Power transmission and transformation project design quality multi-dimensional analysis and evaluation method and system

Abstract

The invention provides a power transmission and transformation project design quality multi-dimensional analysis and evaluation method and system, and is applied to the technical field of power transmission and transformation projects. The method comprises the following steps: taking multi-dimensional real-time input information for evaluating the design quality of the power transmission and transformation project, wherein the multi-dimensional real-time input information comprises multiple pieces of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information or power transmission and transformation project approval information; inputting the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model; and outputting an evaluation score of the power transmission and transformation project design quality based on the power transmission and transformation project design quality evaluation model. The power transmission and transformation project design quality problem is effectively evaluated, the evaluation score predicted based on the multi-dimensional input information can more effectively reflect the power transmission and transformation project design quality, and the power transmission and transformation project design level can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission and transformation engineering, and particularly to a multi-dimensional analysis and evaluation method and system for the design quality of power transmission and transformation projects. Background Art

[0002] The power system is an electric energy production and consumption system composed of power plants, power transmission and transformation lines, power supply and distribution stations, and electricity consumption. Its function is to convert the primary energy in nature into electric energy through power generation power devices, and then supply the electric energy to each user through power transmission, transformation, and distribution. To achieve this function, the power system also has corresponding information and control systems at each link and different levels to measure, adjust, control, protect, communicate, and dispatch the production process of electric energy to ensure that users obtain safe and high-quality electric energy.

[0003] Power transmission and transformation projects play a key role in connecting and transmitting electric energy in the power system, directly affecting the reliability, economy, and safety of the power system. Generally, the higher the voltage level of a power transmission and transformation project, the greater the power transmitted and the farther the transmission distance.

[0004] In order to timely discover and rectify the design quality problems of power grid projects and improve the project design quality, a design quality evaluation method is established based on the grouping and classification of design quality problems to assist in improving the overall design quality of power grid projects. Further engineering design quality management needs to be carried out. However, there is currently a lack of evaluation means for the overall design quality of power grid projects. Summary of the Invention

[0005] To overcome the above-mentioned defect that there is currently a lack of evaluation means for the overall design quality of power grid projects, the present invention provides a multi-dimensional analysis and evaluation method for the design quality of power transmission and transformation projects, and the method includes:

[0006] Obtain multi-dimensional real-time input information for evaluating the design quality of power transmission and transformation projects, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information;

[0007] Input the multi-dimensional input information into a pre-trained design quality evaluation model for power transmission and transformation projects;

[0008] Based on the design quality evaluation model for power transmission and transformation projects, output the evaluation score of the design quality of the power transmission and transformation project.

[0009] Optionally, the power transmission and transformation project review information includes one or more of the following: preliminary design review opinions of power transmission and transformation projects, construction drawing review opinions of power transmission and transformation projects, or implementation situation review opinions of power transmission and transformation projects;

[0010] The power transmission and transformation project design information includes one or more of the following: the design depth of the power transmission and transformation project, the implementation status of the power transmission and transformation project design;

[0011] The power transmission and transformation project equipment information includes: the implementation status of the power transmission and transformation project equipment;

[0012] The power transmission and transformation project approval information includes: the power transmission and transformation project has not implemented the preliminary design review document, and the power transmission and transformation project has not implemented the construction drawing review document.

[0013] Optionally, the pre-training process of the power transmission and transformation project design quality evaluation model includes:

[0014] Obtain multi-dimensional historical input information for evaluating the power transmission and transformation project design quality and the labeled evaluation scores of the multi-dimensional historical input information;

[0015] Input the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and based on the power transmission and transformation project design quality evaluation model, output the predicted evaluation scores of the multi-dimensional historical input information;

[0016] According to the labeled evaluation scores and the predicted evaluation scores, update the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model;

[0017] Train the power transmission and transformation project design quality evaluation model according to the updated initial network connection weights and the updated initial network node update thresholds.

[0018] Optionally, the power transmission and transformation project design quality evaluation model includes an input layer, a hidden layer, and an output layer, and the number of neurons in the input layer is the same as the dimension of the input information.

[0019] Optionally, the power transmission and transformation project design quality evaluation model is constructed based on a backpropagation neural network.

[0020] Optionally, the determination process of the initial network connection weights and the initial network node update thresholds includes:

[0021] Determine the initial network connection weights and the initial network node update thresholds according to the thinking evolutionary algorithm.

[0022] Optionally, the determining the initial network connection weights and the initial network node update thresholds according to the thinking evolutionary algorithm includes:

[0023] Randomly generate an initial population, the initial population includes a number of individuals, where each individual includes a set of network connection weights and network node update thresholds;

[0024] Divide the initial population into a number of sub-populations;

[0025] For each sub-group, perform a convergence operation on multiple individuals within the sub-group to determine the superior individual of the sub-group;

[0026] Perform a divergence processing operation on the superior individual of each sub-group to determine a candidate sub-group;

[0027] If the candidate sub-group meets the termination condition, determine the optimal individual in the candidate sub-group, and based on the optimal individual, determine the initial network connection weights and the initial network node update threshold;

[0028] If the candidate sub-group does not meet the termination condition, perform an evolutionary process based on the candidate sub-group to determine a number of new sub-groups until the candidate sub-group determined based on the number of new sub-groups meets the termination condition.

[0029] Optionally, the thinking evolution algorithm includes determining an optimized backpropagation MEA-BP prediction model of the thinking evolution algorithm.

[0030] On the other hand, the present invention also provides a multi-dimensional analysis and evaluation system for the design quality of a power transmission and transformation project, including:

[0031] An acquisition module for acquiring multi-dimensional real-time input information for evaluating the design quality of a power transmission and transformation project, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information;

[0032] An input module for inputting the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model;

[0033] An output module for outputting an evaluation score of the design quality of the power transmission and transformation project based on the power transmission and transformation project design quality evaluation model.

[0034] Optionally, the power transmission and transformation project review information includes one or more of the following: preliminary design review opinions of the power transmission and transformation project, construction drawing review opinions of the power transmission and transformation project, or implementation review opinions of the power transmission and transformation project;

[0035] The power transmission and transformation project design information includes one or more of the following: design depth of the power transmission and transformation project, implementation of the power transmission and transformation project design;

[0036] The power transmission and transformation project equipment information includes: implementation of the power transmission and transformation project equipment;

[0037] The power transmission and transformation project approval information includes: failure to implement the preliminary design review document of the power transmission and transformation project, failure to implement the construction drawing review document of the power transmission and transformation project.

[0038] Optionally, it further includes:

[0039] A training module, configured to obtain multi-dimensional historical input information for evaluating the design quality of a power transmission and transformation project and the marked evaluation scores of the multi-dimensional historical input information;

[0040] Input the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and based on the power transmission and transformation project design quality evaluation model, output the predicted evaluation scores of the multi-dimensional historical input information;

[0041] Update the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model according to the marked evaluation scores and the predicted evaluation scores;

[0042] Train the power transmission and transformation project design quality evaluation model according to the updated initial network connection weights and the updated initial network node update thresholds.

[0043] Optionally, the power transmission and transformation project design quality evaluation model includes an input layer, a hidden layer, and an output layer, and the number of neurons in the input layer is the same as the dimension of the input information.

[0044] Optionally, the power transmission and transformation project design quality evaluation model is constructed based on a backpropagation neural network.

[0045] Optionally, the training process is further configured to determine the initial network connection weights and the initial network node update thresholds according to the thinking evolution algorithm.

[0046] Optionally, the training process specifically includes randomly generating an initial population, where the initial population includes a number of individuals, and each individual includes a set of network connection weights and network node update thresholds; dividing the initial population into a number of sub-populations; for each sub-population, performing a convergence operation on multiple individuals within the sub-population to determine the superior individuals of the sub-population; performing a divergence operation on the superior individuals of each sub-population to determine candidate sub-populations; if the candidate sub-populations meet the termination conditions, determining the optimal individual in the candidate sub-populations, and determining the initial network connection weights and the initial network node update thresholds according to the optimal individual; if the candidate sub-populations do not meet the termination conditions, performing an evolution process according to the candidate sub-populations to determine a number of new sub-populations until the candidate sub-populations determined according to the number of new sub-populations meet the termination conditions.

[0047] Optionally, the thinking evolution algorithm includes determining a thinking evolution algorithm optimized backpropagation MEA-BP prediction model.

[0048] On the other hand, the present invention further provides a computer device, including: one or more processors;

[0049] The processor is used to store one or more programs;

[0050] When the one or more programs are executed by the one or more processors, the multi-dimensional analysis and evaluation method for the design quality of the power transmission and transformation project described in any one of the above is implemented.

[0051] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the multi-dimensional analysis and evaluation method for the design quality of the power transmission and transformation project described in any one of the above is implemented.

[0052] Compared with the prior art, the beneficial effects of the present invention are:

[0053] The present invention provides a multi-dimensional analysis and evaluation method for the design quality of a power transmission and transformation project, including: obtaining multi-dimensional real-time input information for evaluating the design quality of the power transmission and transformation project, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information; inputting the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model; and outputting an evaluation score of the design quality of the power transmission and transformation project based on the power transmission and transformation project design quality evaluation model. The present invention uses a pre-trained power transmission and transformation engineer design quality evaluation model to predict the multi-dimensional real-time input information for evaluating the design quality of the power transmission and transformation project, determine the evaluation score of the design quality of the power transmission and transformation project, can effectively evaluate and evaluate the design quality problems of the power transmission and transformation project, and the evaluation score predicted based on the multi-dimensional input information can more effectively reflect the design quality of the power transmission and transformation project, which helps to improve the design level of the power transmission and transformation project. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic flowchart of the multi-dimensional analysis and evaluation method for the design quality of the power transmission and transformation project of the present invention;

[0055] Figure 2 It is a schematic diagram of the neural network topology structure for evaluating the design quality of the power transmission and transformation project of the present invention;

[0056] Figure 3 It is a schematic diagram of the BP neural network topology structure of the present invention;

[0057] Figure 4 It is a schematic flowchart of the MEA-BP project cost prediction model of the present invention;

[0058] Figure 5 It is a schematic diagram of the structure of the multi-dimensional analysis and evaluation system for the design quality of the power transmission and transformation project of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The following further elaborates on the specific implementation manners of the present invention with reference to the accompanying drawings.

[0060] Embodiment 1:

[0061] A multi-dimensional analysis and evaluation method for the design quality of a power transmission and transformation project provided by the present invention has a process schematic diagram as Figure 1 shown, including:

[0062] Step 101: Obtain multi-dimensional real-time input information for evaluating the design quality of a power transmission and transformation project, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information.

[0063] Step 102: Input the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model.

[0064] Step 103: Based on the power transmission and transformation project design quality evaluation model, output an evaluation score of the design quality of the power transmission and transformation project.

[0065] The present invention uses a pre-trained power transmission and transformation engineer design quality evaluation model to predict the multi-dimensional real-time input information for evaluating the design quality of a power transmission and transformation project, determine the evaluation score of the design quality of the power transmission and transformation project, can effectively evaluate and evaluate the design quality problems of the power transmission and transformation project, and the evaluation score predicted based on the multi-dimensional input information can more effectively reflect the design quality of the power transmission and transformation project, which helps to improve the design level of the power transmission and transformation project.

[0066] In step 101 above, group and classify by design quality problems to divide the multi-dimensional input information for evaluating the design quality of power transmission and transformation projects. For example, the review information of power transmission and transformation projects includes one or more of the following: preliminary design review opinions of power transmission and transformation projects, construction drawing review opinions of power transmission and transformation projects, or implementation review opinions of power transmission and transformation projects. Another example is that the design information of power transmission and transformation projects includes one or more of the following: the depth of design of power transmission and transformation projects, the implementation of the design of power transmission and transformation projects. Another example is that the equipment information of power transmission and transformation projects includes: the implementation of the equipment of power transmission and transformation projects. Another example is that the approval information of power transmission and transformation projects includes: the failure to implement the preliminary design review document of power transmission and transformation projects, the failure to implement the construction drawing review document of power transmission and transformation projects. Exemplarily, the multi-dimensional input information may include the following multiple: preliminary design review opinions of power transmission and transformation projects, construction drawing review opinions of power transmission and transformation projects, implementation review opinions of power transmission and transformation projects, the depth of design of power transmission and transformation projects, the implementation of the design of power transmission and transformation projects, the implementation of the equipment of power transmission and transformation projects, the failure to implement the preliminary design review document of power transmission and transformation projects, the failure to implement the construction drawing review document of power transmission and transformation projects. In this example, the preliminary design review opinions of power transmission and transformation projects may include that the preliminary design review opinions are not closed, the construction drawing review opinions of power transmission and transformation projects may include that the construction drawing review opinions are not closed, the implementation review opinions of power transmission and transformation projects may include that the management and technical implementation standards are not in place, the depth of design of power transmission and transformation projects includes insufficient design depth, the implementation of the design of power transmission and transformation projects includes the failure to implement the general design in place, the implementation of the equipment of power transmission and transformation projects includes the failure to implement the general equipment in place, the failure to implement the preliminary design review document of power transmission and transformation projects includes the failure to implement the preliminary design approval document, and the failure to implement the construction drawing review document of power transmission and transformation projects includes the failure to implement the construction drawing approval document.

[0067] In one implementation manner, the pre-training process of the above-mentioned power transmission and transformation project design quality evaluation model includes:

[0068] Obtain multi-dimensional historical input information for evaluating the design quality of power transmission and transformation projects and the marked evaluation scores of the multi-dimensional historical input information;

[0069] Input the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and based on the power transmission and transformation project design quality evaluation model, output the predicted evaluation scores of the multi-dimensional historical input information;

[0070] According to the marked evaluation scores and the predicted evaluation scores, update the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model;

[0071] According to the updated initial network connection weights and the updated initial network node update thresholds, train the power transmission and transformation project design quality evaluation model.

[0072] The above multi-dimensional historical input information can be data regarding the design quality problems of power transmission and transformation projects. Through training based on a large amount of data on engineering design quality problems, effective evaluation and assessment can be carried out for engineering design quality problems. The information included in the multi-dimensional historical input information can refer to the above-mentioned multi-dimensional real-time input information, and the similarities will not be elaborated.

[0073] In this implementation method, a neural network topology structure is constructed according to the grouping and classification of the design quality problems of power transmission and transformation projects. The topology structure is trained according to the training process, and the obtained training model can evaluate and analyze the design quality of power transmission and transformation projects. The power transmission and transformation project design quality evaluation model can include an input layer, a hidden layer, and an output layer. The number of neurons in the input layer is the same as the dimension of the input information. For example, the number of neurons in the input layer is 8, namely the preliminary design review opinions are not finalized, the construction drawing review opinions are not finalized, the management and technical execution standards are not in place, the design depth is insufficient, the general design is not implemented in place, the general equipment is not implemented in place, the preliminary design approval documents are not executed, and the construction drawing approval documents are not executed. Another example is that the number of neurons in the hidden layer is 5, and the number of neurons in the output layer is 1, that is, the engineering design quality evaluation score. Exemplarily, the topology structure of the power transmission and transformation project design quality evaluation model is as Figure 2 shown.

[0074] Exemplarily, the power transmission and transformation project design quality evaluation model is constructed based on a backpropagation (BP, Back Propagation) neural network. The schematic diagram of the BP neural network topology structure is as Figure 3 shown. The BP neural network includes an input layer, a hidden layer, and an output layer. In the neural network topology structure diagram, X1, X2, X3 are the input values of the neural network, Y1, Y2, Y3 are the predicted values of the neural network, and each edge in the neural network has a weight value. The neural network can be regarded as a non-linear function, and the input value and the predicted value are the independent variable and the dependent variable of the function respectively. When the number of input nodes is n and the number of output nodes is m, the neural network represents the function mapping relationship from n independent variables to m dependent variables. Based on Figure 3 the shown BP neural network topology structure to construct the power transmission and transformation project design quality evaluation model, the number of neurons in the input layer, hidden layer, and output layer can be modified according to the grouping and classification of the power transmission and transformation project design quality problems to obtain the power transmission and transformation project design quality evaluation model.

[0075] The construction process of the BP neural network training model can include the following steps:

[0076] (1) Construct the BP neural network topology structure.

[0077] In this step, construct as Figure 3In the shown BP neural network topology, during the forward transmission of the data stream, the input signal is processed layer by layer from the input layer through the hidden layer until the output layer. The state of neurons in each layer only affects the state of neurons in the next layer.

[0078] (2) Training steps of the BP neural network.

[0079] Through model training in this step, the neural network is enabled with the abilities of associative memory and prediction.

[0080] 2-1) Network initialization.

[0081] Based on the system input-output sequence (X, Y), determine the number of nodes n in the input layer, the number of nodes l in the hidden layer, and the number of nodes m in the output layer of the neural network, and initialize the connection weights w ij , w jk , initialize the threshold of the hidden layer as a and the threshold of the output layer as b (for example, the initial weights and thresholds are random numbers in the interval [-0.5, 0.5]), and give the learning rate (for example, the learning rate value is 0.1) and the neuron activation function f(x). In the embodiments of the present invention, the initialized connection weights (i.e., the initial network connection weights) and thresholds (i.e., the initial network node update thresholds) can be determined based on the calculation results of the thinking evolution algorithm of the embodiments of the present invention.

[0082] 2-2) Calculation of the hidden layer output.

[0083] First, determine the number of hidden layer nodes. According to the empirical formula where h is the number of hidden layer nodes, m and n are the numbers of nodes in the input layer and output layer respectively, and a is an adjustment constant between 1 and 10.

[0084] According to the input variable x, the connection weights w ij between the input layer and the hidden layer, and the hidden layer threshold a, calculate the hidden layer output H:

[0085]

[0086] where, H j is the hidden layer output, f(x) is the hidden layer activation function, x is the input variable, and e is a constant.

[0087] 2-3) Output layer calculation.

[0088] According to the hidden layer output H, the connection weights w jk and the threshold b, calculate the prediction layer output O:

[0089]

[0090] where, O kis the output of the prediction layer, l is the number of hidden layer nodes, H j is the output of the hidden layer, w jk is the connection weight, b k is the threshold, k represents the k-th output layer, and m is the number of output layer nodes.

[0091] 2-4) Error calculation.

[0092] According to the predicted output O of the neural network and the expected output Y, calculate the prediction error e of the BP neural network:

[0093] e k = Y k - O k

[0094] where e k is the prediction error, Y k is the expected output, O k is the output of the prediction layer.

[0095] 2-5) Weight update.

[0096] Update the network connection weight w ij according to the network prediction error e, w jk :

[0097]

[0098] where w ij is the connection weight, η is the learning efficiency, H j is the output of the hidden layer, e k is the prediction error, i represents the i-th input layer, n is the number of input layer nodes, j represents the j-th hidden layer, l is the number of hidden layer nodes, and x is the input variable;

[0099] w jk = w jk + ηH j e k i = 1, 2,..., n; j = 1, 2,..., m

[0100] where w jk is the connection weight, η is the learning efficiency, H j is the output of the hidden layer, e k is the prediction error, i represents the i-th input layer, n is the number of input layer nodes, j represents the j-th output layer, and m is the number of output layer nodes.

[0101] 2-6) Threshold update.

[0102] Update the network node thresholds a and b according to the network prediction error e.

[0103]

[0104] Among them, a j is the network node threshold, η is the learning efficiency, H j is the output of the hidden layer, x is the input variable, k represents the k-th output layer, m is the number of output layer nodes, w jk is the connection weight, e k is the prediction error, j represents the j-th hidden layer, and l is the number of hidden layer nodes;

[0105] b k = b k + e k k = 1, 2,..., m

[0106] Among them, b k is the network node threshold, e k is the prediction error, k represents the k-th output layer, and m is the number of output layer nodes.

[0107] 2 - 7) Determine whether the algorithm iteration ends. If it does not end, return to step 2 - 2).

[0108] Determine whether the algorithm iteration ends according to the preset number of iterations.

[0109] It can be understood that the learning rate generally takes the value of 0.1, and the number of iterations is determined according to the size of the training set. The training objective is to minimize the variance (the sum of the squares of the model output - the actual sample value on all output nodes of the neural network is the smallest). Different combinations of learning rates and numbers of iterations can be selected, and then the value with the smallest error on the validation set is selected and determined.

[0110] During the training process of the power transmission and transformation engineering design quality evaluation model, the determination process of the initial network connection weights and the initial network node update thresholds involved includes: determining the initial network connection weights and the initial network node update thresholds according to the Mind Evolutionary Algorithm. In this method, the Mind Evolutionary Algorithm (MEA) is used to optimize the weights and thresholds of the neural network to avoid the neural network falling into local minima and improve the convergence speed.

[0111] For example, determining the initial network connection weights and the initial network node update thresholds according to the Mind Evolutionary Algorithm includes:

[0112] Randomly generate an initial population. The initial population includes several individuals, and each individual includes a set of network connection weights and network node update thresholds;

[0113] Divide the initial population into several sub - populations;

[0114] For each sub - population, perform a convergence operation on multiple individuals within the sub - population to determine the superior individual of the sub - population;

[0115] Perform a dissimilation operation on the superior individuals of each sub-group to determine a candidate sub-group;

[0116] If the candidate sub-group meets the termination condition, determine the optimal individual in the candidate sub-group, and based on the optimal individual, determine the initial network connection weights and the initial network node update threshold;

[0117] If the candidate sub-group does not meet the termination condition, perform an evolutionary process based on the candidate sub-group to determine several new sub-groups until the candidate sub-group determined based on the several new sub-groups meets the termination condition.

[0118] Optionally, the mind evolutionary algorithm includes the determination of a mind evolutionary algorithm optimized backpropagation (MEA-BP, mindevolutionary algorithm - BP) prediction model. This MEA-BP prediction model can be an MEA-BP project cost prediction model. See Figure 4 The construction process of the MEA-BP project cost prediction model can include the following steps:

[0119] (1) Initial population

[0120] MEA is a learning algorithm that realizes the evolutionary process through iterative operations. The set of all individuals in each generation of the evolutionary process is called a population. The initial population refers to after the algorithm is initialized, the individuals are randomly scattered in the solution space, and then the scores of each individual are calculated. Some individuals with high scores become the winners, and an initial population is formed with them as the center.

[0121] A population can be divided into several sub-groups. The sub-groups can be divided into two categories: superior sub-groups and temporary sub-groups. The superior sub-groups record the information of the winners in the global competition, and the temporary sub-groups record the process of the global competition.

[0122] (2) Sub-population convergence operation

[0123] The convergence operation is a process in which individuals compete to become the one with the highest score within the sub-group environment.

[0124] Randomly scatter the individuals of the new generation near the individuals with high scores in the previous generation of the sub-group according to a normal distribution, and calculate the scores of each individual according to the evaluation function. The individual with the highest calculated score becomes the new superior individual of the sub-group. The score of the new superior individual is called the score of the sub-group.

[0125] This normal distribution can be expressed as N(x,∑), where x is the center vector of the normal distribution and ∑ is the covariance matrix of the normal distribution. When each dimension variable is independent of each other, this matrix becomes a diagonal matrix. In the i-th generation of iteration, its diagonal individual is denoted as {σ id}, where d = 1, 2, ··· is the dimension of the entire solution space. During the convergence operation, the new generation of individuals is spread using a normal distribution, which is adaptively adjusted.

[0126] The formula for calculating the spread variance of the new generation of individuals is:

[0127] σ (i+1)d = c1σ id + c2δ

[0128] where σ (i+1)d is the diagonal individual of the (i + 1)-th generation, σ id is the diagonal individual of the i-th generation, c1, c2 are optional constants, and δ is the distance between the winners of two generations.

[0129] (3) Sub-population alienation operation

[0130] The alienation operation is a process in which each sub-group in the entire solution space competes to become the winner. When the sub-group is just formed, the score of the sub-group keeps increasing. If the score of the sub-group increases very slowly, it means that the sub-group is approaching maturity. If the temporary sub-group is mature and its score is not higher than the score of any sub-group with a higher score, then the sub-group has no competitive ability and should be abandoned. In non-linear numerical optimization, the individuals in the abandoned sub-group are randomly spread in the entire solution space. The method for judging the maturity of the sub-group is as follows: If the score growth of a sub-group is lower than the pre-specified ε within M consecutive generations, then the i-th generation of this sub-group is mature:

[0131] max(Δf|t = i - M + 1, i - m + 2,..., i - 1; M - 1 < i < ∞) < ε

[0132] where Δf is the score growth of the sub-group, Δf|t is the score growth of the sub-group in the t-th generation, i is the i-th generation, M is M consecutive generations, and ε is the pre-specified score threshold. This formula can be used as the judgment basis for whether the above candidate sub-group meets the termination condition. In Figure 4 , the termination condition can also include whether the current generation number is the last generation (the generation number obtained after continuous evolutionary processing).

[0133] (4) Analyze the optimal individual

[0134] When the conditions of stagnant convergence and alienation operation are met, the thinking evolution algorithm ends the optimization process. At this time, according to the coding rule, the optimal individual found is analyzed to obtain the weights and thresholds of the corresponding BP neural network.

[0135] (5) Train the BP neural network

[0136] The optimized weights and thresholds are added to the BP neural network training model as the initial weights and thresholds of the BP neural network, and the BP neural network is trained.

[0137] The following uses a specific embodiment to illustrate the embodiments of the present invention, including the following steps:

[0138] Step 1: Construct a BP neural network training model.

[0139] Step 2: Construct an MEA-BP project cost prediction model.

[0140] Step 3: Construct a BP neural network topology for the design quality of power transmission and transformation projects.

[0141] Step 4: Conduct multi-dimensional analysis and evaluation of the design quality of power transmission and transformation projects based on the BP neural network for the design quality of power transmission and transformation projects.

[0142] In this embodiment, multi-dimensional analysis and evaluation of the design quality of power transmission and transformation projects can be carried out based on the BP neural network. By means of machine learning algorithms, a neural network topology is constructed, with the classification of design quality problems as the input, to realize the multi-dimensional analysis and evaluation of the design quality of power transmission and transformation projects, so as to better evaluate the design quality of the project and thus promote the improvement of the design quality of power transmission and transformation projects.

[0143] Embodiment 2:

[0144] Based on the same inventive concept, the present invention also provides a multi-dimensional analysis and evaluation system for the design quality of power transmission and transformation projects. The structural schematic diagram is as Figure 5 shown, including:

[0145] An acquisition module for acquiring multi-dimensional real-time input information for evaluating the design quality of power transmission and transformation projects, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information;

[0146] An input module for inputting the multi-dimensional input information into a pre-trained design quality evaluation model for power transmission and transformation projects;

[0147] An output module for outputting an evaluation score of the design quality of the power transmission and transformation project based on the design quality evaluation model for power transmission and transformation projects.

[0148] In a possible implementation manner, the power transmission and transformation project review information includes one or more of the following: preliminary design review opinions of power transmission and transformation projects, construction drawing review opinions of power transmission and transformation projects, or implementation situation review opinions of power transmission and transformation projects;

[0149] The power transmission and transformation project design information includes one or more of the following: the design depth of the power transmission and transformation project, the implementation status of the power transmission and transformation project design;

[0150] The power transmission and transformation project equipment information includes: the implementation status of the power transmission and transformation project equipment;

[0151] The power transmission and transformation project approval information includes: the power transmission and transformation project has not implemented the preliminary design review document, and the power transmission and transformation project has not implemented the construction drawing review document.

[0152] In a possible implementation, it further includes:

[0153] A training module, configured to obtain multi-dimensional historical input information for evaluating the design quality of the power transmission and transformation project and the marked evaluation scores of the multi-dimensional historical input information;

[0154] Input the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and based on the power transmission and transformation project design quality evaluation model, output the predicted evaluation scores of the multi-dimensional historical input information;

[0155] According to the marked evaluation scores and the predicted evaluation scores, update the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model;

[0156] According to the updated initial network connection weights and the updated initial network node update thresholds, train the power transmission and transformation project design quality evaluation model.

[0157] In a possible implementation, the power transmission and transformation project design quality evaluation model includes an input layer, a hidden layer, and an output layer, and the number of neurons in the input layer is consistent with the dimension of the input information.

[0158] In a possible implementation, the power transmission and transformation project design quality evaluation model is constructed based on a backpropagation neural network.

[0159] In a possible implementation, the training process is further configured to determine the initial network connection weights and the initial network node update thresholds according to the thinking evolutionary algorithm.

[0160] In a possible implementation, the training process is specifically used to randomly generate an initial population, where the initial population includes a number of individuals, and each individual includes a set of network connection weights and network node update thresholds; divide the initial population into a number of sub-populations; for each sub-population, perform a convergence operation on multiple individuals within the sub-population to determine the superior individual of the sub-population; perform a divergence operation on the superior individual of each sub-population to determine a candidate sub-population; if the candidate sub-population meets the termination condition, determine the optimal individual in the candidate sub-population, and based on the optimal individual, determine the initial network connection weights and the initial network node update thresholds; if the candidate sub-population does not meet the termination condition, perform an evolution process based on the candidate sub-population to determine a number of new sub-populations until the candidate sub-population determined based on the number of new sub-populations meets the termination condition.

[0161] In a possible implementation, the thinking evolution algorithm includes determining a thinking evolution algorithm optimized backpropagation MEA-BP prediction model.

[0162] Embodiment 3:

[0163] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a multi-dimensional analysis and evaluation method for the design quality of a power transmission and transformation project in the above embodiment.

[0164] Embodiment 4:

[0165] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). A computer-readable storage medium is a memory device in a computer device, used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the steps of a multi-dimensional analysis and evaluation method for the design quality of a power transmission and transformation project in the above embodiments.

[0166] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0167] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0168] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one flow or multiple flows and / or blocksFigure 1 The functions specified in one or more boxes.

[0169] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 process or multiple processes and / or boxes Figure 1 or more boxes.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the scope of its protection. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that after reading the present invention, various changes, modifications or equivalent replacements can still be made to the specific implementation manners of the application. However, these changes, modifications or equivalent replacements are all within the scope of protection of the claims pending for approval of the application.

Claims

1. A multi - dimensional analysis and evaluation method for the design quality of power transmission and transformation projects, characterized in that, Including: Obtain multi-dimensional real-time input information for evaluating the design quality of a power transmission and transformation project, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information; Input the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model; Based on the power transmission and transformation project design quality evaluation model, output an evaluation score of the design quality of the power transmission and transformation project.

2. The method according to claim 1, characterized in that, The power transmission and transformation project review information includes one or more of the following: preliminary design review opinions of the power transmission and transformation project, construction drawing review opinions of the power transmission and transformation project, or implementation review opinions of the power transmission and transformation project; The power transmission and transformation project design information includes one or more of the following: design depth of the power transmission and transformation project, implementation of the power transmission and transformation project design; The power transmission and transformation project equipment information includes: implementation of the power transmission and transformation project equipment; Power transmission and transformation project approval information includes: failure to implement the preliminary design review document of the power transmission and transformation project, failure to implement the construction drawing review document of the power transmission and transformation project.

3. The method according to claim 1 or 2, characterized in that, The pre-training process of the power transmission and transformation project design quality evaluation model includes: Obtain multi-dimensional historical input information for evaluating the design quality of a power transmission and transformation project and the marked evaluation scores of the multi-dimensional historical input information; Input the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and based on the power transmission and transformation project design quality evaluation model, output the predicted evaluation scores of the multi-dimensional historical input information; According to the marked evaluation scores and the predicted evaluation scores, update the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model; According to the updated initial network connection weights and the updated initial network node update thresholds, train the power transmission and transformation project design quality evaluation model.

4. The method according to claim 3, characterized in that, The power transmission and transformation project design quality evaluation model includes an input layer, a hidden layer, and an output layer, and the number of neurons in the input layer is consistent with the dimension of the input information.

5. The method according to claim 4, characterized in that, The power transmission and transformation project design quality evaluation model is constructed based on a backpropagation neural network.

6. The method according to claim 3, characterized in that, The determination process of the initial network connection weights and the initial network node update thresholds includes: According to the thinking evolution algorithm, determine the initial network connection weights and the initial network node update thresholds.

7. The method according to claim 6, characterized in that, The determining the initial network connection weights and the initial network node update thresholds according to the thinking evolution algorithm includes: Randomly generate an initial population, where the initial population includes several individuals, and each individual includes a set of network connection weights and network node update thresholds; Divide the initial population into several sub-populations; For each sub-population, perform a convergence operation on multiple individuals within the sub-population to determine the superior individuals of the sub-population; Perform a dissimilation operation on the superior individuals of each sub-population to determine a candidate sub-population; If the candidate sub-population meets the termination condition, determine the optimal individual in the candidate sub-population, and according to the optimal individual, determine the initial network connection weights and the initial network node update thresholds; If the candidate sub-group does not meet the termination condition, evolutionary processing is performed based on the candidate sub-group to determine a number of new sub-groups until the candidate sub-group determined based on the number of new sub-groups meets the termination condition.

8. The method according to claim 6, characterized in that, The thinking evolutionary algorithm includes determining an optimized backpropagation MEA-BP prediction model of the thinking evolutionary algorithm.

9. A multi - dimensional analysis and evaluation system for the design quality of power transmission and transformation projects, characterized in that, It includes: An acquisition module for acquiring multi-dimensional real-time input information for evaluating the design quality of a power transmission and transformation project, where the multi-dimensional real-time input information includes multiple of power transmission and transformation project review information, power transmission and transformation project design information, power transmission and transformation project equipment information, or power transmission and transformation project approval information; An input module for inputting the multi-dimensional input information into a pre-trained power transmission and transformation project design quality evaluation model; An output module for outputting an evaluation score of the power transmission and transformation project design quality based on the power transmission and transformation project design quality evaluation model.

10. The system according to claim 9, characterized in that, The power transmission and transformation project review information includes one or more of the following: preliminary design review opinions of the power transmission and transformation project, construction drawing review opinions of the power transmission and transformation project, or implementation review opinions of the power transmission and transformation project; The power transmission and transformation project design information includes one or more of the following: design depth of the power transmission and transformation project, implementation of the power transmission and transformation project design; The power transmission and transformation project equipment information includes: implementation of the power transmission and transformation project equipment; The power transmission and transformation project approval information includes: failure to implement the preliminary design review document of the power transmission and transformation project, failure to implement the construction drawing review document of the power transmission and transformation project.

11. The system according to claim 9 or 10, wherein, It further includes: A training module for acquiring multi-dimensional historical input information for evaluating the design quality of a power transmission and transformation project and the marked evaluation scores of the multi-dimensional historical input information; Inputting the multi-dimensional historical input information into the power transmission and transformation project design quality evaluation model, and outputting the predicted evaluation scores of the multi-dimensional historical input information based on the power transmission and transformation project design quality evaluation model; Updating the initial network connection weights and the initial network node update thresholds of the power transmission and transformation project design quality evaluation model according to the marked evaluation scores and the predicted evaluation scores; Training the power transmission and transformation project design quality evaluation model according to the updated initial network connection weights and the updated initial network node update thresholds.

12. The system according to claim 11, wherein, The power transmission and transformation project design quality evaluation model includes an input layer, a hidden layer, and an output layer, and the number of neurons in the input layer is the same as the dimension of the input information.

13. The system according to claim 12, wherein, The power transmission and transformation project design quality evaluation model is constructed based on a backpropagation neural network.

14. The system according to claim 11, wherein, The training process is also used to determine the initial network connection weights and the initial network node update thresholds according to the thinking evolutionary algorithm.

15. The system according to claim 14, wherein, The training process is specifically used to randomly generate an initial population, where the initial population includes a number of individuals, and each individual includes a set of network connection weights and network node update thresholds; divide the initial population into a number of sub-populations; for each sub-population, perform a convergence operation on multiple individuals within the sub-population to determine the superior individual of the sub-population; perform a divergence operation on the superior individual of each sub-population to determine a candidate sub-population; if the candidate sub-population meets the termination condition, determine the optimal individual in the candidate sub-population, and based on the optimal individual, determine the initial network connection weights and the initial network node update thresholds; if the candidate sub-population does not meet the termination condition, perform an evolution process based on the candidate sub-population to determine a number of new sub-populations until the candidate sub-population determined based on the number of new sub-populations meets the termination condition.

16. The system according to claim 14, wherein, The thinking evolution algorithm includes determining a thinking evolution algorithm optimized backpropagation MEA-BP prediction model.

17. A computer device, wherein, Including: One or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the multi-dimensional analysis and evaluation method for the design quality of the power transmission and transformation project described in any one of claims 1 to 8 is implemented.

18. A computer-readable storage medium, wherein, There is a computer program stored thereon, and when the computer program is executed, the multi-dimensional analysis and evaluation method for the design quality of the power transmission and transformation project described in any one of claims 1 to 8 is implemented.

Images