Control method, device, equipment, medium and product for water pump operation

Abstract

Embodiments of the present application provide a water pump operation control method, device, equipment, medium and product. The method comprises: acquiring multi-dimensional operation data collected in real time by a distributed sensor network deployed in a water pump system; performing data cleaning and feature extraction on the multi-dimensional operation data by an edge computing node to generate a standardized data package; uploading the standardized data package to the cloud to generate a variable frequency speed regulation instruction and a multi-pump collaborative control strategy based on the standardized data package and historical operation data by a model deployed in the cloud; and when receiving the variable frequency speed regulation instruction and the multi-pump collaborative control strategy issued by the cloud, adjusting and collaboratively controlling the operation parameters of the water pump by a control unit. The method is used to improve the operation efficiency of the water pump system, reduce energy consumption and reduce manual intervention.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, apparatus, equipment, medium, and product for controlling the operation of a water pump. Background Technology

[0002] With the development of industrial automation and smart water management, higher demands are being placed on water pump systems, which are the core power source for liquid transportation. The operating efficiency, stability, and energy consumption level of water pumps directly affect the economic benefits and operational safety of the entire system. Therefore, achieving refined and intelligent control of water pump systems has become an urgent need for the current industry development.

[0003] Current water pump systems typically use a combination of field-programmable logic controllers (FPGAs) and frequency converters to control the start-up, shutdown, and speed regulation of individual pumps. For some more complex water pump systems, a simple closed-loop regulation of the pump is performed based on a proportional-integral-derivative (PID) control algorithm using preset constant pressure or liquid level values.

[0004] However, the above-mentioned pump control strategies all rely on fixed preset parameters, making it difficult to dynamically and adaptively adjust according to real-time changes in water demand or pipeline conditions. This can easily lead to pumps operating in an inefficient zone with frequent start-stop cycles, reducing pump operating efficiency and causing energy waste. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for controlling the operation of a water pump, in order to improve the operating efficiency of the water pump and reduce energy waste.

[0006] In a first aspect, embodiments of this application provide a method for controlling the operation of a water pump, including:

[0007] Acquire multi-dimensional operational data in real time from a distributed sensor network deployed in the water pump system;

[0008] By using edge computing nodes, multi-dimensional operational data is cleaned and feature extracted to generate standardized data packages;

[0009] Standardized data packets are uploaded to the cloud so that a global optimization control strategy can be generated based on the standardized data packets and historical operating data by a model deployed in the cloud. The global optimization control strategy includes variable frequency speed control commands and multi-pump collaborative control strategies.

[0010] The edge computing nodes determine whether the real-time monitored multi-dimensional operational data meets the preset emergency shutdown conditions; if so, they generate and execute local emergency control commands.

[0011] Among them, the global optimization control strategy generated in the cloud and the local emergency control command generated by the edge computing node constitute a hybrid decision model. The local emergency control command is used for emergency operations with real-time requirements higher than the preset threshold, while the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

[0012] Optionally, edge computing nodes can be used to perform data cleaning and feature extraction on multi-dimensional operational data to generate standardized data packages, specifically including:

[0013] The multi-dimensional operational data is subjected to noise suppression processing by an adaptive filtering algorithm deployed on edge computing nodes to obtain optimized operational data. The adaptive filtering algorithm includes Kalman filtering or wavelet denoising algorithm, which is used to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional operational data.

[0014] Feature extraction is performed on the optimized runtime data to generate a standardized data package for input into the cloud model.

[0015] Optionally, the preset emergency shutdown conditions include at least one of the following: motor temperature exceeding a first threshold, vibration amplitude exceeding a second threshold, or current overload exceeding a third threshold.

[0016] Optionally, after uploading the standardized data package to the cloud, the model deployed in the cloud identifies potential fault characteristics based on the standardized data package and historical operating data through anomaly detection algorithms and generates fault warning information, which includes fault type and root cause analysis results.

[0017] Among them, the root cause analysis results refer to the mapping relationship between fault characteristics and fault types. The mapping relationship is identified based on the association rule mining of multi-dimensional operational data.

[0018] Optionally, after uploading the standardized data package to the cloud, a digital twin model that is synchronized with the water pump system in real time can be built and updated in the cloud.

[0019] Real-time collected multi-dimensional operational data is input into a digital twin model to predict the remaining lifespan of preset key components of the water pump and generate maintenance recommendations.

[0020] Optionally, the digital twin model receives standardized data packets uploaded by edge computing nodes in real time at a preset update cycle, and dynamically updates the boundary conditions and input parameters of the digital twin model according to the received standardized data packets, so as to achieve real-time synchronization with the physical water pump system.

[0021] Secondly, embodiments of this application provide a control device for the operation of a water pump, comprising:

[0022] The acquisition module is used to acquire multi-dimensional operational data collected in real time by the distributed sensor network deployed in the water pump system;

[0023] The processing module is used to perform data cleaning and feature extraction on multi-dimensional running data through edge computing nodes, and generate standardized data packets;

[0024] The processing module is also used to upload standardized data packets to the cloud, so as to generate a global optimization control strategy based on the standardized data packets and historical operating data through the model deployed in the cloud. The global optimization control strategy includes variable frequency speed control commands and multi-pump collaborative control strategies.

[0025] The processing module is also used to determine whether the multi-dimensional operational data monitored in real time meets the preset emergency shutdown conditions through edge computing nodes; when the conditions are met, it generates and executes local emergency control commands.

[0026] Among them, the global optimization control strategy generated in the cloud and the local emergency control command generated by the edge computing node constitute a hybrid decision model. The local emergency control command is used for emergency operations with real-time requirements higher than the preset threshold, while the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

[0027] Optionally, the processing module is also used to perform noise suppression processing on the multi-dimensional running data through an adaptive filtering algorithm deployed on the edge computing node to obtain optimized running data; wherein, the adaptive filtering algorithm includes Kalman filtering or wavelet denoising algorithm, which is used to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional running data;

[0028] Feature extraction is performed on the optimized runtime data to generate a standardized data package for input into the cloud model.

[0029] Optionally, the preset emergency shutdown conditions include at least one of the following: motor temperature exceeding a first threshold, vibration amplitude exceeding a second threshold, or current overload exceeding a third threshold.

[0030] Optionally, the processing module is also used to identify potential fault characteristics and generate fault warning information based on the standardized data packets and historical operating data through an anomaly detection algorithm after the standardized data packets are uploaded to the cloud. The fault warning information includes the fault type and root cause analysis results.

[0031] Among them, the root cause analysis results refer to the mapping relationship between fault characteristics and fault types. The mapping relationship is identified based on the association rule mining of multi-dimensional operational data.

[0032] Optionally, the processing module is also used to build and update a digital twin model that is synchronized with the pump system in real time in the cloud after the standardized data package is uploaded to the cloud;

[0033] Real-time collected multi-dimensional operational data is input into a digital twin model to predict the remaining lifespan of preset key components of the water pump and generate maintenance recommendations.

[0034] Optionally, the digital twin model receives standardized data packets uploaded by edge computing nodes in real time at a preset update cycle, and dynamically updates the boundary conditions and input parameters of the digital twin model according to the received standardized data packets, so as to achieve real-time synchronization with the physical water pump system.

[0035] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0036] The memory stores the instructions that the computer executes;

[0037] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0038] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0039] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0040] The pump operation control method, apparatus, equipment, medium, and product provided in this application acquire multi-dimensional operational data in real time from a distributed sensor network deployed in the pump system; perform data cleaning and feature extraction on the multi-dimensional operational data through edge computing nodes to generate standardized data packets; upload the standardized data packets to the cloud, and generate variable frequency speed control commands and multi-pump collaborative control strategies based on the standardized data packets and historical operational data through a model deployed in the cloud; upon receiving the variable frequency speed control commands and multi-pump collaborative control strategies issued by the cloud, the control unit performs corresponding adjustments to the pump's operating parameters and performs collaborative control. This process solves the problems of noise and redundancy in the original data, provides high-quality, standardized input for the model deployed in the cloud, realizes real-time adaptive adjustment of pump operating parameters, and solves the problem of traditional solutions relying on manually preset fixed parameters, thereby improving the operating efficiency of the pump system, reducing energy consumption, and reducing manual intervention. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] Figure 1 A schematic diagram illustrating a scenario for the pump operation control method provided in this application;

[0043] Figure 2 A flowchart illustrating the pump operation control method provided in this application;

[0044] Figure 3 A schematic diagram of the control device for the operation of the water pump provided in this application;

[0045] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0046] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0049] In industrial production, agricultural irrigation, urban water supply and sewage treatment, water pump systems are core power equipment, and their operating status directly affects energy efficiency, production safety and maintenance costs.

[0050] Existing water pump systems typically consist of independently installed water pumps and their associated mechanical control cabinets. They rely on traditional relay logic or programmable logic controllers to achieve basic start-stop and constant-speed operation control. Monitoring during the operation of the water pump system usually depends on manual operation, such as manually reading data through instruments like pressure gauges and thermometers, or judging the equipment status through periodic inspections.

[0051] However, this existing technology has significant limitations under complex operating conditions. First, manual operation is easily affected by subjective factors and is difficult to respond to dynamic demands in real time, leading to energy waste or system failure. Second, the lack of comprehensive monitoring of pump operating parameters (such as flow rate, pressure, energy consumption, vibration, etc.) makes it difficult to achieve refined energy efficiency management. Third, traditional systems lack intelligent diagnostic capabilities, and fault warnings are delayed, resulting in high maintenance costs and the risk of sudden shutdowns.

[0052] Furthermore, with the development of industrial technology and smart water management, users have an increasingly urgent need for remote equipment monitoring, data-driven decision-making, and automated operation and maintenance. For example, in large industrial parks or urban water supply networks, the centralized management of hundreds or thousands of water pumps requires efficient system management solutions.

[0053] Based on the above scenarios, it can be seen that existing technologies have low data acquisition comprehensiveness, simple control logic, reliance on manual operation and maintenance, and lack intelligent diagnosis and predictive maintenance functions, making it difficult to meet the needs of modern industry for energy saving, automation and remote management.

[0054] The pump operation control method provided in this application acquires multi-dimensional operational data in real time from a distributed sensor network deployed in the pump system; performs data cleaning and feature extraction on the multi-dimensional operational data through edge computing nodes to generate standardized data packets; uploads the standardized data packets to the cloud, and generates variable frequency speed control commands and multi-pump collaborative control strategies based on the standardized data packets and historical operational data through a model deployed in the cloud; upon receiving the variable frequency speed control commands and multi-pump collaborative control strategies issued by the cloud, the control unit performs corresponding adjustments to the pump's operating parameters and performs collaborative control. In this process, the cleaning and feature extraction of the real-time multi-dimensional operational data by edge computing nodes solves the problem of noise and redundancy in the original data, providing high-quality, standardized input for the cloud model; the dynamic generation of control commands by the cloud-deployed model based on the standardized data packets and historical operational data enables real-time adaptive adjustment of pump operating parameters, solving the problem of traditional solutions relying on manually preset fixed parameters; and the execution of cloud commands by the control unit after receiving them through edge computing nodes constructs a complete closed loop from data acquisition to cloud decision-making and local execution. This application effectively solves the technical problems of traditional water pump control schemes relying on manual on-site inspections and static fixed control strategies, thereby achieving the effects of improving the operating efficiency of water pump systems, reducing energy consumption, and reducing manual intervention.

[0055] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0056] This application is applicable to scenarios such as industrial production (e.g., chemical, metallurgical, power), agricultural irrigation, urban water supply, and sewage treatment. Figure 1 A schematic diagram illustrating a scenario for the pump operation control method provided in this application, such as... Figure 1 As shown, in a typical industrial scenario, water pumps are distributed across multiple factory areas or pumping stations (e.g., pump 1, ..., pump n, where n is a positive integer greater than 1). Local data needs to be uploaded to edge nodes (e.g., industrial PCs or embedded devices) via an IoT gateway. The edge nodes then transmit critical data to a cloud server via 5G / 4G networks. The cloud server analyzes historical operating data using algorithms (e.g., machine learning models), generates optimization strategies, and distributes them to edge nodes or terminal devices (pumps). For example, in urban water supply systems, smart pump modules can monitor pipeline pressure fluctuations in real time and dynamically adjust the start-stop strategies of multiple pumps to balance supply and demand; in agricultural irrigation scenarios, the system can automatically adjust pump flow based on soil moisture sensor data to achieve precision irrigation.

[0057] Figure 2 A flowchart illustrating the pump operation control method provided in this application is shown below. Figure 2 As shown, the method includes:

[0058] S201. Obtain multi-dimensional operational data in real time from the distributed sensor network deployed in the water pump system.

[0059] More specifically, pressure sensors, flow sensors, vibration sensors, and temperature sensors are deployed at predetermined key locations such as the water pump inlet, outlet, pump body bearing end, and motor windings. These sensors form a distributed sensor network via an industrial fieldbus, collecting pressure, flow, vibration amplitude, and temperature values ​​in real time during water pump operation at a predetermined sampling frequency, thus providing the collected data as multi-dimensional operational data.

[0060] S202. Perform data cleaning and feature extraction on multi-dimensional operational data through edge computing nodes to generate standardized data packages.

[0061] More specifically, the process involves cleaning and extracting features from multi-dimensional operational data using edge computing nodes to generate standardized data packages. This includes: using adaptive filtering algorithms deployed on edge computing nodes to suppress noise in the multi-dimensional operational data, resulting in optimized operational data; wherein the adaptive filtering algorithms include Kalman filtering or wavelet denoising algorithms, used to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional operational data; and extracting features from the optimized operational data to generate standardized data packages for inputting models to the cloud.

[0062] Optionally, the received multi-dimensional operational data is first cleaned using the data preprocessing engine built into the edge computing node to remove null and abrupt values ​​caused by sensor interruptions or communication anomalies. Then, an adaptive filtering algorithm deployed on the edge computing node performs noise suppression on the cleaned data to obtain optimized operational data. Subsequently, the edge computing node further extracts features from the optimized operational data to extract time-domain and frequency-domain features, and encapsulates the extracted data into standardized data packets conforming to a preset communication protocol format for subsequent uploading to the cloud. The adaptive filtering algorithm includes Kalman filtering or wavelet denoising algorithms to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional operational data.

[0063] In one possible embodiment, an edge computing gateway is deployed as an edge computing node in an industrial water supply pumping station. This gateway incorporates a wavelet denoising algorithm to process the collected multi-dimensional operational data in real time. When the water pump generates mechanical vibrations during normal operation, the signals collected by the vibration sensors are mixed with high-frequency noise components. A multi-level wavelet decomposition algorithm is used to separate the effective vibration features from the high-frequency noise, thereby preserving the low-frequency features related to bearing wear. The denoised vibration data, along with pressure and temperature data, is encapsulated by the gateway into a standardized JSON data packet and uploaded to the cloud via a target protocol.

[0064] This embodiment deploys an adaptive filtering algorithm on edge computing nodes to suppress noise in real time on the raw data collected by sensors, reducing the impact of mechanical vibration and electromagnetic interference on data quality, enhancing the accuracy of the vibration characteristics uploaded to the cloud in reflecting the bearing's operating status, and providing a reliable data foundation for accurate fault diagnosis by the cloud model.

[0065] Optionally, the edge computing node determines whether the multi-dimensional operational data monitored in real time meets the preset emergency shutdown conditions; when the conditions are met, a local emergency control command is generated and executed; wherein, the global optimization control strategy generated in the cloud and the local emergency control command generated by the edge computing node constitute a hybrid decision model, the local emergency control command is used for emergency operations with real-time requirements higher than the preset threshold, and the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

[0066] For example, the edge computing node has pre-set emergency stop logic rules, which trigger an emergency stop if any of the following conditions are met: motor temperature exceeds 85°C, vibration amplitude exceeds 10 mm / s, or current exceeds 20% of the rated value. During one operation, the edge computing node monitors in real time that the winding temperature of the water pump motor continues to rise and reaches 88°C, exceeding the preset first threshold of 85°C. The edge computing node immediately generates an emergency stop command locally, without waiting for cloud decision-making, and directly outputs it to the emergency stop terminal of the frequency converter via hardwiring, thereby controlling the emergency stop of the water pump.

[0067] This embodiment presets emergency shutdown conditions at the edge computing node and executes local control, improving emergency response speed. In the event of network interruption or cloud delay, local emergency control commands can still be reliably executed, avoiding the risk of equipment damage or safety incidents due to waiting for cloud decisions.

[0068] Optionally, the preset emergency shutdown conditions include at least one of the following: motor temperature exceeding a first threshold, vibration amplitude exceeding a second threshold, or current overload exceeding a third threshold.

[0069] In one possible embodiment, for a large centrifugal pump, the edge computing node is configured with three sets of emergency shutdown thresholds. In this scenario, the motor temperature threshold is set to 90°C, the vibration amplitude threshold is set to 12 mm / s, and the current overload threshold is set to 120% of the rated current. When the edge computing node detects that any one of the data exceeds the corresponding threshold for 1 second (i.e., the preset duration), it determines that the preset emergency shutdown conditions are met.

[0070] This embodiment covers three high-risk fault scenarios commonly encountered in water pump operation—high temperature, severe vibration, and overload—by setting multi-dimensional and configurable emergency shutdown conditions. Different thresholds can be flexibly adjusted according to the rated parameters of the water pump and the on-site operating conditions, ensuring equipment safety while avoiding misjudgments caused by excessive sensitivity or insensitivity.

[0071] S203. Upload the standardized data packet to the cloud so that the model deployed in the cloud can generate a global optimization control strategy based on the standardized data packet and historical operating data. The global optimization control strategy includes variable frequency speed control commands and multi-pump collaborative control strategies.

[0072] More specifically, edge computing nodes upload standardized data packets to the cloud (or cloud server) via 4G / 5G or Ethernet. The cloud server deploys a pre-trained machine learning model, which takes the real-time received standardized data packets and stored historical operating data as input. The model calculates a global optimization control strategy for the current operating conditions, including variable frequency speed control commands and multi-pump collaborative control strategies. The variable frequency speed control commands adjust the operating speed of a single pump, while the multi-pump collaborative control strategy indicates the number of pumps activated, the speed distribution of each pump, and the timing of main / standby pump switching in scenarios where multiple pumps operate in parallel.

[0073] Optionally, after uploading the standardized data package to the cloud, the model deployed in the cloud identifies potential fault characteristics based on the standardized data package and historical operating data through an anomaly detection algorithm, and generates fault warning information. The fault warning information includes fault type and root cause analysis results. The root cause analysis results refer to the mapping relationship between fault characteristics and fault type, which is identified based on association rule mining of multi-dimensional operating data.

[0074] In one possible embodiment, an anomaly detection model is deployed in the cloud to continuously analyze the vibration, current, and flow data of the water pump using a time series prediction algorithm. If, during an analysis, the anomaly detection model detects that the vibration amplitude continuously increases for 30 minutes, with a cumulative increase exceeding 15% of the initial value; simultaneously, the current value increases by more than 5% of the rated current, and the flow rate decreases by more than 8% of the rated flow rate, then this characteristic combination of increased vibration, increased current, and decreased flow rate is input into a fault knowledge base pre-established through association rule mining for matching. This identifies the fault type corresponding to this characteristic combination as "impeller blockage," and generates a fault warning message which is pushed to the maintenance personnel's mobile app. The fault warning message indicates that "the impeller may be blocked; it is recommended to check the inlet filter."

[0075] Optionally, the fault knowledge base is pre-built based on historical fault data using an association rule mining algorithm. This association rule mining algorithm uses the Apriori algorithm to mine the mapping relationship between different feature combinations and fault types from historical operating data and corresponding historical fault data.

[0076] This embodiment deploys anomaly detection algorithms on a cloud-based model and combines them with a fault knowledge base built through association rule mining to achieve a diagnostic chain from data anomalies to fault types, and then to root cause analysis. When maintenance personnel receive fault warning information, they can not only know that the equipment may have a fault, but also know the possible causes of the fault and suggested handling measures, thus shortening the fault investigation time.

[0077] Optionally, after uploading the standardized data package to the cloud, a digital twin model that is synchronized with the water pump system in real time is built and updated in the cloud; multi-dimensional operating data collected in real time is input into the digital twin model to predict the remaining life of the preset key components of the water pump and generate maintenance suggestions.

[0078] In one possible embodiment, a cloud server constructs a digital twin model of the water pump based on the physical parameters and historical operating data of one or more pump models. This model uses finite element analysis as its core algorithm to simulate the wear patterns of the pump bearings and mechanical seals during long-term operation. During daily operation, real-time vibration, temperature, and flow data are continuously uploaded via edge computing nodes. The digital twin model first estimates the current actual load on the bearing based on the real-time vibration data, inputs the load into the finite element analysis module to calculate the real-time stress distribution of key bearing components; then, based on the fatigue crack propagation formula, it converts the real-time stress into crack propagation rate; finally, combining linear cumulative damage theory, it dynamically updates the cumulative wear data of the bearing and mechanical seal based on the cumulative operating time and real-time stress history, thereby further predicting the remaining life of the bearing to be approximately 180 days and the remaining life of the mechanical seal to be approximately 90 days. Maintenance recommendations are generated based on the remaining life, such as recommending mechanical seal replacement within 90 days and preparing bearing spare parts within 180 days.

[0079] Optionally, the digital twin model receives standardized data packets uploaded by edge computing nodes in real time at a preset update cycle, and dynamically updates the boundary conditions and input parameters of the digital twin model according to the received standardized data packets, so as to achieve real-time synchronization with the physical water pump system.

[0080] For example, the digital twin model receives standardized data packets uploaded by edge computing nodes in real time with an update cycle of 1 second, and dynamically corrects the boundary conditions and input parameters of the model according to the latest data to achieve real-time synchronization with the physical water pump system; after each data update, the digital twin model re-runs the calculation and outputs updated component wear data and prediction results of remaining life.

[0081] This embodiment achieves dynamic prediction of the remaining lifespan of key components by constructing a digital twin model that is synchronized in real time with the physical water pump. This avoids the problems of over-maintenance or under-maintenance caused by scheduled maintenance in existing technologies, improves the accuracy of maintenance timing, and reduces operation and maintenance costs and the probability of unexpected failures.

[0082] S204. Upon receiving the variable frequency speed control command and multi-pump collaborative control strategy issued by the cloud, the control unit performs corresponding adjustment and collaborative control of the water pump's operating parameters.

[0083] More specifically, after receiving control commands from the cloud, the edge computing node parses and verifies them. For variable frequency speed control commands, the edge computing node converts them into analog signals or communication commands and sends them to the frequency converter to adjust the operating frequency of the water pump motor. For multi-pump collaborative control strategies, the edge computing node controls the start / stop status and speed distribution of the corresponding water pumps according to the strategy, realizing automatic switching and load balancing among multiple pumps.

[0084] For example, the cloud-deployed model takes real-time received pipeline pressure values, water flow demand, and real-time flow, outlet pressure, and current data of each water pump as input. It uses a multi-objective optimization algorithm to calculate the optimal number of pumps to be turned on and the optimal pump speed distribution scheme under the current operating conditions, with the goal of minimizing the total system energy consumption and balancing equipment losses, while meeting the water supply demand. At the same time, the model determines the timing of switching between the main and standby pumps based on the cumulative running time of each pump. When the cumulative running time of the main pump reaches the preset rotation cycle, the standby pump is switched to the main pump.

[0085] The pump operation control method provided in this application embodiment performs data cleaning and feature extraction on real-time collected multi-dimensional operating data through edge computing nodes, generates standardized data packets, and uploads them to the cloud. A model deployed in the cloud generates variable frequency speed control commands and multi-pump collaborative control strategies based on the standardized data packets and historical operating data. The edge computing nodes receive the commands and execute the corresponding strategies through the control unit. This achieves real-time data-driven and cloud-based intelligent decision-making for pump operation, effectively improving the operating efficiency and intelligence level of the pump system.

[0086] Figure 3 A schematic diagram of the control device for the operation of the water pump provided in this application is shown below. Figure 3 As shown, the water pump operation control device 30 provided in this embodiment includes:

[0087] The acquisition module 301 is used to acquire multi-dimensional operational data collected in real time by a distributed sensor network deployed in the water pump system.

[0088] Processing module 302 is used to perform data cleaning and feature extraction on multi-dimensional running data through edge computing nodes to generate standardized data packets;

[0089] The processing module 302 is also used to upload standardized data packets to the cloud so as to generate a global optimization control strategy based on the standardized data packets and historical operating data through the model deployed in the cloud. The global optimization control strategy includes variable frequency speed control commands and multi-pump collaborative control strategies.

[0090] The processing module 302 is also used to determine whether the multi-dimensional operational data monitored in real time meets the preset emergency shutdown conditions through the edge computing node; when the conditions are met, it generates and executes local emergency control instructions.

[0091] Among them, the global optimization control strategy generated in the cloud and the local emergency control command generated by the edge computing node constitute a hybrid decision model. The local emergency control command is used for emergency operations with real-time requirements higher than the preset threshold, while the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

[0092] Optionally, the processing module 302 is further configured to perform noise suppression processing on the multi-dimensional running data through an adaptive filtering algorithm deployed on the edge computing node to obtain optimized running data; wherein, the adaptive filtering algorithm includes Kalman filtering or wavelet denoising algorithm, which is used to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional running data;

[0093] Feature extraction is performed on the optimized runtime data to generate a standardized data package for input into the cloud model.

[0094] Optionally, the preset emergency shutdown conditions include at least one of the following: motor temperature exceeding a first threshold, vibration amplitude exceeding a second threshold, or current overload exceeding a third threshold.

[0095] Optionally, the processing module 302 is also used to identify potential fault characteristics based on the standardized data packet and historical operating data through an anomaly detection algorithm after the standardized data packet is uploaded to the cloud, and generate fault warning information, which includes fault type and root cause analysis results.

[0096] Among them, the root cause analysis results refer to the mapping relationship between fault characteristics and fault types. The mapping relationship is identified based on the association rule mining of multi-dimensional operational data.

[0097] Optionally, the processing module 302 is also used to build and update a digital twin model that is synchronized with the water pump system in real time in the cloud after the standardized data packet is uploaded to the cloud;

[0098] Real-time collected multi-dimensional operational data is input into a digital twin model to predict the remaining lifespan of preset key components of the water pump and generate maintenance recommendations.

[0099] Optionally, the digital twin model receives standardized data packets uploaded by edge computing nodes in real time at a preset update cycle, and dynamically updates the boundary conditions and input parameters of the digital twin model according to the received standardized data packets, so as to achieve real-time synchronization with the physical water pump system.

[0100] The water pump operation control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0101] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0102] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0103] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0104] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0105] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0106] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0107] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0108] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0109] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0110] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0111] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0114] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0116] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for controlling the operation of a water pump, characterized in that, include: Acquire multi-dimensional operational data in real time from a distributed sensor network deployed in the water pump system; The multi-dimensional operational data is cleaned and its features are extracted by edge computing nodes to generate standardized data packets. The standardized data packet is uploaded to the cloud so that a global optimization control strategy can be generated based on the standardized data packet and historical operating data by a model deployed in the cloud. The global optimization control strategy includes variable frequency speed control commands and multi-pump collaborative control strategies. The edge computing nodes determine whether the real-time monitored multi-dimensional operational data meets the preset emergency shutdown conditions; if so, they generate and execute local emergency control commands. The cloud-generated global optimization control strategy and the edge computing node-generated local emergency control command constitute a hybrid decision model. The local emergency control command is used for emergency operations with real-time requirements exceeding a preset threshold, while the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

2. The method according to claim 1, characterized in that, The multi-dimensional operational data is cleaned and its features are extracted using edge computing nodes to generate standardized data packages, specifically including: The multi-dimensional operational data is subjected to noise suppression processing by an adaptive filtering algorithm deployed on edge computing nodes to obtain optimized operational data; wherein, the adaptive filtering algorithm includes Kalman filtering or wavelet denoising algorithm, which is used to dynamically eliminate mechanical vibration noise or electromagnetic interference noise in the multi-dimensional operational data; Feature extraction is performed on the optimized runtime data to generate the standardized data package for inputting into the model in the cloud.

3. The method according to claim 1, characterized in that, The preset emergency shutdown conditions include at least one of the following: motor temperature exceeding a first threshold, vibration amplitude exceeding a second threshold, or current overload exceeding a third threshold.

4. The method according to claim 1, characterized in that, Also includes: After the standardized data packet is uploaded to the cloud, the model deployed in the cloud identifies potential fault characteristics based on the standardized data packet and historical operating data through an anomaly detection algorithm and generates fault warning information, which includes fault type and root cause analysis results. The root cause analysis results refer to the mapping relationship between fault characteristics and fault types, which is identified based on association rule mining of multi-dimensional operational data.

5. The method according to claim 1, characterized in that, Also includes: After the standardized data package is uploaded to the cloud, a digital twin model that is synchronized with the water pump system in real time is built and updated in the cloud. The multi-dimensional operational data collected in real time is input into the digital twin model to predict the remaining lifespan of preset key components of the water pump and generate maintenance recommendations.

6. The method according to claim 5, characterized in that, The digital twin model receives standardized data packets uploaded by edge computing nodes in real time at a preset update cycle, and dynamically updates the boundary conditions and input parameters of the digital twin model according to the received standardized data packets, so as to achieve real-time synchronization with the physical water pump system.

7. A control device for the operation of a water pump, characterized in that, include: The acquisition module is used to acquire multi-dimensional operational data collected in real time by the distributed sensor network deployed in the water pump system; The processing module is used to perform data cleaning and feature extraction on the multi-dimensional operational data through edge computing nodes to generate standardized data packets; The processing module is also used to upload the standardized data packet to the cloud so as to generate a global optimization control strategy based on the standardized data packet and historical operating data through the model deployed in the cloud. The global optimization control strategy includes variable frequency speed control command and multi-pump collaborative control strategy. The processing module is also used to determine whether the multi-dimensional operational data monitored in real time meets the preset emergency shutdown conditions through the edge computing node; when the conditions are met, it generates and executes local emergency control instructions. The cloud-generated global optimization control strategy and the edge computing node-generated local emergency control command constitute a hybrid decision model. The local emergency control command is used for emergency operations with real-time requirements exceeding a preset threshold, while the global optimization control strategy is used for optimizing operating parameters under non-preset emergency conditions.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images