A water supply pressure balancing control method and system in an industrial workshop

Abstract

The present invention relates to a water supply pressure balancing control method and system in an industrial workshop, which relates to the field of water pressure control. The method monitors water quality parameters of water supply in a preset time window in the past to predict water quality parameters of water supply in a preset time window in the future, performs filtration blockage prediction and scaling prediction on water supply pipelines according to the predicted water quality parameter sequence to obtain filtration blockage parameter sequence and scaling parameter sequence and performs water pressure impact analysis to obtain an impact water pressure sequence, monitors and obtains an actual water pressure sequence in a preset time window in the future, calculates and obtains a water pressure prediction coefficient in combination with the impact water pressure sequence, configures water pressure weights and equipment weights to perform water pressure balancing control optimization to obtain optimal water pressure control parameters for water pressure control, and solves the technical problem that a water supply pressure control method is difficult to adapt to the complex and changeable water quality conditions and water supply needs in an industrial workshop, resulting in unstable water supply pressure and severe equipment wear.

Description

Technical Field

[0001] The present invention relates to the field of water pressure control, and in particular to a water supply pressure balancing control method and system in an industrial workshop. Background Art

[0002] In industrial workshops, the stability and reliability of water supply systems are crucial for the smooth operation of production activities. However, traditional water supply pressure control methods often rely on fixed water pressure setpoints and simple feedback adjustment mechanisms, making them difficult to adapt to the complex and changing water quality conditions and water supply needs within the workshop. Firstly, water quality parameters within industrial workshops fluctuate over time due to various factors. These changes in water quality parameters can directly affect the condition of water supply pipelines, such as causing filter blockage and scaling on pipe walls, which in turn adversely affects water pressure. Failure to accurately predict and respond to these water quality changes can lead to unstable water pressure, impacting production efficiency and product quality. Secondly, traditional water pressure control methods often overlook the wear of water supply equipment itself. In actual operation, the degree of wear of water supply equipment varies over time and with changing usage conditions. Failure to fully account for and optimize this wear can lead to unstable water pressure, premature equipment failure, and increased repair and replacement costs. Summary of the Invention

[0003] The present invention aims to solve the technical problem that the water supply pressure control method in the existing technology is difficult to adapt to the complex and changeable water quality conditions and water supply needs in industrial workshops, resulting in unstable water supply pressure and serious equipment wear. It provides a water supply pressure balancing control method and system in industrial workshops to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a method for controlling water pressure balance of water supply in an industrial workshop, the method comprising: in the industrial workshop, monitoring water quality parameters of water supply within a preset time window in the past, predicting water quality parameters of water supply within a preset time window in the future, and obtaining a predicted water quality parameter sequence; based on the predicted water quality parameter sequence, predicting filtration blockage and scaling of the water supply pipeline, obtaining a filtration blockage parameter sequence and a scaling parameter sequence, and performing water pressure impact analysis to obtain an impact water pressure sequence; within a preset time window in the future, monitoring and obtaining an actual water pressure sequence, and calculating and obtaining a water pressure prediction coefficient in combination with the impact water pressure sequence; based on the water pressure prediction coefficient, configuring water pressure weights and equipment weights, performing water pressure balance control optimization, obtaining optimal water pressure control parameters, and performing water pressure control, wherein the optimization is performed to improve constant pressure control accuracy and reduce equipment wear.

[0006] In a second aspect, the present invention provides a water supply pressure balancing control system in an industrial workshop, the system comprising: a water quality prediction module, for monitoring the water supply quality parameters within a preset time window in the past in the industrial workshop, and predicting the water supply quality parameters within a preset time window in the future to obtain a predicted water quality parameter sequence; a water pressure analysis module, for predicting filtration blockage and scaling of the water supply pipeline based on the predicted water quality parameter sequence, obtaining a filtration blockage parameter sequence and a scaling parameter sequence, and performing water pressure impact analysis to obtain an impact water pressure sequence; a prediction calculation module, for monitoring and obtaining an actual water pressure sequence within a preset time window in the future, and calculating a water pressure prediction coefficient in combination with the impact water pressure sequence; a water pressure control module, for configuring water pressure weights and equipment weights based on the water pressure prediction coefficient, performing water pressure balancing control optimization, obtaining optimal water pressure control parameters, and performing water pressure control, wherein the optimization is performed to improve constant pressure control accuracy and reduce equipment wear.

[0007] The beneficial effects of the present invention are: by predicting water supply quality parameters and their impact on pipelines, and then predicting water pressure changes, and combining actual water pressure monitoring data for optimized control, balanced control of water supply pressure in industrial workshops is achieved, the accuracy of constant pressure control is effectively improved, and the wear of water supply equipment is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 The present invention provides a flow chart of a method for controlling water pressure balance in an industrial workshop.

[0009] Figure 2 This is a structural schematic diagram of a water supply pressure balancing control system in an industrial workshop provided by the present invention.

[0010] Description of the accompanying drawings: water quality prediction module 11, water pressure analysis module 12, prediction calculation module 13, water pressure control module 14. DETAILED DESCRIPTION

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0014] Example 1:

[0015] like Figure 1 As shown, an embodiment of the present invention provides a method for controlling water pressure balance in an industrial workshop, the method comprising:

[0016] S10: In the industrial workshop, monitor the water quality parameters of the water supply within a preset time window in the past, predict the water quality parameters of the water supply within a preset time window in the future, and obtain a predicted water quality parameter sequence.

[0017] For example, within an industrial workshop, the system first sets a past time window, such as the past month (30 days), and regularly monitors and records water quality parameters of the water supply system daily. These parameters, including water hardness, pH, turbidity, and sediment content, comprehensively reflect the water quality status. This creates a historical dataset containing daily water quality parameters from the past 30 days. Data analysis techniques, such as deep learning algorithms, are then used to train and learn from this historical dataset to construct a water quality parameter prediction model. This water quality parameter prediction model predicts water quality parameters within a preset time window (e.g., the next 30 days) based on past patterns and trends in water quality parameters, outputting a sequence of predicted water quality parameters. For example, it can predict the approximate ranges for parameters such as water hardness and pH for each day in the future, providing important information for subsequent pipeline status prediction and water pressure control. This method of predicting future water quality parameters based on historical data provides early insight into water quality trends and supports scientific decision-making for water supply management in industrial workshops.

[0018] S20: Based on the predicted water quality parameter sequence, filter blockage prediction and scaling prediction of the water supply pipeline are performed to obtain a filter blockage parameter sequence and a scaling parameter sequence, and water pressure impact analysis is performed to obtain an impact water pressure sequence.

[0019] Optionally, the filter blockage and scaling of water supply pipelines can be predicted based on the predicted water quality parameter sequence. In industrial workshop water supply systems, impurities and minerals in the water gradually deposit in the pipelines over long periods of time, leading to filter blockage and scaling on the inner walls of the pipelines. These problems directly affect the water flow within the pipelines, and thus the water pressure. To accurately predict this situation, a pipeline impact analyzer is constructed. The pipeline impact analyzer uses the predicted water quality parameter sequence (such as impurity content indicators such as hardness and sand content) as input and comprehensively considers the maintenance cycle of the water supply equipment (for example, maintenance every 30 days to remove blockages and treat scaling materials) to predict filter blockage parameters (such as blockage degree and blockage rate) and scaling parameters (such as scale thickness and scaling rate) at various time points in the pipeline over a period of time. The output is a filter blockage parameter sequence and a scaling parameter sequence.

[0020] After obtaining these prediction parameters, further water pressure impact analysis is performed. This process primarily predicts the potential water pressure changes under predicted filter blockage and scaling conditions by analyzing the relationship between filter blockage, scaling, and water pressure in historical data. For example, it may be found that for every 10% increase in pipeline blockage, water pressure decreases by 5%. Based on this relationship, the water pressure changes affected by filter blockage and scaling at each future time point can be predicted, resulting in a sequence of impacted water pressures. Finally, this impacted water pressure sequence can be used as input for periodic water pressure control optimization. For example, at the end of each time window (e.g., 30 days), the water pressure control strategy is adjusted based on the latest forecast results to ensure stable operation of the water supply system.

[0021] S30: Within a future preset time window, monitor and obtain the actual water pressure sequence, and calculate and obtain the water pressure prediction coefficient in combination with the influencing water pressure sequence.

[0022] Furthermore, the actual water pressure of the water supply system is monitored in real time within a preset time window in the future. This time window can be a fixed period, such as 30 days. The actual water pressure values ​​are recorded at multiple time points daily, thus generating an actual water pressure series. Simultaneously, the influence water pressure series for the corresponding time points is predicted based on the predicted water quality parameter series. This series represents the theoretically achievable water pressure values ​​under the predicted conditions, ignoring other interfering factors. Next, the actual water pressure series is compared with the influence water pressure series, and the error between the actual water pressure and the corresponding influence water pressure at each time point is calculated. This error reflects the difference between the actual and predicted conditions and can be caused by a variety of factors, such as pipe blockage and scaling being more or less severe than predicted, or unexpected changes in other parts of the water supply system. The magnitudes or proportions of these errors are averaged or weighted to generate a water pressure prediction coefficient, which serves as a measure of prediction accuracy and reflects the degree of deviation between the current state of the water supply system and the predicted state.

[0023] The weights for subsequent optimized water supply control parameters can then be adjusted based on the value of the water pressure prediction coefficient. If the actual water pressure is generally lower than the corresponding influencing water pressure, this indicates that the impact of blockage and scaling on water pressure is actually greater than predicted. Therefore, when optimizing the water supply control parameters, greater emphasis will be placed on the equipment weights to avoid excessive impurities causing severe equipment wear and affecting the long-term stable operation of the water supply system. Conversely, if the actual water pressure is generally higher than the corresponding influencing water pressure, this indicates that the impact of blockage and scaling on water pressure is actually smaller than predicted. Therefore, when optimizing the water supply control parameters, greater emphasis will be placed on adjusting the water pressure weights to ensure constant water pressure and improve production quality.

[0024] S40: According to the water pressure prediction coefficient, configure the water pressure weight and equipment weight, perform water pressure balance control optimization, obtain the optimal water pressure control parameters, and perform water pressure control, wherein the optimization is performed to improve the constant pressure control accuracy and reduce equipment wear.

[0025] Specifically, based on the water pressure prediction coefficient, water pressure and equipment weights are further configured to optimize water pressure equalization control. The water pressure weight primarily focuses on the stability and accuracy of the water supply system's water pressure, ensuring that the water pressure meets production requirements and remains constant. The equipment weight, on the other hand, prioritizes reducing wear on water supply equipment and extending its service life. Specifically, if the water pressure prediction coefficient indicates that actual water pressure is generally lower than predicted, this suggests that the impact of pipeline blockage and scaling may be more severe than expected. In this case, the equipment weight is appropriately increased, as the focus in this case is on preventing excessive wear on equipment due to excessive impurities. Accordingly, the water pressure weight is appropriately reduced, but still maintains a certain level of attention to ensure that low water pressure does not affect production. Conversely, if the water pressure prediction coefficient indicates that actual water pressure is generally higher than predicted, this indicates that pipeline conditions may be better than expected, with less impact from blockage and scaling. In this case, greater emphasis is placed on configuring the water pressure weight to improve the accuracy of constant pressure control and ensure production quality. Simultaneously, the equipment weight is correspondingly reduced, but still maintained at a reasonable level to prevent potential problems caused by ignoring equipment conditions.

[0026] After configuring water pressure and equipment weights, these weights are used to construct a water pressure balancing function that comprehensively considers water pressure stability and equipment wear. Next, a search and optimization process is performed within the water pressure control parameter space. By continuously iterating and adjusting the water pressure control parameters, the optimal combination of water pressure control parameters is found that achieves the optimal solution for the water pressure balancing function (i.e., achieving the highest constant pressure control accuracy and the lowest equipment wear). Once this optimal solution is found, the corresponding water pressure control parameters are used for actual water pressure control, thus achieving intelligent and refined management of the water supply system.

[0027] In a preferred embodiment, in an industrial workshop, water supply quality parameters within a past preset time window are monitored, and water supply quality parameters within a future preset time window are predicted to obtain a predicted water quality parameter sequence, including: in the industrial workshop, water supply quality parameters at multiple time nodes within a past preset time window are monitored, and they are arranged in chronological order to obtain a historical water quality parameter sequence, wherein the water supply equipment is maintained after each preset time window; the historical water quality parameter sequence is input into a pre-trained water quality parameter predictor, and the prediction output is used to obtain a predicted water quality parameter sequence for multiple time nodes within a future preset time window.

[0028] Preferably, a preset time window is set. This time window serves as the basic unit for observation and data collection. For example, it can be set to the past month or week. The basic unit covers the water quality parameters of the water supply at different time points every day within this month or week. These water quality parameters include but are not limited to water hardness, pH value, dissolved oxygen content, turbidity, and the concentration of various impurities that may be present. They can comprehensively reflect the water quality status and its potential impact on the water supply system.

[0029] The water quality of the water supply system is continuously monitored within a preset time window, recording water quality parameters at each time point and chronologically arranging this data to form a historical water quality parameter sequence. This sequence forms the basis for subsequent water quality predictions. Furthermore, after each preset time window, necessary maintenance is performed on the water supply equipment, such as cleaning filters and checking pipe conditions, to ensure proper equipment operation and consistent water quality. This regular maintenance is crucial for maintaining the long-term stability of the water supply system.

[0030] After obtaining enough historical water quality parameter sequences, these data are used to train a water quality parameter predictor. This predictor, based on a deep learning model, predicts water quality parameters within a preset time window in the future by learning the changing patterns and trends of water quality parameters from historical data. Specifically, the historical water quality parameter sequence is input into the pre-trained water quality parameter predictor, which will predict the water quality parameter values ​​at various time nodes in the future (such as the next time window) based on these historical data, forming a predicted water quality parameter sequence. For example, if the set time window is the past month, the water quality parameter predictor will predict the water quality parameter values ​​at different time nodes every day in the next month based on the historical data within this month, such as hardness, pH value, etc. In this way, the future trend of water quality changes can be understood in advance, providing a scientific basis for subsequent water supply management decisions.

[0031] In a preferred embodiment, the training steps of the water quality parameter predictor include: collecting a set of sample historical water quality parameter sequences based on the workshop water supply quality data records within a historical period, and collecting water quality parameter sequences after different sample historical water quality parameter sequences, and marking to obtain a set of sample predicted water quality parameter sequences; using deep learning to construct a water quality parameter predictor; using the sample historical water quality parameter sequence set and the sample predicted water quality parameter sequence set to perform supervised training and testing on the water quality parameter predictor, and completing the training after the accuracy test is passed.

[0032] Specifically, the training of the water quality parameter predictor aims to ensure that it can accurately and reliably predict future water quality parameters. The training process is based on historical water quality series. A large number of sample historical water quality parameter series are collected based on historical water quality data records from the workshop water supply. This historical data records the changes in water quality parameters of the water supply system over different time periods and forms the basis for training the predictor. Water quality parameter series following these sample historical water quality parameter series, representing actual water quality parameter changes, are also collected as prediction targets for the predictor. By annotating these actual water quality parameter series, a set of sample predicted water quality parameter series is obtained for subsequent supervised training. The prediction framework uses deep learning technology to construct the water quality parameter predictor. Deep learning is a powerful machine learning technique that can automatically learn complex patterns and regularities from large amounts of data. Deep learning models (such as recurrent neural networks (RNNs) and long short-term memory (LSTM) networks) are used to process time series data to capture trends in water quality parameters over time.

[0033] After constructing the predictor model, supervised training is performed on a set of sample historical water quality parameter sequences and a set of sample predicted water quality parameter sequences. During training, the sample historical water quality parameter sequences are input into the predictor to predict future water quality parameter sequences, which are then compared with the actual sample predicted water quality parameter sequences. By calculating the prediction error and adjusting the model parameters through backpropagation, the predictor's accuracy can be gradually improved. Subsequently, after training is complete, the predictor is tested for accuracy. The predictive performance of the predictor is verified using the test set data. If the accuracy test passes, it indicates that the predictor has demonstrated good predictive capabilities and can be trained and applied to actual water quality parameter prediction tasks.

[0034] In a preferred embodiment, according to the predicted water quality parameter sequence, the filtration blockage prediction and scaling prediction of the water supply pipeline are performed to obtain the filtration blockage parameter sequence and scaling parameter sequence, including: based on the water supply equipment maintenance record data in the historical time, a sample water quality parameter sequence set is collected, and the filtration blockage parameters and scaling parameters corresponding to multiple time nodes in the water supply pipeline under different sample water quality parameter sequences are collected, and the sample filtration blockage parameter sequence set and the sample scaling parameter sequence set are marked to obtain the sample filtration blockage parameter sequence set and the sample scaling parameter sequence set; a pipeline impact analyzer is constructed based on deep learning, and the sample water quality parameter sequence set, the sample filtration blockage parameter sequence set and the sample scaling parameter sequence set are used to perform supervised training and testing on the pipeline impact analyzer until the test is qualified; the predicted water quality parameter sequence is input into the pipeline impact analyzer, and the filtration blockage parameter sequence and scaling parameter sequence are obtained as output.

[0035] Preferably, in order to accurately predict the filter blockage and scaling conditions of the water supply pipeline, a deep learning-based analysis process is used to predict historical internal pipeline impacts for subsequent pipeline analysis. First, a series of sample water quality parameter sequence sets are collected based on the water supply equipment maintenance record data over a historical period. These sample data not only cover the changes in water quality parameters over different time periods, but also record the filter blockage parameters (such as blockage degree, blockage rate, etc.) and scaling parameters (such as scale thickness, scaling rate, etc.) corresponding to multiple time nodes in the water supply pipeline under these water quality conditions. By annotating these actual filter blockage and scaling parameters, a sample filter blockage parameter sequence set and a sample scaling parameter sequence set are obtained, providing a data basis for subsequent analyzer training.

[0036] Subsequently, a pipeline impact analyzer was constructed using deep learning technology. This analyzer is capable of learning the complex relationships between water quality parameters and filter blockage and scaling parameters. During the training process, the analyzer receives a set of sample water quality parameter sequences, a set of sample filter blockage parameter sequences, and a set of sample scaling parameter sequences as input for supervised training. By continuously adjusting the analyzer's model parameters, it accurately predicts filter blockage and scaling in water supply pipelines under varying water quality parameters. After multiple iterations and testing, the analyzer is considered to have demonstrated good predictive capabilities when its prediction accuracy meets acceptable standards.

[0037] During the actual prediction process, the predicted water quality parameter sequence is input into the trained Pipeline Impact Analyzer. The analyzer, based on the input water quality parameter sequence and the previously learned relationships between water quality parameters and filter blockage and scaling parameters, outputs corresponding filter blockage parameter sequences and scaling parameter sequences. These predictions provide information about the future state of the water supply pipeline, enabling proactive maintenance planning to prevent the adverse effects of pipeline blockage and scaling on the water supply system. For example, suppose water quality parameter data is collected at different time periods over the past month, along with the filter blockage and scaling conditions of the water supply pipeline under these water quality conditions. By training the Pipeline Impact Analyzer, a model is generated that accurately predicts future filter blockage and scaling conditions. When the predicted water quality parameter sequence is fed into this model, it outputs the filter blockage and scaling parameter sequences for the water supply pipeline over the next period of time, providing support for subsequent decision-making.

[0038] In a preferred embodiment, a water pressure impact analysis is performed to obtain an impact water pressure sequence, including: collecting a sample filter blockage parameter set and a sample scaling parameter set based on water pressure monitoring and maintenance data of the water supply equipment, and collecting water pressures under different sample filter blockage parameters and sample scaling parameters to obtain a sample impact water pressure set; using the sample filter blockage parameter set and the sample scaling parameter set as input features, using the sample impact water pressure set as a decision feature, and constructing an impact water pressure classifier based on a decision tree; combining each group of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and scaling parameter sequence, inputting the combination into the impact water pressure classifier, and performing decision classification to obtain the impact water pressures of multiple time nodes in a preset time window in the future to obtain an impact water pressure sequence.

[0039] For example, based on the water pressure monitoring and maintenance data of the water supply equipment, a sample filter blockage parameter set and a sample scaling parameter set are collected. These sample data reflect the actual water pressure of the water supply system under different filter blockage and scaling conditions. At the same time, the water pressure values ​​corresponding to these sample filter blockage parameters and scaling parameters are recorded to form a sample water pressure influencing set. Then, a decision tree algorithm is used to construct a classifier that affects water pressure. In this classifier, the sample filter blockage parameter set and the sample scaling parameter set are used as input features, while the sample water pressure influencing set is used as a decision feature. By training the decision tree model, it is able to learn and understand the complex relationship between filter blockage and scaling parameters and water pressure. The decision tree model forms multiple decision paths by continuously dividing the input feature space, and each path corresponds to a specific water pressure category or value.

[0040] After constructing the impact water pressure classifier, each combination of filter blockage and scaling parameters within the previously predicted filter blockage and scaling parameter sequences is fed into the classifier as input data. Based on this input data, the classifier finds the corresponding decision path within the decision tree and outputs the impact water pressure values ​​for multiple time nodes within a preset future time window. These impact water pressure values ​​are arranged chronologically to form an impact water pressure sequence. By inputting the filter blockage and scaling parameter sequences into the classifier, the impact water pressure sequence for a specific time period can be quickly obtained. This automated prediction process significantly improves decision-making efficiency and reduces the time and effort required for manual analysis and judgment.

[0041] In a preferred embodiment, within a future preset time window, the actual water pressure sequence is monitored and obtained, and combined with the influencing water pressure sequence, a water pressure prediction coefficient is calculated, including: within the future preset time window, continuously monitoring the actual water pressure at the time node to obtain the actual water pressure sequence; using the influencing water pressure sequence as a reference, calculating the error amplitude between each actual water pressure and the corresponding influencing water pressure to obtain a water pressure error coefficient sequence; calculating the mean of the water pressure error coefficient sequence to obtain a water pressure prediction coefficient.

[0042] Specifically, within a preset time window in the future, the actual water pressure values ​​at each time node are continuously monitored, and these values ​​are arranged in chronological order to form an actual water pressure sequence. This sequence reflects the changes in water pressure during the actual operation of the water supply system. Subsequently, the error margin between each actual water pressure and the corresponding influencing water pressure is calculated based on the influencing water pressure sequence previously predicted by the model. Specifically, the actual water pressure value of each time node is subtracted from the corresponding influencing water pressure value, and then divided by the influencing water pressure value itself to obtain a water pressure error coefficient. This coefficient can be positive or negative. A positive number indicates that the actual water pressure is higher than the predicted value, and a negative number indicates that the actual water pressure is lower than the predicted value. In this way, a water pressure error coefficient sequence is obtained, which reflects the deviation between the actual water pressure and the predicted water pressure.

[0043] To obtain an overall water pressure prediction coefficient, the water pressure error coefficient sequence is averaged. This average represents the average deviation between the actual and predicted water pressures over the entire preset time window. The water pressure prediction coefficient provides an intuitive understanding of the water supply system's water pressure prediction accuracy, allowing analysis of the prediction model's effectiveness and determining whether model parameters need to be adjusted or the prediction strategy optimized.

[0044] For example, assuming a preset time window of one month and daily monitoring of actual water pressure, a sequence of 30 actual water pressure values ​​is generated. Simultaneously, the one-month sequence of influencing water pressures is used as the prediction baseline. By calculating the margin of error between each actual water pressure and the corresponding influencing water pressure, a sequence of 30 water pressure error coefficients is generated. Finally, the mean of this sequence is calculated to obtain the water pressure prediction coefficient. If the water pressure prediction coefficient is close to 0, the prediction model is relatively accurate; if the deviation is significant, further analysis and optimization are required. In summary, this monitoring and calculation process can promptly detect deviations in water supply system water pressure predictions, providing strong support for subsequent model adjustments and optimization. Furthermore, continuous monitoring and calculation can also assess the stability and reliability of the water supply system, providing a scientific basis for water supply management.

[0045] In a preferred embodiment, according to the water pressure prediction coefficient, the water pressure weight and the equipment weight are configured, and the water pressure equalization control optimization is performed to obtain the optimal water pressure control parameters and perform water pressure control, including: performing a correction calculation on the preset water pressure weight according to the sum of the water pressure prediction coefficient and 1 to obtain the water pressure weight; calculating the equipment weight according to the water pressure weight; and constructing a water pressure equalization function based on the water pressure weight and the equipment weight, as shown in the following formula:

[0046] ; Among them, WPfit is water pressure adaptability, and are the water pressure weight and equipment weight respectively, M is the number of time nodes in the preset time window, P is the preset water pressure of constant pressure water supply, is the controlled water pressure at the i-th time node after the water pressure control parameters are applied, X is a small real number, The wear coefficient of the water supply equipment at the i-th time node after the water pressure control parameters are controlled is randomly generated in the water pressure control parameter space, and the water pressure control prediction is performed in combination with the filter blockage parameter sequence and the scaling parameter sequence to obtain the control water pressure sequence and the water supply equipment wear coefficient sequence; according to the control water pressure sequence and the water supply equipment wear coefficient sequence, the water pressure fitness is calculated based on the water pressure balance function; the water pressure control parameters are continuously randomly generated, and the water pressure balance control optimization is performed until convergence, and the water pressure control parameters with the largest water pressure fitness are output to obtain the optimal water pressure control parameters for water pressure control.

[0047] Furthermore, the water pressure prediction coefficient is used to optimize water pressure balance control, and ultimately the optimal water pressure control parameters are obtained for actual water pressure control. Specifically, the preset water pressure weight is corrected and calculated based on the sum of the water pressure prediction coefficient and 1. The significance of this correction process is that if the water pressure prediction coefficient is positive, it means that the actual water pressure is generally higher than the predicted value, that is, the impact of blockage and scaling on water pressure is actually smaller than expected. In this case, the water pressure weight is increased to ensure the constancy of water pressure, thereby improving production quality. Specifically, (1 + water pressure prediction coefficient) is multiplied by the preset water pressure weight (for example, initially set to 0.5) to obtain the corrected water pressure weight. Next, the equipment weight is calculated based on the corrected water pressure weight. The calculation of the equipment weight is relatively simple and can be obtained directly by subtracting the water pressure weight from 1. This ensures that the sum of the water pressure weight and the equipment weight is 1.

[0048] Subsequently, a water pressure balancing function is constructed based on the corrected water pressure weights and equipment weights. This function comprehensively considers the water pressure stability and equipment wear. Through a series of complex mathematical operations, it takes into account factors such as water pressure control parameters, controlled water pressure, and water supply equipment wear coefficient. The specific water pressure balancing function formula is:

[0049] ; Among them, WPfit is water pressure adaptability, and are the water pressure weight and equipment weight respectively, M is the number of time nodes in the preset time window, P is the preset water pressure of constant pressure water supply, is the controlled water pressure at the i-th time node after the water pressure control parameters are applied, X is a small real number, is the wear coefficient of the water supply equipment at the i-th time node after the water pressure control parameters are applied. The small real number X is introduced to avoid the denominator being 0 during the calculation process, ensuring the stability and accuracy of the calculation.

[0050] During parameter optimization, a set of water pressure control parameters is randomly generated within the water pressure control parameter space. These parameters are then combined with the previously predicted filter blockage and scaling parameter sequences to predict water pressure control. Simulation and calculation yield a control water pressure sequence and a water supply equipment wear coefficient sequence. Based on these predictions, the water pressure fitness is calculated using the water pressure balance function. The water pressure fitness reflects the overall system performance under the current water pressure control parameters, including water pressure stability and equipment wear. To find the optimal water pressure control parameters, the system continues to randomly generate water pressure control parameters and optimize water pressure balance control. This process continues iteratively until the water pressure fitness converges to a maximum value. At this point, the output water pressure control parameters are optimal, ensuring constant water pressure in the water supply system and minimizing equipment wear. For example, in an industrial workshop water supply system, water pressure prediction coefficients were obtained based on past water pressure monitoring data and prediction results. The aforementioned process then proceeds to modify water pressure weights, calculate equipment weights, construct a water pressure balance function, and optimize water pressure control parameters. Ultimately, a set of optimal water pressure control parameters is obtained and applied to practical water pressure control. This ensures stable operation of the water supply system, improves production quality, and reduces equipment wear and maintenance costs.

[0051] In a preferred embodiment, water pressure control parameters are randomly generated in the water pressure control parameter space, and water pressure control prediction is performed in combination with the filter blockage parameter sequence and the scaling parameter sequence to obtain a control water pressure sequence and a water supply equipment wear coefficient sequence, including: collecting a sample water pressure control parameter set, a sample filter blockage parameter set and a sample scaling parameter set based on historical data of water pressure control adjustment, and collecting the ratio of the control water pressure and water supply equipment wear parameter under different parameter combinations to the maximum water supply equipment wear parameter as the water supply equipment wear coefficient, to obtain a sample control water pressure set and a sample water supply equipment wear coefficient set; based on depth Learning, constructing a water supply control adjustment predictor; using the sample water pressure control parameter set, the sample filter blockage parameter set and the sample scaling parameter set as input features, using the sample control water pressure set and the sample water supply equipment wear coefficient set as output features, and conducting supervised training and testing on the water supply control adjustment predictor until the test is qualified; randomly generating water pressure control parameters in the water pressure control parameter space, combining multiple groups of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and the scaling parameter sequence, respectively inputting them into the water supply control adjustment predictor, and outputting a control water pressure sequence and a water supply equipment wear coefficient sequence.

[0052] Specifically, based on the historical data of water pressure control adjustment, a sample water pressure control parameter set, a sample filter blockage parameter set and a sample scaling parameter set are collected. These data reflect the actual operating conditions of the water supply system under different water pressure control parameters, filter blockage and scaling conditions. In the process of collecting data, attention is paid to the control water pressure and water supply equipment wear under different parameter combinations. In order to quantify the degree of wear of the water supply equipment, the ratio of the water supply equipment wear parameter to the maximum water supply equipment wear parameter is calculated. This ratio can be regarded as the water supply equipment wear coefficient. The water supply equipment wear parameter is, for example, the size of the water supply pipe wear. The maximum water supply equipment wear parameter is the maximum wear size of the water supply pipe in the historical time, for example, 6mm. For example, if the water supply equipment wear parameter at a certain point in time is 0.5, and the maximum water supply equipment wear parameter in the historical time is 1.0, then the water supply equipment wear coefficient at that point in time is 0.5. This coefficient reflects the relative degree of wear of the water supply equipment under the current parameter combination. For example, it can be compared to the amplitude of the change in valve accuracy, and serves as an important indicator for evaluating the status of the water supply equipment.

[0053] Next, a water supply control adjustment predictor was constructed using deep learning technology. This predictor is capable of learning the complex relationships between water pressure control parameters, filter blockage parameters, and scaling parameters, as well as the control water pressure and water supply equipment wear coefficient. During training, supervised training and testing were performed using sets of sample water pressure control parameters, filter blockage parameters, and scaling parameters as input features, while sets of sample control water pressure and water supply equipment wear coefficients were used as output features. By continuously adjusting the predictor's model parameters, it was able to accurately predict the control water pressure and water supply equipment wear coefficient under different parameter combinations.

[0054] Finally, a set of water pressure control parameters was randomly generated within the water pressure control parameter space. These parameters, combined with multiple sets of filter blockage and scaling parameters within the filter blockage and scaling parameter sequences, were input into the trained water supply control adjustment predictor. Based on the input parameters, the predictor outputs a corresponding sequence of controlled water pressures and a sequence of water supply equipment wear coefficients. These predictions provide the expected operating conditions of the water supply system under different parameter combinations, helping to identify the optimal water pressure control parameters for precise water pressure control and effective protection of water supply equipment.

[0055] For example, in an industrial plant's water supply system, a water supply control adjustment predictor was trained based on historical data. A set of water pressure control parameters was then randomly generated and fed into the predictor, along with current filter blockage and scaling parameters. The predictor outputs the control water pressure and water supply equipment wear coefficient for each time point over a period of time. By analyzing these predictions, the water pressure control parameters can be adjusted to optimize the water supply system's operating efficiency and equipment lifespan.

[0056] The embodiment of the present invention provides a method for controlling water pressure balance in an industrial workshop, which has at least the following technical effects:

[0057] 1. Deep learning technology enables accurate prediction of water quality parameters, enabling the prediction of filter blockage and scaling in water supply pipelines. This predictive capability enables dynamic adjustments to water pressure control based on future water quality changes, rather than relying solely on current water pressure conditions. This forward-looking control strategy significantly improves the accuracy and stability of water pressure control and reduces pressure fluctuations caused by water quality changes.

[0058] 2. By introducing the concepts of water pressure weighting and equipment weighting and constructing a water pressure balancing function, we achieve dual optimization of water pressure stability and equipment wear. This optimization strategy not only ensures stable water pressure in the water supply system, but also extends the service life of water supply equipment and reduces maintenance costs.

[0059] 3. Leveraging historical and real-time monitoring data, the system intelligently optimizes water pressure control parameters through machine learning algorithms such as deep learning and decision trees. This data-driven optimization method automatically adapts to varying water supply environments and equipment conditions to find the optimal combination of water pressure control parameters. Compared to empirical or rule-based control methods, this intelligent optimization approach offers greater flexibility and adaptability, significantly improving the overall performance of the water supply system.

[0060] Example 2:

[0061] like Figure 2 As shown, based on the same inventive concept as the water supply pressure balancing control method in an industrial workshop provided in Example 1, an embodiment of the present invention further provides a water supply pressure balancing control system in an industrial workshop, the system comprising:

[0062] The water quality prediction module 11 is used to monitor the water quality parameters of the water supply within a preset time window in the past in the industrial workshop, predict the water quality parameters of the water supply within a preset time window in the future, and obtain a predicted water quality parameter sequence.

[0063] The water pressure analysis module 12 is used to predict the filtration blockage and scaling of the water supply pipeline according to the predicted water quality parameter sequence, obtain the filtration blockage parameter sequence and scaling parameter sequence, and perform water pressure impact analysis to obtain the impact water pressure sequence.

[0064] The prediction calculation module 13 is used to monitor and obtain the actual water pressure sequence within a preset time window in the future, and calculate the water pressure prediction coefficient in combination with the influencing water pressure sequence.

[0065] The water pressure control module 14 is used to configure the water pressure weight and equipment weight according to the water pressure prediction coefficient, optimize the water pressure balance control, obtain the optimal water pressure control parameters, and perform water pressure control, wherein the optimization is performed to improve the constant pressure control accuracy and reduce equipment wear.

[0066] Furthermore, the water quality prediction module 11 is further configured to perform the following steps:

[0067] In an industrial workshop, water supply quality parameters at multiple time nodes within a preset time window in the past are monitored and arranged in chronological order to obtain a historical water quality parameter sequence, wherein the water supply equipment is maintained after the end of each preset time window; the historical water quality parameter sequence is input into a pre-trained water quality parameter predictor, and the prediction output is used to obtain a predicted water quality parameter sequence for multiple time nodes within a preset time window in the future.

[0068] Furthermore, the water quality prediction module 11 is further configured to perform the following steps:

[0069] According to the workshop water supply quality data records in the historical period, a set of sample historical water quality parameter sequences is collected, and water quality parameter sequences after different sample historical water quality parameter sequences are collected, and the sample predicted water quality parameter sequence sets are marked; deep learning is used to construct a water quality parameter predictor; the sample historical water quality parameter sequence set and the sample predicted water quality parameter sequence set are used to conduct supervised training and testing on the water quality parameter predictor, and the training is completed after the accuracy test is passed.

[0070] Furthermore, the water pressure analysis module 12 is further configured to perform the following steps:

[0071] Based on the water supply equipment maintenance record data in historical time, a set of sample water quality parameter sequences is collected, and the filtration blockage parameters and scaling parameters corresponding to multiple time nodes in the water supply pipeline under different sample water quality parameter sequences are collected, and the sample filtration blockage parameter sequence set and the sample scaling parameter sequence set are marked to obtain; a pipeline impact analyzer is constructed based on deep learning, and the sample water quality parameter sequence set, the sample filtration blockage parameter sequence set and the sample scaling parameter sequence set are used to perform supervised training and testing on the pipeline impact analyzer until the test is qualified; the predicted water quality parameter sequence is input into the pipeline impact analyzer, and the filtration blockage parameter sequence and the scaling parameter sequence are obtained as output.

[0072] Furthermore, the water pressure analysis module 12 is further configured to perform the following steps:

[0073] According to the water pressure monitoring and maintenance data of the water supply equipment, a sample filter blockage parameter set and a sample scaling parameter set are collected, and the water pressure under different sample filter blockage parameters and sample scaling parameters are collected to obtain a sample influencing water pressure set; the sample filter blockage parameter set and the sample scaling parameter set are used as input features, and the sample influencing water pressure set is used as a decision feature, and based on a decision tree, an influencing water pressure classifier is constructed; each group of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and the scaling parameter sequence are combined and input into the influencing water pressure classifier, and the decision classification is performed to obtain the influencing water pressure of multiple time nodes in a preset time window in the future, and an influencing water pressure sequence is obtained.

[0074] Furthermore, the prediction calculation module 13 is further configured to perform the following steps:

[0075] In a preset future time window, the actual water pressure at each time node is continuously monitored to obtain an actual water pressure sequence; based on the influencing water pressure sequence, the error amplitude between each actual water pressure and the corresponding influencing water pressure is calculated to obtain a water pressure error coefficient sequence; the mean of the water pressure error coefficient sequence is calculated to obtain a water pressure prediction coefficient.

[0076] Furthermore, the water pressure control module 14 is further configured to perform the following steps:

[0077] The preset water pressure weight is corrected and calculated based on the sum of the water pressure prediction coefficient and 1 to obtain the water pressure weight; the equipment weight is calculated based on the water pressure weight; and a water pressure balancing function is constructed based on the water pressure weight and the equipment weight, as shown in the following formula: ; Among them, WPfit is water pressure adaptability, and are the water pressure weight and equipment weight respectively, M is the number of time nodes in the preset time window, P is the preset water pressure of constant pressure water supply, is the controlled water pressure at the i-th time node after the water pressure control parameters are applied, X is a small real number, The wear coefficient of the water supply equipment at the i-th time node after the water pressure control parameters are controlled is randomly generated in the water pressure control parameter space, and the water pressure control prediction is performed in combination with the filter blockage parameter sequence and the scaling parameter sequence to obtain the control water pressure sequence and the water supply equipment wear coefficient sequence; according to the control water pressure sequence and the water supply equipment wear coefficient sequence, the water pressure fitness is calculated based on the water pressure balance function; the water pressure control parameters are continuously randomly generated, and the water pressure balance control optimization is performed until convergence, and the water pressure control parameters with the largest water pressure fitness are output to obtain the optimal water pressure control parameters for water pressure control.

[0078] Furthermore, the water pressure control module 14 is further configured to perform the following steps:

[0079] According to the historical data of water pressure control adjustment, a sample water pressure control parameter set, a sample filter blockage parameter set and a sample scaling parameter set are collected, and the ratio of the control water pressure and water supply equipment wear parameter to the maximum water supply equipment wear parameter under different parameter combinations is collected as the water supply equipment wear coefficient, and the sample control water pressure set and the sample water supply equipment wear coefficient set are obtained; based on deep learning, a water supply control adjustment predictor is constructed; the sample water pressure control parameter set, the sample filter blockage parameter set and the sample scaling parameter set are used as input features, and the sample control water pressure set and the sample water supply equipment wear coefficient set are used as output features, and the water supply control adjustment predictor is supervised trained and tested until the test is qualified; water pressure control parameters are randomly generated in the water pressure control parameter space, and multiple groups of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and the scaling parameter sequence are combined and input into the water supply control adjustment predictor respectively, and the control water pressure sequence and the water supply equipment wear coefficient sequence are obtained as output.

[0080] Through the above-mentioned detailed description of the water supply pressure balancing control method in an industrial workshop in this specification, those skilled in the art can clearly understand the water supply pressure balancing control system in an industrial workshop in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0081] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one 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. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A water supply pressure balancing control method in an industrial workshop, characterized in that: The method comprises: In industrial workshops, water quality parameters of the water supply within a preset time window in the past are monitored, and water quality parameters of the water supply within a preset time window in the future are predicted to obtain a predicted water quality parameter sequence; According to the predicted water quality parameter sequence, filter blockage prediction and scaling prediction of the water supply pipeline are performed to obtain filter blockage parameter sequence and scaling parameter sequence, and water pressure impact analysis is performed to obtain the impact water pressure sequence, including: Based on the water supply equipment maintenance record data in the historical period, a set of sample water quality parameter sequences is collected. The filter blockage parameters and scaling parameters corresponding to multiple time nodes in the water supply pipeline under different sample water quality parameter sequences are collected, and the sample filter blockage parameter sequence set and the sample scaling parameter sequence set are obtained by annotation. Constructing a pipeline impact analyzer based on deep learning, using the sample water quality parameter sequence set, the sample filtration blocking parameter sequence set, and the sample scaling parameter sequence set, to perform supervised training and testing on the pipeline impact analyzer until the test passes; Inputting the predicted water quality parameter sequence into the pipeline impact analyzer, and outputting a filter blockage parameter sequence and a scaling parameter sequence; In a future preset time window, the actual water pressure sequence is monitored and obtained, and the water pressure prediction coefficient is calculated based on the influencing water pressure sequence; According to the water pressure prediction coefficient, the water pressure weight and the equipment weight are configured to optimize the water pressure balance control, obtain the optimal water pressure control parameters, and perform water pressure control, including: Correcting and calculating the preset water pressure weight according to the sum of the water pressure prediction coefficient and 1 to obtain the water pressure weight; Calculating and obtaining equipment weight according to the water pressure weight; Based on the water pressure weight and equipment weight, a water pressure balancing function is constructed as follows: ； Among them, WPfit is water pressure adaptability, and are the water pressure weight and equipment weight respectively, M is the number of time nodes in the preset time window, P is the preset water pressure of constant pressure water supply, is the controlled water pressure at the i-th time node after the water pressure control parameters are applied, X is a small real number, is the wear coefficient of the water supply equipment at the i-th time node after being controlled according to the water pressure control parameters; Randomly generate water pressure control parameters in the water pressure control parameter space, combine the filter blockage parameter sequence and the scaling parameter sequence, perform water pressure control prediction, and obtain a control water pressure sequence and a water supply equipment wear coefficient sequence; Calculating the water pressure adaptability based on the control water pressure sequence and the water supply equipment wear coefficient sequence and the water pressure balance function; Continue to randomly generate water pressure control parameters and perform water pressure balance control optimization until convergence, output the water pressure control parameters with the maximum water pressure adaptability, obtain the optimal water pressure control parameters, and perform water pressure control.

2. The water supply pressure balance control method in an industrial workshop according to claim 1, characterized in that: In industrial workshops, water quality parameters of the water supply within a preset time window in the past are monitored, and water quality parameters of the water supply within a preset time window in the future are predicted to obtain a predicted water quality parameter sequence, including: In industrial workshops, water quality parameters of water supply at multiple time points within a preset time window in the past are monitored and arranged in chronological order to obtain a historical water quality parameter sequence. The water supply equipment is maintained after each preset time window. The historical water quality parameter sequence is input into a pre-trained water quality parameter predictor, and the prediction output obtains a predicted water quality parameter sequence for multiple time nodes within a future preset time window.

3. The water pressure balance control method for water supply in an industrial workshop according to claim 2, characterized in that: The training steps of the water quality parameter predictor include: According to the workshop water supply quality data records in the historical time, collect the sample historical water quality parameter sequence set, and collect the water quality parameter sequence after the different sample historical water quality parameter sequences, and mark and obtain the sample predicted water quality parameter sequence set; Using deep learning to build a water quality parameter predictor; The water quality parameter predictor is supervisedly trained and tested using the sample historical water quality parameter sequence set and the sample predicted water quality parameter sequence set, and the training is completed after the accuracy test is qualified.

4. The water pressure balance control method for water supply in an industrial workshop according to claim 1, characterized in that: Conduct water pressure impact analysis to obtain the impact water pressure sequence, including: According to the water pressure monitoring and maintenance data of the water supply equipment, a sample filter blockage parameter set and a sample scaling parameter set are collected, and the water pressure under different sample filter blockage parameters and sample scaling parameters are collected to obtain a sample-affected water pressure set; Using the sample filtration blocking parameter set and the sample scaling parameter set as input features, using the sample water pressure influencing set as a decision feature, and constructing an influencing water pressure classifier based on a decision tree; Each set of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and scaling parameter sequence is input into the influencing water pressure classifier, and decision classification is performed to obtain the influencing water pressures of multiple time nodes in a future preset time window to obtain an influencing water pressure sequence.

5. The water pressure balancing control method for water supply in an industrial workshop according to claim 1, characterized in that: In a future preset time window, the actual water pressure sequence is monitored and obtained, and the water pressure prediction coefficient is calculated based on the influencing water pressure sequence, including: In the future preset time window, the actual water pressure at each time node is continuously monitored to obtain the actual water pressure sequence; Based on the influencing water pressure sequence, the error range between each actual water pressure and the corresponding influencing water pressure is calculated to obtain a water pressure error coefficient sequence; The mean of the water pressure error coefficient sequence is calculated to obtain the water pressure prediction coefficient.

6. The water pressure balance control method for water supply in an industrial workshop according to claim 1, characterized in that: Randomly generate water pressure control parameters in the water pressure control parameter space, combine the filter blockage parameter sequence and the scaling parameter sequence, perform water pressure control prediction, and obtain the control water pressure sequence and the water supply equipment wear coefficient sequence, including: Based on the historical data of water pressure control adjustment, a sample water pressure control parameter set, a sample filter blockage parameter set, and a sample scaling parameter set are collected. The ratio of the control water pressure and the water supply equipment wear parameter to the maximum water supply equipment wear parameter under different parameter combinations is collected as the water supply equipment wear coefficient, and a sample control water pressure set and a sample water supply equipment wear coefficient set are obtained; Build a water supply control adjustment predictor based on deep learning; Using the sample water pressure control parameter set, the sample filter blockage parameter set, and the sample scaling parameter set as input features, and using the sample control water pressure set and the sample water supply equipment wear coefficient set as output features, supervised training and testing are performed on the water supply control adjustment predictor until the test is qualified; Water pressure control parameters are randomly generated in the water pressure control parameter space, and multiple groups of filter blockage parameters and scaling parameters in the filter blockage parameter sequence and scaling parameter sequence are combined and input into the water supply control adjustment predictor respectively, and the control water pressure sequence and the water supply equipment wear coefficient sequence are obtained as output.

7. A water pressure balancing control system for water supply in an industrial workshop, characterized in that: A system for implementing a water supply pressure balancing control method in an industrial workshop according to any one of claims 1 to 6, comprising: The water quality prediction module is used to monitor the water quality parameters of the water supply within a preset time window in the past in the industrial workshop, predict the water quality parameters of the water supply within a preset time window in the future, and obtain a sequence of predicted water quality parameters; A water pressure analysis module is used to predict filtration blockage and scaling of the water supply pipeline based on the predicted water quality parameter sequence, obtain a filtration blockage parameter sequence and a scaling parameter sequence, and perform water pressure impact analysis to obtain an impact water pressure sequence; A prediction calculation module is used to monitor and obtain the actual water pressure sequence within a preset time window in the future, and calculate the water pressure prediction coefficient based on the influencing water pressure sequence; The water pressure control module is used to configure the water pressure weight and equipment weight according to the water pressure prediction coefficient, optimize the water pressure balance control, obtain the optimal water pressure control parameters, and perform water pressure control, wherein the optimization is performed to improve the constant pressure control accuracy and reduce equipment wear.

Images