Intelligent monitoring method and device for water supply control

Abstract

This application discloses an intelligent monitoring method and device for water supply control, belonging to the field of power plant control system development technology. It includes: acquiring and structurally encapsulating the operating parameter data of the water supply system to obtain feature matrix data; then constructing a supervisory intelligent agent model based on large-scale modeling technology; and learning and identifying reasonable control output ranges under different system operating states. When the control law command deviates from the reasonable range, an operating parameter adjustment command is generated to achieve intelligent auxiliary decision support. The supervisory intelligent agent model, based on large-scale modeling technology, can quickly determine whether the current control law command is within the reasonable control output range by learning historical normal operating data, thus achieving intelligent auxiliary decision support. This improves the intelligence level and operational reliability of the water supply control system, reduces the workload of operators, reduces false alarms and missed alarms, and optimizes system performance, demonstrating significant technological advancement and practical application value.

Description

Technical Field

[0001] This application relates to the field of intelligent operation and maintenance technology of industrial control and thermal systems, and more specifically, to an intelligent monitoring method and device for water supply control. Background Technology

[0002] The overall functionality of power plant thermal control systems is becoming increasingly complex. Control in many areas has shifted from error-based to model-based control, leading to more complex control logic and less transparent control law solutions. This increases the likelihood of miscalculations and consequently, greater safety hazards. Many major accidents can be attributed to negligence or deficiencies in the control system's execution monitoring. Current research often relies on setting execution limits and thresholds to ensure the control system doesn't exceed these limits, failing to consider the actual constraints imposed by the system's current state on the control components. This results in situations, especially dynamic processes with varying operating conditions, requiring manual operation to exit automatic mode to prevent hazards. This increases the workload of operators and reduces their trust in the automatic control equipment.

[0003] As a crucial component of a power plant's thermal system, the feedwater system is responsible for recovering and transporting condensate. Its operational status directly impacts evaporator liquid level, main unit safety, and the efficiency of the entire thermal cycle. Traditional feedwater control systems primarily rely on preset logic to regulate variables such as water level, pressure, and flow rate through a DCS system. However, this type of control has the following shortcomings: On the one hand, the system lacks sufficient state awareness and cannot identify subtle changes in operating status or potential trends in the system. On the other hand, the response is delayed, and when operational fluctuations or disturbances occur, it cannot quickly determine whether manual intervention is required. Furthermore, the system lacks intelligent analysis and cannot dynamically adjust control strategies, resulting in false alarms, missed alarms, and unnecessary protection actions. Moreover, control recommendations are lacking, and the system struggles to provide interpretable and quantifiable auxiliary decision-making suggestions. Summary of the Invention

[0004] The present invention provides an intelligent monitoring water supply control method and device to overcome the deficiencies in the prior art, realize real-time perception of the operating status of the water supply system, trend prediction, anomaly identification and control suggestion output, and has the function of dynamic adjustment of control output threshold.

[0005] This invention provides an intelligent monitoring method for water supply control, the method comprising: Step 1: Obtain the operating parameter data of the water supply system and perform structured encapsulation processing to obtain feature matrix data; the operating parameter data represents the real-time operating parameters of the fluid state and equipment operating status of the water supply system; Step 2: Construct a supervised agent model based on large model technology through parameter fine-tuning and prompt word methods; the supervised agent model is configured to learn and identify reasonable control output ranges under different system operating states; the supervised agent model is trained based on feature matrix data generated during the historical normal operation of the water supply system; Step 3: Obtain the control law command of the current water supply control system, and determine whether the control law command is within the reasonable control output range of the current operating state predicted by the supervisory agent model based on the supervisory agent model; if the control law command is not within the reasonable control output range, generate an operating parameter adjustment command to achieve intelligent auxiliary decision support.

[0006] Furthermore, the supervised agent model adopts a two-layer agent architecture, including an edge layer agent deployed on the local controller and a cloud agent deployed in the cloud. The edge layer agent is responsible for real-time data collection, preliminary analysis, and emergency response, while the cloud agent is responsible for complex data analysis, long-term trend prediction, and optimization strategy generation.

[0007] Furthermore, the step of generating an operating parameter adjustment instruction when the control law instruction is outside the reasonable control output range to achieve intelligent auxiliary decision support includes: Immediately freeze the execution of the control law instructions, and generate operating parameter adjustment instructions based on the current operating status and historical operating data to dynamically adjust the control suggestion trigger threshold and alarm trigger threshold; The Bayesian network analysis mechanism is activated, and the root cause and severity level of the fault are inferred based on the feature matrix data corresponding to the current operating state, so as to obtain the Bayesian network analysis results. Based on the Bayesian network analysis results, the adjusted alarm trigger threshold, and the current system operating status, control recommendations are generated that include suggestions for adjusting quantitative setpoints and / or troubleshooting suggestions.

[0008] Furthermore, the Bayesian network analysis mechanism is configured to: comprehensively analyze multiple relevant key parameter data and output the probability distribution of the root cause of the fault, wherein the relevant key parameters include at least pump current, flow rate, and pipeline pressure.

[0009] Furthermore, after generating the operating parameter adjustment instruction when the control law instruction is not within the reasonable control output range, the method further includes: It connects to the main water supply control system via an industrial communication interface and can operate in one of three modes: non-intervention mode, linkage control mode, and automatic optimization mode. In the non-intervention mode, only steps 1 to 3 are executed, and no control commands are sent to the main control system; In the linkage control mode, the control suggestions generated in step 3 are pushed to the operator, and after obtaining the operator's confirmation, the modified control parameters are sent to the main water supply control system through the industrial communication interface. In the automatic optimization mode, based on the analysis results of step 3 and the generated control suggestions, the optimized control commands are sent directly to the main water supply control system through the industrial communication interface.

[0010] Furthermore, in the linkage control mode, the control suggestions include interpretable quantitative setpoint adjustment suggestions and fault diagnosis suggestions; in the automatic optimization mode, the optimized control instructions are used to automatically fine-tune operating parameters to optimize performance.

[0011] Furthermore, the structured encapsulation process includes noise reduction, anomaly removal, unit normalization, and structured encapsulation.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent monitoring water supply control method as described above.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent monitoring water supply control method as described above.

[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent monitoring water supply control method as described above.

[0015] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects: This application acquires and structures the operating parameter data of the water supply system to obtain feature matrix data. Then, based on large-scale modeling technology, it constructs a supervised intelligent agent model capable of learning and identifying reasonable control output ranges under different system operating conditions. When the control law command deviates from the reasonable range, it generates operating parameter adjustment commands to achieve intelligent auxiliary decision support. By collecting and structuring key operating parameters, the system can accurately perceive the real-time operating status of the water supply system, including fluid state and equipment operating status. This precise state perception capability enables the system to identify subtle changes and potential trends in the operating status, overcoming the shortcomings of traditional control systems that rely solely on preset logic and cannot perceive complex operating condition changes. The supervised intelligent agent model, based on large-scale modeling technology, learns from historical normal operating data to quickly determine whether the current control law command is within the reasonable control output range, achieving intelligent auxiliary decision support. This improves the intelligence level and operational reliability of the water supply control system, reduces the workload of operators, reduces false alarms and missed alarms, optimizes system performance, and has significant technological advancements and practical application value. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 One of the flowcharts of an optional intelligent monitoring water supply control method provided in this application embodiment; Figure 2 A second schematic flowchart of an optional intelligent monitoring water supply control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of an optional electronic device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0019] The terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0020] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0021] Figure 1 The illustration shows one of the flowcharts of an optional intelligent monitoring water supply control method according to an embodiment of this application; as shown. Figure 1 As shown, the intelligent monitoring water supply control method according to an embodiment of this application includes: Step 1: Obtain the operating parameter data of the water supply system and perform structured encapsulation processing to obtain feature matrix data; the operating parameter data represents the real-time operating parameters of the fluid state and equipment operating status of the water supply system; Step 2: Construct a supervised agent model based on large model technology through parameter fine-tuning and prompt word methods; the supervised agent model is configured to learn and identify reasonable control output ranges under different system operating states; the supervised agent model is trained based on feature matrix data generated during the historical normal operation of the water supply system; Step 3: Obtain the control law command of the current water supply control system, and determine whether the control law command is within the reasonable control output range of the current operating state predicted by the supervisory agent model based on the supervisory agent model; if the control law command is not within the reasonable control output range, generate an operating parameter adjustment command to achieve intelligent auxiliary decision support.

[0022] Taking a power plant's feedwater system as an example, key parameters of the feedwater system, such as feedwater pump operating current, system flow rate, water level, vacuum, temperature, and valve opening, are first acquired in real time through a data acquisition interface. These parameters characterize the real-time operating parameters of the fluid state and equipment operating status of the feedwater system. Then, the acquired raw data undergoes noise reduction and outlier processing, and after unifying units, a structured feature matrix is ​​formed. For example, assuming the acquired feedwater pump operating current is 100A, the system flow rate is 500t / h, and the water level is 1.5m, a feature matrix containing these parameters is formed after processing.

[0023] Next, based on large model technology, a supervised agent model is constructed through parameter fine-tuning and cue word methods. This model is trained on feature matrix data generated during the historical normal operation of the water supply system, and can learn and identify reasonable control output ranges under different system operating conditions. For example, assuming the current water pump outlet pressure is 3.8 MPa and the flow rate is 500 t / h, the agent model, based on historical data analysis, determines that the normal pressure range under the current operating conditions should be 3.6-4.0 MPa.

[0024] When the control system outputs a command to increase the pressure to 4.2 MPa, the supervisory agent model receives this control law command and determines that it is outside the reasonable control output range predicted by the supervisory agent model for the current operating state. At this point, it generates an operating parameter adjustment command to achieve intelligent assisted decision support. For example, the system sends a warning to the operator, suggesting adjusting the pressure setpoint to 4.0 MPa and recommending checking changes in pipeline resistance, thus providing operators with reasonable, quantifiable, and verifiable adjustment suggestions and achieving intelligent assisted decision support.

[0025] In an optional embodiment, the intelligent monitoring water supply control method of this application adopts a two-layer intelligent agent model, including an edge layer intelligent agent deployed on a local controller and a cloud intelligent agent deployed in the cloud. The edge layer intelligent agent is responsible for real-time data acquisition, preliminary analysis and emergency response, while the cloud intelligent agent is responsible for complex data analysis, long-term trend prediction and optimization strategy generation.

[0026] In this embodiment, the supervisory agent model adopts a two-layer agent architecture. The edge layer agent is deployed on the local controller and is responsible for real-time data acquisition, preliminary analysis, and emergency response. For example, when abnormal pump vibration is detected, the edge agent can immediately issue an alarm and adjust the pump speed. The cloud agent is responsible for more complex data analysis, such as long-term trend prediction and optimization strategy generation. The cloud may analyze historical data, discover the trend of pump efficiency decreasing over time, and generate preventative maintenance recommendations. This two-layer architecture improves the system's real-time performance and reliability, enhances the system's computing power and intelligence level, and also improves the system's flexibility, allowing for dynamic adjustment of task allocation between the edge and cloud layers according to different scenarios.

[0027] In one alternative embodiment, Figure 2This is a second flowchart illustrating an optional intelligent monitoring water supply control method provided in this application. The intelligent monitoring water supply control method of this application, which generates an operating parameter adjustment instruction when the control law instruction is outside the reasonable control output range to achieve intelligent auxiliary decision support, includes: immediately freezing the execution of the control law instruction, and generating an operating parameter adjustment instruction based on the current operating state and historical operating data to dynamically adjust the trigger threshold and alarm trigger threshold of the control suggestion; initiating a Bayesian network analysis mechanism to infer the root cause and severity level of the fault based on the feature matrix data corresponding to the current operating state, and obtaining the Bayesian network analysis result; and generating a control suggestion containing a quantitative setpoint adjustment suggestion and / or a fault investigation suggestion based on the Bayesian network analysis result, the adjusted alarm trigger threshold, and the current system operating state.

[0028] In this embodiment, when a control law command is outside the reasonable control output range, the system first immediately freezes the execution of the control law command. Then, based on the current operating status and historical operating data, the system dynamically adjusts the control suggestion trigger threshold and alarm trigger threshold. For example, considering that the unit is currently in a load ramp-up phase, the system appropriately relaxes the pressure upper limit to 4.1 MPa, but still considers 4.2 MPa to be risky.

[0029] Next, a Bayesian network analysis mechanism is activated to infer the root cause and severity of the fault based on the feature matrix data corresponding to the current operating state. For example, the Bayesian network comprehensively analyzes multiple relevant key parameters, such as pump current, flow rate, and pipeline pressure, and gives the following diagnostic results: the probability of a sudden change in pipeline resistance is 60%, the probability of sensor failure is 30%, and the probability of internal pump failure is 10%.

[0030] Finally, based on the Bayesian network analysis results, the adjusted alarm trigger thresholds, and the current system operating status, control recommendations are generated, including quantitative setpoint adjustment suggestions and / or troubleshooting suggestions. For example, the system may prioritize suggesting checking the pipeline network condition while also reminding operators to pay attention to potential pressure sensor malfunctions, thus providing operators with more targeted troubleshooting suggestions, helping to quickly adjust the control law, and reducing false alarms, missed alarms, and unnecessary protection actions.

[0031] In an optional embodiment, the Bayesian network analysis mechanism in the intelligent monitoring water supply control method of this application is configured to: comprehensively analyze multiple relevant key parameter data and output the probability distribution of fault root causes, wherein the relevant key parameters include at least pump current, flow rate, and pipeline pressure.

[0032] In this embodiment, the Bayesian network analysis mechanism is configured to comprehensively analyze multiple relevant key parameter data and output the probability distribution of fault root causes. For example, in a water supply system, when the system detects an abnormal increase in pump outlet pressure, the Bayesian network will comprehensively analyze key parameters such as pump current, flow rate, and pipeline pressure. Assuming the current pump current is 105A (normal range is 100±5A), the flow rate is 520t / h (normal range is 500±20t / h), and the pipeline pressure is 0.8MPa (normal range is 0.9±0.1MPa), the Bayesian network outputs the probability distribution of fault root causes based on the abnormality of these parameters, such as a 60% probability of a sudden change in pipeline resistance, a 30% probability of sensor failure, and a 10% probability of internal pump failure. This probabilistic diagnostic result can help operators conduct more targeted troubleshooting, enhance the interpretability of the system, and support knowledge accumulation and updates, facilitating the integration of expert experience and new fault cases into the network.

[0033] In an optional embodiment, the intelligent monitoring water supply control method of this application, after generating the operating parameter adjustment instruction when the control law instruction is not within the reasonable control output range, further includes: connecting to the main water supply control system through an industrial communication interface, and selecting one mode to operate in non-intervention mode, linkage control mode and automatic optimization mode; in the non-intervention mode, only steps 1 to 3 are executed, and no control instruction is sent to the main control system. In the linkage control mode, the control suggestions generated in step 3 are pushed to the operator, and after obtaining the operator's confirmation, the modified control parameters are sent to the main water supply control system through the industrial communication interface. In the automatic optimization mode, based on the analysis results of step 3 and the generated control suggestions, the optimized control commands are sent directly to the main water supply control system through the industrial communication interface.

[0034] In this embodiment, the monitoring system connects to the main water supply control system via an industrial communication interface and can operate in one of three modes: non-intervention mode, linkage control mode, or automatic optimization mode. In non-intervention mode, only data acquisition, preprocessing, and model judgment steps are performed, without sending control commands to the main control system. This mode is mainly used when the system is first deployed to establish baseline data and verify the accuracy of the model.

[0035] In the linkage control mode, when an anomaly is detected, the system pushes control suggestions to the operator. After receiving operator confirmation, the system sends modified control parameters to the main water supply control system via the industrial communication interface. For example, when a decrease in water supply pump efficiency is detected, the system suggests adjusting operating parameters or arranging maintenance. After operator confirmation, the system sends the adjusted parameters to the main control system, achieving linkage control.

[0036] In automatic optimization mode, based on the analysis results and generated control suggestions, the system directly sends optimized control commands to the main water supply control system via the industrial communication interface to automatically fine-tune operating parameters to optimize performance. For example, under stable operating conditions, the system automatically adjusts the number and speed of the water supply pumps according to load changes to achieve optimal energy efficiency. This flexible switching between the three modes ensures both system safety and reliability while maximizing the benefits of intelligent operation.

[0037] In an optional embodiment, in the intelligent monitoring water supply control method of this application, under the linkage control mode, the control suggestions include interpretable quantitative setpoint adjustment suggestions and fault diagnosis suggestions; under the automatic optimization mode, the optimized control instructions are used to automatically fine-tune operating parameters to optimize performance.

[0038] In this embodiment, under the linkage control mode, the control recommendations include interpretable quantifiable setpoint adjustment suggestions and troubleshooting suggestions. For example, if the system detects an abnormal increase in the outlet pressure of the feedwater pump, and the Bayesian network analysis results indicate a high probability of a sudden change in pipeline resistance, the control recommendations pushed to the operator will explicitly suggest adjusting the pressure setpoint to 4.0 MPa and recommend checking the changes in pipeline resistance. It will also provide specific troubleshooting directions for possible sudden changes in pipeline resistance, such as checking whether pipeline valves have been mistakenly closed or whether there is any blockage in the pipeline, helping the operator quickly understand and implement the adjustment strategy.

[0039] In automatic optimization mode, optimized control commands are used to automatically fine-tune operating parameters to optimize performance. For example, based on real-time load changes and historical data, the system automatically adjusts the speed of the water supply pump to reduce energy consumption while ensuring that the water supply pressure and flow meet requirements, thus achieving automatic optimized operation of the system. In this mode, the system can flexibly adjust control parameters according to actual conditions without manual intervention, improving the system's automation level and operating efficiency.

[0040] In an optional embodiment, the structured encapsulation processing in the intelligent monitoring water supply control method of this application includes noise reduction, anomaly removal, unit normalization, and structured encapsulation.

[0041] In this embodiment, the structured encapsulation process includes denoising, anomaly removal, unit normalization, and structured encapsulation. For example, the collected water pump operating current data may contain noise interference, such as instantaneous current fluctuations. Denoising can smooth these fluctuations, resulting in a more stable current value. For outliers, such as a current value collected at a certain moment that significantly exceeds the normal range, it may be erroneous data caused by sensor malfunction, and these outliers are removed through anomaly removal. Then, all parameters are normalized to convert data with different units into a unified dimensionless form, facilitating subsequent analysis and processing. Finally, the processed data is structured and encapsulated to form a feature matrix containing multiple parameters, which serves as input data for the supervised agent model. This provides an accurate and standardized data foundation for model training and real-time analysis, thereby improving the system's state perception capability and intelligent analysis level.

[0042] Exemplary electronic devices Figure 3 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application, such as... Figure 3 As shown, it includes a processor 302, a communication interface 304, a memory 306, and a communication bus 308. The processor 302, communication interface 304, and memory 306 communicate with each other via the communication bus 308. Memory 306 is used to store computer programs; When processor 302 executes a computer program stored in memory 306, it performs the following steps: S1, acquire the operating parameter data of the water supply system and perform structured encapsulation processing to obtain feature matrix data; the operating parameter data represents the real-time operating parameters of the fluid state and equipment operating state of the water supply system; S2, a supervised agent model is constructed based on large model technology through parameter fine-tuning and prompt word methods; the supervised agent model is configured to learn and identify reasonable control output ranges under different system operating states; the supervised agent model is trained based on feature matrix data generated during the historical normal operation of the water supply system; S3, obtain the control law command of the current water supply control system, and determine whether the control law command is within the reasonable control output range of the current operating state predicted by the supervisory agent model based on the supervisory agent model; if the control law command is not within the reasonable control output range, generate an operating parameter adjustment command to achieve intelligent auxiliary decision support.

[0043] Optionally, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not indicate that there is only one bus or one type of bus. The communication interface is used for communication between the aforementioned electronic device and other devices.

[0044] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0045] The processors mentioned above can be general-purpose processors, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; they can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0046] Exemplary computer program products and computer-readable storage media In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the intelligent monitored water supply control method according to various embodiments of this application as described in the "Exemplary Methods" section above.

[0047] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0048] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the moving object tracking methods according to various embodiments of this application described in the "Exemplary Methods" section of this specification.

[0049] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0050] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0051] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0052] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0053] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0054] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for intelligent monitoring and control of water supply, characterized in that, include: Step 1: Obtain the operating parameter data of the water supply system and perform structured encapsulation processing to obtain feature matrix data; The operating parameter data represents the real-time operating parameters of the fluid state and equipment operating status of the water supply system; Step 2: Construct a supervised agent model based on large model technology through parameter fine-tuning and prompt word methods; the supervised agent model is configured to learn and identify reasonable control output ranges under different system operating states; the supervised agent model is trained based on feature matrix data generated during the historical normal operation of the water supply system; Step 3: Obtain the control law command of the current water supply control system, and determine whether the control law command is within the reasonable control output range of the current operating state predicted by the supervisory agent model based on the supervisory agent model; If the control law instruction is not within the reasonable control output range, an operating parameter adjustment instruction is generated; It connects to the main water supply control system via an industrial communication interface and can operate in one of three modes: non-intervention mode, linkage control mode, and automatic optimization mode. In the non-intervention mode, only steps 1 to 3 are executed, and no control commands are sent to the main control system; In the linkage control mode, the control suggestions generated in step 3 are pushed to the operator, and after obtaining the operator's confirmation, the modified control parameters are sent to the main water supply control system through the industrial communication interface. In the automatic optimization mode, based on the analysis results of step 3 and the generated control suggestions, the optimized control commands are sent directly to the main water supply control system through the industrial communication interface to achieve intelligent auxiliary decision support.

2. The intelligent monitoring water supply control method as described in claim 1, characterized in that, The supervised agent model adopts a two-layer agent architecture, including an edge-layer agent deployed on the local controller and a cloud-based agent deployed in the cloud. The edge-layer agent is responsible for real-time data collection, preliminary analysis, and emergency response, while the cloud-based agent is responsible for complex data analysis, long-term trend prediction, and optimization strategy generation.

3. The intelligent monitoring water supply control method as described in claim 1, characterized in that, When the control law instruction is outside the reasonable control output range, generating an operating parameter adjustment instruction to achieve intelligent auxiliary decision support includes: Immediately freeze the execution of the control law instructions, and generate operating parameter adjustment instructions based on the current operating status and historical operating data to dynamically adjust the control suggestion trigger threshold and alarm trigger threshold; The Bayesian network analysis mechanism is activated, and the root cause and severity level of the fault are inferred based on the feature matrix data corresponding to the current operating state, so as to obtain the Bayesian network analysis results. Based on the Bayesian network analysis results, the adjusted alarm trigger threshold, and the current system operating status, control recommendations are generated that include suggestions for adjusting quantitative setpoints and / or troubleshooting suggestions.

4. The intelligent monitoring water supply control method as described in claim 3, characterized in that, The Bayesian network analysis mechanism is configured to: comprehensively analyze multiple relevant key parameter data and output the probability distribution of the root cause of the fault. The relevant key parameters include at least pump current, flow rate, and pipeline pressure.

5. The intelligent monitoring water supply control method as described in claim 1, characterized in that, In the linkage control mode, the control suggestions include interpretable quantitative setpoint adjustment suggestions and troubleshooting suggestions; in the automatic optimization mode, the optimized control instructions are used to automatically fine-tune operating parameters to optimize performance.

6. The intelligent monitoring water supply control method as described in claim 1, characterized in that, The structured encapsulation process includes noise reduction, anomaly removal, unit normalization, and structured encapsulation.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent monitoring water supply control method as described in any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent monitoring water supply control method as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent monitoring water supply control method as described in any one of claims 1 to 6.

Images