Method and device for evaluating environmental protection monitoring capability of power grid

Abstract

The application provides a kind of power grid environmental protection monitoring ability evaluation method and device, belongs to environmental protection monitoring technical field.The method includes: obtaining the score data that multiple experts score the importance degree and overall importance degree of each environmental protection monitoring ability evaluation index, according to the score data, establish initial matrix;The covariance matrix of initial matrix is calculated, and according to each eigenvalue of covariance matrix, the corresponding eigenvector is selected to establish feature matrix;According to the feature matrix, the dimensionality of initial matrix is reduced to obtain the final matrix;According to the final matrix, the weight of each environmental protection monitoring ability evaluation index is calculated using the preset linear regression algorithm;Based on the weight and the historical data corresponding to each environmental protection monitoring ability evaluation index in the power grid project to be evaluated, the environmental protection monitoring ability evaluation result of the power grid project to be evaluated is determined.The environmental protection monitoring ability of power grid enterprise or project can be objectively and accurately evaluated.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method and apparatus for evaluating the environmental monitoring capabilities of power grids. Background Technology

[0002] The environmental protection work of the power grid faces multiple challenges, including stricter regulatory requirements, higher work standards, and heavier corporate responsibilities. The national strategy for ecological civilization construction and people's environmental awareness have become the norm. The national and local legal and policy systems are continuously improving, and a regulatory model of simplified approval, strong supervision, and strict accountability has been fully established. The environmental responsibilities of power grid companies are constantly being strengthened, placing higher demands on their environmental protection capabilities.

[0003] Environmental monitoring capabilities are a crucial safeguard for power grid companies in responding to external regulatory risks, and a key factor in implementing comprehensive supervision and improving the effectiveness of environmental protection work. In small and medium-sized construction projects of power grid companies, it is often necessary to quickly assess the environmental monitoring capabilities of the projects in order to conduct environmental management and remediation. Therefore, objective and effective assessment methods are extremely important.

[0004] In relevant evaluation methods, the weights of various indicators are generally determined using the equal weighting method or principal component analysis. However, the equal weighting method does not consider the individual factors, making it difficult to objectively assess environmental monitoring capabilities; the principal component analysis method ignores secondary factors, resulting in an incomplete weight allocation and making it difficult to accurately assess environmental monitoring capabilities. Summary of the Invention

[0005] This invention provides a method and apparatus for evaluating the environmental monitoring capabilities of power grids, so as to objectively and accurately evaluate the environmental monitoring capabilities of power grid enterprises or projects.

[0006] In a first aspect, embodiments of the present invention provide a method for evaluating the environmental monitoring capabilities of a power grid, comprising:

[0007] We obtained scoring data from multiple experts who rated the importance and overall importance of various environmental monitoring capability evaluation indicators, and established an initial matrix based on the scoring data.

[0008] Calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors based on the eigenvalues ​​of the covariance matrix to establish the feature matrix;

[0009] Based on the feature matrix, the initial matrix is ​​reduced in dimensionality to obtain the final matrix;

[0010] Based on the final matrix, the weights of each environmental monitoring capability evaluation indicator are calculated using a pre-set linear regression algorithm.

[0011] Based on the weights and historical data corresponding to the environmental monitoring capability evaluation indicators of the power grid project to be evaluated, the environmental monitoring capability evaluation results of the power grid project to be evaluated are determined.

[0012] In one possible implementation, based on the eigenvalues ​​of the covariance matrix, corresponding eigenvectors are selected to construct the feature matrix, including:

[0013] Select a preset number of feature vectors corresponding to feature values ​​from smallest to largest as target feature vectors, where the preset number is less than the number of experts;

[0014] Arrange the target feature vectors according to the magnitude of their feature values ​​to create a feature matrix.

[0015] In one possible implementation, the preset quantity is determined as follows:

[0016] according to Determine the preset quantity;

[0017] In the formula, k represents the preset number, σ represents the standard deviation of the normal distribution corresponding to each eigenvalue of the covariance matrix, and m represents the number of experts corresponding to the obtained scoring data.

[0018] In one possible implementation, an initial matrix is ​​constructed based on the assigned data, including:

[0019] Based on the mean and standard deviation of the assigned scores for each environmental monitoring capability evaluation indicator, the assigned scores for each environmental monitoring capability evaluation indicator are standardized; and based on the mean and standard deviation of the assigned scores for the overall importance, the assigned scores for the overall importance are standardized.

[0020] For each environmental monitoring capability evaluation indicator and its overall importance, the standardized scoring data is subjected to zero-mean processing to obtain the standard scoring data corresponding to each environmental monitoring capability evaluation indicator and its overall importance.

[0021] Based on the standard scoring data, an initial matrix is ​​established. The last column of the initial matrix corresponds to the overall importance, and each of the remaining columns corresponds to a different environmental monitoring capability evaluation index. Each row of the initial matrix corresponds to a different expert.

[0022] In one possible implementation, the covariance matrix of the initial matrix is ​​calculated by:

[0023] according to Calculate the covariance matrix of the initial matrix;

[0024] In the formula, C represents the covariance matrix, m represents the number of experts corresponding to the obtained scoring data, and X represents the initial matrix.T This represents the transpose of the initial matrix.

[0025] In one possible implementation, the final matrix includes the final matrix of indicators corresponding to each environmental monitoring capability evaluation indicator and the overall final matrix corresponding to the overall importance.

[0026] Based on the final matrix, a pre-defined linear regression algorithm is used to calculate the weights of each environmental monitoring capability evaluation indicator, including:

[0027] According to θ=(Q T Q) -1 Q T Y, calculate the weight of each environmental monitoring capability evaluation indicator;

[0028] In the formula, θ represents the set of weights for environmental monitoring capability evaluation indicators, θ=(θ1,θ2,θ3,...,θ n ), θ j Let Q represent the weight of the j-th environmental monitoring capability evaluation indicator, and let Q represent the final indicator matrix. T Y represents the transpose of the final index matrix, and Y represents the overall final matrix.

[0029] In one possible implementation, the environmental monitoring capability evaluation result of the power grid project under evaluation is determined based on the weights and historical data corresponding to each environmental monitoring capability evaluation indicator in the project under evaluation, including:

[0030] according to Calculate the environmental monitoring capability evaluation results of the power grid project to be evaluated;

[0031] In the formula, G represents the environmental monitoring capability evaluation result of the power grid project to be evaluated, and θ j G represents the weight of the j-th environmental monitoring capability evaluation indicator. j This represents the historical data corresponding to the j-th environmental monitoring capability evaluation indicator in the power grid project to be evaluated, and n represents the total number of environmental monitoring capability evaluation indicators.

[0032] In one possible implementation, the primary indicators in the various environmental monitoring capability evaluation indicators include monitoring equipment indicators, monitoring factor indicators, personnel allocation indicators, system formulation indicators, and risk management indicators;

[0033] The secondary indicators of monitoring equipment include indicators of the completeness of monitoring tools, the processing capacity of monitoring equipment, the maintenance of monitoring equipment, the age of monitoring equipment, and the scientific nature of monitoring methods.

[0034] The secondary indicators of the monitoring factor indicators include water factor indicators, atmospheric factor indicators, noise factor indicators, electromagnetic factor indicators, and solid waste factor indicators.

[0035] The secondary indicators for personnel allocation include personnel division of labor indicators, personnel environmental protection training indicators, and personnel professional title level indicators;

[0036] The secondary indicators for system development include environmental monitoring system indicators, work instruction development indicators, and monitoring management method development indicators;

[0037] The secondary indicators of risk management indicators include indicators of sudden environmental changes.

[0038] Secondly, embodiments of the present invention provide a power grid environmental monitoring capability evaluation device, comprising:

[0039] The acquisition module is used to acquire the scoring data obtained by multiple experts on the importance and overall importance of various environmental monitoring capability evaluation indicators, and to establish an initial matrix based on the scoring data;

[0040] The calculation module is used to calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors based on the eigenvalues ​​of the covariance matrix to establish the feature matrix; based on the feature matrix, the initial matrix is ​​reduced in dimension to obtain the final matrix; based on the final matrix, a preset linear regression algorithm is used to calculate the weights of each environmental monitoring capability evaluation index.

[0041] The evaluation module is used to determine the evaluation results of the environmental monitoring capabilities of the power grid project under evaluation based on the weights and historical data corresponding to the various environmental monitoring capability evaluation indicators in the project under evaluation.

[0042] In one possible implementation, the computation module is specifically used for:

[0043] Select a preset number of feature vectors corresponding to feature values ​​from smallest to largest as target feature vectors, where the preset number is less than the number of experts;

[0044] Arrange the target feature vectors according to the magnitude of their feature values ​​to create a feature matrix.

[0045] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0046] This invention employs the eigenvalues ​​of the covariance matrix to select corresponding eigenvectors, establishing a feature matrix. The initial matrix is ​​then dimensionality-reduced using this feature matrix, filtering out biased data from different experts and ensuring the accuracy of the final scores while simultaneously reducing data dimensionality. Based on the final matrix, a pre-defined linear regression algorithm is used to calculate the weights of each environmental monitoring capability evaluation indicator. This allows for the objective and accurate determination of the weights of each environmental monitoring capability evaluation indicator in the power grid environmental element monitoring capability evaluation, based on expert scores. Furthermore, when determining the environmental monitoring capability evaluation result of the power grid project under evaluation based on the weights of these indicators, the stability and reproducibility of each evaluation result are ensured, guaranteeing the validity and reliability of the evaluation results for the power grid project. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating the implementation of the power grid environmental monitoring capability evaluation method provided in this embodiment of the invention.

[0049] Figure 2 This is a schematic diagram of the normal distribution of feature values ​​provided in an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of the power grid environmental monitoring capability evaluation device provided in an embodiment of the present invention. Detailed Implementation

[0051] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0052] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0053] Figure 1 The implementation flowchart of the power grid environmental monitoring capability evaluation method provided in this embodiment of the invention is described in detail below:

[0054] Step S101: Obtain the scoring data obtained by multiple experts on the overall importance of various environmental monitoring capability evaluation indicators, and establish an initial matrix based on the scoring data.

[0055] In this embodiment, the experts are professionals in the field of environmental monitoring with sufficient environmental knowledge. Specifically, the scoring data obtained from expert evaluation can be obtained through a questionnaire.

[0056] For example, m experts score the importance of n pre-set environmental monitoring capability evaluation indicators, and also score the overall importance of all environmental monitoring capability evaluation indicators, resulting in assigned scores. The assigned scores for the n environmental monitoring capability evaluation indicators can be represented as D1 = {d...} 11 ,d 12 ,d 13 ,…,d ij ,…,d mn}, where d ij This represents the score given by the i-th expert to the j-th environmental monitoring capability evaluation indicator; the overall importance of all environmental monitoring capability evaluation indicators is scored, and the resulting score data can be D2={d1,d2,d3,…,d i ,…,d m}, where d i This represents the data from the i-th expert's score on the overall importance of the environmental monitoring capability evaluation indicators.

[0057] Step S102: Calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors based on the eigenvalues ​​of the covariance matrix to establish the feature matrix.

[0058] In this embodiment, the covariance matrix is ​​a symmetric matrix, and the data on its diagonal represent the variance of the assigned scores for each dimension, namely, each environmental monitoring capability evaluation indicator and its overall importance. A feature matrix is ​​then established using eigenvalues ​​and eigenvectors. This feature matrix can be built based on the magnitude of the variance to filter the assigned scores from different experts, selecting scores with smaller variances to determine the weights of each indicator.

[0059] Step S103: Based on the feature matrix, reduce the dimensionality of the initial matrix to obtain the final matrix.

[0060] In this embodiment, the initial matrix is ​​reduced in dimensionality by using the feature matrix. This reduces the data dimensionality while retaining data with small variance, thereby ensuring the consistency of the scoring data for each expert and improving data stability.

[0061] Specifically, the last column of the initial matrix corresponds to the overall importance level, and each of the remaining columns corresponds to a different environmental monitoring capability evaluation index. Each row of the initial matrix corresponds to a different expert, meaning the initial matrix is ​​an m-row, n+1-column matrix. With a preset number of experts (k), the characteristic matrix is ​​a k-row, n+1-column matrix. Correspondingly, the final matrix obtained is J = PX, where J represents the final matrix, P represents the characteristic matrix, and X represents the initial matrix.

[0062] In addition, the final matrix includes data corresponding to each environmental monitoring capability evaluation indicator and data corresponding to the overall importance. Therefore, the final matrix can be split to obtain the final matrix of each environmental monitoring capability evaluation indicator and the overall final matrix corresponding to the overall importance.

[0063] Step S104: Based on the final matrix, use a preset linear regression algorithm to calculate the weights of each environmental monitoring capability evaluation indicator.

[0064] In this embodiment, a preset linear regression algorithm is used to preset the true values ​​of the weights of each environmental monitoring capability evaluation indicator, and then the optimal weights of each environmental monitoring capability evaluation indicator are objectively calculated by solving the algorithm.

[0065] Step S105: Based on the weights and historical data corresponding to the environmental monitoring capability evaluation indicators of the power grid project to be evaluated, determine the environmental monitoring capability evaluation result of the power grid project to be evaluated.

[0066] Optional, according to Calculate the environmental monitoring capability evaluation results of the power grid project to be evaluated;

[0067] In the formula, G represents the environmental monitoring capability evaluation result of the power grid project to be evaluated, and θ j G represents the weight of the j-th environmental monitoring capability evaluation indicator. j This represents the historical data corresponding to the j-th environmental monitoring capability evaluation indicator in the power grid project to be evaluated, and n represents the total number of environmental monitoring capability evaluation indicators.

[0068] This invention, through the eigenvalues ​​of the covariance matrix, selects corresponding eigenvectors to establish a feature matrix. The initial matrix is ​​then dimensionality-reduced using this feature matrix, filtering out specific data from different experts and ensuring the accuracy of the final scores while simultaneously reducing data dimensionality. Based on the final matrix, a pre-defined linear regression algorithm is used to calculate the weights of various environmental monitoring capability evaluation indicators. This allows for the objective and accurate determination of the weights of each environmental monitoring capability evaluation indicator in the power grid environmental monitoring capability evaluation, based on expert scores. Furthermore, when determining the environmental monitoring capability evaluation result of the power grid project under evaluation based on the weights of these indicators, the stability and reproducibility of each evaluation result are ensured, guaranteeing the validity and reliability of the evaluation results for the power grid project.

[0069] In one possible implementation, step S102 selects the corresponding eigenvectors based on the eigenvalues ​​of the covariance matrix to establish the feature matrix, which can be detailed as follows:

[0070] Select a preset number of feature vectors corresponding to feature values ​​from smallest to largest as target feature vectors, where the preset number is less than the number of experts;

[0071] Arrange the target feature vectors according to the magnitude of their feature values ​​to create a feature matrix.

[0072] In this embodiment, the eigenvalues ​​actually indicate the magnitude of the variance. By arranging and selecting eigenvectors according to the eigenvalues ​​from smallest to largest, the eigenvectors corresponding to smaller variances can be retained. A smaller variance also indicates that the scores given by different experts are similar, and the resulting scores are more reliable.

[0073] In addition, the target feature vectors are arranged by row, and the number of rows in the feature matrix is ​​a preset number.

[0074] Optionally, the method for determining the preset quantity is as follows:

[0075] according to Determine the preset quantity;

[0076] In the formula, k represents the preset number, σ represents the standard deviation of the normal distribution corresponding to each eigenvalue of the covariance matrix, and m represents the number of experts corresponding to the obtained scoring data.

[0077] In this embodiment, see Figure 2 The diagram shows the normal distribution of eigenvalues. The eigenvalues ​​and their corresponding eigenvectors follow a normal distribution. The shaded area represents the larger eigenvalues, which correspond to data with greater bias. Therefore, the eigenvalues ​​corresponding to the area outside the shaded area are selected.

[0078] Furthermore, it is obvious that there cannot be half an eigenvector, and the number of corresponding eigenvectors is an integer. Therefore, k is chosen as an integer obtained by rounding down.

[0079] In one possible implementation, step S101, which establishes an initial matrix based on the assigned data, can be detailed as follows:

[0080] Based on the mean and standard deviation of the assigned scores for each environmental monitoring capability evaluation indicator, the assigned scores for each environmental monitoring capability evaluation indicator are standardized; and based on the mean and standard deviation of the assigned scores for the overall importance, the assigned scores for the overall importance are standardized.

[0081] For each environmental monitoring capability evaluation indicator and its overall importance, the standardized scoring data is subjected to zero-mean processing to obtain the standard scoring data corresponding to each environmental monitoring capability evaluation indicator and its overall importance.

[0082] Based on the standard scoring data, an initial matrix is ​​established. The last column of the initial matrix corresponds to the overall importance, and each of the remaining columns corresponds to a different environmental monitoring capability evaluation index. Each row of the initial matrix corresponds to a different expert.

[0083] In this embodiment, by standardizing and zero-meaning the assigned data, each data point in the initial matrix can be placed near zero, thus avoiding the influence of different dimensions on subsequent calculation results and reducing calculation errors.

[0084] Specifically, according to The scoring data corresponding to each environmental monitoring capability evaluation indicator is standardized; where z ij This represents the standardized data corresponding to the score assigned by the i-th expert to the j-th environmental monitoring capability evaluation indicator. Let represent the mean of the scores assigned to the j-th environmental monitoring capability evaluation indicator, where s j Let $\begin{pmatrix} \ ...

[0085] according to The scoring data for the overall importance of environmental monitoring capability evaluation indicators are standardized; where z i This represents the standardized data corresponding to the score assigned by the i-th expert regarding the overall importance of the environmental monitoring capability evaluation indicators. This represents the mean of the assigned scores corresponding to the overall importance. s represents the standard deviation of the assigned scores corresponding to the overall importance, where,

[0086] According to x ij =z ij -μ j The scoring data corresponding to each environmental monitoring capability evaluation indicator is processed to zero mean; where x ij This represents the standard scoring data, μ, representing the score assigned by the i-th expert to the j-th environmental monitoring capability evaluation indicator after zero-mean normalization. j This represents the mean of the assigned scores for the j-th environmental monitoring capability evaluation indicator after standardization.

[0087] According to x i =z i -μ, is used to normalize the scores for the overall importance of environmental monitoring capability evaluation indicators to zero; where x i This represents the assigned score data corresponding to the overall importance of the environmental monitoring capability evaluation indicators given by the i-th expert after zero-mean normalization, i.e., the standard assigned score data. μ represents the mean of the assigned score data corresponding to the overall importance after standardization.

[0088] Therefore, the initial matrix can be represented as:

[0089] Accordingly, the final matrix can be represented as: Where J represents the final matrix, the final index matrix can be expressed as: The overall final matrix can be represented as y represents the data corresponding to the score given by the i-th expert to the j-th environmental monitoring capability evaluation indicator in the final matrix. i This represents the data corresponding to the overall importance score given by the i-th expert to the environmental monitoring capability evaluation indicators in the final matrix.

[0090] In one possible implementation, step S102, which calculates the covariance matrix of the initial matrix, can be detailed as follows:

[0091] according to Calculate the covariance matrix of the initial matrix;

[0092] In the formula, C represents the covariance matrix, m represents the number of experts corresponding to the obtained scoring data, and X represents the initial matrix. T This represents the transpose of the initial matrix.

[0093] In this embodiment, the last column of the initial matrix corresponds to the overall importance level, and each of the remaining columns corresponds to a different environmental monitoring capability evaluation index. Each row of the initial matrix corresponds to a different expert, that is, the initial matrix is ​​a matrix with m rows and n+1 columns.

[0094] Since the subsequent process involves dimensionality reduction of the expert-assigned data, rather than dimensionality reduction of the environmental monitoring capability evaluation indicators, therefore, according to Calculate the covariance matrix of the initial matrix; the resulting covariance matrix is ​​an m-row, m-column matrix.

[0095] In one possible implementation, the final matrix includes the final matrix of indicators corresponding to each environmental monitoring capability evaluation indicator and the overall final matrix corresponding to the overall importance.

[0096] Step S104, based on the final matrix, uses a preset linear regression algorithm to calculate the weights of each environmental monitoring capability evaluation indicator, which can be detailed as follows:

[0097] According to θ=(Q T Q) -1 Q T Y, calculate the weight of each environmental monitoring capability evaluation indicator;

[0098] In the formula, θ represents the set of weights for environmental monitoring capability evaluation indicators, θ=(θ1,θ2,θ3,...,θ n ), θ j Let Q represent the weight of the j-th environmental monitoring capability evaluation indicator, and let Q represent the final indicator matrix. T Y represents the transpose of the final index matrix, and Y represents the overall final matrix.

[0099] In this embodiment, the optimal weights of each environmental monitoring capability evaluation index are calculated by a preset linear regression algorithm. This allows for the prior preset of the actual weights of each environmental monitoring capability evaluation index, followed by the solution of the weights, thereby objectively calculating the optimal weights of each environmental monitoring capability evaluation index. These optimal weights serve as the weights of each index in the environmental monitoring capability evaluation, ensuring the accuracy and stability of the weights of each environmental monitoring capability evaluation index.

[0100] Optionally, assume that the weights of each environmental monitoring capability evaluation indicator are θ=(θ1,θ2,θ3,…,θ n ), then we have In the formula, y represents the objective function established using a preset linear regression algorithm. Let θj represent the importance of the j-th environmental monitoring capability evaluation indicator, θ0 represent the bias term, ε represent the error term, and h0(x) represent the fitting plane of the objective function.

[0101] The fitted plane h0(x) can be converted into a matrix expression, i.e.:

[0102]

[0103] For each expert, then:

[0104]

[0105] Among them, y i This represents the data corresponding to the overall importance score of the i-th expert for the environmental monitoring capability evaluation indicators in the final matrix. ε represents the data corresponding to the score given by the i-th expert to the j-th environmental monitoring capability evaluation indicator in the final matrix. ij This represents the error term of the data corresponding to the score given by the i-th expert on the j-th environmental monitoring capability evaluation indicator in the final matrix.

[0106] The error term follows a Gaussian distribution, that is:

[0107]

[0108] In the formula, p(ε) ij ) represents the Gaussian probability density function of the error term, and σ represents the standard deviation of the error term.

[0109] Then we have:

[0110]

[0111] In the formula, This represents the probability density function of the weights of the environmental monitoring capability evaluation indicators, given that the importance of each indicator and the overall importance of the indicators are determined.

[0112] Simulating a specific combination of parameters and data using the likelihood function yields a result that is exactly the true value.

[0113]

[0114] In the formula, L(θ) represents the likelihood function of the weights of the environmental monitoring capability evaluation indicators, and k represents the preset quantity.

[0115] Taking the logarithm of the likelihood function above for calculation, the corresponding formula after taking the logarithm is:

[0116]

[0117] By solving for the extreme point θ of logL(θ), the optimal parameters, i.e. the optimal weights of each environmental monitoring capability evaluation index, can be determined.

[0118] The formula for the logarithm of the likelihood function can be transformed as follows to simplify the calculation.

[0119]

[0120] Since a larger likelihood function leads to a higher accuracy in calculating the optimal weights, a larger logL(θ) is better. If the cost function is a constant, then the smaller the cost function in the latter half of the formula, the better. This represents the cost function.

[0121] For the final matrix Q, the squared terms are equal to the transpose multiplied by itself, so the cost function can be expressed as:

[0122]

[0123] Taking the partial derivative with respect to θ, we have:

[0124]

[0125] Setting the partial derivative to 0, we can obtain:

[0126] θ=(Q T Q) -1 Q T Y;

[0127] Finally, the optimal weights for each environmental monitoring capability evaluation index are obtained, which can be specifically expressed as θ=(θ1,θ2,θ3,…,θ n ), where θ j This represents the weight corresponding to the j-th environmental monitoring capability evaluation indicator.

[0128] In one possible implementation, the primary indicators in the various environmental monitoring capability evaluation indicators include monitoring equipment indicators, monitoring factor indicators, personnel allocation indicators, system formulation indicators, and risk management indicators;

[0129] The secondary indicators of monitoring equipment include indicators of the completeness of monitoring tools, the processing capacity of monitoring equipment, the maintenance of monitoring equipment, the age of monitoring equipment, and the scientific nature of monitoring methods.

[0130] The secondary indicators of the monitoring factor indicators include water factor indicators, atmospheric factor indicators, noise factor indicators, electromagnetic factor indicators, and solid waste factor indicators.

[0131] The secondary indicators for personnel allocation include personnel division of labor indicators, personnel environmental protection training indicators, and personnel professional title level indicators;

[0132] The secondary indicators for system development include environmental monitoring system indicators, work instruction development indicators, and monitoring management method development indicators;

[0133] The secondary indicators of risk management indicators include indicators of sudden environmental changes.

[0134] In this embodiment, the monitoring factor indicators can be directly obtained monitoring data, standardized data of the monitoring factors, or 0 / 1 data corresponding to whether the data of each monitoring factor exceeds a preset threshold (e.g., 0 for exceeding the preset threshold, 1 for not exceeding the preset threshold). Correspondingly, the data corresponding to monitoring equipment indicators, personnel setup indicators, system formulation indicators, and risk management indicators can also be represented using 0 / 1 data. For example, the indicator of complete monitoring tools is 1 if all monitoring tools are complete, and 0 if incomplete; the environmental monitoring system indicator is 1 if an environmental monitoring system has been formulated, and 0 if no such system has been formulated. Furthermore, the secondary indicators of risk management indicators can also include external policy change indicators, for example, 1 for a change in external policies, and 0 for no change in external policies.

[0135] Alternatively, methods such as grading or deduction can be used to obtain data corresponding to each environmental monitoring capability evaluation indicator. For example, the scientific nature of monitoring methods can include multiple levels such as scientific, relatively scientific, relatively unscientific, and unscientific, with each level corresponding to a numerical value for calculation. This is merely an example, and there are no restrictions on the method for determining historical data for each environmental monitoring capability evaluation indicator.

[0136] When evaluating the environmental monitoring capabilities of power grid projects based on historical data of environmental monitoring capability evaluation indicators, calculations can be performed directly using historical data of each secondary indicator. In the formula, G represents the environmental monitoring capability evaluation result of the power grid project to be evaluated, n represents the total number of all secondary indicators in the environmental monitoring capability evaluation index, and θ j G represents the weight of the j-th secondary indicator. j This represents the historical data corresponding to the j-th secondary indicator in the power grid project to be evaluated.

[0137] This invention employs eigenvectors selected from the eigenvalues ​​of the covariance matrix to establish a feature matrix. The initial matrix is ​​then dimensionality-reduced using this feature matrix, filtering out specific data from different experts and ensuring the accuracy of the final scores while simultaneously reducing data dimensionality. Specifically, by selecting eigenvalues ​​with smaller variances based on their normal distribution and removing those with larger variances, the remaining scores maintain consistency across environmental monitoring capability evaluation indicators, avoiding errors in weighting caused by significant differences in expert scores. Furthermore, a pre-defined linear regression algorithm is used to calculate the weights of each environmental monitoring capability evaluation indicator based on the final matrix. This allows for the objective and accurate determination of the weights of each indicator in the power grid environmental monitoring capability evaluation, ensuring the stability and reproducibility of each evaluation result and guaranteeing the validity and reliability of the evaluation results for the power grid project.

[0138] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0139] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0140] Figure 3 A schematic diagram of the power grid environmental monitoring capability evaluation device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0141] like Figure 3 As shown, the power grid environmental monitoring capability evaluation device 30 includes:

[0142] The acquisition module 31 is used to acquire the scoring data obtained by multiple experts scoring the importance and overall importance of various environmental monitoring capability evaluation indicators, and to establish an initial matrix based on the scoring data;

[0143] The calculation module 32 is used to calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors according to the eigenvalues ​​of the covariance matrix to establish the feature matrix; based on the feature matrix, the initial matrix is ​​reduced in dimension to obtain the final matrix; based on the final matrix, a preset linear regression algorithm is used to calculate the weights of various environmental monitoring capability evaluation indicators.

[0144] Evaluation module 33 is used to determine the evaluation result of the environmental monitoring capability of the power grid project under evaluation based on the weights and historical data corresponding to the various environmental monitoring capability evaluation indicators in the power grid project under evaluation.

[0145] In one possible implementation, the computing module 32 is specifically used for:

[0146] Select a preset number of feature vectors corresponding to feature values ​​from smallest to largest as target feature vectors, where the preset number is less than the number of experts;

[0147] Arrange the target feature vectors according to the magnitude of their feature values ​​to create a feature matrix.

[0148] In one possible implementation, the computing module 32 is further used for:

[0149] according to Determine the preset quantity;

[0150] In the formula, k represents the preset number, σ represents the standard deviation of the normal distribution corresponding to each eigenvalue of the covariance matrix, and m represents the number of experts corresponding to the obtained scoring data.

[0151] In one possible implementation, module 31 is specifically used for:

[0152] Based on the mean and standard deviation of the assigned scores for each environmental monitoring capability evaluation indicator, the assigned scores for each environmental monitoring capability evaluation indicator are standardized; and based on the mean and standard deviation of the assigned scores for the overall importance, the assigned scores for the overall importance are standardized.

[0153] For each environmental monitoring capability evaluation indicator and its overall importance, the standardized scoring data is subjected to zero-mean processing to obtain the standard scoring data corresponding to each environmental monitoring capability evaluation indicator and its overall importance.

[0154] Based on the standard scoring data, an initial matrix is ​​established. The last column of the initial matrix corresponds to the overall importance, and each of the remaining columns corresponds to a different environmental monitoring capability evaluation index. Each row of the initial matrix corresponds to a different expert.

[0155] In one possible implementation, the computing module 32 is specifically used for:

[0156] according to Calculate the covariance matrix of the initial matrix;

[0157] In the formula, C represents the covariance matrix, m represents the number of experts corresponding to the obtained scoring data, and X represents the initial matrix. T This represents the transpose of the initial matrix.

[0158] In one possible implementation, the final matrix includes the final matrix of indicators corresponding to each environmental monitoring capability evaluation indicator and the overall final matrix corresponding to the overall importance.

[0159] Calculation module 32 is specifically used for:

[0160] According to θ=(Q T Q) -1 Q T Y, calculate the weight of each environmental monitoring capability evaluation indicator;

[0161] In the formula, θ represents the set of weights for environmental monitoring capability evaluation indicators, θ=(θ1,θ2,θ3,...,θ n ), θ j Let Q represent the weight of the j-th environmental monitoring capability evaluation indicator, and let Q represent the final indicator matrix. T Y represents the transpose of the final index matrix, and Y represents the overall final matrix.

[0162] In one possible implementation, the evaluation module 33 is specifically used for:

[0163] according to Calculate the environmental monitoring capability evaluation results of the power grid project to be evaluated;

[0164] In the formula, G represents the environmental monitoring capability evaluation result of the power grid project to be evaluated, and θ j G represents the weight of the j-th environmental monitoring capability evaluation indicator. j This represents the historical data corresponding to the j-th environmental monitoring capability evaluation indicator in the power grid project to be evaluated, and n represents the total number of environmental monitoring capability evaluation indicators.

[0165] In one possible implementation, the primary indicators in the various environmental monitoring capability evaluation indicators include monitoring equipment indicators, monitoring factor indicators, personnel allocation indicators, system formulation indicators, and risk management indicators;

[0166] The secondary indicators of monitoring equipment include indicators of the completeness of monitoring tools, the processing capacity of monitoring equipment, the maintenance of monitoring equipment, the age of monitoring equipment, and the scientific nature of monitoring methods.

[0167] The secondary indicators of the monitoring factor indicators include water factor indicators, atmospheric factor indicators, noise factor indicators, electromagnetic factor indicators, and solid waste factor indicators.

[0168] The secondary indicators for personnel allocation include personnel division of labor indicators, personnel environmental protection training indicators, and personnel professional title level indicators;

[0169] The secondary indicators for system development include environmental monitoring system indicators, work instruction development indicators, and monitoring management method development indicators;

[0170] The secondary indicators of risk management indicators include indicators of sudden environmental changes.

[0171] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0172] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0173] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0174] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for evaluating the environmental monitoring capabilities of a power grid, characterized in that, include: The scoring data obtained by multiple experts on the importance and overall importance of various environmental monitoring capability evaluation indicators is obtained, and an initial matrix is ​​established based on the scoring data. Calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors based on the eigenvalues ​​of the covariance matrix to establish the feature matrix; Based on the feature matrix, the initial matrix is ​​reduced in dimensionality to obtain the final matrix; Based on the final matrix, the weights of each environmental monitoring capability evaluation index are calculated using a preset linear regression algorithm. Based on the weights and historical data corresponding to the environmental monitoring capability evaluation indicators of the power grid project to be evaluated, the environmental monitoring capability evaluation result of the power grid project to be evaluated is determined. The step of selecting corresponding eigenvectors based on each eigenvalue of the covariance matrix to establish a feature matrix includes: A preset number of feature vectors corresponding to feature values ​​are selected as target feature vectors, from smallest to largest, where the preset number is less than the number of experts. Arrange the target feature vectors according to the magnitude of their feature values ​​to establish a feature matrix; The method for determining the preset quantity is as follows: according to Determine the preset quantity; In the formula, This indicates the preset quantity. The standard deviation represents the normal distribution corresponding to each eigenvalue of the covariance matrix. This indicates the number of experts corresponding to the obtained scoring data.

2. The method for evaluating the environmental monitoring capabilities of power grids according to claim 1, characterized in that, The step of establishing an initial matrix based on the assigned data includes: Based on the mean and standard deviation of the assigned scores for each environmental monitoring capability evaluation indicator, the assigned scores for each environmental monitoring capability evaluation indicator are standardized; and based on the mean and standard deviation of the assigned scores for the overall importance, the assigned scores for the overall importance are standardized. For each environmental monitoring capability evaluation indicator and its overall importance, the standardized scoring data is subjected to zero-mean processing to obtain the standard scoring data corresponding to each environmental monitoring capability evaluation indicator and its overall importance. Based on the standard scoring data, an initial matrix is ​​established, wherein the last column of the initial matrix corresponds to the overall importance, each of the remaining columns corresponds to a different environmental monitoring capability evaluation index, and each row of the initial matrix corresponds to a different expert.

3. The method for evaluating the environmental monitoring capabilities of power grids according to claim 2, characterized in that, The calculation of the covariance matrix of the initial matrix includes: according to Calculate the covariance matrix of the initial matrix; In the formula, Let the covariance matrix be represented. This indicates the number of experts corresponding to the obtained scoring data. Denotes the initial matrix, This represents the transpose of the initial matrix.

4. The method for evaluating the environmental monitoring capabilities of power grids according to claim 1, characterized in that, The final matrix includes the final matrix of indicators corresponding to each environmental monitoring capability evaluation indicator and the overall final matrix corresponding to the overall importance. The step involves calculating the weights of each environmental monitoring capability evaluation indicator based on the final matrix using a preset linear regression algorithm, including: according to Calculate the weights of each environmental monitoring capability evaluation indicator; In the formula, The set of weights representing the evaluation indicators for environmental monitoring capabilities. , Indicates the first The weights corresponding to the environmental monitoring capability evaluation indicators This represents the final matrix of the aforementioned indicators. This represents the transpose of the final matrix of the indices. This represents the overall final matrix.

5. The method for evaluating the environmental monitoring capabilities of power grids according to any one of claims 1-4, characterized in that, The environmental monitoring capability evaluation result of the power grid project under evaluation is determined based on the weights and historical data corresponding to each environmental monitoring capability evaluation indicator in the project under evaluation, including: according to Calculate the environmental monitoring capability evaluation results of the power grid project to be evaluated; In the formula, This indicates the evaluation result of the environmental monitoring capability of the power grid project to be evaluated. Indicates the first The weights of the environmental monitoring capability evaluation indicators Indicates the first [item] in the power grid project to be evaluated. Historical data corresponding to each environmental monitoring capability evaluation indicator This indicates the total number of environmental monitoring capability evaluation indicators.

6. The method for evaluating the environmental monitoring capabilities of power grids according to claim 5, characterized in that, The primary indicators among the various environmental monitoring capability evaluation indicators include monitoring equipment indicators, monitoring factor indicators, personnel allocation indicators, system formulation indicators, and risk management indicators; The secondary indicators of the monitoring equipment indicators include the completeness of monitoring tools, the processing capacity of monitoring equipment, the maintenance of monitoring equipment, the age of monitoring equipment, and the scientific nature of monitoring methods. The secondary indicators of the monitoring factor indicators include water factor indicators, atmospheric factor indicators, noise factor indicators, electromagnetic factor indicators, and solid waste factor indicators. The secondary indicators of the personnel allocation indicators include personnel division of labor indicators, personnel environmental protection training indicators, and personnel professional title level indicators. The secondary indicators for the system development indicators include environmental monitoring system indicators, work instruction development indicators, and monitoring management method development indicators; The secondary indicators of the risk management indicators include indicators of sudden environmental changes.

7. A device for evaluating the environmental monitoring capabilities of a power grid, characterized in that, include: The acquisition module is used to acquire the scoring data obtained by multiple experts on the importance and overall importance of various environmental monitoring capability evaluation indicators, and to establish an initial matrix based on the scoring data; The calculation module is used to calculate the covariance matrix of the initial matrix, and select the corresponding eigenvectors according to each eigenvalue of the covariance matrix to establish the feature matrix; Based on the feature matrix, the initial matrix is ​​reduced in dimensionality to obtain the final matrix; Based on the final matrix, the weights of each environmental monitoring capability evaluation index are calculated using a preset linear regression algorithm. The evaluation module is used to determine the environmental monitoring capability evaluation result of the power grid project to be evaluated based on the weights and historical data corresponding to the environmental monitoring capability evaluation indicators of each project to be evaluated. The calculation module is specifically used for: A preset number of feature vectors corresponding to feature values ​​are selected as target feature vectors, from smallest to largest, where the preset number is less than the number of experts. Arrange the target feature vectors according to the magnitude of their feature values ​​to establish a feature matrix; The calculation module is also used for: according to Determine the preset quantity; In the formula, This indicates the preset quantity. The standard deviation represents the normal distribution corresponding to each eigenvalue of the covariance matrix. This indicates the number of experts corresponding to the obtained scoring data.

Images