A water plant water quantity intelligent balance control method, system, device and storage medium

Abstract

The present application relates to water plant water production technology field, specifically to a kind of water plant water quantity intelligent balance control method, system, equipment and storage medium, including steps S1, obtain the historical data of water plant and are pretreated, obtain the historical data after pretreatment, while abnormal data are early warned;Step S2, the historical data after pretreatment is input into pre-trained water quantity prediction network, and the optimal water supply water quantity of water plant current stage is obtained;Step S3, in response to the water quantity control mode selected by user, the weight corresponding in water quantity prediction network under different modes is adjusted, and the optimal water supply water quantity under each mode of water plant current stage is obtained;Step S4, the optimal water supply water quantity under each mode of water plant current stage is sent to corresponding water pump or valve by intelligent control terminal to adjust corresponding water plant water supply water quantity.

Description

Technical Field

[0001] This invention relates to the field of water treatment technology in waterworks, specifically to a method, system, equipment, and storage medium for intelligent water balance control in waterworks. Background Technology

[0002] Water plants play a crucial and complex role in the entire water supply process. On the one hand, they need to strictly control water production costs while ensuring that the quality of the effluent meets the relevant national standards; on the other hand, they must also ensure the stability of the water supply to meet the continuous water demand for urban production and daily life. Currently, water plants have actively conducted extensive technical research and achieved a series of application results in terms of achieving effluent quality standards and reducing water production costs. By adopting advanced water treatment processes and equipment and continuously optimizing the water production process, they have accumulated rich experience in improving water quality and reducing costs.

[0003] However, the current scheduling methods used by water plants still have significant shortcomings in ensuring stable water supply. Currently, scheduling during water plant operation largely relies on traditional experience. On-site staff mainly adjust the water inflow manually based on past peak and off-peak water supply patterns and current water pressure values. This experience-based and plant-specific approach lacks precise quantitative analysis and scientific predictive models, making it difficult to achieve accurate and stable water volume control. During peak and off-peak water usage periods, water plants often experience overflows in their clear water tanks, wasting water resources, or are emptied due to insufficient water supply, thus affecting normal water supply. Furthermore, the process control of water plants requires extremely high stability in the inflow; frequent fluctuations in inflow can adversely affect various production stages, significantly increasing the difficulty of optimizing and controlling the plant's operation. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this application provides a method, system, equipment, and storage medium for intelligent water balance control of water plants, aiming to break through the limitations of traditional experience-based scheduling, achieve precise control of the influent water volume of water plants, and provide strong support for the stable operation and efficient management of water plants.

[0005] The technical means adopted by this invention to solve its technical problem is: a water plant water volume intelligent balance control method, the improvement of which includes the following steps:

[0006] Step S1: Obtain historical data from the water plant and preprocess it to obtain preprocessed historical data, while issuing early warnings for abnormal data;

[0007] Step S2: Input the preprocessed historical data into the pre-trained water volume prediction network to obtain the optimal water supply volume for the current stage of the water plant.

[0008] Step S3: In response to the water control mode selected by the user, adjust the corresponding weights in the water prediction network under different modes to obtain the optimal water supply volume of each mode at the current stage of the water plant.

[0009] Step S4: Send the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pump or valve through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

[0010] The method following step S2 in the above technical solution further includes:

[0011] Step S5: Compare and analyze the actual water supply with the predicted water supply, calculate the prediction error, and when the prediction error exceeds the set threshold, feed back the actual water supply data, error data, etc. to the water supply prediction network and retrain the network model parameters.

[0012] Step S1 in the above technical solution includes:

[0013] Step S101: The acquired real-time data is transformed into high-quality data content through data cleaning, data integration, data reduction and data transformation.

[0014] Step S102: For the preprocessed data, when important data is abnormal, data warnings are issued through methods including but not limited to redundant data replacement, similar data replacement, historical data simulation, and abnormal timing, and three alarm modes are set: attention mode, processing mode, and system shutdown mode.

[0015] Step S103: Based on the alarm mode, switch the system operation status. The "Attention" mode and "Handling" mode do not require shutting down the water supply system, but alarm information needs to be issued to guide relevant personnel to handle the situation. The "System Shutdown" mode requires automatically shutting down the water supply system and notifying relevant personnel to handle the situation on site.

[0016] The water quantity prediction network in step S2 of the above technical solution includes a water plant water supply prediction model, a water plant water treatment process simulation model, and a greedy optimization model based on multi-objectives, wherein...

[0017] The water plant's water supply prediction model predicts the hourly water supply for the next 24 hours based on the plant's historical water supply volume.

[0018] (1);

[0019] Among them, a t,i The predicted water supply volume is given by t (date), i (time) and m (time), with values ​​ranging from 0 to 23. t,jThe input data for performing water supply forecasting is as follows: j represents the influencing factor number, including but not limited to historical water supply volume, historical meteorological data, and historical date type; F() is the constructed time series forecasting model.

[0020] The water treatment process simulation model described above simulates the water supply volume and clear water tank level changes in real time based on water volume, liquid level, and equipment signal data during water plant operation.

[0021] (2);

[0022] Among them, b t,k For water supply volume, c t,k n represents the water level in the clear water tank. t,k G() represents the equipment signal data and online instrument data from other water plants, and G() is the constructed time-series water production process simulation model used to predict the water supply volume and clear water tank level changes at the next time step based on the data from the previous time step.

[0023] The greedy optimization model based on multiple objectives generates the optimal value of the raw water volume for the water plant by connecting the water plant supply prediction model and the water plant water treatment process simulation model, based on the target level of the clear water tank, water supply energy consumption, and water supply electricity consumption indicators required for operation.

[0024] (3);

[0025] (4);

[0026] Among them, f t,k The optimal value of raw water quantity output by the model, where t represents the weight set for the corresponding control objective, and x... i This indicates the corresponding control objectives, including but not limited to the objectives of raising the level of the clear water tank, reducing water supply power consumption, and reducing water supply costs; y i This indicates the corresponding operational target, including but not limited to the upper and lower limits of the clear water tank level control and the upper and lower limits of the equipment control for process operation.

[0027] The multiple objectives mentioned in the above technical solution include, but are not limited to: stable influent flow, clear water tank level within a reasonable range, reduced water supply unit consumption, and reasonable use of peak and off-peak electricity pricing for water production. The weights of each individual parameter are adjusted and optimized based on the specific water plant.

[0028] The water control mode in step S3 of the above technical solution is generated using the following logic:

[0029] Based on the control objective of a stable influent flow mode, we strive to ensure that the fluctuation range of influent flow does not exceed the maximum fluctuation range required by the water plant's operating process, and ensure that the clear water tank level does not run out or overflow during the operation of the water plant.

[0030] Based on the control objective of the lowest energy consumption mode, under the condition of meeting the stable water inflow mode, the water production unit consumption during the operation of the water plant is reduced, that is, the electricity consumption required per ton of water. The objectives include, but are not limited to, raising the liquid level of the water plant's clear water tank to reduce the energy consumption of the water pump.

[0031] Based on the control objective of the lowest electricity cost mode, under the condition of meeting the stable water inflow mode, the peak-valley electricity pricing strategy is used to minimize water production during peak electricity price periods and maximize water production during off-peak electricity price periods, thereby achieving the lowest possible electricity cost during the operation of the water plant.

[0032] The intelligent control terminal described in the above technical solution includes, but is not limited to, a combination of PLC control cabinet and corresponding circuits. It also has remote monitoring and manual intervention functions. Users can remotely monitor the water supply of the water plant through mobile terminals or monitoring centers. In case of emergencies, the operating parameters of water pumps or valves can be manually adjusted to realize emergency intervention on the water supply of the water plant.

[0033] The technical means adopted by this invention to solve its technical problem is: a water plant intelligent water balance control system, comprising:

[0034] The data processing and early warning module is used to acquire historical data from the water plant and preprocess it to obtain preprocessed historical data, while also providing early warnings for abnormal data.

[0035] The intelligent water volume prediction module is used to input the pre-processed historical data into a pre-trained water volume prediction network to obtain the optimal water supply volume of the water plant at the current stage.

[0036] The control mode selection module is used to adjust the corresponding weights in the water volume prediction network under different modes in response to the water volume control mode selected by the user, so as to obtain the optimal water supply volume of each mode in the current stage of the water plant.

[0037] The intelligent water volume control module sends the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pumps or valves through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

[0038] The technical means adopted by this invention to solve its technical problem is: a device, comprising: at least one processor and at least one memory, wherein,

[0039] The memory stores program instructions or code;

[0040] The program instructions or code are loaded and executed by the processor, enabling the electronic device to implement the intelligent water balance control method for water plants as described above.

[0041] The technical means adopted by the present invention to solve its technical problem is: a storage medium storing program instructions or code thereon, wherein the program instructions or code are loaded and executed by a processor to realize the intelligent water balance control method for water plants as described above.

[0042] The beneficial effects of this invention are:

[0043] A smart water balance control method for water plant production and supply balance is proposed to achieve prediction and control of water plant inflow. In addition, for different water plant application needs, a variety of smart water balance control modes are proposed for water volume control, which effectively realizes smart water volume control of water plant and achieves corresponding energy saving and consumption reduction goals. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating an intelligent water balance control method for a water plant, as shown in an embodiment of the present invention.

[0045] Figure 2 This is a flowchart illustrating step S1 in an embodiment of the present invention;

[0046] Figure 3 This is a flowchart illustrating another intelligent water balance control method for water plants, as shown in an embodiment of the present invention.

[0047] Figure 4 This is a structural block diagram of a water plant intelligent water balance control system according to an embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0049] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0050] The following will clearly and completely describe the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention. Furthermore, all connections / linkages involved in the patent do not simply refer to direct contact between components, but rather to the ability to form a better connection structure by adding or reducing connecting accessories according to specific implementation conditions. The various technical features in this invention can be combined interactively without contradicting each other.

[0051] like Figure 1 As shown, this application provides a method for intelligent water balance control in a water plant, comprising the following steps:

[0052] Step S1: Obtain historical data from the water plant and preprocess it to obtain preprocessed historical data, while issuing early warnings for abnormal data.

[0053] Specifically, the historical data of the water plant includes historical water supply volume, meteorological data, date type, water volume, liquid level and equipment operating status data during the operation of the water plant, and the target values ​​for the operation of the water plant.

[0054] In one possible implementation, such as Figure 2 As shown, step 1 includes:

[0055] Step S101: The acquired real-time data is transformed into high-quality data content through data cleaning, data integration, data reduction and data transformation.

[0056] Specifically, data cleaning includes: identifying and removing duplicate data, marking and processing missing data; for data fields with a missing rate of less than 10%, mean imputation is used; for data fields with a missing rate of more than 10%, machine learning algorithms are used for prediction imputation; data integration involves integrating water plant operation data, meteorological data, and user water usage data from different data sources to eliminate data conflicts; data reduction reduces data dimensionality and volume through attribute selection and numerical reduction; and data transformation includes standardizing the data to make it conform to a normal distribution with a mean of 0 and a standard deviation of 1.

[0057] Step S102: For the preprocessed data, when important data is abnormal, data warnings are issued through methods including but not limited to redundant data replacement, similar data replacement, historical data simulation, and abnormal timing, and three alarm modes are set: attention mode, processing mode, and system shutdown mode.

[0058] The "Pay Attention" mode refers to situations where data anomalies exist but redundant instruments can compensate, requiring manual judgment to determine whether on-site instrument inspection is necessary, but this does not affect system operation. The "Processing" mode refers to situations where data anomalies are severe but can be compensated for with fitting, requiring manual on-site inspection of instruments and network issues, but this will not affect system operation in the short term. The "System Cutoff" mode refers to situations where data anomalies cannot be compensated for, requiring manual intervention to control the system and inspect and repair on-site instruments and equipment.

[0059] Step S103: Based on the alarm mode, switch the system operation status. The "Attention" mode and "Handling" mode do not require shutting down the water supply system, but alarm information needs to be issued to guide relevant personnel to handle the situation. The "System Shutdown" mode requires automatically shutting down the water supply system and notifying relevant personnel to handle the situation on site.

[0060] Through the above embodiments, the detailed data cleaning, integration, reduction, and transformation operations in step S101 can effectively improve data quality. Identifying and removing duplicate data avoids data redundancy interference; using appropriate filling methods for data fields with different missing rates ensures data integrity; data integration eliminates conflicts between different data sources, making the data more consistent; data reduction reduces data dimensionality and volume, improving data processing efficiency; and standardized data transformation helps subsequent models better learn data characteristics, laying a solid foundation for accurate water volume prediction.

[0061] Meanwhile, the established three-level alarm modes and corresponding handling methods enable precise hierarchical control of abnormal data. The "Attention Required Mode" prompts manual judgment only when minor data anomalies exist and redundant instruments are available, reducing unnecessary intervention and ensuring the continuity of normal system operation. The "Handling Required Mode" guides manual investigation for more serious anomalies, provided compensation is possible, to prevent the anomaly from escalating and affecting system operation. The "System Shutdown Mode" quickly shuts down the system when data anomalies cannot be compensated for, preventing serious production accidents caused by erroneous data and ensuring the safety and reliability of the water plant's operation.

[0062] Step S2: Input the preprocessed historical data into the pre-trained water volume prediction network to obtain the optimal water supply volume for the current stage of the water plant.

[0063] In one possible implementation, the water quantity prediction network includes a water plant supply quantity prediction model, a water plant water treatment process simulation model, and a greedy optimization model based on multiple objectives, wherein...

[0064] The water plant's water supply prediction model predicts the hourly water supply for the next 24 hours based on the plant's historical water supply volume.

[0065] (1);

[0066] Among them, a t,i The predicted water supply volume is given by t (date), i (time) and m (time), with values ​​ranging from 0 to 23. t,j The input data for performing water supply volume forecasting is as follows: j represents the influencing factor number, including but not limited to historical water supply volume, historical meteorological data, and historical date type; F() is the constructed time series forecasting model.

[0067] Optionally, the time-series prediction model F() is constructed using a Long Short-Term Memory (LSTM) network. By extracting and analyzing features from input data such as historical water supply volume, historical meteorological data, and historical date types, the model parameters are trained to improve the accuracy of predicting the water supply volume of the water plant in the next 24 hours.

[0068] The water treatment process simulation model described above simulates the water supply volume and clear water tank level changes in real time based on water volume, liquid level, and equipment signal data during water plant operation.

[0069] (2);

[0070] Among them, b t,k For water supply volume, c t,k n represents the water level in the clear water tank. t,k G() represents the equipment signal data and online instrument data from other water plants. G() is the constructed time-series water production process simulation model, used to predict the water supply volume and clear water tank level changes at the next moment based on the data from the previous moment.

[0071] Optionally, the time-series water production process simulation model G() is constructed based on a hybrid architecture of convolutional neural network (CNN) and recurrent neural network (RNN). CNN is used to extract the spatial features of equipment signal data, and RNN is used to analyze the time series features of water volume and liquid level, so as to realize accurate real-time simulation of water supply volume and clear water tank level changes during water plant operation.

[0072] The greedy optimization model based on multiple objectives generates the optimal value of the raw water volume for the water plant by connecting the water plant supply prediction model and the water plant water treatment process simulation model, based on the target level of the clear water tank, water supply energy consumption, and water supply electricity consumption indicators required for operation.

[0073] (3);

[0074] (4);

[0075] Among them, f t,kThe optimal value of raw water quantity output by the model, where t represents the weight set for the corresponding control objective, and x... i This indicates the corresponding control objectives, including but not limited to the objectives of raising the level of the clear water tank, reducing water supply power consumption, and reducing water supply costs; y i This indicates the corresponding operational target, including but not limited to the upper and lower limits of the clear water tank level control and the upper and lower limits of the equipment control for process operation.

[0076] Optionally, the weight t of the corresponding control target is determined by the Analytic Hierarchy Process (AHP). First, a hierarchical structure model of the control targets is constructed, and then the relative importance between each control target is determined by expert scoring. Then, the weight t corresponding to each control target is calculated to achieve the reasonable generation of the optimal value of the raw water quantity of the water plant.

[0077] Through the above embodiments, the water volume prediction network realizes the intelligentization of the entire chain of the water supply system from demand prediction and process simulation to optimization control. While ensuring water supply security, it effectively reduces operating costs and improves the level of refined management of water plants, resulting in significant economic and social benefits.

[0078] Step S3: In response to the water control mode selected by the user, adjust the corresponding weights in the water prediction network under different modes to obtain the optimal water supply volume for each mode at the current stage of the water plant.

[0079] In one possible implementation, the water volume control mode is generated using the following logic:

[0080] Based on the control objective of a stable influent flow mode, we strive to ensure that the fluctuation range of influent flow does not exceed the maximum fluctuation range required by the water plant's operating process, and ensure that the clear water tank level does not run out or overflow during the operation of the water plant.

[0081] Based on the control objective of the lowest energy consumption mode, under the condition of meeting the stable water inflow mode, the water production unit consumption during the operation of the water plant is reduced, that is, the electricity consumption required per ton of water. The objectives include, but are not limited to, raising the liquid level of the water plant's clear water tank to reduce the energy consumption of the water pump.

[0082] Based on the control objective of the lowest electricity cost mode, under the condition of meeting the stable water inflow mode, the peak-valley electricity pricing strategy is used to minimize water production during peak electricity price periods and maximize water production during off-peak electricity price periods, thereby achieving the lowest possible electricity cost during the operation of the water plant.

[0083] Optionally, the multiple objectives include, but are not limited to: stable influent flow, clear water tank level within a reasonable range, reduced water supply unit consumption, and reasonable use of peak and off-peak electricity pricing for water production. The weights of each individual parameter are adjusted and optimized based on the specific water plant.

[0084] Through the above embodiments, by optimizing the multi-dimensional target, the water supply mode selected according to the user's real-time needs, and adjusting the weight t of the control target set in the corresponding mode in the above formula (3), it is possible to significantly reduce operating costs and energy consumption while ensuring water supply safety, and at the same time improve the system's intelligence level and management efficiency, thus achieving good economic and environmental benefits.

[0085] Step S4: Send the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pump or valve through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

[0086] In one possible implementation, the intelligent control terminal includes, but is not limited to, a combination of a PLC control cabinet and corresponding circuits, and has both remote monitoring and manual intervention functions. Users can remotely monitor the water supply volume of the water plant through a mobile terminal or monitoring center. In case of emergencies, the operating parameters of the water pump or valve can be manually adjusted to realize emergency intervention on the water supply volume of the water plant.

[0087] Through the above embodiments, the intelligent control terminal significantly improves the control accuracy, emergency response capability, and management efficiency of the water supply system through automation, remote control, and intelligent means, while reducing operation and maintenance costs and safety risks, providing strong support for the modern operation of water plants.

[0088] In another possible implementation, such as Figure 3 As shown, after step S2, the method further includes:

[0089] Step S5: Compare and analyze the actual water supply with the predicted water supply, calculate the prediction error, and when the prediction error exceeds the set threshold, feed back the actual water supply data, error data, etc. to the water supply prediction network and retrain the network model parameters.

[0090] By comparing actual and predicted water volume in real time, model retraining is triggered when the error exceeds a threshold (e.g., ±5%), which can improve long-term prediction accuracy by 15%-20%. At the same time, the feedback mechanism enables the water volume prediction network to have a complete intelligent closed loop of "perception-decision-execution-learning", which continuously improves performance without human intervention, significantly enhancing the intelligence level and long-term operational value of the water supply system.

[0091] The following are system embodiments of this application, which can be used to execute the intelligent water balance control method for water plants involved in this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of the intelligent water balance control method for water plants involved in this application.

[0092] Please see Figure 4This application provides a water plant water volume intelligent balance control system 20, which includes: a data processing and early warning module 201, an intelligent water volume prediction module 202, a control mode selection module 203, and an intelligent water volume control module 204.

[0093] Among them, the data processing and early warning module 201 is used to acquire historical data of the water plant and preprocess it to obtain preprocessed historical data, and at the same time provide early warning for abnormal data;

[0094] The intelligent water volume prediction module 202 is used to input the pre-processed historical data into a pre-trained water volume prediction network to obtain the optimal water supply volume of the water plant at the current stage.

[0095] The control mode selection module 203 is used to adjust the corresponding weights in the water volume prediction network under different modes in response to the water volume control mode selected by the user, so as to obtain the optimal water supply volume of each mode in the current stage of the water plant.

[0096] The intelligent water volume control module 204 sends the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pumps or valves through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

[0097] It should be noted that the intelligent water balance control system for water plants provided in the above embodiments is only illustrated by the division of the above functional modules when performing intelligent water balance control. In actual applications, the above functions can be assigned to different functional modules as needed. That is, the internal structure of the intelligent water balance control system for water plants will be divided into different functional modules to complete all or part of the functions described above. The above modules can be embedded in the processor of the computer device in hardware form or independent of the processor, or they can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0098] Furthermore, the intelligent water balance control system for water plants and the method embodiment of the intelligent water balance control method for water plants provided in the above embodiments belong to the same concept. The specific way each module performs its operation has been described in detail in the method embodiment, and will not be repeated here.

[0099] Please see Figure 5 This application provides an electronic device 4000.

[0100] exist Figure 5In this design, data interaction between the processor 4001 and the memory 4003 can be achieved through at least one communication bus 4002. This communication bus 4002 may include a path for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0101] Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0102] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc. The memory 4003 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program instructions or code in the form of instructions or data structures and accessible by the electronic device 4000, but not limited thereto.

[0103] The memory 4003 stores program instructions or code, and the processor 4001 can read the program instructions or code stored in the memory 4003 through the communication bus 4002.

[0104] When the program instructions or code are executed by the processor 4001, the intelligent water balance control method for water plants in the above embodiments is implemented.

[0105] Furthermore, this application embodiment provides a storage medium storing program instructions or code, which is loaded and executed by a processor to realize the intelligent water balance control method for water plants as described above.

[0106] This application provides a computer program product, which includes program instructions or code. The program instructions or code are stored in a storage medium. The processor of the electronic device reads the program instructions or code from the storage medium, loads and executes the program instructions or code, so that the electronic device realizes the intelligent water balance control method for water plants as described above.

[0107] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for intelligent water balance control in a water plant, characterized in that, Includes the following steps: Step S1: Obtain historical data from the water plant and preprocess it to obtain preprocessed historical data, while issuing early warnings for abnormal data; Step S2: Input the preprocessed historical data into a pre-trained water volume prediction network to obtain the optimal water supply volume for the current stage of the water plant; the water volume prediction network includes a water plant water supply prediction model, a water plant water treatment process simulation model, and a greedy optimization model based on multiple objectives, wherein... The water plant's water supply prediction model predicts the hourly water supply for the next 24 hours based on the plant's historical water supply volume. （1）； Among them, a t,i The predicted water supply volume is given by t (date), i (time), and m (time). t,j The input data for performing water supply forecasting is as follows: j represents the influencing factor number, including historical water supply volume, historical meteorological data, and historical date type; F() is the constructed time series forecasting model. The water treatment process simulation model described above simulates the water supply volume and clear water tank level changes in real time based on water volume, liquid level, and equipment signal data during water plant operation. （2）； Among them, b t,i For water supply volume, c t,i n represents the water level in the clear water tank. t,i G() represents the equipment signal data and online instrument data from other water plants, and G() is the constructed time-series water production process simulation model used to predict the water supply volume and clear water tank level changes at the next time step based on the data from the previous time step. The greedy optimization model based on multiple objectives includes: stable influent flow, clear water tank level within a reasonable range, reduced water supply unit consumption, and rational use of peak and off-peak electricity pricing for water production. The weights of each parameter are adjusted and optimized based on the specific water plant. By connecting the water plant supply prediction model and the water plant water treatment process simulation model, and based on the target clear water tank level, water supply energy consumption, and water supply electricity consumption indicators required for operation, the optimal value of the raw water volume for the water plant is generated: （3）； （4）； Among them, f t,j The optimal value of raw water quantity output by the model, where T represents the weight set for the corresponding control objective, and x... t,j,k This indicates the corresponding control objectives, including the target for raising the level of the clear water tank, the target for reducing water supply power consumption, and the target for reducing water supply costs; y t,j,k This indicates the corresponding operational targets, including the upper and lower limits for controlling the level in the clear water tank and the upper and lower limits for controlling the equipment during process operation; Step S3: In response to the water control mode selected by the user, adjust the corresponding weights in the water prediction network under different modes to obtain the optimal water supply volume of each mode at the current stage of the water plant. Step S4: Send the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pump or valve through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

2. The intelligent water balance control method for a water plant according to claim 1, characterized in that, The method following step S2 further includes: Step S5: Compare and analyze the actual water supply with the predicted water supply, calculate the prediction error, and when the prediction error exceeds the set threshold, feed the actual water supply data and error data back to the water supply prediction network to retrain the network model parameters.

3. The intelligent water balance control method for a water plant according to claim 1, characterized in that, Step S1 includes: Step S101: The acquired real-time data is transformed into high-quality data content through data cleaning, data integration, data reduction and data transformation. Step S102: For the preprocessed data, when important data is abnormal, data warnings are issued through methods including redundant data replacement, similar data replacement, historical data simulation, and abnormal timing, and three alarm modes are set: attention mode, processing mode, and system shutdown mode. Step S103: Based on the alarm mode, switch the system operation status. The "Attention" mode and "Handling" mode do not require shutting down the water supply system, but alarm information needs to be issued to guide relevant personnel to handle the situation. The "System Shutdown" mode requires automatically shutting down the water supply system and notifying relevant personnel to handle the situation on site.

4. The intelligent water balance control method for a water plant according to claim 1, characterized in that, The water control mode in step S3 is generated using the following logic: Based on the control objective of a stable influent flow mode, we strive to ensure that the fluctuation range of influent flow does not exceed the maximum fluctuation range required by the water plant's operating process, and ensure that the clear water tank level does not run out or overflow during the operation of the water plant. Based on the control objective of the lowest energy consumption mode, under the condition of meeting the stable water inflow mode, the water production unit consumption during the operation of the water plant is reduced, that is, the electricity consumption required per ton of water. The objectives include raising the liquid level of the water plant's clear water tank to reduce the energy consumption of the water pump. Based on the control objective of the lowest electricity cost mode, under the condition of meeting the stable water inflow mode, the peak-valley electricity pricing strategy is used to minimize water production during peak electricity price periods and maximize water production during off-peak electricity price periods, thereby achieving the lowest possible electricity cost during the operation of the water plant.

5. The intelligent water balance control method for a water plant according to claim 1, characterized in that, The intelligent control terminal includes a combination of PLC control cabinet and corresponding circuits, and has both remote monitoring and manual intervention functions. Users can remotely monitor the water supply of the water plant through mobile terminals or monitoring centers. In case of emergencies, the operating parameters of water pumps or valves can be manually adjusted to realize emergency intervention on the water supply of the water plant.

6. A water plant intelligent water balance control system, characterized in that, This system is used to implement the intelligent water balance control method for water plants as described in any one of claims 1 to 5, comprising: The data processing and early warning module is used to acquire historical data from the water plant and preprocess it to obtain preprocessed historical data, while also providing early warnings for abnormal data. The intelligent water volume prediction module is used to input the pre-processed historical data into a pre-trained water volume prediction network to obtain the optimal water supply volume of the water plant at the current stage. The control mode selection module is used to adjust the corresponding weights in the water volume prediction network under different modes in response to the water volume control mode selected by the user, so as to obtain the optimal water supply volume of each mode in the current stage of the water plant. The intelligent water volume control module sends the optimal water supply volume for each mode of the current stage of the water plant to the corresponding water pumps or valves through the intelligent control terminal to adjust the water supply volume of the water plant accordingly.

7. A water plant intelligent water balance control device, characterized in that, include: At least one processor, at least one memory, wherein, The memory stores program instructions or code; The program instructions or code are loaded and executed by the processor, enabling the electronic device to implement the intelligent water balance control method for water plants as described in any one of claims 1 to 5.

8. A storage medium storing program instructions or code thereon, characterized in that, The program instructions or code are loaded and executed by the processor to implement the intelligent water balance control method for water plants as described in any one of claims 1 to 5.

Images