the service performance improvement effect of the water conservancy project according to the importance value and a multi-dimensional normal cloud model.

Description

Technical Field

[0001] This invention relates to the field of water conservancy engineering technology, and in particular to a method, apparatus and equipment for evaluating the performance improvement effect of water conservancy projects. Background Technology

[0002] Water conservancy plays a vital role in industrial and agricultural production, water supply, flood control, tide control, and drainage. Most of my country's existing sluice gates were constructed relatively early, and the emergence of engineering defects not only prevents timely scheduling according to flood control requirements, affecting their flood control and drainage benefits, but also hinders their overall economic benefits. In particular, the failure of large and medium-sized sluice gates can cause casualties, regional ecological disasters, and significant economic losses. Therefore, it is essential to implement reinforcement projects to improve the serviceability of these defective projects as soon as possible. However, evaluating the effectiveness of these performance improvements remains a crucial issue. Summary of the Invention

[0003] In view of this, the present invention provides a method, apparatus and equipment for evaluating the performance improvement effect of water conservancy projects, which is beneficial to determining the performance improvement effect of water conservancy projects, thereby determining the effectiveness of engineering reinforcement and maintenance measures.

[0004] According to a first aspect of the present invention, a method for evaluating the performance improvement effect of a hydraulic engineering project is provided, the method comprising:

[0005] Construct evaluation indicators for improving the service performance of water conservancy projects;

[0006] The importance value of the evaluation index is determined by the projection pursuit method optimized by the genetic algorithm;

[0007] The effectiveness of improving the service performance of water conservancy projects is evaluated based on the importance values ​​and the multidimensional normal cloud model.

[0008] Preferably, the evaluation indicators for improving the service performance of the constructed water conservancy project include:

[0009] The effects of improving flood control safety, seepage safety, concrete structure safety, metal structure safety, and electrical equipment safety are used as primary evaluation indicators.

[0010] The following are considered as secondary evaluation indicators: the flood control safety improvement effect includes flow capacity and gate top elevation; the seepage safety improvement effect includes seepage prevention length, horizontal slope, and outlet slope; the concrete structure safety improvement effect includes structural stability, structural settlement, and structural bearing capacity; the metal structure safety improvement effect includes steel gates and hoists; and the electrical equipment safety improvement effect includes motors, power control cabinets, and power distribution equipment.

[0011] The structural stability includes the stability of the gate chamber and the stability of the connecting structures on both banks; the structural settlement includes the settlement of the gate chamber and the settlement of the connecting structures on both banks; the structural bearing capacity includes the bearing capacity of the base plate, the bearing capacity of the gate pier, the bearing capacity of the breast wall, the bearing capacity of the frame, the bearing capacity of the working bridge, and the bearing capacity of the traffic bridge; the steel gate includes the strength of the main beam, the strength of the longitudinal beam, and the strength of the panel; the hoist includes the gear hardness, the frame vibration, and the opening and closing force; the motor includes the insulation resistance, DC resistance, three-phase current, and three-phase voltage; and the power control cabinet includes the grounding resistance and wiring conditions as three-level evaluation indicators.

[0012] Preferably, the projection pursuit method based on genetic algorithm optimization for determining the importance value of the evaluation index includes:

[0013] Obtain a normalized sample evaluation index set, wherein the sample evaluation index set includes index values ​​corresponding to different samples and different evaluation indicators.

[0014] Construct a projection index function based on the projection pursuit method;

[0015] The importance value of the evaluation index is obtained by optimizing the projection index function using a genetic algorithm.

[0016] Preferably, the step of constructing the projection index function based on the projection pursuit method includes:

[0017] A one-dimensional projection value is constructed based on the sample evaluation index set and the projection direction;

[0018] Calculate the standard deviation and local density of the one-dimensional projection value, and construct a projection index function based on the standard deviation and local density.

[0019] Preferably, the step of optimizing the projection index function according to the genetic algorithm to obtain the importance value of the evaluation index includes:

[0020] Using the projection direction as the optimization variable and maximizing the projection index function as the solution objective, the optimal projection direction optimized based on the genetic algorithm is calculated to obtain the importance value of the evaluation index.

[0021] Preferably, the step of evaluating the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model includes:

[0022] Based on the multidimensional positive normal cloud theory, a predetermined number of cloud droplets are obtained from the multidimensional normal cloud model;

[0023] Based on the virtual cloud theory, the target expectation, target entropy, and target hyperentropy are obtained from the cloud droplets.

[0024] Preferably, before evaluating the performance improvement effect of the water conservancy project based on the importance value and the multidimensional normal cloud model, the method further includes:

[0025] Based on the multidimensional inverse normal cloud theory, a multidimensional normal cloud model is generated from the sample evaluation index set.

[0026] According to a second aspect of the present invention, a device for evaluating the performance improvement effect of hydraulic engineering is provided, the device comprising:

[0027] The module is used to construct evaluation indicators for improving the service performance of water conservancy projects;

[0028] The determination module is used to determine the importance value of the evaluation index based on the projection pursuit method optimized by the genetic algorithm;

[0029] The evaluation module is used to evaluate the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model.

[0030] According to a third aspect of this application, a storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-mentioned method for evaluating the performance improvement of water conservancy projects.

[0031] According to a fourth aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-mentioned method for evaluating the performance improvement of water conservancy projects.

[0032] By employing the above technical solution, this invention provides a method, apparatus, and equipment for evaluating the performance improvement effect of water conservancy projects. First, it constructs evaluation indicators for the performance improvement effect of water conservancy projects. Then, it determines the importance values ​​of the evaluation indicators based on a projection pursuit method optimized by a genetic algorithm. Finally, it evaluates the performance improvement effect of water conservancy projects based on the importance values ​​and a multidimensional normal cloud model. Through this invention, on the one hand, the projection pursuit method optimized by a genetic algorithm can accurately determine the importance values ​​of the evaluation indicators for use by the multidimensional normal cloud model. On the other hand, by using the multidimensional normal cloud model to handle the evaluation problem of multiple indicators with weights (i.e., the importance values ​​of the evaluation indicators) in complex systems, it can accurately reflect the performance improvement effect of water conservancy projects, thus enabling the evaluation of the effectiveness of water conservancy project maintenance and reinforcement schemes.

[0033] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of the present invention more obvious and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of this application. In the drawings:

[0035] Figure 1 A flowchart illustrating an evaluation method for improving the service performance of a water conservancy project, provided by an embodiment of the present invention, is shown.

[0036] Figure 2 A flowchart illustrating another method for evaluating the performance improvement of water conservancy projects according to an embodiment of the present invention is shown.

[0037] Figure 3 This diagram illustrates the structure of a device for evaluating the performance improvement of water conservancy projects according to an embodiment of the present invention.

[0038] Figure 4 This invention provides a schematic diagram of another device for evaluating the performance improvement of water conservancy projects according to an embodiment of the present invention.

[0039] Figure 5 This diagram illustrates an example of a system of evaluation indicators for improving the service performance of water conservancy projects, as provided in an embodiment of the present invention. Detailed Implementation

[0040] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0041] This embodiment provides a method for evaluating the performance improvement effect of water conservancy projects, such as... Figure 1 As shown, the method includes:

[0042] 101. Construct evaluation indicators for improving the service performance of water conservancy projects.

[0043] In this embodiment, a water conservancy project is a complex system, and improving its service performance is an even more complex issue. The evaluation of the effect of service performance improvement is a comprehensive and systematic analysis process. Therefore, it is decomposed into several multi-level structures with subsystems, and then evaluated in a certain order, that is, from bottom to top, so that this process can be reasonably completed.

[0044] The formulation of evaluation indicators directly affects the final evaluation results, and the concept of evaluation indicators must be clearly defined. When formulating evaluation indicators, there are generally two types: quantitative and qualitative. Quantitative evaluation indicators often require quantification using certain methods; therefore, the quantification methods should be easy to implement in practice, and the selected evaluation indicators should make full use of existing data.

[0045] The evaluation indicators can be graded, for example, the evaluation indicators include level 1, level 2 and level 3, level 1 is further subdivided into level 2, and level 2 is further subdivided into level 3.

[0046] 102. The importance value of the evaluation index is determined by the projection pursuit method optimized by the genetic algorithm.

[0047] In this embodiment, the genetic algorithm is a search algorithm that simulates the genetic and evolutionary processes in the biological world, embodying the competitive mechanism of "survival of the fittest, competition for survival, and elimination of the weak." The basic idea of ​​the genetic algorithm is to start with a randomly generated initial "population" of solutions and search for the best solution. Each solution in the population is called a "chromosome." The genetic algorithm evaluates the quality of a chromosome based on its "fitness value." The higher the fitness value, the higher the probability of selection; conversely, the lower the fitness value, the lower the probability of selection. Selected chromosomes then enter the next generation. The chromosomes in the next generation continue to generate new chromosomes, or "offspring," through genetic operations such as crossover and mutation. Finally, after several generations, the algorithm converges to the best chromosome, which is the optimal or approximate solution to the problem.

[0048] Genetic algorithms, based on natural selection and natural gene mechanisms, can solve very difficult optimization problems by simulating complex optimization processes using simple encoding techniques and genetic operators. Genetic algorithms only require the optimization problem to be computable, overcoming limitations imposed by factors such as whether the problem structure is linear, continuous, differentiable, unimodal, or noisy. Furthermore, they are not bound by the form of the optimization criterion function or the number of optimization variables, and have no special requirements for the search space (such as convexity or connectivity). Guided by the fitness function value, they can perform an adaptive global search within the search space, resulting in a simple operation but rich computational results.

[0049] Genetic algorithm optimization is a novel optimization method that simulates intelligent processes. Compared with conventional optimization methods, the result of genetic algorithm optimization is a set of good solutions rather than a single solution, which provides users of the algorithm with a choice of options. Therefore, genetic algorithm optimization is particularly suitable for dealing with complex system evaluation problems.

[0050] The standard genetic algorithm is a commonly used method in engineering. Let the parameter optimization problem of the model be:

[0051]

[0052] sta j ≤c j ≤b j (j = 1, 2, ..., p)

[0053] Where: f — optimization criterion function

[0054] C = {c j — The model has p parameters (optimization variables) to be optimized;

[0055] [a j ,b j ]—c j The initial range of change (search range);

[0056] X—the N-dimensional input vector of the model;

[0057] Y—M-dimensional input vector of the model;

[0058] F—General nonlinear model, i.e., F:R N →R M ;

[0059] || ||——Normal number;

[0060] q—a real constant, such as q=1 for the least squares criterion, q=2 for the least squares criterion, etc., which can be determined according to the actual modeling requirements.

[0061] Projection pursuit is a new type of multidimensional data analysis method. It is an effective exploratory analysis method for processing and analyzing high-dimensional data, especially high-dimensional data from non-normal population distributions. Its basic idea is to project high-dimensional data onto a low-dimensional (1-3 dimension) subspace through some combination. By maximizing (minimizing) a certain projection index, the projection that can reflect the structure or characteristics of high-dimensional data can be found. The data structure is then analyzed in the low-dimensional space to achieve the purpose of studying and analyzing high-dimensional data.

[0062] The projection index function is constructed by projection pursuit method, and the optimal projection direction corresponding to the maximum projection index function is obtained by genetic algorithm. The optimal projection direction corresponds to the optimal weight of each evaluation index, which is the importance value of each evaluation index.

[0063] 103. Evaluate the performance improvement effect of water conservancy projects based on the importance values ​​and the multidimensional normal cloud model.

[0064] In this embodiment, the multidimensional normal cloud model is used to process the evaluation problem of multiple indicators and weights (that is, the importance values ​​of the evaluation indicators) in complex systems, which can accurately reflect the improvement effect of the service performance of water conservancy projects.

[0065] The final evaluation of the performance improvement effect of water conservancy projects is determined based on the primary, secondary, and tertiary evaluation indicators. For example, the evaluation value of the indicator is a real value on the closed interval [0, 1], and it is stipulated that the larger the score value, the better the condition of the indicator, that is, the better the performance improvement effect of the water conservancy project.

[0066] Table 1 shows the evaluation criteria for improving the service performance of water conservancy projects.

[0067] Table 1:

[0068]

[0069]

[0070] This invention provides a method, apparatus, and equipment for evaluating the performance improvement effect of water conservancy projects. First, it constructs evaluation indicators for the performance improvement effect of water conservancy projects. Then, it determines the importance values ​​of the evaluation indicators based on a projection pursuit method optimized by a genetic algorithm. Finally, it evaluates the performance improvement effect of water conservancy projects based on the importance values ​​and a multidimensional normal cloud model. Through this invention, on the one hand, the projection pursuit method optimized by a genetic algorithm can accurately determine the importance values ​​of the evaluation indicators for use in a multidimensional normal cloud model. On the other hand, by using a multidimensional normal cloud model to handle the evaluation problem of multiple indicators with weights (i.e., the importance values ​​of the evaluation indicators) in complex systems, it can accurately reflect the performance improvement effect of water conservancy projects, thus enabling the evaluation of the effectiveness of water conservancy project maintenance and reinforcement schemes.

[0071] Furthermore, as a refinement and extension of the specific implementation methods described above, and to fully illustrate the specific implementation process in this embodiment, another method for evaluating the performance improvement effect of water conservancy projects is provided, such as... Figure 2 As shown, the method includes:

[0072] 201. The effects of improving flood control safety, seepage safety, concrete structure safety, metal structure safety, and electrical equipment safety will be used as primary evaluation indicators.

[0073] 202. The following are considered as secondary evaluation indicators: the flood control safety improvement effect including flow capacity and gate top elevation; the seepage safety improvement effect including seepage prevention length, horizontal slope, and outlet slope; the concrete structure safety improvement effect including structural stability, structural settlement, and structural bearing capacity; the metal structure safety improvement effect including steel gates and hoists; and the electrical equipment safety improvement effect including motors, power control cabinets, and power distribution equipment.

[0074] 203. The structural stability, including the stability of the gate chamber and the stability of the connecting structures on both banks; the structural settlement, including the settlement of the gate chamber and the settlement of the connecting structures on both banks; the structural bearing capacity, including the bearing capacity of the base plate, the bearing capacity of the gate pier, the bearing capacity of the breast wall, the bearing capacity of the frame, the bearing capacity of the working bridge, and the bearing capacity of the traffic bridge; the steel gate, including the strength of the main beam, the strength of the longitudinal beam, and the strength of the panel; the hoist, including the gear hardness, the frame vibration, and the opening and closing force; the motor, including the insulation resistance, DC resistance, three-phase current, and three-phase voltage; and the power control cabinet, including the grounding resistance and wiring conditions, are used as the third-level evaluation indicators.

[0075] For steps 201-203 of the embodiment, as follows Figure 5 As shown, flood control safety improvement effect, seepage safety improvement effect, concrete structure safety improvement effect, metal structure safety improvement effect and electrical equipment safety improvement effect are used as primary evaluation indicators. According to the definition and characteristics of the primary indicators, the primary indicators are further divided into several secondary indicators. Similarly, the secondary indicators are further divided into several tertiary indicators. In this way, a total of thirteen secondary indicators and twenty-two tertiary indicators are divided to construct the evaluation indicators for service performance improvement effect.

[0076] 204. Obtain the normalized sample evaluation index set, wherein the sample evaluation index set includes the index values ​​corresponding to different samples and different evaluation indicators.

[0077] For this embodiment, the original sample evaluation index set without normalization is: {x * (i,j)|i=1,2,…,n,j=1,2,…,p}, where x * (i,j) represents the index value corresponding to the j-th evaluation index of the i-th sample, where n and p are the number of samples (sample size) and the number of evaluation indicators, respectively. To eliminate the dimensions of each evaluation index and unify the range of variation of each evaluation index, the values ​​of each evaluation index can be normalized first to obtain the normalized sample evaluation index set x(i,j), specifically:

[0078]

[0079] 205. Construct the projection index function based on the projection pursuit method.

[0080] In this embodiment, the construction of the projection index function based on the projection pursuit method includes: constructing a one-dimensional projection value based on the sample evaluation index set and the projection direction; calculating the standard deviation and local density of the one-dimensional projection value; and constructing the projection index function based on the standard deviation and local density.

[0081] Among them, the projection pursuit method integrates the sample evaluation index set x(i,j) of p-dimensional data into a single value. Let z(i) be the one-dimensional projection value along the projection direction, i.e.:

[0082]

[0083] Then, classification is performed based on the one-dimensional scatter plot of the one-dimensional projection values ​​{z(i)|i=1,2,…,n}, where, Let z be a unit-length vector. When considering the comprehensive projection index values, the distribution characteristics of the one-dimensional projection value z(i) should be such that the local projections are as dense as possible, ideally clustered into several point groups, while the overall projection point groups are as dispersed as possible. Therefore, the projection index function is expressed as:

[0084]

[0085] Among them, S z D is the standard deviation of the one-dimensional projected value z(i); z Let z(i) be the local density of the one-dimensional projection value, i.e.:

[0086]

[0087] In the formula, E(z) is the average value of the one-dimensional projection values ​​{z(i)|i=1,2,…,n}; R is the window radius of the local density. Its selection should ensure that the average number of projection points included within the window is not too small, avoiding excessive deviation in the moving average, while also preventing it from becoming too high as n increases. R can be determined experimentally, and its range is as follows: Generally, 0.1 times S can be taken. z r(i,j) represents the distance between samples, r(i,j)=|z(i)-z(j)|, u(t) is a unit step function, its function value is 1 when t≥0; its function value is 0 when t>0.

[0088] 206. Optimize the projection index function using a genetic algorithm to obtain the importance value of the evaluation index.

[0089] In this embodiment, the step of optimizing the projection index function according to the genetic algorithm to obtain the importance value of the evaluation index includes: using the projection direction as the optimization variable and maximizing the projection index function as the solution objective, calculating the optimal projection direction optimized by the genetic algorithm to obtain the importance value of the evaluation index.

[0090] Given a sample evaluation index set for each index value, the projection index function... Only according to the projection direction The projection direction changes with the data structure, reflecting different features. The optimal projection direction is the one that maximizes the exposure of a certain type of feature structure in the high-dimensional data. Therefore, the optimal projection direction can be estimated by solving the problem of maximizing the projection index function, i.e.:

[0091]

[0092] This is a This is a complex nonlinear optimization problem involving optimizing variables.

[0093] Then, the optimization results are solved. Specifically, the genetic algorithm toolbox that comes with MATLAB can be used to write an M-file of the function to be optimized and the constraints according to the actual problem. By setting various genetic parameters, the optimal projection direction based on the genetic algorithm optimization is calculated, thereby obtaining the importance value of each evaluation index.

[0094] 207. Evaluate the performance improvement effect of water conservancy projects based on the importance values ​​and the multidimensional normal cloud model.

[0095] In this embodiment, before evaluating the performance improvement effect of the water conservancy project based on the importance value and the multidimensional normal cloud model, the method further includes: generating a multidimensional normal cloud model from the sample evaluation index set based on the multidimensional inverse normal cloud theory. The evaluation of the performance improvement effect of the water conservancy project based on the importance value and the multidimensional normal cloud model includes: obtaining a preset number of cloud droplets from the multidimensional normal cloud model based on the multidimensional forward normal cloud theory; and obtaining the target expectation, target entropy, and target hyperentropy from the cloud droplets based on virtual cloud theory.

[0096] Among them, the multidimensional inverse normal cloud theory:

[0097] The multidimensional inverse normal cloud model can transform quantitative data into qualitative concepts. This is achieved through an inverse normal cloud generator based on statistical principles. The multidimensional inverse normal cloud generator (whose function is to calculate a multidimensional normal cloud model from known sample data, that is, to reverse-engineer the fuzzy patterns behind the data from disordered data, and these fuzzy patterns are represented using numerical features) calculates as follows:

[0098] Input: Sample evaluation index set: drop(x) 1i x 2i , ..., x ni (i = 1, 2, ..., N)

[0099] Output: Digital features of a multidimensional normal cloud model (Ex1, Ex2, ..., Ex n ,En1,En2,…,En n He1, He2, ..., He nEach of these three indicators corresponds to one of the three numerical characteristics.

[0100] The specific calculation process from input to output is as follows:

[0101] (1) According to x i Calculate the mean of the sample evaluation index set Get what you expect

[0102] (2) Calculate the absolute central distance of the sample evaluation index set. make Obtain the entropy En;

[0103] (3) Calculate the variance of the sample evaluation index set. make Find the hyperentropy He.

[0104] It should be noted that the multidimensional normal cloud model is represented using numerical features. The multidimensional normal cloud model is used to characterize the significant randomness and fuzziness present, as well as the relationship between them. It is described qualitatively and quantitatively, with three data points representing the model's features: expectation (Ex), representing the spatial distribution of the data; entropy (En), representing the degree of uncertainty; and hyperentropy (He), used to represent the uncertainty of entropy, i.e., the entropy of entropy. The multidimensional normal cloud model assumes that the model follows a normal distribution in space.

[0105] Among them, the multidimensional positive normal cloud theory:

[0106] The multidimensional normal cloud model considers the influence of several indicators, can reflect multidimensional qualitative concepts, and has a relatively fast computation speed. Its relevant definitions are as follows:

[0107] First, since the theory of multidimensional positive normal clouds can only be applied to normal clouds, this prerequisite judgment is necessary. Specifically, let U{X1,X2,…,X… n} is an n-dimensional quantitative universe of discourse, and C is U{X1,X2,…,X}. n Qualitative concepts on}, if quantitative values ​​follow a sequence x(x1, x2, ..., x... n )~N(Ex(Ex1, Ex2, …, Ex n ),En'(En1',En2',...,En n ') 2 ); where En'(En1', En2', ..., En n ')~N(En(En1, En2,...,En n ), He(He1, He2, ..., He n ) 2 En' follows a normal distribution; furthermore, x(x1, x2, ..., x...) nThe degree of certainty for C is:

[0108]

[0109] Then x(x1, x2, ..., x) n The distribution of ) on U is an n-dimensional normal cloud.

[0110] Then, the calculation method of the multidimensional positive normal cloud generator (whose function is to generate new sample data from the known digital features of the multidimensional normal cloud model, that is, from the multidimensional normal cloud model, and this new sample data is the cloud droplet) is as follows:

[0111] Input: Digital features of a multidimensional normal cloud model (Ex1, Ex2, ..., Ex n ,En1,En2,…,En n He1, He2, ..., He n The goal is to generate cloud droplets, and the number of cloud droplets is required to be a preset number, N.

[0112] Output: drop(x) 1i x 2i , ..., x ni μ i (i = 1, 2, ..., N)

[0113] The specific calculation process from input to output is as follows:

[0114] (1) Generate an expected value En(En1,En2,…,En) n ), with variance He(He1,He2,…,He) n ) 2 n-dimensional normally distributed random numbers En'(En1', En2', ..., En) n ');

[0115] (2) Generate an expected value Ex(Ex1,Ex2,…,Ex) n ), with variance En'(En1', En2', ..., En). n ') 2 n-dimensional normally distributed random numbers x(x1, x2, ..., xn) n );

[0116] (3) Calculation

[0117] (4) Let drop(x) 1i x 2i , ..., x ni μ i Let (x) be a cloud droplet, where (x) 1i x 2i , ..., xni ) represents the corresponding value of the qualitative concept in this instance, μ i For (x) 1i x 2i , ..., x ni The degree of quantitative change;

[0118] (5) Repeat the above steps until N cloud droplets are generated, where N is the preset number.

[0119] As another implementation, the above-mentioned multidimensional normal cloud model digital features (Ex1,Ex2,...,Ex) n ,En1,En2,…,En n He1, He2, ..., He n The formula for calculating the expected value Ex in () is as follows:

[0120] Ex = (C min +C max ) / 2

[0121] In the formula: C min C max These are the upper and lower boundary values ​​for the corresponding level (for example, Table 1 includes four levels, each with corresponding upper and lower boundary values). For (-∞, C max ] or [C min In the case of (+∞), the default boundary is determined based on the measured values.

[0122] The above multidimensional normal cloud model digital features (Ex1, Ex2, ..., Ex n ,En1,En2,…,En n He1, He2, ..., He n The formula for calculating the entropy En is:

[0123] En = Ex max / 3

[0124] Where: Ex max This refers to the maximum expected value of a certain indicator across different levels, i.e., Ex1, Ex2, ..., Ex n The maximum value in.

[0125] The above multidimensional normal cloud model digital features (Ex1, Ex2, ..., Ex n ,En1,En2,…,En n He1, He2, ..., He n The superentropy He is assigned a value based on the entropy En. A larger En value corresponds to a larger He value, generally 0.01≤He≤0.1.

[0126] Virtual cloud theory states that by calculating the digital characteristics of a base cloud model (referred to as the base cloud), a cloud model with new digital characteristics is obtained. This can be divided into two types: floating clouds and integrated clouds. Floating clouds are suitable when the correlation between base clouds is weak, while integrated clouds are suitable when there is some correlation between them. The construction method of the floating cloud virtualized from n base clouds after considering weights (i.e., importance values) is shown in the following formula, yielding the target expectation Ex. 目标 Target entropy En 目标 With target hyperentropy He 目标 :

[0127]

[0128] The construction method of the virtual integrated cloud based on n base clouds after considering weights, i.e., importance values, is shown in the following formula:

[0129]

[0130] Where: n—the number of base clouds;

[0131] ω i —The weight corresponding to the i-th base cloud (that is, the i-th evaluation index) is the importance value.

[0132] In summary: (1) The projection pursuit method based on genetic algorithm optimization is more reasonable and reliable in determining the weights of evaluation indicators.

[0133] (2) The multidimensional normal cloud model accurately reflects the performance improvement effect of water conservancy projects, and therefore can be used to evaluate the effect of water conservancy project maintenance and reinforcement schemes.

[0134] (3) In the past, there was no good method for evaluating the effectiveness of measures to improve the service performance of water conservancy projects. The evaluation method provided in the above embodiments effectively solves this problem and is conducive to promoting the construction of a scientific evaluation system for water conservancy project maintenance and reinforcement schemes.

[0135] This invention provides a method, apparatus, and equipment for evaluating the performance improvement effect of water conservancy projects. First, it constructs evaluation indicators for the performance improvement effect of water conservancy projects. Then, it determines the importance values ​​of the evaluation indicators based on a projection pursuit method optimized by a genetic algorithm. Finally, it evaluates the performance improvement effect of water conservancy projects based on the importance values ​​and a multidimensional normal cloud model. Through this invention, on the one hand, the projection pursuit method optimized by a genetic algorithm can accurately determine the importance values ​​of the evaluation indicators for use in a multidimensional normal cloud model. On the other hand, by using a multidimensional normal cloud model to handle the evaluation problem of multiple indicators with weights (i.e., the importance values ​​of the evaluation indicators) in complex systems, it can accurately reflect the performance improvement effect of water conservancy projects, thus enabling the evaluation of the effectiveness of water conservancy project maintenance and reinforcement schemes.

[0136] Furthermore, as Figure 1 and Figure 2 The specific implementation of the method shown in this invention provides a device for evaluating the performance improvement effect of water conservancy projects, such as... Figure 3 As shown, the device includes: a construction module 31, a determination module 32, and an evaluation module 33;

[0137] Module 31 is used to construct evaluation indicators for improving the service performance of water conservancy projects;

[0138] The determination module 32 is used to determine the importance value of the evaluation index based on the projection pursuit method optimized by the genetic algorithm;

[0139] Evaluation module 33 is used to evaluate the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model.

[0140] Accordingly, in order to construct evaluation indicators for the performance improvement of water conservancy projects, module 31 is constructed. Specifically, it can be used to take the improvement effects of flood control safety, seepage safety, concrete structure safety, metal structure safety, and electrical equipment safety as primary evaluation indicators. The improvement effects of flood control safety include flow capacity and gate top elevation; the improvement effects of seepage safety include seepage prevention length, horizontal slope, and outlet slope; the improvement effects of concrete structure safety include structural stability, structural settlement, and structural bearing capacity; the improvement effects of metal structure safety include steel gates and hoists; and the improvement effects of electrical equipment safety include electrical... The motor, power control cabinet, and power distribution equipment are used as secondary evaluation indicators. The structural stability, including the stability of the gate chamber and the stability of the connecting structures on both banks, the structural settlement, including the settlement of the gate chamber and the settlement of the connecting structures on both banks, the structural bearing capacity, including the bearing capacity of the base plate, the bearing capacity of the gate pier, the bearing capacity of the breast wall, the bearing capacity of the frame, the bearing capacity of the working bridge, and the bearing capacity of the traffic bridge, the steel gate, including the strength of the main beam, the strength of the longitudinal beam, and the strength of the panel, the hoist, including the gear hardness, frame vibration, and opening and closing force, the motor, including the insulation resistance, DC resistance, three-phase current, and three-phase voltage, and the power control cabinet, including the grounding resistance and wiring conditions, are used as tertiary evaluation indicators.

[0141] Accordingly, in order to determine the importance value of the evaluation index using the projection pursuit method optimized by the genetic algorithm, the determination module 32 includes: an acquisition unit 321, a construction unit 322, and an optimization unit 323;

[0142] The acquisition unit 321 can be specifically used to acquire a normalized sample evaluation index set, wherein the sample evaluation index set includes index values ​​corresponding to different samples and different evaluation indicators.

[0143] The construction unit 322 can be specifically used to construct a projection index function based on the projection pursuit method;

[0144] The optimization unit 323 can be specifically used to optimize the projection index function according to the genetic algorithm to obtain the importance value of the evaluation index.

[0145] Accordingly, in order to construct a projection index function based on the projection pursuit method, the construction unit 322 can be used to construct a one-dimensional projection value based on the sample evaluation index set and the projection direction; calculate the standard deviation and local density of the one-dimensional projection value; and construct the projection index function based on the standard deviation and local density.

[0146] Accordingly, in order to optimize the projection index function according to the genetic algorithm and obtain the importance value of the evaluation index, the optimization unit 323 can be specifically used to calculate the optimal projection direction based on the genetic algorithm optimization with the projection direction as the optimization variable and the maximization of the projection index function as the solution objective, so as to obtain the importance value of the evaluation index.

[0147] Accordingly, in order to evaluate the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model, the evaluation module 33 can be used to obtain a preset number of cloud droplets from the multidimensional normal cloud model based on the multidimensional positive normal cloud theory; and to obtain the target expectation, target entropy and target hyperentropy from the cloud droplets based on the virtual cloud theory.

[0148] In specific application scenarios, a device for evaluating the performance improvement of water conservancy projects, such as... Figure 4 As shown, it also includes: a generation module 34, specifically used to generate a multidimensional normal cloud model from the sample evaluation index set based on the multidimensional inverse normal cloud theory.

[0149] It should be noted that other corresponding descriptions of the functional units involved in the water conservancy project service performance improvement effect evaluation device provided in this embodiment can be found in the following references. Figures 1 to 2 The corresponding description will not be repeated here.

[0150] Based on the above, Figures 1 to 2 Accordingly, this embodiment also provides a storage medium, which may be volatile or non-volatile, storing a computer program that, when executed by a processor, implements the above-described method. Figures 1 to 2 The method for evaluating the performance improvement of water conservancy projects is shown.

[0151] Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present invention.

[0152] Based on the above, Figures 1 to 2 The method shown and Figure 3 , Figure 4 To achieve the above objectives, this embodiment also provides a computer device, which includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the above-described virtual device embodiment. Figures 1 to 2 The method for evaluating the performance improvement of water conservancy projects is shown.

[0153] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0154] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0155] The storage medium may also include an operating network communication module. An operating system is a program that manages the hardware and software resources of the aforementioned computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used for communication between the various components within the storage medium, as well as for communication with other hardware and software within the information processing device.

[0156] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware.

[0157] This invention provides a method, apparatus, and equipment for evaluating the performance improvement effect of water conservancy projects. First, it constructs evaluation indicators for the performance improvement effect of water conservancy projects. Then, it determines the importance values ​​of the evaluation indicators based on a projection pursuit method optimized by a genetic algorithm. Finally, it evaluates the performance improvement effect of water conservancy projects based on the importance values ​​and a multidimensional normal cloud model. Through this invention, on the one hand, the projection pursuit method optimized by a genetic algorithm can accurately determine the importance values ​​of the evaluation indicators for use in a multidimensional normal cloud model. On the other hand, by using a multidimensional normal cloud model to handle the evaluation problem of multiple indicators with weights (i.e., the importance values ​​of the evaluation indicators) in complex systems, it can accurately reflect the performance improvement effect of water conservancy projects, thus enabling the evaluation of the effectiveness of water conservancy project maintenance and reinforcement schemes.

[0158] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or they can be located in one or more apparatuses different from this embodiment, with corresponding changes. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0159] The serial numbers used above are for descriptive purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosures are merely a few specific implementation scenarios of the present invention; however, the present invention is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A method for evaluating the performance improvement effect of water conservancy projects, characterized in that, The method includes: Construct evaluation indicators for improving the service performance of water conservancy projects; The importance value of the evaluation index is determined by the projection pursuit method optimized by the genetic algorithm; The effectiveness of improving the service performance of water conservancy projects is evaluated based on the importance values ​​and the multidimensional normal cloud model.

2. The method according to claim 1, characterized in that, The evaluation indicators for improving the service performance of water conservancy projects include: The effects of improving flood control safety, seepage safety, concrete structure safety, metal structure safety, and electrical equipment safety are used as primary evaluation indicators. The following are considered as secondary evaluation indicators: the flood control safety improvement effect includes flow capacity and gate top elevation; the seepage safety improvement effect includes seepage prevention length, horizontal slope, and outlet slope; the concrete structure safety improvement effect includes structural stability, structural settlement, and structural bearing capacity; the metal structure safety improvement effect includes steel gates and hoists; and the electrical equipment safety improvement effect includes motors, power control cabinets, and power distribution equipment. The structural stability includes the stability of the gate chamber and the stability of the connecting structures on both banks; the structural settlement includes the settlement of the gate chamber and the settlement of the connecting structures on both banks; the structural bearing capacity includes the bearing capacity of the base plate, the bearing capacity of the gate pier, the bearing capacity of the breast wall, the bearing capacity of the frame, the bearing capacity of the working bridge, and the bearing capacity of the traffic bridge; the steel gate includes the strength of the main beam, the strength of the longitudinal beam, and the strength of the panel; the hoist includes the gear hardness, the frame vibration, and the opening and closing force; the motor includes the insulation resistance, DC resistance, three-phase current, and three-phase voltage; and the power control cabinet includes the grounding resistance and wiring conditions as three-level evaluation indicators.

3. The method according to claim 1, characterized in that, The projection pursuit method based on genetic algorithm optimization determines the importance value of the evaluation index, including: Obtain a normalized sample evaluation index set, wherein the sample evaluation index set includes index values ​​corresponding to different samples and different evaluation indicators. Construct a projection index function based on the projection pursuit method; The importance value of the evaluation index is obtained by optimizing the projection index function using a genetic algorithm.

4. The method according to claim 3, characterized in that, The construction of the projection index function based on the projection pursuit method includes: A one-dimensional projection value is constructed based on the sample evaluation index set and the projection direction; Calculate the standard deviation and local density of the one-dimensional projection value, and construct a projection index function based on the standard deviation and local density.

5. The method according to claim 3, characterized in that, The step of optimizing the projection index function using a genetic algorithm to obtain the importance value of the evaluation index includes: Using the projection direction as the optimization variable and maximizing the projection index function as the solution objective, the optimal projection direction optimized based on the genetic algorithm is calculated to obtain the importance value of the evaluation index.

6. The method according to claim 3, characterized in that, The evaluation of the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model includes: Based on the multidimensional positive normal cloud theory, a predetermined number of cloud droplets are obtained from the multidimensional normal cloud model; Based on the virtual cloud theory, the target expectation, target entropy, and target hyperentropy are obtained from the cloud droplets.

7. The method according to claim 6, characterized in that, Before evaluating the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model, the method further includes: Based on the multidimensional inverse normal cloud theory, a multidimensional normal cloud model is generated from the sample evaluation index set.

8. A device for evaluating the performance improvement effect of water conservancy projects, characterized in that, The device includes: The module is used to construct evaluation indicators for improving the service performance of water conservancy projects; The determination module is used to determine the importance value of the evaluation index based on the projection pursuit method optimized by the genetic algorithm; The evaluation module is used to evaluate the performance improvement effect of water conservancy projects based on the importance value and the multidimensional normal cloud model.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the evaluation method for improving the service performance of water conservancy projects as described in any one of claims 1 to 7.

10. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the evaluation method for improving the service performance of water conservancy projects as described in any one of claims 1 to 7.

Images