Adaptive Load Balancing Multi-Pump Confluence Control Method and System

Abstract

The present invention provides an adaptive load balancing multi-pump confluence control method and system, which relates to the technical field of multi-pump control and includes: collecting multiple confluence pump status information of the multiple confluence pumps; collecting operation load information; converting and evenly distributing the basic confluence flow rate to obtain the total confluence flow rate and multiple basic confluence flow rates; constructing a confluence function to balance the wear parameters of multiple selected confluence pumps and minimize the noise and temperature of the multiple selected confluence pumps; based on the multiple basic confluence flow rates and the confluence function, according to the multiple confluence pump status information, performing multi-pump confluence control optimization to obtain an optimal confluence control parameter combination, and performing multi-pump confluence control on the multiple selected confluence pumps. The present invention solves the technical problem in the multi-pump confluence control of the prior art that precise adjustment cannot be made according to the actual operation load and the pump status information, resulting in uneven load distribution and inaccurate control of the pumps, thereby reducing the service life of the pumps and the stability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-pump control, and particularly to a multi-pump confluence control method and system with adaptive load balancing. Background Art

[0002] In a multi-pump confluence system, how to accurately adjust the operating parameters of each pump is a major challenge. First of all, traditional methods cannot respond to load changes in real time, resulting in the system not achieving the best energy efficiency and stability. Secondly, in a multi-pump system, the loads of the pumps are often unbalanced. Some pumps may work excessively, while other pumps may be idle. This load imbalance leads to low operating efficiency of the pumps, increases the energy consumption and maintenance costs of the system. At the same time, due to the uneven load, some pumps may bear excessive pressure and flow, resulting in excessive wear and noise problems. This not only affects the service life of the pumps, but also may affect the overall stability and operating comfort of the system. Summary of the Invention

[0003] This application provides a multi-pump confluence control method and system with adaptive load balancing, aiming to solve the technical problem that in the multi-pump confluence control of the prior art, precise adjustment cannot be made according to the actual operation load and the state information of the pumps, resulting in uneven load distribution and inaccurate control of the pumps, thereby reducing the service life of the pumps and the stability of the system.

[0004] In the first aspect disclosed in this application, a multi-pump confluence control method with adaptive load balancing is provided. The method is applied to a multi-pump confluence hydraulic device, and the device includes a plurality of confluence pumps. The method includes: collecting a plurality of confluence pump state information of the plurality of confluence pumps, wherein each confluence pump state information includes pump flow information and hydraulic oil temperature information; collecting operation load information of the multi-pump confluence operation; according to the operation load information, converting and evenly distributing the basic confluence flow of the plurality of confluence pumps to obtain the total confluence flow and the basic confluence flows of the plurality of selected confluence pumps; constructing a confluence function for multi-pump confluence control to balance the wear parameters of the plurality of selected confluence pumps and minimize the noise and temperature of the plurality of selected confluence pumps; based on the plurality of basic confluence flows and the confluence function, according to the plurality of confluence pump state information, performing multi-pump confluence control optimization to obtain an optimal confluence control parameter combination, and performing multi-pump confluence control on the plurality of selected confluence pumps.

[0005] The second aspect disclosed in this application provides an adaptive load-balanced multi-pump confluence control system, which is applied to a multi-pump confluence hydraulic device. The device includes multiple confluence pumps. The system is used for the above-mentioned adaptive load-balanced multi-pump confluence control method. The system includes: a status information acquisition module, which is used to acquire the status information of the multiple confluence pumps, where each confluence pump status information includes pump flow information and hydraulic oil temperature information; a load information acquisition module, which is used to acquire the operation load information of the multi-pump confluence operation; a confluence flow acquisition module, which is used to convert and evenly distribute the basic confluence flow of the multiple confluence pumps according to the operation load information to obtain the total confluence flow and the basic confluence flows of the multiple selected confluence pumps; a confluence function construction module, which is used to balance the wear parameters of the multiple selected confluence pumps, minimize the noise and temperature of the multiple selected confluence pumps, and construct a confluence function for multi-pump confluence control; a multi-pump confluence control module, which is used to perform multi-pump confluence control optimization based on the multiple basic confluence flows and the confluence function, according to the status information of the multiple confluence pumps, obtain the optimal confluence control parameter combination, and perform multi-pump confluence control on the multiple selected confluence pumps.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By collecting the status information of multiple confluence pumps in real time, including pump flow and hydraulic oil temperature, and collecting operation load information, the flow distribution of the pumps can be automatically adjusted according to the actual load, which can ensure the load balance of the pumps, reduce the overload of some pumps, and improve the working stability and efficiency of the system; by constructing a confluence function to balance the wear parameters, noise and temperature of the pumps, the balanced use of the pumps can be achieved during the multi-pump confluence control process, while reducing the excessive wear and noise of a single pump, extending the service life of the pumps, and improving the overall reliability of the system; by converting and distributing the basic confluence flow and combining the confluence function for control optimization, the control parameters of the pumps can be adjusted more precisely, which enables the system to dynamically adjust the operation state of the pumps according to different operation loads, improving the energy efficiency and control accuracy of the system; through the iterative optimization algorithm, optimizing the control parameters based on the confluence function can find the optimal control parameter combination under changing working conditions, and through cross-update and iterative adjustment, a dynamic and adaptive control optimization scheme is provided to ensure that the system can maintain the best control effect under various load conditions, effectively improving the global optimization ability.

[0008] The above description is only an overview of the technical solution of the present application. In order to be able to more clearly understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below. Description of the Drawings

[0009] Figure 1 It is a schematic flowchart of the adaptive load balancing multi-pump confluence control method provided by the embodiment of the present application;

[0010] Figure 2 It is a schematic structural diagram of the adaptive load balancing multi-pump confluence control system provided by the embodiment of the present application.

[0011] Description of the reference numerals: The status information acquisition module 10, the load information acquisition module 20, the confluence flow rate acquisition module 30, the confluence function construction module 40, and the multi-pump confluence control module 50. Specific Embodiments

[0012] The embodiment of the present application provides an adaptive load balancing multi-pump confluence control method and system, which solves the technical problem in the multi-pump confluence control of the prior art that it is impossible to make precise adjustments according to the actual operating load and the status information of the pumps, resulting in uneven load distribution and inaccurate control of the pumps, thereby reducing the service life of the pumps and the stability of the system.

[0013] After introducing the basic principle of the present application, the various non-limiting embodiments of the present application will be specifically introduced below in conjunction with the drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Embodiment 1, as Figure 1 shown, the embodiment of the present application provides an adaptive load balancing multi-pump confluence control method, which is applied to a multi-pump confluence hydraulic device, and the device includes a plurality of confluence pumps. The method includes:

[0015] Collect the state information of a plurality of confluence pumps of the plurality of confluence pumps, wherein each confluence pump state information includes pump flow information and hydraulic oil temperature information.

[0016] The adaptive load balancing multi-pump confluence control method provided by the embodiments of the present application is applied to a multi-pump confluence hydraulic device. The device includes multiple confluence pumps, that is, multiple confluence pumps are connected to a hydraulic device to achieve multi-pump confluence control. A flow sensor and a temperature sensor are installed on each confluence pump. The flow of hydraulic oil is monitored in real time through the flow sensor to obtain pump flow information. The pump flow information refers to the amount of hydraulic oil output by the hydraulic pump per unit time, usually in liters per minute. The pump flow information reflects the working efficiency of the pump and the operating state of the hydraulic system. The temperature of the hydraulic oil is monitored in real time through the temperature sensor to obtain hydraulic oil temperature information. The hydraulic oil temperature information refers to the real-time temperature of the hydraulic oil, usually in degrees Celsius. The hydraulic oil temperature information reflects the heat load and heat dissipation of the hydraulic system. Excessive temperature may cause a decrease in the efficiency of the hydraulic system and equipment damage. Integrate the pump flow information and the hydraulic oil temperature information of each confluence pump to obtain multiple confluence pump status information.

[0017] Furthermore, collecting the multiple confluence pump status information of the multiple confluence pumps includes:

[0018] Collect the multiple current pump flow information of the multiple confluence pumps; collect the multiple current hydraulic oil temperature information of the multiple confluence pumps; integrate the multiple pump flow information and the multiple hydraulic oil temperature information to obtain multiple confluence pump status information.

[0019] Install flow sensors at the inlet and outlet or inside the pump body of each confluence pump. These sensors can measure the flow of liquid through the pump in real time. Use the flow sensors to collect the flow data of each pump, and summarize to obtain multiple pump flow information. The pump flow information refers to the amount of hydraulic oil output by the hydraulic pump per unit time, usually in liters per minute. The pump flow information reflects the working efficiency of the pump and the operating state of the hydraulic system.

[0020] Install temperature sensors in the hydraulic oil circuit of each confluence pump. These sensors can measure the temperature of the hydraulic oil in real time. Use the temperature sensors to collect the hydraulic oil temperature data of each pump, and summarize to obtain multiple hydraulic oil temperature information. The hydraulic oil temperature information refers to the real-time temperature of the hydraulic oil, usually in degrees Celsius. The hydraulic oil temperature information reflects the heat load and heat dissipation of the hydraulic system. Excessive temperature may cause a decrease in the efficiency of the hydraulic system and equipment damage.

[0021] Combine the flow information and the hydraulic oil temperature information of each pump to generate a comprehensive status information. Traverse multiple pumps to obtain multiple confluence pump status information, providing basic data for subsequent optimization control.

[0022] Collect the operation load information of the multi-pump confluence operation.

[0023] The operation load information refers to the load that the hydraulic system needs to bear during actual operation, including the weight of the load to be supported or lifted and the moving speed. These information reflect the working requirements of the hydraulic system under specific operation conditions. A weight sensor and a speed sensor are installed at key positions of the hydraulic system. The load weight is measured by the weight sensor, the moving speed of the hydraulic actuator is measured by the speed sensor, and the load weight and moving speed are read through the sensor interface to obtain the operation load information.

[0024] According to the operation load information, convert and evenly distribute the basic confluence flow rates of the multiple confluence pumps to obtain the total confluence flow rate and the basic confluence flow rates of the multiple selected confluence pumps.

[0025] According to the operation load information, convert and obtain the total confluence flow rate required for this load. Specifically, analyze the weight load to be supported or lifted and the moving speed. The greater the weight load and the faster the moving speed, the greater the required hydraulic flow rate. Obtain the total confluence flow rate according to the analysis result. Decide the number of confluence pumps required under this load. For a small load, not too many confluence pumps are needed to work, reducing power consumption. Randomly select multiple selected confluence pumps according to the number, and then evenly divide the total confluence flow rate to obtain multiple basic confluence flow rates.

[0026] Furthermore, according to the operation load information, convert and evenly distribute the basic confluence flow rates of the multiple confluence pumps to obtain the total confluence flow rate and the basic confluence flow rates of the multiple selected confluence pumps, including:

[0027] According to the operation load information, decide and obtain the number of confluence pumps, and randomly select multiple selected confluence pumps with the number of confluence pumps; based on the historical operation data of multi-pump confluence, collect the sample operation load information set and the sample total confluence flow rate set; use the sample operation load information set and the sample total confluence flow rate set to train the total confluence flow rate converter; based on the total confluence flow rate converter, perform confluence flow rate conversion on the operation load to obtain the total confluence flow rate; distribute the total confluence flow rate according to the number of confluence pumps to obtain multiple basic confluence flow rates.

[0028] According to the historical operation data of multi-pump confluence, establish a relationship model between the load and the flow rate requirement based on a decision tree. Use this model to predict the required number of confluence pumps, and this number of confluence pumps needs to be rounded according to the actual situation. Randomly select the required number of pumps from all available confluence pumps for operation to ensure optimizing the resource utilization of the system while meeting the operation requirements.

[0029] Extract data from historical operation records and retrieve multi-pump confluence historical operation data. This data includes the recorded data of multi-pump confluence operations over a past period of time, including the operation load and the corresponding total confluence flow rate of historical operations. Extract a representative set of sample operation load information from it. This set contains operation load data such as load weight, moving speed, etc., and a set of sample total confluence flow rates, which contains confluence flow rate data corresponding to the sample operation load information.

[0030] Select a suitable model for training, such as a support vector machine, neural network, etc. Divide the data set into a training set and a test set. The training set is used to train the model, and the test set is used to verify the performance of the model. For example, the splitting ratio is 80% for the training set and 20% for the test set. Use the training set data to train the model so that it can learn the relationship between the load information and the total confluence flow rate. Use the test set to evaluate the prediction performance of the model, check the accuracy, error, and other performance metrics of the model. According to the feedback of the model performance, adjust the model parameters to improve the prediction accuracy. Cross-validation can be used to select the best model parameters. Finally, obtain a model that meets the accuracy requirements as the total confluence flow rate converter for real-time prediction of the total confluence flow rate required by the operation load information.

[0031] Input the operation load information into the total confluence flow rate converter. The converter model uses the features and patterns learned during the training process to predict the total confluence flow rate that matches the operation load and outputs the required total confluence flow rate. This value represents the overall flow rate required by the system under a specific operation load. Evenly distribute the total confluence flow rate to multiple selected confluence pumps. This can be achieved through simple equal division, so that each pump processes an equal flow rate to obtain multiple basic confluence flow rates.

[0032] Furthermore, according to the operation load information, make a decision to obtain the number of confluence pumps, including:

[0033] Based on the multi-pump confluence historical operation data, collect a set of sample operation load information and the number of sample confluence pumps; use the set of sample operation load information and the number of sample confluence pumps, and based on a decision tree, construct a decision maker for the number of confluence pumps to be enabled; based on the decision maker for the number of confluence pumps to be enabled, input and make a decision on the operation load information to obtain the number of confluence pumps.

[0034] Extract data from historical operation records to obtain multi-pump confluence historical operation data. This data includes the operation load information of multi-pump confluence operations and the actual number of confluence pumps used. Extract representative operation loads from it, as well as the actual number of pumps used for each set of operation load information, to form a set of sample operation load information and the number of sample confluence pumps.

[0035] A decision tree is a supervised learning model based on feature selection, used for classification and regression tasks. The model represents the decision-making process through a tree structure, where each node represents a feature, each branch represents a feature value, and the leaf node represents a predicted value. The job load information is extracted from the original data as a feature vector, including load weight, moving speed, etc. The number of combined pumps is used as the target variable. The preprocessed dataset is input into the decision tree algorithm for training to generate a decision tree model. The cross-validation technique is used to evaluate the accuracy and robustness of the model. Finally, a decision tree model that meets the accuracy requirements is obtained as the decision maker for the number of enabled combined pumps, which is used to predict new job load conditions to determine the number of combined pumps that need to be enabled.

[0036] Input the job load information into the decision maker for the number of enabled combined pumps to predict the required number of combined pumps, which is used to adjust the number of enabled pumps to adapt to real-time job load conditions.

[0037] To balance the wear parameters of the multiple selected combined pumps and minimize the noise and temperature of the multiple selected combined pumps, a combined flow function for multi-pump combined flow control is constructed.

[0038] During the multi-pump combined flow control process, calculate the wear parameter of each combined pump and obtain its distribution discreteness, which can be represented by statistical quantities such as standard deviation or variance. Calculate the ratio of the hydraulic oil temperature of each combined pump to the preset temperature and find the average value. Calculate the ratio of the noise of each combined pump to the preset noise and find the average value. Perform a weighted operation on the distribution discreteness of the wear parameters, the temperature ratio, and the noise ratio to obtain a combined flow function for multi-pump combined flow control, thereby achieving the balance of the wear parameters of the combined pumps and minimizing the noise and temperature during the multi-pump combined flow control process.

[0039] Furthermore, to balance the wear parameters of the multiple selected combined pumps and minimize the noise and temperature of the multiple selected combined pumps, a combined flow function for multi-pump combined flow control is constructed as follows:

[0040] ;

[0041] where MPM is the combined flow fitness, , and are weights, is the distribution discreteness information of the multiple combined pump wear parameters of the multiple selected combined pumps analyzed by combining multiple combined flow control parameters with the multiple combined pump status information. M is the number of multiple selected combined pumps, is the controlled hydraulic oil temperature of the i-th selected combined pump under the combined pump status information and combined flow control parameters, is the preset hydraulic oil temperature, is the noise of the i-th selected confluence pump under the confluence pump status information and confluence control parameters, is the preset noise.

[0042] Specifically, the confluence function is as follows:

[0043] ;

[0044] In this confluence function, the first term calculates the logarithm of the wear parameter, and the weight represents its influence degree on the confluence fitness; the second term calculates the logarithm of the temperature ratio, and the temperature ratio characterizes the deviation degree of the controlled hydraulic oil temperature from the preset hydraulic oil temperature, and the weight represents the influence degree of the temperature term on the confluence fitness; the third term calculates the logarithm of the noise ratio, and the noise ratio characterizes the deviation degree of the confluence pump noise from the preset noise, and the weight represents the influence degree of the noise term on the confluence fitness. Through this confluence function, the wear, temperature and noise of each confluence pump are converted into logarithms and weighted and summed to calculate the overall confluence fitness, which helps to smooth and standardize the influence of different parameters on the system performance, and then evaluate and obtain the confluence fitness. The fitness value calculated by the confluence function helps to determine the pros and cons of the control parameters, so as to optimize the control strategy of the pump.

[0045] Based on the multiple basic confluence flows and the confluence function, according to the multiple confluence pump status information, perform multi-pump confluence control optimization to obtain the optimal confluence control parameter combination, and perform multi-pump confluence control on the multiple selected confluence pumps.

[0046] The obtained multiple basic confluence flows are used as initial control parameters, and a crossover operation is introduced to enhance the randomness of the solution and increase the global search ability. New control parameter combinations are generated through the crossover operation, and their fitness is evaluated using the confluence function. Using the crossover operation and the confluence fitness function, iterative optimization is performed on the basis of the multiple basic confluence flows to gradually obtain a better control parameter combination, and finally the confluence control parameter combination with the maximum confluence fitness is output as the optimal confluence control parameter combination. The obtained optimal confluence control parameter combination is used to perform multi-pump confluence control on the multiple selected confluence pumps to achieve the optimized control of multi-pump confluence.

[0047] Furthermore, based on the multiple basic confluence flows and the confluence function, according to the multiple confluence pump status information, perform multi-pump confluence control optimization to obtain the optimal confluence control parameter combination, including:

[0048] Taking the flow rates of the multiple basic confluence pumps as the adjustment direction, adjust the pump flow rate information of the multiple selected confluence pumps to obtain multiple adjusted pump flow rate information. Allocate the total confluence flow rate according to the ratio of the adjusted pump flow rate information to obtain multiple first confluence pump flow rates, which are used as the first confluence control parameter combination. Based on the first confluence control parameter combination and in combination with the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps, perform aging prediction, temperature prediction, and noise prediction respectively, and calculate the first confluence fitness based on the confluence function. Randomly cross-update the multiple first confluence pump flow rates to obtain multiple first cross-confluence control parameter combinations. In combination with the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps, perform aging prediction, temperature prediction, and noise prediction respectively, and calculate multiple first cross-confluence fitness values based on the confluence function. Continue to take the flow rates of the multiple basic confluence pumps as the adjustment direction, adjust the multiple adjusted pump flow rate information, and perform iterative optimization until convergence. Output the confluence control parameter combination with the maximum confluence fitness to obtain the optimal confluence control parameter combination.

[0049] Taking the flow rates of multiple basic confluence pumps as the adjustment direction, these flow rate values are the initial flow rate values of each confluence pump obtained through preliminary calculation. Adjust these flow rate values, and the adjustment can be to increase or decrease the pump flow rate to optimize performance. After adjustment, multiple adjusted pump flow rate information is obtained. Calculate the ratio of the multiple adjusted pump flow rate information, and allocate the total confluence flow rate according to the ratio, so that the flow rate of each pump after adjustment is consistent with the total confluence flow rate. The final flow rate is used as the first confluence control parameter combination for subsequent control and optimization.

[0050] Use historical data and prediction models to predict the aging status of each pump. The aging prediction model can be constructed based on the pump's operating time, load, and historical aging data. Use the hydraulic oil temperature information and control parameter combination to predict the temperature change of each pump under given control conditions. A regression model can be used for temperature prediction. Use the noise data and control parameter combination to predict the noise level of the pump. The noise prediction model can be trained based on the noise data and operating status. Substitute the aging, temperature, and noise prediction values, as well as the temperature and noise preset values, into the confluence function. The confluence function performs weighted calculation according to multiple objectives, including the lowest noise, optimal temperature, and minimum aging, to obtain the first confluence fitness of the first confluence control parameter combination to evaluate the performance of the control parameter combination.

[0051] Through random crossover operations, new combinations of confluence control parameters are generated to explore new solutions by swapping the flow values of two pumps, thereby enhancing the global optimization ability and randomness. Specifically, two pumps are randomly selected from the selected confluence pumps, and the flow values of these two pumps are swapped to generate a new flow combination. The updated flow combination is recorded as the first crossover confluence control parameter combination. The evaluation process of the foregoing steps is repeated to perform aging prediction, temperature prediction, and noise prediction on the first crossover confluence control parameter combination, and based on the confluence function, multiple first crossover confluence fitness values are calculated.

[0052] Set parameters such as the number of iterations and convergence threshold of the optimization algorithm. In each iteration, repeat the foregoing adjustment and crossover steps to adjust the flow parameters of the pumps. For each adjusted flow combination, use the confluence function to calculate the new confluence fitness. According to the newly calculated fitness value, select the flow combination with the maximum fitness as the current optimal parameter combination. If the optimization algorithm meets the convergence condition, such as the fitness change is less than the set threshold or the maximum number of iterations is reached, stop the optimization process; otherwise, continue to adjust the flow and perform the next iteration. Output the finally determined optimal confluence control parameter combination, that is, the flow combination that maximizes the confluence fitness, and this combination is used in actual multi-pump confluence control to achieve the best system performance.

[0053] Furthermore, based on the first confluence control parameter combination and in combination with the hydraulic oil temperature information in the confluence pump state information of the multiple selected confluence pumps, aging prediction, temperature prediction, and noise prediction are respectively performed, and based on the confluence function, the first confluence fitness is calculated, including:

[0054] Based on the test data of the confluence pumps, collect the sample confluence control parameter set, the sample hydraulic oil temperature information set, and collect the sample wear parameter set, the sample control hydraulic oil temperature set, and the sample confluence pump noise set; use the sample confluence control parameter set and the sample hydraulic oil temperature information set as input data, and use the sample wear parameter set, the sample control hydraulic oil temperature set, and the sample confluence pump noise set as supervision data to train the confluence predictor; use the confluence predictor to perform confluence control prediction on the multiple first confluence control parameters in the first confluence control parameter combination in combination with the hydraulic oil temperature information in the confluence pump state information of the multiple selected confluence pumps to obtain multiple first wear parameters, multiple first control hydraulic oil temperatures, and multiple first confluence pump noises; calculate the first aging distribution discreteness information of the multiple first wear parameters, and based on the confluence function, calculate the first confluence fitness.

[0055] In a laboratory environment, the confluence pump is tested and data is collected. The set of sample confluence control parameters obtained is a data set of confluence control parameters recorded under different test conditions; the set of sample hydraulic oil temperature information is a data set of hydraulic oil temperature data recorded during the test, and this data is used to analyze the temperature performance of the pump under different conditions; the set of sample wear parameters is the pump wear-related data recorded during the test, including the degree of pump wear, wear rate, etc.; the set of sample controlled hydraulic oil temperature is the hydraulic oil temperature data recorded under different control parameters, and this data is used to analyze the influence of control parameters on the oil temperature; the set of sample confluence pump noise is the pump noise data recorded during the test, and it is used to analyze the relationship between the noise level and control parameters and load.

[0056] Select a suitable type of prediction model, such as support vector machine, random forest, or neural network, etc. Select important features from the input data to construct a feature matrix. Use the sample confluence control parameters and sample hydraulic oil temperature information as input data, and use the sample wear parameters, sample controlled hydraulic oil temperature, and sample confluence pump noise as supervised data. Input the input data and supervised data into the model. Through an optimization algorithm, such as gradient descent, adjust the model parameters to minimize the prediction error. Use cross-validation techniques to evaluate the performance of the model to ensure the generalization ability of the model on different data sets. Adjust the hyperparameters of the model according to the evaluation results to improve the prediction performance, and obtain a prediction model that meets the accuracy requirements as the confluence predictor. This confluence predictor can predict the wear, hydraulic oil temperature, and noise of the confluence pump based on the input data, providing support for the optimization of multi-pump confluence control.

[0057] Combine each control parameter in the first confluence control parameter combination with the hydraulic oil temperature of the selected confluence pump as input data and input it into the confluence predictor. Use the predictor to predict the wear condition of each selected confluence pump, predict the hydraulic oil temperature of each selected confluence pump, and predict the noise level of each selected confluence pump, obtaining multiple first wear parameters, multiple first controlled hydraulic oil temperatures, and multiple first confluence pump noises.

[0058] For multiple first wear parameters, first calculate the mean of the wear parameters, and then calculate the variance of the wear parameters based on the mean. This variance describes the distribution discreteness of the wear parameters, and the discreteness reflects the change range and consistency of the wear parameters. The smaller the variance, the smaller the change range and the more consistent the wear parameters. Substitute the first aging distribution discreteness information into the confluence function, combine with other parameter terms, and calculate to obtain the first confluence fitness.

[0059] In summary, the adaptive load-balanced multi-pump confluence control method provided by the embodiments of this application has the following technical effects:

[0060] By collecting the status information of multiple confluence pumps in real time, including pump flow rate and hydraulic oil temperature, and collecting operation load information, it is possible to automatically adjust the flow distribution of the pumps according to the actual load, which can ensure the load balance of the pumps, reduce the overload of some pumps, and improve the working stability and efficiency of the system; by constructing a confluence function to balance the wear parameters, noise and temperature of the pumps, the balanced use of the pumps can be achieved during the multi-pump confluence control process, while reducing the excessive wear and noise of a single pump, extending the service life of the pumps, and enhancing the overall reliability of the system; by converting and distributing the basic confluence flow rate and combining the confluence function for control optimization, the control parameters of the pumps can be adjusted more precisely, which enables the system to dynamically adjust the operating state of the pumps according to different operation loads, improving the energy efficiency and control accuracy of the system; through the iterative optimization algorithm, optimizing the control parameters based on the confluence function can find the optimal combination of control parameters under changing working conditions, and through cross-updating and iterative adjustment, a dynamic and adaptive control optimization scheme is provided to ensure that the system can maintain the best control effect under various load conditions, effectively enhancing the global optimization ability.

[0061] Embodiment 2, based on the same inventive concept as the multi-pump confluence control method for adaptive load balancing in the foregoing embodiment, as Figure 2 shown, the embodiment of the present application provides a multi-pump confluence control system for adaptive load balancing, the system is applied to a multi-pump confluence hydraulic device, the device includes a plurality of confluence pumps, and the system includes:

[0062] A status information collection module 10, the status information collection module 10 is used to collect a plurality of confluence pump status information of the plurality of confluence pumps, wherein each confluence pump status information includes pump flow rate information and hydraulic oil temperature information; a load information collection module 20, the load information collection module 20 is used to collect the operation load information of the multi-pump confluence operation; a confluence flow rate acquisition module 30, the confluence flow rate acquisition module 30 is used to convert and evenly distribute the basic confluence flow rate of the plurality of confluence pumps according to the operation load information to obtain the total confluence flow rate and the basic confluence flow rates of a plurality of selected confluence pumps; a confluence function construction module 40, the confluence function construction module 40 is used to balance the wear parameters of the plurality of selected confluence pumps, minimize the noise and temperature of the plurality of selected confluence pumps, and construct a confluence function for multi-pump confluence control; a multi-pump confluence control module 50, the multi-pump confluence control module 50 is used to perform multi-pump confluence control optimization based on the plurality of basic confluence flow rates and the confluence function, according to the plurality of confluence pump status information, to obtain an optimal confluence control parameter combination, and perform multi-pump confluence control on the plurality of selected confluence pumps.

[0063] Furthermore, the system further includes a confluence pump status information acquisition module to perform the following operation steps:

[0064] Collect the current multiple pump flow rate information of the multiple combined pumps; collect the current multiple hydraulic oil temperature information of the multiple combined pumps; integrate the multiple pump flow rate information and the multiple hydraulic oil temperature information to obtain the multiple combined pump status information.

[0065] Furthermore, the system further includes a basic combined flow rate acquisition module to perform the following operation steps:

[0066] According to the operation load information, decide to obtain the number of combined pumps, and randomly select multiple selected combined pumps for the obtained number of combined pumps; based on the historical operation data of multi-pump combination, collect the sample operation load information set and the sample total combined flow rate set; use the sample operation load information set and the sample total combined flow rate set to train the total combined flow rate converter; based on the total combined flow rate converter, perform combined flow rate conversion on the operation load to obtain the total combined flow rate; perform distribution of the total combined flow rate according to the number of combined pumps to obtain multiple basic combined flow rates.

[0067] Furthermore, the system further includes a combined pump number acquisition module to perform the following operation steps:

[0068] Based on the historical operation data of multi-pump combination, collect the sample operation load information set and the sample number of combined pumps; use the sample operation load information set and the sample number of combined pumps, and based on the decision tree, construct a combined pump activation number decision maker; based on the combined pump activation number decision maker, perform input decision on the operation load information to obtain the number of combined pumps.

[0069] Furthermore, to balance the wear parameters of the multiple selected combined pumps and minimize the noise and temperature of the multiple selected combined pumps, construct a combined function for multi-pump combination control as follows:

[0070] ;

[0071] where MPM is the combination fitness, , and are weights, is the distribution discreteness information of the multiple combined pump wear parameters of the multiple selected combined pumps analyzed by combining the multiple combined pump state information with the multiple combined control parameters, M is the number of the multiple selected combined pumps, is the control hydraulic oil temperature of the i-th selected combined pump under the combined pump state information and the combined control parameters, is the preset hydraulic oil temperature, is the combined pump noise of the i-th selected combined pump under the combined pump state information and the combined control parameters, is the preset noise.

[0072] Furthermore, the system further includes an optimal confluence control parameter combination acquisition module to perform the following operation steps:

[0073] Taking the multiple basic confluence pump flow rates as the adjustment direction, adjust the pump flow rate information of the multiple selected confluence pumps to obtain multiple adjusted pump flow rate information. Allocate the total confluence flow rate according to the ratio of the adjusted pump flow rate information to obtain multiple first confluence pump flow rates as the first confluence control parameter combination. Based on the first confluence control parameter combination and in combination with the hydraulic oil temperature information in the confluence pump state information of the multiple selected confluence pumps, perform aging prediction, temperature prediction, and noise prediction respectively, and calculate and obtain the first confluence fitness based on the confluence function. Randomly cross-update the multiple first confluence pump flow rates to obtain multiple first cross-confluence control parameter combinations. In combination with the hydraulic oil temperature information in the confluence pump state information of the multiple selected confluence pumps, perform aging prediction, temperature prediction, and noise prediction respectively, and calculate and obtain multiple first cross-confluence fitnesses. Continue to take the multiple basic confluence pump flow rates as the adjustment direction, adjust the multiple adjusted pump flow rate information, and perform iterative optimization until convergence, and output the confluence control parameter combination with the maximum confluence fitness to obtain the optimal confluence control parameter combination.

[0074] Furthermore, the system further includes a first confluence fitness acquisition module to perform the following operation steps:

[0075] Based on the test data of the confluence pump, collect a sample confluence control parameter set, a sample hydraulic oil temperature information set, and collect a sample wear parameter set, a sample control hydraulic oil temperature set, and a sample confluence pump noise set. Use the sample confluence control parameter set and the sample hydraulic oil temperature information set as input data, and use the sample wear parameter set, the sample control hydraulic oil temperature set, and the sample confluence pump noise set as supervision data to train a confluence predictor. Use the confluence predictor to perform confluence control prediction on the multiple first confluence control parameters in the first confluence control parameter combination respectively in combination with the hydraulic oil temperature information in the confluence pump state information of the multiple selected confluence pumps to obtain multiple first wear parameters, multiple first control hydraulic oil temperatures, and multiple first confluence pump noises. Calculate the first aging distribution discreteness information of the multiple first wear parameters, and calculate and obtain the first confluence fitness based on the confluence function.

[0076] Through the foregoing detailed description of the multi-pump confluence control method for adaptive load balancing in this specification, those skilled in the art can clearly know the adaptive load balancing multi-pump confluence control system in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related parts, reference can be made to the description in the method part.

[0077] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Adaptive load balancing multi-pump confluence control method, characterized in that, The method is applied to a multi-pump combined flow hydraulic device, and the multi-pump combined flow hydraulic device includes a plurality of combined flow pumps. The method includes: Collecting a plurality of combined flow pump state information of the plurality of combined flow pumps, wherein each combined flow pump state information includes pump flow information and hydraulic oil temperature information; Collecting operation load information of the multi-pump combined flow operation; According to the operation load information, converting and evenly distributing the basic combined flow of the plurality of combined flow pumps to obtain a total combined flow and the basic combined flows of the plurality of selected combined flow pumps; Constructing a combined flow function for multi-pump combined flow control to balance the wear parameters of the plurality of selected combined flow pumps and minimize the noise and temperature of the plurality of selected combined flow pumps; Based on the plurality of basic combined flows and the combined flow function, according to the plurality of combined flow pump state information, performing multi-pump combined flow control optimization to obtain an optimal combined flow control parameter combination, and performing multi-pump combined flow control on the plurality of selected combined flow pumps; Constructing a combined flow function for multi-pump combined flow control to balance the wear parameters of the plurality of selected combined flow pumps and minimize the noise and temperature of the plurality of selected combined flow pumps, as shown in the following formula: ； where MPM is the confluence fitness, , and are weights, is the distribution discreteness information of the multiple confluence pump wear parameters of the multiple selected confluence pumps analyzed by combining the multiple confluence control parameters and the multiple confluence pump status information, M is the number of the multiple selected confluence pumps, is the control hydraulic oil temperature of the i-th selected confluence pump under the confluence pump status information and the confluence control parameters, is the preset hydraulic oil temperature, is the confluence pump noise of the i-th selected confluence pump under the confluence pump status information and the confluence control parameters, is the preset noise.

2. The adaptive load balancing multi-pump confluence control method according to claim 1, wherein Collecting a plurality of combined flow pump state information of the plurality of combined flow pumps, including: Collecting the current pump flow information of the plurality of combined flow pumps; Collecting the current hydraulic oil temperature information of the plurality of combined flow pumps; Integrating the plurality of pump flow information and the plurality of hydraulic oil temperature information to obtain a plurality of combined flow pump state information.

3. The adaptive load balancing multi-pump confluence control method according to claim 1, wherein According to the operation load information, converting and evenly distributing the basic combined flow of the plurality of combined flow pumps to obtain a total combined flow and the basic combined flows of the plurality of selected combined flow pumps, including: According to the operation load information, making a decision to obtain the number of combined flow pumps, and randomly selecting a plurality of selected combined flow pumps with the obtained number of combined flow pumps; Based on the multi-pump combined flow historical operation data, collecting a sample operation load information set and a sample total combined flow set; Using the sample operation load information set and the sample total combined flow set to train a total combined flow converter; Based on the total combined flow converter, performing combined flow conversion on the operation load to obtain a total combined flow; Distributing the total combined flow according to the number of combined flow pumps to obtain a plurality of basic combined flows.

4. The adaptive load balancing multi-pump confluence control method according to claim 3, wherein According to the operation load information, making a decision to obtain the number of combined flow pumps, including: Based on the multi-pump combined flow historical operation data, collecting a sample operation load information set and the number of combined flow pumps; Using the sample operation load information set and the number of combined flow pumps, based on a decision tree, constructing a combined flow pump activation number decision maker; Based on the combined flow pump activation number decision maker, inputting and making a decision on the operation load information to obtain the number of combined flow pumps.

5. The adaptive load balancing multi-pump confluence control method according to claim 1, characterized in that Based on the plurality of basic combined flows and the combined flow function, according to the plurality of combined flow pump state information, performing multi-pump combined flow control optimization to obtain an optimal combined flow control parameter combination, including: Taking the plurality of basic combined flow pump flows as the adjustment direction, adjusting the pump flow information of the plurality of selected combined flow pumps to obtain a plurality of adjusted pump flow information, and distributing the total combined flow according to the ratio of the adjusted pump flow information to obtain a plurality of first combined flow pump flows as the first combined flow control parameter combination; Based on the first confluence control parameter combination, combined with the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps, aging prediction, temperature prediction and noise prediction are respectively carried out, and based on the confluence function, the first confluence fitness is calculated and obtained; Randomly cross-update the flow rates of the multiple first confluence pumps to obtain multiple first cross-confluence control parameter combinations. Combined with the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps, aging prediction, temperature prediction and noise prediction are respectively carried out, and based on the confluence function, multiple first cross-confluence fitnesses are calculated and obtained; Continue to adjust the multiple adjusted pump flow rate information in the direction of the multiple basic confluence pump flow rates, perform iterative optimization until convergence, output the confluence control parameter combination with the maximum confluence fitness, and obtain the optimal confluence control parameter combination.

6. The adaptive load balancing multi-pump confluence control method according to claim 5, characterized in that Based on the first confluence control parameter combination, combined with the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps, aging prediction, temperature prediction and noise prediction are respectively carried out, and based on the confluence function, the first confluence fitness is calculated and obtained, including: Based on the test data of the confluence pump, a sample confluence control parameter set, a sample hydraulic oil temperature information set are collected, and a sample wear parameter set, a sample control hydraulic oil temperature set and a sample confluence pump noise set are collected; Using the sample confluence control parameter set and the sample hydraulic oil temperature information set as input data, and using the sample wear parameter set, the sample control hydraulic oil temperature set and the sample confluence pump noise set as supervision data, train the confluence predictor; Using the confluence predictor, respectively combine the hydraulic oil temperature information in the confluence pump status information of the multiple selected confluence pumps with the multiple first confluence control parameters in the first confluence control parameter combination to carry out confluence control prediction, and obtain multiple first wear parameters, multiple first control hydraulic oil temperatures and multiple first confluence pump noises; Calculate and obtain the first aging distribution discreteness information of the multiple first wear parameters, and calculate and obtain the first confluence fitness based on the confluence function.

7. Adaptive load-balanced multi-pump confluence control system, characterized in that, The system is applied to a multi-pump confluence hydraulic device. The multi-pump confluence hydraulic device includes multiple confluence pumps and is used to implement the adaptive load balancing multi-pump confluence control method according to any one of claims 1-6. The system includes: A status information acquisition module, which is used to acquire the confluence pump status information of the multiple confluence pumps. Among them, each confluence pump status information includes pump flow rate information and hydraulic oil temperature information; A load information acquisition module, which is used to acquire the operation load information of the multi-pump confluence operation; A confluence flow rate acquisition module, which is used to convert and evenly distribute the basic confluence flow rates of the multiple confluence pumps according to the operation load information to obtain the total confluence flow rate and the multiple basic confluence flow rates of the multiple selected confluence pumps; A confluence function construction module, which is used to construct a confluence function for multi-pump confluence control by balancing the wear parameters of the multiple selected confluence pumps and minimizing the noise and temperature of the multiple selected confluence pumps; A multi-pump confluence control module, which is used to optimize the multi-pump confluence control based on the multiple basic confluence flows and the confluence function, obtain the optimal confluence control parameter combination according to the multiple confluence pump status information, and perform multi-pump confluence control on the multiple selected confluence pumps; Construct a confluence function for multi-pump confluence control by balancing the wear parameters of the multiple selected confluence pumps and minimizing the noise and temperature of the multiple selected confluence pumps, as shown in the following formula: ； Among them, MPM is the confluence fitness, , and are weights, is the distribution discreteness information of the confluence pump wear parameters of multiple selected confluence pumps analyzed by combining multiple confluence control parameters and the multiple confluence pump status information, M is the number of multiple selected confluence pumps, is the control hydraulic oil temperature of the i-th selected confluence pump under the confluence pump status information and the confluence control parameters, is the preset hydraulic oil temperature, is the confluence pump noise of the i-th selected confluence pump under the confluence pump status information and the confluence control parameters, is the preset noise.

Images