Irrigation pump station operation efficiency comprehensive evaluation model training method

Abstract

The invention relates to the technical field of model training methods, in particular to an irrigation pump station operation efficiency comprehensive evaluation model training method which performs model training based on incremental learning and inputs irrigation pump station data collected in real time into an efficiency evaluation model. The method enables the efficiency evaluation model to learn the features in the irrigation pump station data collected in real time, learns new knowledge and ability from the real-time irrigation pump station data on the basis of maintaining the ability of the original efficiency evaluation model, can obtain knowledge from the inference task of the old efficiency evaluation model through incremental learning, and improves the efficiency of the irrigation pump station. Efficiency evaluation model learning solves a new efficiency evaluation model reasoning task, meanwhile, knowledge learned in the previous efficiency evaluation model reasoning task is reserved, and it is avoided that when new irrigation pump station data comes, efficiency evaluation model parameters are retrained. According to the method, knowledge can be obtained from an old irrigation pump station operation efficiency comprehensive evaluation model through an incremental learning method, so that the operation efficiency of the model is improved.

Description

Technical Field

[0001] The invention relates to the technical field of model training methods, and in particular to a training method for a comprehensive evaluation model of operation efficiency of an irrigation pump station. Background Art

[0002] An integrated prefabricated pump station is a pump station that integrates the main components such as wellbore, pump, pipeline, control system and ventilation system into one in the factory, and is pre-installed and tested before leaving the factory. It is suitable for water supply, drainage and waterlogging prevention projects. In recent years, integrated prefabricated pump stations have been widely used in my country. In the irrigation system where the integrated prefabricated pump station is located, the pump station is the core equipment, and its operating efficiency directly affects the water resource utilization rate and energy consumption level of agricultural irrigation. However, the accurate evaluation of the operating efficiency of the pump station faces many challenges: diverse data sources, complex and dynamic feature distribution, lack of labels for some data, and redundancy of high-dimensional data. These problems lead to low data utilization efficiency, insufficient model generalization ability, and poor adaptability to real-time changes in the efficiency evaluation process of the existing technology. Traditional methods usually rely on static models trained offline and cannot adapt to the dynamic changes of real-time operation data of pump stations. At the same time, since the irrigation pump station data contains multi-source, multi-dimensional, and highly nonlinear characteristics, the existing generation method is difficult to expand the sample space of real data. When the training data is insufficient, the model often shows poor performance. In addition, high-dimensional data processing technology is prone to losing important information during the dimensionality reduction process, resulting in an inaccurate description of the pump station operation characteristics.

[0003] Therefore, the present invention proposes a training method for a comprehensive evaluation model of irrigation pump station operation efficiency to solve the above problems. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention develops a training method for a comprehensive evaluation model of the operation efficiency of an irrigation pump station. The present invention can improve the accuracy, real-time performance and adaptability of the model and meet the actual needs of the irrigation system through a comprehensive evaluation method for the efficiency of an irrigation pump station that can dynamically learn new data features, expand the sample space and efficiently process high-dimensional data.

[0005] The technical solution to the technical problem of the present invention is a training method for a comprehensive evaluation model of the operation efficiency of an irrigation pump station. The model training is performed based on incremental learning. The training method is as follows: Import the original irrigation pump station data set into the existing offline irrigation pump station operation efficiency comprehensive evaluation model for training to obtain a basic efficiency evaluation model, input the new irrigation pump station data set into the basic efficiency evaluation model, and judge whether the newly input irrigation pump station data set is available. If not, terminate the training of the model and output the basic efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the basic efficiency evaluation model for training to generate the efficiency evaluation model, input the new irrigation pump station data set into the newly generated efficiency evaluation model again, and judge whether the new irrigation pump station data set is available. If not, terminate the training of the model and output the newly generated efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the newly generated efficiency evaluation model for training, and generate a new efficiency evaluation model again. Iterate multiple times until the final efficiency evaluation model is output. The final efficiency evaluation model outputs the prediction result of the operation efficiency of the irrigation pump station. When the data in the irrigation pump station dataset is insufficient for multiple trainings, a generative adversarial network based on feature distribution adversarial loss is used to expand the data samples. After sample expansion, an autoencoder algorithm based on dynamic projection is used to reduce the data dimension.

[0006] In a specific implementation manner, the incremental learning process is as follows: The incremental learning process is a process of continuous learning through training. When the irrigation pump station is performing a task, the comprehensive evaluation model of the irrigation pump station operation efficiency evaluates the operation efficiency of the pump station based on the data collected during the task execution. At the same time, the operation efficiency of the irrigation pump station is manually labeled, and the labeled labels are low operation efficiency, medium operation efficiency and high operation efficiency. The irrigation pump station is input into the basic efficiency evaluation model when performing its first task. The irrigation pump station dataset is represented as ,judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the second task Irrigation pump station dataset, judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the third task Irrigation pump station dataset, judge Is the data available in multiple iterations? After the task, the dataset When it is unavailable, the iteration is stopped, that is, the training process of the model by incremental learning is terminated, and the final efficiency evaluation model is output. , Indicates that the irrigation pump station is in operation When the task is completed, it is input into the new efficiency evaluation model The irrigation pump station dataset and the final efficiency evaluation model The output efficiency prediction result is expressed as , used for training The data set is represented as , The pseudo-labels are integrated into Efficiency prediction results and dataset , .

[0007] In a specific implementation manner, the conditions for determining whether the data in the new irrigation pump station dataset is available are as follows: The operating efficiency of the irrigation pump station is manually labeled, and the labeled content is the operating efficiency of the irrigation pump station, which is low operating efficiency, medium operating efficiency and high operating efficiency. The data in the labeled new irrigation pump station dataset is input into the basic efficiency evaluation model for training, and the accuracy of the trained basic efficiency evaluation model is compared with the accuracy of the untrained basic efficiency evaluation model. If the accuracy of the trained basic efficiency evaluation model is improved, the data in the new irrigation pump station dataset is available, otherwise it is not available.

[0008] In a specific implementation, an irrigation pump station dataset is constructed: The relevant data of the irrigation pump station operation process is monitored through a variety of sensors, and the relevant operation events and environmental data are recorded at the same time. The sensors include flow meters, pressure sensors, current sensors and temperature sensors. The data collected by the monitoring process sensors include real-time electrical, mechanical and hydraulic data. Operation events include manual intervention of pump station operators, start and stop of pump stations and fault records of pump stations. Environmental data include climate, meteorology and soil moisture. The collected data is uniformly stored in a distributed database system in a standardized storage format.

[0009] In a specific implementation, the process of data sample expansion based on the generative adversarial network with feature distribution adversarial loss is as follows: Data samples are expanded through the generator and discriminator. Specifically, the generator is optimized through feature distribution adversarial loss and polynomial kernel function, and the discriminator is trained using weighted feature distribution adversarial loss and adaptive weighting coefficients. The collaborative optimization of the generator and the discriminator is achieved through the feedback control mechanism, thereby generating more realistic irrigation pump station data.

[0010] In a specific implementation manner, the data sample expansion process is specifically as follows: (1) The characteristic distribution of the data in the collected irrigation pump station data set is corrected through the adaptively calculated mapping matrix. The calculation process is as follows: , , in, The mapping matrix representing the characteristics of irrigation pump station data, represents the weight coefficient of the mapping matrix, represents the standard deviation of the input irrigation pump station data, represents the mean of the input irrigation pump station data, Indicates the number of irrigation pump station data features input in the current batch. express The index of Indicates Irrigation pump station data features, Represents the original pump station data characteristics, , represents the corrected irrigation pump station data characteristics, represents the mapping function, Represents the mapping function about The Jacobian matrix of The principal component analysis function was used; (2) Optimize the generator network: The nonlinear data characteristics of the irrigation pump station are captured by the feature distribution adversarial loss and polynomial kernel function optimization generator. The polynomial kernel function is used to fit the flow characteristic curve of the pump station. The nonlinear changes under actual working conditions are correctly characterized by adjustment, and then the irrigation pump station data that fits the actual situation is generated. The basic adversarial loss calculation formula of the generator is as follows: , in, Representation Generator The basic adversarial loss, express Subject to the characteristic distribution of irrigation pump station data expectations, represents the discriminator, A random noise vector representing the input generator Subject to the noise distribution expectations; At the same time, the feature distribution is used to constrain the adversarial loss, and the randomness factor input by the perturbation generator is used to randomly generate the constraint loss, and then the total loss is calculated. The calculation formula is as follows: , , , , in, Represents the weighted coefficient for adjusting the feature distribution against the loss strength, represents the weighted coefficient for adjusting the strength of the randomly generated constraint loss, Representation Generator The feature distribution of adversarial loss, represents the randomly generated constraint loss, represents the coefficient that controls the weight of the gradient multiplication term, represents the gradient calculation, represents the polynomial kernel function used to measure the nonlinear relationship between the generated data samples and the target irrigation pump station data, represents the order of the polynomial kernel function, express norm, represents the strength coefficient of the randomly generated constraint term, Indicates the use of random factors The amount of change in the output of the post-generator, the randomness factor , represents the hyperparameter controlling the noise amplitude, Indicates that the mean is zero and the variance is the unit matrix Normally distributed noise; (3) Train the discriminator network: The discriminator uses weighted feature distribution adversarial loss to dynamically adjust the adaptive weighting coefficient through the feedback mechanism, calculate the total loss of the discriminator with enhanced distinguishing ability, and then calculate the total loss function of the discriminator. The calculation formula is as follows: , , in, represents the total loss function of the discriminator, represents the weighted coefficient of the discriminator loss, represents the feature distribution adversarial loss function of the discriminator, represents the first adaptive weighting coefficient of the discriminator, represents the second adaptive weighting coefficient of the discriminator; The adaptive weighting coefficient of the discriminator is dynamically updated based on the feedback control method. The calculation formula is as follows: , , in, Indicates a parameter update operation. and Respectively represent the first adaptive weighting coefficient and the second adaptive weighting coefficient of the updated discriminator, represents the learning rate of the adaptive weight coefficient, It means to find partial derivative; (4) Co-optimize the generator and discriminator: The generator and discriminator are collaboratively optimized through the feedback control mechanism. The calculation formula is as follows: , , in, and Respectively represent the optimized generator parameters and discriminator parameters, and Respectively represent the generator parameters and discriminator parameters before optimization, represents the learning rate of the generator, represents the learning rate of the discriminator, Represents the generator loss function pair The gradient of Denotes the discriminator loss function The gradient of (5) Optimize the generated data samples: The generated data samples are optimized by nonlinear fitting, the nonlinear feature distribution is captured and improved, the generated irrigation pump station data is corrected by local weighting to make it more consistent with the real irrigation pump station data feature distribution, and the distribution of the generated data samples and the real samples in high-dimensional space is optimized and corrected by cosine similarity and difference penalty terms. The calculation formula is as follows: , in, represents the optimized irrigation pump station data sample, Represents the cosine similarity calculation function, represents the adjustment coefficient for penalizing the difference between the generated irrigation pump station data and the original irrigation pump station data, represents the corrected irrigation pump station data features, that is, the irrigation pump station data features generated by the generator, Represents, that is, the real irrigation pump station data characteristics; (6) Repeat the above steps (1)-(5) and set the stop iteration condition until the preset iteration condition is met, thus completing the data sample expansion.

[0011] In a specific implementation, the process of data dimensionality reduction based on the dynamic projection autoencoder algorithm is as follows: The autoencoder algorithm based on dynamic projection is optimized to improve the dimensionality reduction effect. The autoencoder is optimized by randomly initializing its parameters. The forward propagation of the autoencoder is realized through the ReLU activation function. The parameters are iteratively updated by the gradient descent method to minimize the reconstruction error and dynamically adjust the projection direction. The Softmax function is used to classify the reduced data into low operating efficiency, medium operating efficiency and high operating efficiency. The data feature category with the largest class probability is used as the category for the comprehensive evaluation of the operating efficiency of the irrigation pump station, and the prediction result of the operating efficiency of the irrigation pump station is obtained.

[0012] In a specific implementation manner, the data dimension reduction process is as follows: The weight matrix and bias term of the autoencoder are randomly initialized. The initialized parameters obey the normal distribution with a mean of 0 and a variance of the unit matrix. The forward propagation of the irrigation pump station data in the autoencoder is realized through the ReLU activation function. The calculation formula is as follows: , in, represents the features after dimensionality reduction, represents the autoencoder function, Using ReLU activation function, represents the irrigation pump station data input to the autoencoder, represents the weight matrix of the autoencoder, Represents the bias term of the autoencoder; The weight matrix of the autoencoder and the bias term For passing The final result obtained by the iterative update, the update process is as follows: , , in, Indicates the number of iterations The index of , and Respectively represent Second and The weight matrix of the autoencoder after the iteration update, and Respectively represent Second and The bias term of the autoencoder after the iteration update, represents the learning rate, represents the loss function of the autoencoder, represents the gradient of the autoencoder function with respect to the weight matrix, represents the gradient of the autoencoder with respect to the bias term; By optimizing the projection of the high-dimensional features of the input irrigation pump station data, the projection direction of the autoencoder is dynamically adjusted to calculate the irrigation pump station data input to the autoencoder. Reconstruction error of irrigation pump station data after dimensionality reduction , and then calculate the total loss of the autoencoder , the calculation formula is as follows: , , , , in, represents the inverse operation of the autoencoder function, represents the transpose of the decoder weight matrix, represents the transposed bias term of the decoder, Represents the projection matrix The regularization weight of Represents the projection matrix The Frobenius norm of represents the relaxed constraint, represents the slack constraint weight, Represents the projection matrix The transpose of represents the regularization term weight of the feature after dimensionality reduction, represents the regularization term after dimensionality reduction, represents the number of features of the irrigation pump station data input to the autoencoder, express The index of Indicates The representation of a feature after dimensionality reduction; Projection Matrix Update for iteration The final result after the projection matrix is ​​updated according to the gradient calculation rule. The calculation formula is as follows: , , , in, Indicates the number of iterations The index of , and Respectively represent Second and The updated projection matrix after iterations is: , Indicates the input The loss function value of the autoencoder is and Respectively represent Second and The learning rate of the projection matrix at the iteration update, represents the gradient of the encoder’s total loss with respect to the projection matrix, represents the hyperparameter controlling the adaptive step size, represents the gradient of the total loss of the autoencoder; According to setting the convergence threshold of the autoencoder Determine whether the convergence state is reached. If , the algorithm converges and outputs the final stable dimensionality reduction result.

[0013] The effects provided in the content of the invention are only the effects of the embodiments, rather than all the effects of the invention. The above technical solution has the following advantages or beneficial effects: (1) In the comprehensive evaluation task of irrigation pump station operation efficiency, a generative adversarial network based on feature distribution adversarial loss is used to optimize the generator through feature distribution adversarial loss to solve the problem of inconsistent feature distribution of multi-source irrigation pump station data. The generated data is more in line with the actual pump station characteristics. (2) In the comprehensive evaluation task of irrigation pump station operation efficiency, the polynomial kernel function is used to capture the nonlinear characteristics of pump station operation and generate high-fidelity data, which solves the problem that traditional methods are unable to fit complex features well. (3) In the comprehensive evaluation task of irrigation pump station operation efficiency, the discriminator uses weighted feature distribution adversarial loss and adaptive weighting coefficient to improve the ability to distinguish generated samples; (4) In the comprehensive evaluation task of irrigation pump station operation efficiency, an autoencoder based on dynamic projection is used to reduce the data dimension. Dynamic projection is used to optimize the dimension reduction process of high-dimensional irrigation pump station data, solve the problems of redundant information interference and feature loss, and ensure that the core characteristics of the data are retained after dimension reduction. (5) In the comprehensive evaluation task of the operating efficiency of irrigation pumping stations, regularization and relaxation constraint strategies are used to reduce the distortion in the dimensionality reduction process, and multi-dimensional constraints are imposed on the dimensionality reduction results to ensure the physical interpretability of the data; (6) In the comprehensive evaluation task of irrigation pump station operation efficiency, the adaptive learning rate of the projection matrix is ​​dynamically adjusted to make it better adapt to the data feature distribution of different pump stations and improve the model's ability to process high-dimensional data. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0015] Figure 1 It is a flowchart of the efficiency evaluation model training method based on incremental learning in the present invention.

[0016] Figure 2 The figure is a comparison chart of the training time of the present invention under the learning rates of different adaptive weighting coefficients.

[0017] Figure 3 The figure is a distribution comparison diagram of the data generated for the present invention and the real data.

[0018] Figure 4 This is a comparison chart of the convergence process of the dynamic projection autoencoder used in the present invention and the traditional autoencoder.

[0019] Figure 5 This is a comparison of the reconstruction errors of two different dimensionality reduction algorithms: the autoencoder based on dynamic projection and the traditional PCA algorithm in the present invention. DETAILED DESCRIPTION

[0020] In order to clearly illustrate the technical features of the present invention, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0021] Example 1 A training method for a comprehensive evaluation model of irrigation pump station operation efficiency is based on incremental learning. The training method is as follows: Import the original irrigation pump station data set into the existing offline irrigation pump station operation efficiency comprehensive evaluation model for training to obtain a basic efficiency evaluation model, input the new irrigation pump station data set into the basic efficiency evaluation model, and judge whether the newly input irrigation pump station data set is available. If not, terminate the training of the model and output the basic efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the basic efficiency evaluation model for training to generate the efficiency evaluation model, input the new irrigation pump station data set into the newly generated efficiency evaluation model again, and judge whether the new irrigation pump station data set is available. If not, terminate the training of the model and output the newly generated efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the newly generated efficiency evaluation model for training, and generate a new efficiency evaluation model again. Iterate multiple times until the final efficiency evaluation model is output. The final efficiency evaluation model outputs the prediction result of the operation efficiency of the irrigation pump station. When the data in the irrigation pump station dataset is insufficient for multiple trainings, a generative adversarial network based on feature distribution adversarial loss is used to expand the data samples. After sample expansion, an autoencoder algorithm based on dynamic projection is used to reduce the data dimension.

[0022] In a specific implementation manner, the incremental learning process is as follows: The incremental learning process is a process of continuous learning through training. When the irrigation pump station is performing a task, the comprehensive evaluation model of the irrigation pump station operation efficiency evaluates the operation efficiency of the pump station based on the data collected during the task execution. At the same time, the operation efficiency of the irrigation pump station is manually labeled, and the labeled labels are low operation efficiency, medium operation efficiency and high operation efficiency. The irrigation pump station is input into the basic efficiency evaluation model when performing its first task. The irrigation pump station dataset is represented as ,judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the second task Irrigation pump station dataset, judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the third task Irrigation pump station dataset, judge Is the data available in multiple iterations? After the task, the dataset When it is unavailable, the iteration is stopped, that is, the training process of the model by incremental learning is terminated, and the final efficiency evaluation model is output. , Indicates that the irrigation pump station is in operation When the task is completed, it is input into the new efficiency evaluation model The irrigation pump station dataset and the final efficiency evaluation model The output efficiency prediction result is expressed as , used for training The data set is represented as , The pseudo-labels are integrated into Efficiency prediction results and dataset , .

[0023] In a specific implementation manner, the conditions for determining whether the data in the new irrigation pump station dataset is available are as follows: The operating efficiency of the irrigation pump station is manually labeled, and the labeled content is the operating efficiency of the irrigation pump station, which is low operating efficiency, medium operating efficiency and high operating efficiency. The data in the labeled new irrigation pump station dataset is input into the basic efficiency evaluation model for training, and the accuracy of the trained basic efficiency evaluation model is compared with the accuracy of the untrained basic efficiency evaluation model. If the accuracy of the trained basic efficiency evaluation model is improved, the data in the new irrigation pump station dataset is available, otherwise it is not available.

[0024] In a specific implementation, an irrigation pump station dataset is constructed: The relevant data of the irrigation pump station operation process is monitored through a variety of sensors, and the relevant operation events and environmental data are recorded at the same time. The sensors include flow meters, pressure sensors, current sensors and temperature sensors. The data collected by the monitoring process sensors include real-time electrical, mechanical and hydraulic data. Operation events include manual intervention of pump station operators, start and stop of pump stations and fault records of pump stations. Environmental data include climate, meteorology and soil moisture. The collected data is uniformly stored in a distributed database system in a standardized storage format.

[0025] The storage format is JSON or CSV. The JSON storage format is as follows: { "timestamp": "2025-01-01T12:00:00", "Ra": 45.3, / / Current value (A) "Rb": 3.2, / / flow value (m^3 / h) "Rc": 150.6, / / Pump station pressure value (bar) "Rd": 18.2, / / temperature value (℃) "Re": "Normal", / / Status: Normal / Fault "Rf": 120, / / Working time (minutes) "Rg": 3, / / Pumping station mode: 1-Automatic, 2-Manual "Rh": "Start", / / Operation event: start / stop "Ri": 0.95, / / Electricity efficiency (%) "Rj": 40.5 / / Soil moisture (%) } In a specific implementation, the process of data sample expansion based on the generative adversarial network with feature distribution adversarial loss is as follows: Data samples are expanded through the generator and discriminator. Specifically, the generator is optimized through feature distribution adversarial loss and polynomial kernel function, and the discriminator is trained using weighted feature distribution adversarial loss and adaptive weighting coefficients. The collaborative optimization of the generator and the discriminator is achieved through the feedback control mechanism, thereby generating more realistic irrigation pump station data.

[0026] In a specific implementation manner, the data sample expansion process is specifically as follows: (1) The characteristic distribution of the data in the collected irrigation pump station data set is corrected through the adaptively calculated mapping matrix. The calculation process is as follows: , , in, The mapping matrix representing the characteristics of irrigation pump station data, represents the weight coefficient of the mapping matrix, represents the standard deviation of the input irrigation pump station data, represents the mean of the input irrigation pump station data, Indicates the number of irrigation pump station data features input in the current batch. express The index of Indicates Irrigation pump station data features, Represents the original pump station data characteristics, , represents the corrected irrigation pump station data characteristics, represents the mapping function, Represents the mapping function about The Jacobian matrix of The principal component analysis function was used; (2) Optimize the generator network: The nonlinear data characteristics of the irrigation pump station are captured by the feature distribution adversarial loss and polynomial kernel function optimization generator. The polynomial kernel function is used to fit the flow characteristic curve of the pump station. The nonlinear changes under actual working conditions are correctly characterized by adjustment, and then the irrigation pump station data that fits the actual situation is generated. The basic adversarial loss calculation formula of the generator is as follows: , in, Representation Generator The basic adversarial loss, express Subject to the characteristic distribution of irrigation pump station data expectations, represents the discriminator, A random noise vector representing the input generator Subject to the noise distribution expectations; At the same time, the feature distribution is used to constrain the adversarial loss, and the randomness factor input by the perturbation generator is used to randomly generate the constraint loss, and then the total loss is calculated. The calculation formula is as follows: , , , , in, Represents the weighted coefficient for adjusting the feature distribution against the loss strength, set , Represents the weighted coefficient for adjusting the strength of the randomly generated constraint loss, set , Representation Generator The feature distribution of adversarial loss, represents the randomly generated constraint loss, Represents the coefficient that controls the weight of the gradient multiplication term, set , represents the gradient calculation, represents the polynomial kernel function used to measure the nonlinear relationship between the generated data samples and the target irrigation pump station data, represents the order of the polynomial kernel function, express norm, represents the strength coefficient of the randomly generated constraint term, Indicates the use of random factors The amount of change in the output of the post-generator, the randomness factor , represents the hyperparameter controlling the noise amplitude, Indicates that the mean is zero and the variance is the unit matrix Normally distributed noise; (3) Train the discriminator network: The discriminator uses weighted feature distribution adversarial loss to dynamically adjust the adaptive weighting coefficient through the feedback mechanism, calculate the total loss of the discriminator with enhanced distinguishing ability, and then calculate the total loss function of the discriminator. The calculation formula is as follows: , , in, represents the total loss function of the discriminator, represents the weighted coefficient of the discriminator loss, represents the feature distribution adversarial loss function of the discriminator, represents the first adaptive weighting coefficient of the discriminator, represents the second adaptive weighting coefficient of the discriminator; The adaptive weighting coefficient of the discriminator is dynamically updated based on the feedback control method. The calculation formula is as follows: , , in, Indicates a parameter update operation. and Respectively represent the first adaptive weighting coefficient and the second adaptive weighting coefficient of the updated discriminator, Represents the learning rate of the adaptive weight coefficient, set , It means to find partial derivative; (4) Co-optimize the generator and discriminator: The generator and discriminator are collaboratively optimized through the feedback control mechanism. The calculation formula is as follows: , , in, and Respectively represent the optimized generator parameters and discriminator parameters, and Respectively represent the generator parameters and discriminator parameters before optimization, represents the learning rate of the generator, represents the learning rate of the discriminator, Represents the generator loss function pair The gradient of Denotes the discriminator loss function The gradient of (5) Optimize the generated data samples: The generated data samples are optimized by nonlinear fitting, the nonlinear feature distribution is captured and improved, the generated irrigation pump station data is corrected by local weighting to make it more consistent with the real irrigation pump station data feature distribution, and the distribution of the generated data samples and the real samples in high-dimensional space is optimized and corrected by cosine similarity and difference penalty terms. The calculation formula is as follows: , in, represents the optimized irrigation pump station data sample, Represents the cosine similarity calculation function, represents the adjustment coefficient for penalizing the difference between the generated irrigation pump station data and the original irrigation pump station data, represents the corrected irrigation pump station data features, that is, the irrigation pump station data features generated by the generator, Represents, that is, the real irrigation pump station data characteristics; (6) Repeat the above steps (1)-(5) and set the stop iteration condition until the preset iteration condition is met, thus completing the data sample expansion.

[0027] In a specific implementation, the process of data dimensionality reduction based on the dynamic projection autoencoder algorithm is as follows: The autoencoder algorithm based on dynamic projection is optimized to improve the dimensionality reduction effect. The autoencoder is optimized by randomly initializing its parameters. The forward propagation of the autoencoder is realized through the ReLU activation function. The parameters are iteratively updated by the gradient descent method to minimize the reconstruction error and dynamically adjust the projection direction. The Softmax function is used to classify the reduced data into low operating efficiency, medium operating efficiency and high operating efficiency. The data feature category with the largest class probability is used as the category for the comprehensive evaluation of the operating efficiency of the irrigation pump station, and the prediction result of the operating efficiency of the irrigation pump station is obtained.

[0028] In a specific implementation manner, the data dimension reduction process is as follows: The weight matrix and bias term of the autoencoder are randomly initialized. The initialized parameters obey the normal distribution with a mean of 0 and a variance of the unit matrix. The forward propagation of the irrigation pump station data in the autoencoder is realized through the ReLU activation function. The calculation formula is as follows: , in, represents the features after dimensionality reduction, represents the autoencoder function, Using ReLU activation function, represents the irrigation pump station data input to the autoencoder, represents the weight matrix of the autoencoder, Represents the bias term of the autoencoder; The weight matrix of the autoencoder and the bias term For passing The final result obtained by the iterative update, the update process is as follows: , , in, Indicates the number of iterations The index of , and Respectively represent Second and The weight matrix of the autoencoder after the iteration update, and Respectively represent Second and The bias term of the autoencoder after the iteration update, represents the learning rate, , represents the loss function of the autoencoder, represents the gradient of the autoencoder function with respect to the weight matrix, represents the gradient of the autoencoder with respect to the bias term; By optimizing the projection of the high-dimensional features of the input irrigation pump station data, the projection direction of the autoencoder is dynamically adjusted to calculate the irrigation pump station data input to the autoencoder. Reconstruction error of irrigation pump station data after dimensionality reduction , and then calculate the total loss of the autoencoder , the calculation formula is as follows: , , , , in, represents the inverse operation of the autoencoder function, represents the transpose of the decoder weight matrix, represents the transposed bias term of the decoder, Represents the projection matrix The regularization weight of Represents the projection matrix The Frobenius norm of represents the relaxed constraint, represents the slack constraint weight, Represents the projection matrix The transpose of Represents the regularization term weight of the feature after dimensionality reduction, set , represents the regularization term after dimensionality reduction, represents the number of features of the irrigation pump station data input to the autoencoder, express The index of Indicates The representation of a feature after dimensionality reduction; Projection Matrix Update for iteration The final result after the projection matrix is ​​updated according to the gradient calculation rule. The calculation formula is as follows: , , , in, Indicates the number of iterations The index of , and Respectively represent Second and The updated projection matrix after iterations is: , Indicates the input The loss function value of the autoencoder is and Respectively represent Second and The learning rate of the projection matrix at the iteration update, represents the gradient of the encoder’s total loss with respect to the projection matrix, Represents the hyperparameter that controls the adaptive step size, set , represents the gradient of the total loss of the autoencoder; According to setting the convergence threshold of the autoencoder Determine whether convergence has been reached, set ,like , the algorithm converges and outputs the final stable dimensionality reduction result.

[0029] Example 2 In order to verify the influence of the learning rate of the adaptive weight coefficient on the training, such as Figure 2 As shown in the figure, by comparing different learning rates and batch sizes, it can be seen that the generator still maintains a low training time under the conditions of large batch and small learning rate, thereby improving the training efficiency of the model and solving the problem of slow convergence of traditional generative models on high-complexity data distributions.

[0030] Example 3 like Figure 3 As shown in the figure, through feature distribution adversarial loss and adaptive mapping matrix correction, the generated data is closer to the real data in feature distribution, avoiding the deviation phenomenon that is easy to occur in the generator. The distribution curve of the generated data is highly consistent with the real data, indicating that the generator captures the characteristic distribution of the real irrigation pump station data.

[0031] Example 4 like Figure 4 As shown in the figure, by comparing the reconstruction errors of different dimensionality reduction algorithms, the experimental data show that the autoencoder based on dynamic projection can effectively reduce the reconstruction error during dimensionality reduction. Compared with the traditional principal component analysis method, it has lower reconstruction error in each feature dimension.

[0032] Example 5 like Figure 5 As shown in the figure, by comparing the reconstruction errors of different dimensionality reduction algorithms, the experimental data show that the autoencoder based on dynamic projection can effectively reduce the reconstruction error during dimensionality reduction. Compared with the traditional principal component analysis method, it has lower reconstruction error in each feature dimension.

[0033] Although the above describes the specific implementation mode of the invention in conjunction with the drawings, it is not intended to limit the scope of protection of the invention. Based on the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present invention.

Claims

1. A training method for a comprehensive evaluation model of irrigation pump station operation efficiency, characterized in that: Model training is based on incremental learning. The training method is as follows: Import the original irrigation pump station data set into the existing offline irrigation pump station operation efficiency comprehensive evaluation model for training to obtain a basic efficiency evaluation model, input the new irrigation pump station data set into the basic efficiency evaluation model, and judge whether the newly input irrigation pump station data set is available. If not, terminate the training of the model and output the basic efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the basic efficiency evaluation model for training to generate the efficiency evaluation model, input the new irrigation pump station data set into the newly generated efficiency evaluation model again, and judge whether the new irrigation pump station data set is available. If not, terminate the training of the model and output the newly generated efficiency evaluation model. If available, fuse the new irrigation pump station data set with the prediction result of the model, input the fused data into the newly generated efficiency evaluation model for training, and generate a new efficiency evaluation model again. Iterate multiple times until the final efficiency evaluation model is output. The final efficiency evaluation model outputs the prediction result of the operation efficiency of the irrigation pump station. When the data in the irrigation pump station dataset is insufficient for multiple trainings, a generative adversarial network based on feature distribution adversarial loss is used to expand the data samples. After sample expansion, an autoencoder algorithm based on dynamic projection is used to reduce the data dimension.

2. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 1 is characterized in that: The incremental learning process is as follows: The incremental learning process is a process of continuous learning through training. When the irrigation pump station is performing a task, the comprehensive evaluation model of the irrigation pump station operation efficiency evaluates the operation efficiency of the pump station based on the data collected during the task execution. At the same time, the operation efficiency of the irrigation pump station is manually labeled, and the labeled labels are low operation efficiency, medium operation efficiency and high operation efficiency. The irrigation pump station is input into the basic efficiency evaluation model when performing its first task. The irrigation pump station dataset is represented as ,judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the second task Irrigation pump station dataset, judge Is the data available? If available, a new efficiency evaluation model is obtained. ,Will Efficiency prediction results As pseudo labels and datasets Fusion to obtain a new data set And used for Training,dataset Indicates that the irrigation pump station is input into the new efficiency evaluation model when performing the third task Irrigation pump station dataset, judge Is the data available in multiple iterations? After the task, the dataset When it is unavailable, the iteration is stopped, that is, the training process of the model by incremental learning is terminated, and the final efficiency evaluation model is output. , Indicates that the irrigation pump station is in operation task, input into the new efficiency evaluation model The irrigation pump station dataset and the final efficiency evaluation model The output efficiency prediction result is expressed as , used for training The data set is represented as , The pseudo-labels are integrated into Efficiency prediction results and dataset , .

3. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 2 is characterized in that: The conditions for judging whether the data in the new irrigation pump station dataset is available are as follows: The operating efficiency of the irrigation pump station is manually labeled, and the labeled content is the operating efficiency of the irrigation pump station, which is low operating efficiency, medium operating efficiency and high operating efficiency. The data in the labeled new irrigation pump station dataset is input into the basic efficiency evaluation model for training, and the accuracy of the trained basic efficiency evaluation model is compared with the accuracy of the untrained basic efficiency evaluation model. If the accuracy of the trained basic efficiency evaluation model is improved, the data in the new irrigation pump station dataset is available, otherwise it is not available.

4. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 3 is characterized in that: Construct an irrigation pump station dataset: The relevant data of the irrigation pump station operation process is monitored through a variety of sensors, and the relevant operation events and environmental data are recorded at the same time. The sensors include flow meters, pressure sensors, current sensors and temperature sensors. The data collected by the monitoring process sensors include real-time electrical, mechanical and hydraulic data. Operation events include manual intervention of pump station operators, start and stop of pump stations and fault records of pump stations. Environmental data include climate, meteorology and soil moisture. The collected data is uniformly stored in a distributed database system in a standardized storage format.

5. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 4 is characterized in that: The process of data sample expansion based on the generative adversarial network with feature distribution adversarial loss is as follows: Data samples are expanded through the generator and discriminator. Specifically, the generator is optimized through feature distribution adversarial loss and polynomial kernel function, and the discriminator is trained using weighted feature distribution adversarial loss and adaptive weighting coefficients. The collaborative optimization of the generator and the discriminator is achieved through the feedback control mechanism, thereby generating more realistic irrigation pump station data.

6. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 5 is characterized in that: The specific process of data sample expansion is as follows: (1) The characteristic distribution of the data in the collected irrigation pump station data set is corrected through the adaptively calculated mapping matrix. The calculation process is as follows: ， ， in, The mapping matrix representing the characteristics of irrigation pump station data, represents the weight coefficient of the mapping matrix, represents the standard deviation of the input irrigation pump station data, represents the mean of the input irrigation pump station data, Indicates the number of irrigation pump station data features input in the current batch. express The index of Indicates Irrigation pump station data features, Represents the original pump station data characteristics, , represents the corrected irrigation pump station data characteristics, represents the mapping function, Represents the mapping function about The Jacobian matrix of The principal component analysis function was used; (2) Optimize the generator network: The nonlinear data characteristics of the irrigation pump station are captured by the feature distribution adversarial loss and polynomial kernel function optimization generator. The polynomial kernel function is used to fit the flow characteristic curve of the pump station. The nonlinear changes under actual working conditions are correctly characterized by adjustment, and then the irrigation pump station data that fits the actual situation is generated. The basic adversarial loss calculation formula of the generator is as follows: ， in, Representation Generator The basic adversarial loss, express Subject to the characteristic distribution of irrigation pump station data expectations, represents the discriminator, A random noise vector representing the input generator Subject to the noise distribution expectations; At the same time, the feature distribution is used to constrain the adversarial loss, and the randomness factor input by the perturbation generator is used to randomly generate the constraint loss, and then the total loss is calculated. The calculation formula is as follows: ， ， ， ， in, Represents the weighted coefficient for adjusting the feature distribution against the loss strength, represents the weighted coefficient for adjusting the strength of the randomly generated constraint loss, Representation Generator The feature distribution of adversarial loss, represents the randomly generated constraint loss, represents the coefficient that controls the weight of the gradient multiplication term, represents the gradient calculation, represents the polynomial kernel function used to measure the nonlinear relationship between the generated data samples and the target irrigation pump station data, represents the order of the polynomial kernel function, express norm, represents the strength coefficient of the randomly generated constraint term, Indicates the use of random factors The amount of change in the output of the post-generator, the randomness factor , represents the hyperparameter controlling the noise amplitude, Indicates that the mean is zero and the variance is the unit matrix Normally distributed noise; (3) Train the discriminator network: The discriminator uses weighted feature distribution adversarial loss to dynamically adjust the adaptive weighting coefficient through the feedback mechanism, calculate the total loss of the discriminator with enhanced distinguishing ability, and then calculate the total loss function of the discriminator. The calculation formula is as follows: ， ， in, represents the total loss function of the discriminator, represents the weighted coefficient of the discriminator loss, represents the feature distribution adversarial loss function of the discriminator, represents the first adaptive weighting coefficient of the discriminator, represents the second adaptive weighting coefficient of the discriminator; The adaptive weighting coefficient of the discriminator is dynamically updated based on the feedback control method. The calculation formula is as follows: ， ， in, Indicates a parameter update operation. and Respectively represent the first adaptive weighting coefficient and the second adaptive weighting coefficient of the updated discriminator, represents the learning rate of the adaptive weight coefficient, It means to find partial derivative; (4) Co-optimize the generator and discriminator: The generator and discriminator are collaboratively optimized through the feedback control mechanism. The calculation formula is as follows: ， ， in, and Respectively represent the optimized generator parameters and discriminator parameters, and Respectively represent the generator parameters and discriminator parameters before optimization, represents the learning rate of the generator, represents the learning rate of the discriminator, Represents the generator loss function pair The gradient of Denotes the discriminator loss function The gradient of (5) Optimize the generated data samples: The generated data samples are optimized by nonlinear fitting, the nonlinear feature distribution is captured and improved, the generated irrigation pump station data is corrected by local weighting to make it more consistent with the real irrigation pump station data feature distribution, and the distribution of the generated data samples and the real samples in high-dimensional space is optimized and corrected by cosine similarity and difference penalty terms. The calculation formula is as follows: ， in, represents the optimized irrigation pump station data sample, Represents the cosine similarity calculation function, represents the adjustment coefficient for penalizing the difference between the generated irrigation pump station data and the original irrigation pump station data, represents the corrected irrigation pump station data features, that is, the irrigation pump station data features generated by the generator, Represents, that is, the real irrigation pump station data characteristics; (6) Repeat the above steps (1)-(5) and set the stop iteration condition until the preset iteration condition is met, thus completing the data sample expansion.

7. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 6 is characterized by: The process of data dimensionality reduction based on the dynamic projection autoencoder algorithm is as follows: The autoencoder algorithm based on dynamic projection is optimized to improve the dimensionality reduction effect. The autoencoder is optimized by randomly initializing its parameters. The forward propagation of the autoencoder is realized through the ReLU activation function. The parameters are iteratively updated by the gradient descent method to minimize the reconstruction error and dynamically adjust the projection direction. The Softmax function is used to classify the reduced data into low operating efficiency, medium operating efficiency and high operating efficiency. The data feature category with the largest class probability is used as the category for the comprehensive evaluation of the operating efficiency of the irrigation pump station, and the prediction result of the operating efficiency of the irrigation pump station is obtained.

8. The irrigation pump station operation efficiency comprehensive evaluation model training method according to claim 7 is characterized in that: The specific process of data dimensionality reduction is as follows: The weight matrix and bias term of the autoencoder are randomly initialized. The initialized parameters obey the normal distribution with a mean of 0 and a variance of the unit matrix. The forward propagation of the irrigation pump station data in the autoencoder is realized through the ReLU activation function. The calculation formula is as follows: ， in, represents the features after dimensionality reduction, represents the autoencoder function, Using ReLU activation function, represents the irrigation pump station data input to the autoencoder, represents the weight matrix of the autoencoder, Represents the bias term of the autoencoder; The weight matrix of the autoencoder and the bias term For passing The final result obtained by the iterative update, the update process is as follows: ， ， in, Indicates the number of iterations The index of , and Respectively represent Second and The weight matrix of the autoencoder after the iteration update, and Respectively represent Second and The bias term of the autoencoder after the iteration update, represents the learning rate, represents the loss function of the autoencoder, represents the gradient of the autoencoder function with respect to the weight matrix, represents the gradient of the autoencoder with respect to the bias term; By optimizing the projection of the high-dimensional features of the input irrigation pump station data, the projection direction of the autoencoder is dynamically adjusted to calculate the irrigation pump station data input to the autoencoder. Reconstruction error of irrigation pump station data after dimensionality reduction , and then calculate the total loss of the autoencoder , the calculation formula is as follows: ， ， ， ， in, represents the inverse operation of the autoencoder function, represents the transpose of the decoder weight matrix, represents the transpose of the decoder bias term, Represents the projection matrix The regularization weight of Represents the projection matrix The Frobenius norm of represents the relaxed constraint, represents the slack constraint weight, Represents the projection matrix The transpose of represents the regularization term weight of the feature after dimensionality reduction, represents the regularization term after dimensionality reduction, represents the number of features of the irrigation pump station data input to the autoencoder, express The index of Indicates The representation of a feature after dimensionality reduction; Projection Matrix Update for iteration The final result after the projection matrix is ​​updated according to the gradient calculation rule. The calculation formula is as follows: ， ， ， in, Indicates the number of iterations The index of , and Respectively represent Second and The updated projection matrix after iterations is: , Indicates the input The loss function value of the autoencoder is and Respectively represent Second and The learning rate of the projection matrix during the iteration update, represents the gradient of the encoder’s total loss with respect to the projection matrix, represents the hyperparameter controlling the adaptive step size, represents the gradient of the total loss of the autoencoder; According to setting the convergence threshold of the autoencoder Determine whether the convergence state has been reached. If , the algorithm converges and outputs the final stable dimensionality reduction result.

Images