Traction converter water cooling system testing device

Abstract

The invention provides a test device for a traction converter water cooling system. Belongs to the technical field of thermal management and power electronics. The device comprises a cooling liquid circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module and a control module, the heat source power control system is connected with the cooling liquid circulation system; the data acquisition and processing system is connected with the cooling liquid circulation system and the heat source power control system; and the cooling medium supply and recovery module is connected with the cooling liquid circulation system. The device integrates a cooling liquid circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module and a control module, so that close cooperation among the modules is realized, and the overall performance of the system is improved.

Description

Technical Field

[0001] The invention provides a traction converter water cooling system test device, belonging to the technical fields of thermal management and power electronics. Background Art

[0002] As a key component of rail transit equipment such as electric locomotives, EMUs and urban rail transit vehicles, the performance and reliability of traction converters are directly related to the operating efficiency and safety of the entire vehicle. During the operation of the traction converter, a large amount of heat will be generated due to the switching loss and conduction loss of power devices and the heat dissipation requirements of other components. In order to ensure the normal operation of the traction converter, effective cooling measures must be taken to dissipate the heat in time.

[0003] Water cooling system has been widely used in the cooling scheme of traction converter due to its advantages of high heat dissipation efficiency, low noise and convenient maintenance. However, the performance of water cooling system directly affects the heat dissipation effect and service life of traction converter. Therefore, it is particularly important to conduct comprehensive performance testing and verification of water cooling system.

[0004] Traditional traction converter water cooling system testing methods mostly rely on manual operation and simple testing equipment, and the testing process is cumbersome and the accuracy is not high. At the same time, due to limited testing conditions, it is difficult to simulate the various working conditions and heat loss of the traction converter in actual operation, resulting in a large deviation between the test results and the actual use. Summary of the invention

[0005] The present invention provides a traction converter water cooling system test device to solve the problems mentioned in the above background technology: The present invention proposes a traction inverter water cooling system test device, which includes: a coolant circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module and a control module; the heat source power control system is connected to the coolant circulation system; the data acquisition and processing system is connected to the coolant circulation system and the heat source power control system; the cooling medium supply and recovery module is connected to the coolant circulation system; the monitoring and protection module and the cooling circulation system are connected to the control module.

[0006] Furthermore, the cooling liquid circulation system circulates through heat exchange between liquid and liquid to provide cooling liquid for the tractor; The heat source power control system is used to adjust the heating power of the heat source and simulate the heat loss of the traction converter under different working conditions; The data acquisition and processing system is used to collect and process relevant data generated during the experiment, and evaluate the performance of the water cooling system based on the processing results; The coolant supply and recovery module is used to provide cooling medium to the traction converter and to recover the cooling medium after heat exchange; The monitoring and protection module is used to monitor the operating status of the cooling system in real time and take protective measures when abnormal conditions occur; The control module is used to control the operation of the entire cooling system.

[0007] Furthermore, the coolant circulation system includes a pump, a heat exchanger, a water tank, pipes, and various sensors and control valves; The heat source power control system includes a voltage-stabilized power supply, a switch, a voltage regulator, a voltmeter and an ammeter; The data acquisition and processing system includes a terminal device, a data collector and a thermocouple; The cooling medium supply and recovery device includes a liquid storage tank, a pipeline, a valve and a connecting piece; The monitoring and protection module includes a sensor, an alarm device and a cut-off valve; The control module includes a PLC controller and a relay.

[0008] Furthermore, the heat source power control method of the heat source power control system includes: Start the heat source power control system, initialize the hardware and software, calibrate the parameters of key components, and set the target heating power of the heat source according to the test requirements; The voltage of the input heat source is adjusted by the voltage regulator, and the input voltage and current of the heat source are monitored in real time by the voltage meter and the current meter, and the actual heating power is calculated and compared with the target power; Based on the real-time monitoring results, the voltage is fine-tuned through the control algorithm; Based on machine learning algorithms, the historical data of heat source power is learned and analyzed, and the power change trend in the future is predicted; Dynamically adjust the voltage regulation strategy according to the real-time changes in the heat source power; set an overheat protection device in the heat source power control system to automatically cut off the heat source power supply when the actual power exceeds the set threshold; Integrated fault self-diagnosis function to monitor the working status of each component in real time. If any abnormality is found, fault location and alarm will be issued. During the test, the changes in key parameters, the system's operating status and fault information are recorded in real time. The recorded data is deeply mined and analyzed based on the built-in first deep learning model to evaluate the performance and stability of the heat source power control system.

[0009] Furthermore, the voltage is fine-tuned by a control algorithm according to the real-time monitoring result, including: Preprocess the voltage and current data monitored in real time by the voltmeter and ammeter, calculate the actual heating power in real time based on the preprocessed voltage and current data, and compare it with the preset target heating power to obtain the power error; According to the size and change trend of power error, the control strategy is selected, and the parameters of the control strategy are dynamically adjusted using genetic algorithm; Based on the selected control strategy and optimized parameters, the voltage of the input heat source is fine-tuned through the voltage regulator; during the fine-tuning process, the power error is continuously monitored through the real-time feedback mechanism, and the fine-tuning amplitude and frequency are dynamically adjusted according to the error changes; After voltage fine-tuning, stability verification is performed to verify whether the actual power fluctuates stably within the target power range; if there is a deviation, the control parameters are further fine-tuned based on the verification results to form a closed-loop feedback control.

[0010] Furthermore, the data acquisition and processing method of the data acquisition and processing system includes: The relevant data are collected in real time through various sensors, and the collected relevant data are transmitted to the data collector via wired or wireless means; The data collector preprocesses the received relevant data, caches the preprocessed relevant data in a storage unit of the data collector, and transmits the data stored in the storage unit to the data processing unit via wired or wireless means; The data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores it; The integrated data is deeply mined and analyzed through the built-in second deep learning model to extract key information. At the same time, the analysis results are intuitively displayed through data visualization technology; Based on the data analysis results, the performance of the water cooling system is evaluated. At the same time, fault diagnosis and early warning are carried out by combining historical data with abnormal data during the test process. Regularly conduct quality assessments on the collected and processed data, and adjust data collection and processing strategies based on the data quality assessment results.

[0011] Furthermore, the data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores it, including: Identify and delete duplicate, invalid or obviously erroneous data records, check whether each data field is complete, and fill in missing values ​​using interpolation or mean substitution based on the context; and verify the logical relationship between data using preset thresholds and ranges; Unify the data formats output by different sensors into a standard format, and perform unit conversion for data involving different physical quantities; Through timestamp comparison and correction, the data is kept consistent in time. If the data needs to be analyzed in association, the data is aligned on the time axis through time windows or event trigger mechanisms. Aggregate data by time interval according to test requirements, and divide data into different groups according to test conditions, equipment status or data characteristics; Add labels to each data record and extract feature vectors of the data based on statistical analysis and machine learning algorithms; The data that has been preprocessed, time synchronized, aggregated and grouped, labeled, and feature extracted are integrated according to the experimental requirements to form a complete data set; the integrated data set is stored in the data storage system.

[0012] Furthermore, the monitoring and protection method of the monitoring and protection module includes: The various operating data of the water cooling system are collected in real time through sensors, and the collected data are pre-processed; Performing in-depth analysis on the processed data based on a built-in third deep learning model to identify the operating state of the system, wherein the operating state includes normal operation, abnormal operation or fault state; When the system status analysis results show an abnormality or are close to the alarm threshold, the fault warning mechanism is triggered and feedback is given to relevant personnel in a variety of ways; According to the fault warning information, formulate corresponding protection strategies, and send the formulated protection strategies to the control system, which will execute corresponding protection measures; The fault diagnosis algorithm is used to locate the fault and determine the specific location or component where the fault occurred. The cause of the fault is analyzed by combining historical data and real-time data to determine the type, cause and impact of the fault. According to the fault diagnosis results, take corresponding repair measures, and optimize the system based on the cause of the fault and the repair process.

[0013] Furthermore, the control method of the control module includes: Collect various operating data of the water cooling system in real time through sensors and pre-process the collected data; Evaluate the preprocessed data through data analysis algorithms to determine the current state of the system, and select the control strategy based on the current state of the system and the control objectives; According to the control strategy, the control parameters are calculated, and the calculated control parameters are converted into control signals, which are sent to the actuators to adjust the state of the system; After executing the control strategy, continue to monitor the state changes of the system in real time through sensors, obtain feedback data, use data analysis algorithms to evaluate the feedback data, and determine the execution effect of the control strategy; According to the control effect evaluation results, the control strategy is adjusted and optimized.

[0014] Furthermore, the pre-processed data is evaluated by a data analysis algorithm to determine the current state of the system, and a control strategy is selected according to the current state of the system and the control target, including: The built-in fourth deep learning model extracts key features from the preprocessed data. Based on the extracted features, the classification algorithm is used to classify the system status to identify whether the system is currently in normal operation, slight abnormality or serious fault state; Combine historical data with current data, use time series analysis to evaluate the system status in real time, use prediction models to predict the system's operating status in the future, and identify potential risk points or abnormal trends; According to system characteristics and control requirements, a strategy library containing multiple control strategies is established, and control strategies are selected from the strategy library based on the results of state identification and trend prediction; For the selected control strategy, its control parameters are initialized according to the default values, and the control parameters are iteratively optimized using the optimization algorithm.

[0015] Beneficial effects of the present invention: the device integrates a coolant circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module, and a control module, thereby achieving close collaboration among the modules and improving the overall performance of the system; through liquid-to-liquid heat exchange, the coolant circulation system can effectively provide cooling medium, ensure the temperature control of the traction inverter under different working conditions, prevent overheating, and improve the stability and reliability of the system; the adjustment capability and simulation function of the heat source power control system enable accurate simulation of heat loss under different working conditions during the experiment, ensure the reliability of the test results, and provide data support for subsequent optimization; the data acquisition and processing system uses deep learning and data analysis technology to monitor, process and analyze the experimental data in real time, which not only improves the data quality, but also improves the accuracy of the test results. The efficiency of data processing is improved, and the fault diagnosis and early warning capabilities are enhanced to ensure the safe operation of the system; the monitoring and protection module can monitor the operating status of the cooling system in real time, and take protective measures in time under abnormal circumstances to avoid equipment damage and ensure the smooth progress of the experiment; the control module selects the appropriate control strategy according to the system status and control objectives, and continuously adjusts and optimizes the control parameters through the feedback mechanism, so that the system can adapt to changes and improve operating efficiency; the integrated fault self-diagnosis function can monitor the working status of each component in real time, quickly locate the fault and issue an alarm, which improves the maintainability of the system and reduces maintenance costs; the system supports in-depth mining and visual display of data, making performance evaluation and fault diagnosis more intuitive, providing a basis for decision-making, and improving the scientific nature and repeatability of the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a diagram of the device described in the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] One embodiment of the present invention, as Figure 1 As shown, a traction inverter water cooling system test device includes: a coolant circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module and a control module; the heat source power control system is connected to the coolant circulation system; the data acquisition and processing system is connected to the coolant circulation system and the heat source power control system; the cooling medium supply and recovery module is connected to the coolant circulation system; the monitoring and protection module and the cooling circulation system are connected to the control module.

[0019] The cooling liquid circulation system circulates through heat exchange between liquid and liquid to provide cooling liquid for the tractor; The heat source power control system is used to adjust the heating power of the heat source and simulate the heat loss of the traction converter under different working conditions; The data acquisition and processing system is used to collect and process relevant data generated during the experiment, and evaluate the performance of the water cooling system based on the processing results; The coolant supply and recovery module is used to provide cooling medium to the traction converter and to recover the cooling medium after heat exchange; The monitoring and protection module is used to monitor the operating status of the cooling system in real time and take protective measures when abnormal conditions occur; The control module is used to control the operation of the entire cooling system; The coolant circulation system includes a pump, a heat exchanger, a water tank, pipes, various sensors and control valves; The heat source power control system includes a voltage-stabilized power supply, a switch, a voltage regulator, a voltmeter and an ammeter; The data acquisition and processing system includes a terminal device, a data collector and a thermocouple; The cooling medium supply and recovery device includes a liquid storage tank, a pipeline, a valve and a connecting piece; The monitoring and protection module includes a sensor, an alarm device and a cut-off valve; The control module includes a PLC controller and a relay.

[0020] The working principle of the above technical solution is: Coolant circulation system: The coolant circulation system is the core of the entire water cooling system. It is responsible for transporting the cooling liquid to the traction inverter, removing heat through liquid-to-liquid heat exchange, and recycling the cooling liquid.

[0021] Pump: The pump acts as a power source to push the cooling liquid to circulate in the system. When the pump is started, it draws the cooling liquid from the water tank and transports it to the heat exchanger through the pipe.

[0022] Heat exchanger: In the heat exchanger, the cooling liquid exchanges heat with the traction converter, absorbing the heat generated by it. The temperature of the cooling liquid increases after the heat exchange and then flows back to the water tank through the pipe.

[0023] Water tank: The water tank is used to store cooling liquid and serves as the starting point and end point of the cooling liquid circulation. In the water tank, the cooling liquid can be buffered and stored to ensure the stable operation of the system.

[0024] Pipes: Pipes connect components such as pumps, heat exchangers and water tanks to form a complete cooling liquid circulation path.

[0025] Sensors and control valves: Temperature sensors, pressure sensors and flow sensors are used to monitor the temperature, pressure and flow of the cooling liquid respectively to ensure that the system can operate stably under various working conditions. The control valve is used to adjust the flow and direction of the cooling liquid to meet the cooling needs under different working conditions.

[0026] Heat source power control system: The heat source power control system is used to simulate the heat loss of the traction converter under different working conditions and adjust the heating power of the heat source.

[0027] Stabilized power supply: Provides stable power input for the entire system to ensure the normal operation of each component.

[0028] Switch and voltage regulator: By using a switch and a voltage regulator together, the heat source's heating power can be precisely adjusted. When you need to simulate heat loss under different working conditions, you only need to adjust the output voltage of the voltage regulator.

[0029] Voltmeter and ammeter: used to monitor the output voltage and current of the regulated power supply respectively to ensure that the heating power of the heat source is consistent with the set value.

[0030] Data acquisition and processing system: The data acquisition and processing system is used to collect and process the relevant data generated during the experiment to evaluate the performance of the water cooling system.

[0031] Terminal device: As the core component of the data acquisition and processing system, it is responsible for receiving data from various sensors and performing preliminary processing and analysis.

[0032] Data collector: Through the data collector, key data such as temperature, pressure and flow can be collected in real time and transmitted to the terminal device for further processing.

[0033] Thermocouple: As a type of temperature sensor, thermocouple can accurately measure the temperature of cooling liquid and convert it into electrical signals for transmission and processing.

[0034] Cooling medium supply and recovery module: The cooling medium supply and recovery module is responsible for providing cooling medium to the traction converter and recovering the cooling medium after heat exchange.

[0035] Liquid storage tank: used to store cooling medium to ensure continuous operation of the system.

[0036] Pipes, valves and connectors: Through the combination of pipes, valves and connectors, the cooling medium can be transported from the liquid storage tank to the traction converter and the cooling medium can be recovered after heat exchange.

[0037] Monitoring and protection module: The monitoring and protection module is used to monitor the operating status of the cooling system in real time and take protective measures when abnormal conditions occur.

[0038] Sensors: including temperature sensors, pressure sensors, etc., used to monitor key parameters of the cooling system in real time.

[0039] Alarm device: When an abnormal condition is detected, the alarm device will send out an alarm signal to remind the operator to take timely measures to deal with it.

[0040] Shut-off valve: In an emergency, the shut-off valve can quickly cut off the cooling system's fluid supply pipeline.

[0041] Control Module: The control module is used to control the operation of the entire cooling system, including the supply of cooling medium, the start and stop of the circulation pump, the opening of the regulating valve, etc.

[0042] PLC controller: As the core component of the control module, the PLC controller can accurately control the operation of the system according to the preset program and algorithm. It receives data from various sensors and adjusts the operating status of the system based on these data.

[0043] Relay: Relay is used to control the start and stop of each actuator (such as circulation pump, regulating valve, etc.). When the PLC controller sends a control signal, the relay will act accordingly to achieve control of the system.

[0044] The effects of the above technical scheme are as follows: by modularizing the key components such as the coolant circulation system, heat source power control system, data acquisition and processing system, cooling medium supply and recovery module, monitoring and protection module and control module, the structure of the entire test device is clear and easy to maintain, which improves the reliability and stability of the device, facilitates subsequent functional expansion and upgrading, and reduces maintenance costs; the heat source power control system can accurately adjust the heating power of the heat source, thereby simulating the heat loss of the traction inverter under different working conditions; ensures the authenticity and accuracy of the test data, and provides a reliable basis for the performance evaluation and optimization design of the water cooling system; the data acquisition and processing system can collect key data such as temperature, pressure, flow, etc. in real time, and perform efficient processing and analysis; it helps to promptly discover potential problems in the water cooling system and provide strong support for the performance evaluation and optimization of the system. At the same time, the analysis results based on big data can also provide a decision-making basis for the intelligent control of the system; the monitoring and protection module can monitor the operating status of the cooling system in real time, and take quick measures to protect it when abnormal conditions occur; ensuring the safety of the test process and effectively preventing equipment damage or casualties caused by system failures; the control module uses intelligent control components such as PLC controllers and relays to achieve precise control and management of the entire cooling system; improve the automation level of the system, and reduce the cost and risk of manual intervention. At the same time, intelligent control also helps to improve the operating efficiency and stability of the system; due to the modular design, the entire test device is easy to expand and upgrade functions; it provides users with more choices and can flexibly configure and upgrade the system according to actual needs to meet changing test needs.

[0045] In one embodiment of the present invention, the heat source power control method of the heat source power control system includes: Start the heat source power control system, initialize the hardware and software, calibrate the parameters of key components, and set the target heating power of the heat source according to the test requirements. The voltage of the input heat source is precisely adjusted by the voltage regulator, and the input voltage and current of the heat source are monitored in real time by the voltage meter and the current meter, and the actual heating power is calculated and compared with the target power; the actual heating power is calculated by the following formula:

[0046] Where N represents the number of points sampled in one cycle; and Indicates the instantaneous values ​​of voltage and current at the nth sampling point; Represents the phase difference between the voltage and current at the nth sampling point; Indicates the sampling time interval of the nth sampling point; According to the real-time monitoring results, the voltage is fine-tuned through the control algorithm so that the actual heating power gradually approaches and stabilizes within the target power range; Based on machine learning algorithms, the historical data of heat source power is learned and analyzed, and the power change trend in the future (e.g., the next week) is predicted; According to the real-time changes in the heat source power, the voltage regulation strategy is dynamically adjusted. For example, in the case of large power fluctuations, the frequency and amplitude of voltage regulation are increased to ensure the consistency between the actual power and the target power. An overheating protection device is set in the heat source power control system. When the actual power exceeds the set threshold, the heat source power supply is automatically cut off. At the same time, the alarm device is used to remind the operator to pay attention. Integrated fault self-diagnosis function to monitor the working status of each component in real time. If any abnormality is found, fault location and alarm will be issued. During the test, the changes in key parameters, the system's operating status and fault information are recorded in real time. The recorded data is deeply mined and analyzed based on the built-in first deep learning model to evaluate the performance and stability of the heat source power control system.

[0047] The working principle of the above technical solution is as follows: when the heat source power control system is started, the hardware and software are first initialized, including checking the connection status of each hardware component and ensuring that the software program is loaded correctly. Parameters of key components (such as voltage stabilizer, voltage regulator, voltmeter, and ammeter) are calibrated. According to the test requirements, the target heating power of the heat source is set. The power value can simulate the heat loss of the traction converter under different working conditions, and the voltage input to the heat source is accurately adjusted by the voltage regulator to control the heating power of the heat source; the input voltage and current of the heat source are monitored in real time using the voltmeter and ammeter, the actual heating power is calculated, and compared with the target power. According to the real-time monitoring results, the voltage is fine-tuned through the control algorithm. The actual heating power gradually approaches and stabilizes within the target power range. Based on the machine learning algorithm, the historical data of the heat source power is learned and analyzed, and the power change trend in the future (such as the next week) is predicted. According to the real-time changes in the heat source power, the voltage regulation strategy is dynamically adjusted. For example, in the case of large power fluctuations, the frequency and amplitude of the voltage regulation are increased to ensure the consistency between the actual power and the target power. An overheat protection device is set in the heat source power control system. When the actual power exceeds the set threshold, the heat source power supply is automatically cut off to prevent equipment damage or safety accidents. At the same time, the alarm device is used to remind the operator to pay attention. The integrated fault self-diagnosis function monitors the working status of each component in real time. If an abnormality is found, the fault is located and the alarm is issued. During the test, the changes in key parameters, as well as the operating status and fault information of the system are recorded in real time. The key parameters include heat source power, voltage, and current. The recorded data is deeply mined and analyzed based on the built-in first deep learning model. Through the processing and analysis of the data, the performance and stability of the heat source power control system can be evaluated, providing a basis for subsequent improvement and optimization.

[0048] The effects of the above technical scheme are as follows: by accurately adjusting the voltage of the input heat source, the heat source heating power can be precisely controlled, ensuring the accuracy and reliability of the test results; improving the accuracy of the test data, and providing strong support for the performance evaluation and optimization of the water cooling system; the voltage regulation follows the principle of smoothness and stability, avoiding the impact of voltage mutation on the system, helping to protect the system hardware and extend the life of the equipment; reducing the failure rate of the system caused by voltage fluctuations, and improving the stability and reliability of the system; by real-time monitoring of the input voltage and current of the heat source, the actual heating power can be calculated and compared with the target power. According to the comparison results, the voltage is fine-tuned through the control algorithm, so that the actual heating power gradually approaches and stabilizes within the target power range; the real-time tracking and precise control of the heat source power are realized, ensuring the stability and accuracy of the test process; using the machine learning algorithm to learn and analyze the historical data of the heat source power, the power change trend in the future can be predicted; providing a basis for dynamically adjusting the voltage regulation strategy, helping to respond to possible power fluctuations in advance and ensure the consistency of the actual power with the target power; dynamically adjusting the voltage regulation strategy according to the real-time changes in the heat source power. For example, in the case of large power fluctuations, the frequency and amplitude of voltage regulation are increased; the response speed and regulation accuracy of the system to power fluctuations are improved, ensuring the stability and reliability of the test process; an overheating protection device and an integrated fault self-diagnosis function are set up to monitor the working status of each component in real time, and take measures to protect it when an abnormality occurs; effectively prevent equipment damage or safety accidents caused by overheating or failure, and improve the safety and reliability of the system; record the changes in key parameters in real time, as well as the operating status and fault information of the system, and conduct in-depth mining and analysis of the recorded data based on the built-in first deep learning model; provide strong support for the performance and stability evaluation of the heat source power control system, help to discover potential problems and optimize and improve. At the same time, it also provides valuable data resources for subsequent experiments and research. The above formula calculates the average power by sampling data from multiple points, which can more accurately reflect the actual power consumption. Compared with relying only on measurements at a single moment, this method is more representative of the power consumption under actual working conditions. The formula is based on sampling, so it can adapt to various load types (such as resistive, inductive or capacitive loads) and can be used for different power supply types (such as DC or AC power); when used in conjunction with an appropriate control algorithm, this method can dynamically adjust the input voltage so that the actual heating power remains near the target power. Through continuous sampling and calculation, real-time monitoring of power output can be achieved. The use of the above formula can improve the accuracy and response speed of the power control system, and can also provide valuable data support for system optimization.

[0049] In one embodiment of the present invention, the voltage is fine-tuned by a control algorithm according to the real-time monitoring result so that the actual heating power gradually approaches and stabilizes within the target power range; including: Preprocess the voltage and current data monitored in real time by the voltmeter and ammeter, calculate the actual heating power in real time based on the preprocessed voltage and current data, and compare it with the preset target heating power to obtain the power error; According to the size and change trend of power error, the control strategy is selected, and the parameters of the control strategy are dynamically adjusted using genetic algorithm; Based on the selected control strategy and optimized parameters, the voltage of the input heat source is fine-tuned through the voltage regulator; during the fine-tuning process, the power error is continuously monitored through the real-time feedback mechanism, and the fine-tuning amplitude and frequency are dynamically adjusted according to the error changes; After the voltage is fine-tuned, a period of stability verification is carried out to verify whether the actual power fluctuates stably within the target power range; if there is a deviation, the control parameters are further fine-tuned according to the verification results to form a closed-loop feedback control.

[0050] The working principle of the above technical solution is as follows: first, the voltage and current data monitored in real time by the voltmeter and the ammeter are collected, and the data contains noise or abnormal values ​​and needs to be preprocessed; based on the preprocessed voltage and current data, the actual heating power is calculated in real time using the power calculation formula; the calculated actual heating power is compared with the preset target heating power to obtain the power error, and the error value reflects the difference between the current actual power and the target power; according to the size and change trend of the power error, the appropriate control strategy is selected. For example, when the error is large and changes rapidly, the PID (proportional-integral-differential) control with a faster response speed may be selected; when the system is highly nonlinear, fuzzy control may be selected; when the system parameters are time-varying, adaptive control may be selected; and optimization methods such as genetic algorithms are used to dynamically adjust the parameters of the selected control strategy. Genetic algorithms optimize control performance by simulating natural selection and genetic mechanisms to search for the optimal solution in the parameter space; based on the selected control strategy and optimized parameters, the voltage of the input heat source is fine-tuned through the voltage regulator. The goal of fine-tuning is to reduce the power error so that the actual power gradually approaches the target power; during the fine-tuning process, the power error is continuously monitored through a real-time feedback mechanism. If the error is still large, continue to adjust the voltage; if the error is reduced to an acceptable range, maintain the current voltage value; dynamically adjust the fine-tuning amplitude and frequency according to the error change. If the error decreases rapidly, the fine-tuning amplitude and frequency can be appropriately reduced; if the error changes slowly or fluctuates greatly, it may be necessary to increase the fine-tuning amplitude and frequency; after the voltage is fine-tuned, a period of stability verification is performed to ensure that the actual power fluctuates stably within the target power range without excessive deviation or instability; if the stability verification results show that there is a deviation, the control parameters are further fine-tuned according to the verification results. This process forms a closed-loop feedback control system, which is continuously iterated and adjusted until the predetermined stability and accuracy requirements are met.

[0051] The effect of the above technical solution is: by real-time monitoring of voltage and current data, and calculating the actual heating power based on these data, the heating state of the current heat source can be accurately understood. After comparing with the preset target heating power, the power error obtained can guide the subsequent voltage fine-tuning operation; it ensures that the actual heating power can gradually approach and stabilize within the target power range, improving the control accuracy and system stability; according to the size and change trend of the power error, PID control, fuzzy control or adaptive control strategies can be flexibly selected. The control strategy can cope with different system characteristics and working conditions, improve the adaptability and robustness of the system, and maintain a stable control effect under different working conditions; the parameters of the control strategy are dynamically adjusted by using optimization methods such as genetic algorithms, and the adjustment can be based on the real-time system state and feedback data, continuously optimize the control parameters, and improve the control performance; the self-optimization of the control parameters is realized, and the control accuracy and response speed of the system are improved; in the fine-tuning process, the power error is continuously monitored through the real-time feedback mechanism, and the fine-tuning amplitude and frequency are dynamically adjusted according to the error change. Real-time feedback and dynamic adjustment can ensure that the system always remains in the best control state; improve the dynamic response ability and stability of the system, and can quickly adapt to changes in the system state; after the voltage is fine-tuned, stability verification is performed to ensure that the actual power fluctuates stably within the target power range. If there is a deviation, the control parameters are further fine-tuned according to the verification results to form a closed-loop feedback control; through the closed-loop feedback control, the system state is continuously corrected to ensure that the system always remains within the predetermined stability and accuracy requirements.

[0052] In one embodiment of the present invention, the data acquisition and processing method of the data acquisition and processing system includes: The relevant data are collected in real time through various sensors, and the collected relevant data are transmitted to the data collector via wired or wireless means; The data collector preprocesses the received relevant data, caches the preprocessed relevant data in a storage unit of the data collector, and transmits the data stored in the storage unit to the data processing unit via wired or wireless means; The data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores it; The integrated data is deeply mined and analyzed through the built-in second deep learning model to extract key information. At the same time, the analysis results are intuitively displayed in the form of charts, curves, etc. through data visualization technology; Based on the data analysis results, the performance of the water cooling system is evaluated. At the same time, fault diagnosis and early warning are carried out by combining historical data with abnormal data during the test process. Regularly conduct quality assessments on the collected and processed data, and adjust the data collection and processing strategies based on the data quality assessment results. The data quality is assessed in the following ways:

[0053] Where Q is the total data quality score; v is the number of evaluation dimensions; is the weight of the i-th dimension, and the sum of all weights is 1; is the actual score of the i-th dimension; is the target score of the i-th dimension; is the sensitivity coefficient of the i-th dimension, which is used to adjust the sensitivity of score changes.

[0054] The working principle of the above technical solution is as follows: the system deploys sensors at various key locations (such as the coolant circulation system, the heat source power control system, etc.) to collect key data such as temperature, pressure, and flow in real time; the sensor converts the measured physical quantity into an electrical signal according to the measurement object and measurement requirements, and then transmits it to the data collector via wired or wireless means; the collected data is transmitted to the data collector via wired or wireless communication (such as Ethernet, USB, wireless communication, etc.); the data collector, as a data transfer station, is responsible for receiving, caching and forwarding these data; the data collector performs preliminary processing (such as amplification, filtering, linearization, etc.) on the received data to meet the requirements of subsequent processing; the processed data is cached in the storage unit of the data collector for subsequent transmission to the data processing unit; the data collector transmits the data in the storage unit to the data processing unit via wired or wireless means; the data processing unit performs secondary processing on the received data, including data cleaning (such as deduplication, denoising, filling missing values, etc.), data conversion (such as data type conversion, data standardization, etc.) and data integration (such as integrating data from different sensors), etc.; the processed data The data is integrated according to the test requirements to form a complete data set; the data set is archived and stored for subsequent analysis and use; the system's built-in second deep learning model conducts in-depth mining and analysis of the integrated data; the second deep learning model can extract key information, such as temperature change trends, pressure fluctuations, etc.; through data visualization technology, the analysis results are intuitively displayed to users in the form of charts, curves, etc.; it helps users better understand the data and analysis results and make more informed decisions; based on the data analysis results, the performance of the water cooling system is evaluated, such as cooling efficiency, thermal stability, etc.; this helps to promptly discover potential problems in the system and take corresponding measures to optimize and improve it; combined with historical data and abnormal data during the test process, fault diagnosis and early warning are carried out; when the system detects abnormal data, it can automatically trigger the early warning mechanism to remind users to pay attention and take corresponding measures; regular quality assessment of the collected and processed data; the evaluation indicators include data accuracy, completeness, consistency, timeliness, etc.; according to the data quality assessment results, adjust the data collection and processing strategy; this may include optimizing sensor layout, increasing data collection frequency, improving data processing algorithms, etc.

[0055] The effects of the above technical solution are: real-time collection of relevant data by various sensors ensures the timeliness and accuracy of the data; real-time data provides a basis for instant monitoring and rapid response of the system; the high precision of the sensor ensures the accuracy of the collected data; accurate data provides a reliable basis for the performance evaluation and fault diagnosis of the system; the data collector preprocesses the received data to improve the availability and accuracy of the data; the cache mechanism ensures the continuity and integrity of the data and avoids data loss; the data processing unit performs secondary processing on the received data to further improve the quality of the data; the integrated data set provides a comprehensive and accurate data foundation for the deep mining and analysis of the system; the built-in second deep learning model can perform deep mining and analysis on the integrated data to extract key information; the powerful analysis ability of the second deep learning model provides strong support for the performance evaluation and fault diagnosis of the system; through data visualization technology, the analysis results are presented in the form of charts, curves, etc. Intuitive display: Visualized analysis results enable users to understand data and analysis results more intuitively and make more informed decisions. Based on the data analysis results, the performance of the water cooling system is evaluated, such as cooling efficiency, thermal stability, etc. The performance evaluation results provide users with direct feedback on system performance, which helps users understand the operating status of the system and optimize it. Combine historical data with abnormal data during the test to perform fault diagnosis and early warning. The fault diagnosis and early warning mechanism can timely discover potential problems in the system, avoid the occurrence or expansion of faults, and improve the reliability and safety of the system. Regularly evaluate the quality of collected and processed data to ensure the accuracy and completeness of the data. The data quality evaluation results provide a basis for system optimization and improvement. According to the data quality evaluation results, adjust the data collection and processing strategy, such as optimizing the sensor layout, increasing the data collection frequency, and improving the data processing algorithm. Strategy adjustment can further improve the system's data collection and processing capabilities and enhance the overall performance of the system. The proposed data quality assessment formula can quantitatively evaluate data quality from multiple dimensions to ensure the scientific nature of data analysis; regular assessment of data quality can adjust data collection and processing strategies based on the evaluation results to ensure continuous optimization of the data collection process and improve overall data quality; through the setting of weights, users can flexibly adjust the influence of each dimension according to different experimental requirements or data importance, thereby enhancing the applicability of the assessment.

[0056] In one embodiment of the present invention, the data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores the data, including: Identify and delete duplicate, invalid or obviously erroneous data records, check whether each data field is complete, and fill in missing values ​​using interpolation or mean substitution based on the context; and verify the logical relationship between data using preset thresholds and ranges. Unify the data formats output by different sensors into a standard format, and perform unit conversion for data involving different physical quantities; Through timestamp comparison and correction, the data is kept consistent in time. For data that requires correlation analysis, the data is accurately aligned on the time axis through time windows or event trigger mechanisms. According to the test requirements, the data is aggregated at time intervals (such as every minute, every hour), and divided into different groups, such as normal working condition group and abnormal working condition group, according to the test conditions, equipment status or data characteristics. Add labels to each data record, such as device ID, test phase, operation status, etc., and extract feature vectors of the data based on statistical analysis and machine learning algorithms; The data that has been preprocessed, time synchronized, aggregated and grouped, labeled, and feature extracted are integrated according to the experimental requirements to form a complete data set; the integrated data set is stored in the data storage system.

[0057] The working principle of the above technical solution is as follows: First, the system will preliminarily screen the received data, identify and delete duplicate, invalid or obviously erroneous data records, including checking the abnormal values, null values ​​or illogical data in the data records; for missing data fields, the system will use interpolation or mean substitution methods to fill in according to the context to ensure the integrity of the data; the system will verify the logical relationship between the data through the preset thresholds and ranges. For example, check whether the trend of temperature and pressure changes is consistent, whether the flow rate and pump speed match, etc., to ensure the accuracy and rationality of the data; the system will unify the data formats output by different sensors into standard formats, such as CSV, JSON, etc., to facilitate subsequent data processing and analysis. For data involving different physical quantities, such as temperature, pressure, flow, etc., the system will perform unit conversion to ensure that all data uses a unified unit of measurement; the system will maintain consistency in time through timestamp comparison and correction, including adjusting the time difference between different data sources to ensure that all data is based on a unified time base; for data that requires correlation analysis, such as temperature and flow, the system will use time windows or event trigger mechanisms to accurately align the data on the time axis, which will help with subsequent data analysis and mining; according to test requirements, the system will aggregate data at time intervals (such as every minute, every hour). The system will divide data into different groups, such as normal operating conditions group, abnormal operating conditions group, etc., according to test conditions, equipment status or data characteristics. Add labels to each data record, such as equipment ID, test phase, operating status, etc. Based on statistical analysis and machine learning algorithms, the system will extract feature vectors from the data. The feature vector can reflect the inherent laws and characteristics of the data, and provide strong support for subsequent data analysis and mining. The data after preprocessing, time synchronization, aggregation grouping, labeling and feature extraction are integrated according to the test requirements to form a complete data set. The integrated data set is stored in the data storage system, including writing the data into storage media such as databases and file systems to facilitate subsequent data analysis and utilization.

[0058] The effects of the above technical solutions are as follows: by identifying and deleting duplicate, invalid or obviously erroneous data records, and filling in missing values, the accuracy and completeness of the data are significantly improved; logical relationship verification ensures the rationality and consistency between data, avoiding misleading conclusions caused by data errors; data format standardization and unit conversion enable data from different sources to be seamlessly connected, facilitating subsequent data processing and analysis; avoiding calculation errors and misunderstandings caused by inconsistent formats or different units; timestamp comparison and correction ensures the consistency of data in time, providing a basis for subsequent association analysis and time series analysis; the data alignment mechanism enables data that require association analysis to be accurately aligned on the timeline, improving the efficiency and accuracy of data processing; data aggregation by time intervals reduces the amount of data and improves the speed and efficiency of data processing; data grouping enables similar or related data to be classified together, facilitating subsequent data analysis and mining; data labeling adds additional information to each data record, making the data more descriptive and interpretable; feature extraction extracts key information from the data based on statistical analysis and machine learning algorithms, providing strong support for subsequent data analysis and mining; the integrated data set contains all data after preprocessing, time synchronization, aggregation grouping, labeling and feature extraction, forming a comprehensive, accurate and usable data set; the data set provides a basis for subsequent data analysis, mining and visualization, helps to discover patterns and trends in the data, and provides support for decision-making; the integrated data set is stored in the data storage system, ensuring the long-term preservation and accessibility of the data; the data storage system provides efficient data retrieval and query functions, allowing users to quickly find the data they need; data archiving and backup mechanisms ensure the security and reliability of data, and avoid losses caused by data loss or damage.

[0059] In one embodiment of the present invention, the monitoring and protection method of the monitoring and protection module includes: The sensors are used to collect various operating data of the water cooling system in real time, including the temperature, pressure, flow rate and working status of the coolant, and the collected data are pre-processed; Performing in-depth analysis on the processed data based on a built-in third deep learning model to identify the operating state of the system, wherein the operating state includes normal operation, abnormal operation or fault state; When the system status analysis results show an abnormality or are close to the alarm threshold, the fault warning mechanism is triggered and feedback is given to relevant personnel in a variety of ways; According to the fault warning information, a corresponding protection strategy is formulated, which includes reducing the power of the heat source, adjusting the coolant flow, and starting the standby pump, and the formulated protection strategy is sent to the control system, and the control system executes the corresponding protection measures; The fault diagnosis algorithm can be used to accurately locate the fault and determine the specific location or component where the fault occurred. The historical data and real-time data can be combined to analyze the cause of the fault and determine the type, cause and possible impact of the fault. According to the fault diagnosis results, corresponding repair measures are taken, which include replacing faulty components and adjusting system parameters. Based on the cause of the fault and the repair process, the system is optimized, which includes improving the sensor layout and optimizing the protection strategy.

[0060] The working principle of the above technical solution is as follows: the monitoring and protection module collects key operating data such as coolant temperature, pressure, flow and pump working status in real time through sensors arranged in the water cooling system; the collected raw data is preprocessed, including data cleaning, denoising, interpolation, etc.; the module has a built-in third deep learning model, which is trained to identify different operating states of the water cooling system, including normal operation, abnormal operation and fault state; the third deep learning model conducts in-depth analysis of the preprocessed data, extracts features, and judges the current operating state of the system based on the features; when the system status analysis results show an abnormality or are close to the preset alarm threshold, the module will trigger the fault warning mechanism; the warning information is fed back to relevant personnel through various means (such as sound and light alarms, SMS notifications, etc.) so that timely measures can be taken; according to the fault warning information, the module will formulate relevant The module uses a fault diagnosis algorithm to accurately locate the fault and determine the specific location or component where the fault occurs. It combines historical data with real-time data to analyze the cause of the fault and determine the type, cause and possible impact of the fault. Fault information, location results, and diagnostic results are recorded in the fault log. The fault log facilitates subsequent analysis and query, and is helpful for system maintenance and troubleshooting. According to the fault diagnosis results, take corresponding repair measures, such as replacing faulty components and adjusting system parameters. Based on the cause of the fault and the repair process, optimize the system. Optimization measures may include improving sensor layout, optimizing protection strategies, etc., to improve system reliability and stability.

[0061] The effects of the above technical solution are as follows: various operating data of the water cooling system are collected in real time through sensors, ensuring instant understanding of the system status; pre-processing the collected data improves the accuracy and reliability of the data; the built-in third deep learning model can conduct in-depth analysis of the processed data and accurately identify the operating status of the system; when the system status analysis results show an abnormality or are close to the alarm threshold, the fault warning mechanism can be quickly triggered; feedback in various ways (sound and light alarms, SMS notifications, etc.) ensures that relevant personnel can receive warning information in a timely manner; according to the fault warning information, corresponding protection strategies can be quickly formulated, such as reducing the power of the heat source, adjusting the flow of coolant, starting the standby pump, etc.; the protection strategy can be sent to the control system in real time, and the control system will execute the corresponding protection measures to effectively prevent the occurrence and expansion of the fault; the fault can be accurately located through the fault diagnosis algorithm to determine the specific location of the fault The system can identify faults or components; analyze the causes of faults by combining historical data with real-time data, and determine the type, cause and possible impact of the faults; record fault information, location results, diagnosis results, etc. in the fault log to facilitate subsequent analysis and query; the fault log provides an important reference for system maintenance and optimization; according to the fault diagnosis results, corresponding repair measures can be taken, such as replacing faulty components and adjusting system parameters; based on the causes of the faults and the repair process, the system can be optimized, such as improving the sensor layout and optimizing the protection strategy; the reliability and stability of the water cooling system are significantly improved through real-time monitoring, early warning, protection and fault response; the optimization and continuous improvement of the system ensure its ability to operate stably in the long term; timely fault warning and location reduce the impact of faults on the system, reduce downtime and maintenance costs caused by faults; the optimization of the system reduces unnecessary maintenance work and waste of resources.

[0062] In one embodiment of the present invention, the control method of the control module includes: Collect various operating data of the water cooling system in real time through sensors and pre-process the collected data; Evaluate the preprocessed data through data analysis algorithms to determine the current state of the system, and select the control strategy based on the current state of the system and the control objectives; According to the control strategy, the control parameters are calculated, and the calculated control parameters are converted into control signals, which are sent to the actuators to adjust the state of the system; After executing the control strategy, continue to monitor the state changes of the system in real time through sensors, obtain feedback data, use data analysis algorithms to evaluate the feedback data, and determine the execution effect of the control strategy; According to the control effect evaluation results, the control strategy is adjusted and optimized.

[0063] The working principle of the above technical solution is as follows: the control module collects key operating data such as coolant temperature, pressure, flow, etc. in real time through sensors arranged in the water cooling system; the collected raw data is preprocessed, including data cleaning, denoising, interpolation, etc. The control module uses data analysis algorithms to evaluate the preprocessed data and determine the current state of the water cooling system, including normal operation, minor abnormalities, and serious faults; according to the current state of the system and the control target, the control module will select the most appropriate control strategy. For example, in normal operation, the PID (proportional-integral-differential) control strategy is selected to maintain the stable operation of the system; in minor abnormal conditions, the fuzzy control strategy is selected for fine-tuning to adapt to minor changes in the system; in serious fault conditions, it switches to the emergency protection strategy to protect the system from further damage; according to the selected control strategy, the control module will calculate the corresponding control parameters. For example, in PID control, the proportional, integral, and differential coefficients are calculated; in fuzzy control, the membership function and rule base are determined; the control module converts the calculated control parameters into control signals, such as voltage, current, frequency, etc., and then sends them to the actuators (such as pumps, valves, etc.); the actuators adjust the state of the water cooling system according to the received control signals, such as adjusting the speed of the pump, the opening of the valve, etc.; after executing the control strategy, the control module continues to monitor the state changes of the system in real time through sensors and obtain feedback data; the feedback data is evaluated using data analysis algorithms to determine the execution effect of the control strategy, such as whether the expected control target is achieved, how stable the system is, etc.; based on the control effect evaluation results, the control module will adjust and optimize the control strategy. For example, if the control effect is not good, it may be necessary to adjust the parameters of the PID control or switch to a more advanced control strategy.

[0064] The effects of the above technical solution are: various operating data of the water cooling system are collected in real time through sensors and preprocessed to ensure the accuracy and timeliness of the data; the real-time performance enables the system to respond to changes quickly and adjust the control strategy in time to maintain the stable operation of the system; the preprocessed data is accurately evaluated using the data analysis algorithm to accurately determine the current state of the system; the most appropriate control strategy is selected based on the current state of the system and the control target, thereby improving the accuracy and pertinence of the control; different control strategies can be selected according to the different states of the system, such as PID control, fuzzy control, emergency protection strategy, etc.; this flexibility enables the system to adapt to different operating environments and requirements, and improves the adaptability and robustness of the system; the control strategy can be adjusted and optimized based on the control effect evaluation results; this adaptability enables the system to continuously learn and improvement to improve the efficiency and accuracy of control; through precise control parameter calculation and control signal sending, efficient adjustment of system status is achieved; high efficiency enables the system to quickly achieve the expected control goals, reducing energy waste and system losses; real-time monitoring of system status changes and obtaining feedback data ensures the execution effect of the control strategy; stability enables the system to maintain stable performance under various operating conditions, improving the reliability and safety of the system; using data analysis algorithms and advanced control strategies, intelligent control of the water cooling system is achieved; intelligence enables the system to learn and make decisions independently, improving the intelligence level and automation of control; through automated control, the need for manual intervention is reduced, reducing the difficulty of operation and labor costs; automation enables the system to operate continuously and stably, improving work efficiency and economic benefits.

[0065] In one embodiment of the present invention, the pre-processed data is evaluated by a data analysis algorithm to determine the current state of the system, and a control strategy is selected according to the current state of the system and the control target, including: The built-in fourth deep learning model extracts key features from the preprocessed data. Based on the extracted features, the classification algorithm is used to classify the system status to identify whether the system is currently in normal operation, slight abnormality or serious fault state; Combining historical data with current data, using time series analysis to evaluate the system status in real time, using the prediction model to predict the system's operating status in the future, and identifying potential risk points or abnormal trends; the system status is evaluated using the following formula:

[0066] in, represents the system status score at time point t; represents the function that converts the prediction error into a state score; and is the weight coefficient used to balance the importance of historical data and forecast errors in the status score; and Represents the autoregressive coefficient and moving average coefficient in the ARIMA model; Represents past data points in a time series; represents the error term in the moving average model; represents the predicted value for the next time point t+1; p and q represent the orders of the autoregressive term and the moving average term, respectively; is the weight of the predicted value in the state score.

[0067] According to system characteristics and control requirements, a strategy library containing multiple control strategies is established, and control strategies are selected from the strategy library based on the results of state identification and trend prediction; For the selected control strategy, its control parameters are initialized according to the default values, and the control parameters are iteratively optimized using the optimization algorithm.

[0068] The working principle of the above technical solution is: collect data in real time from the sensors of the water cooling system, including coolant temperature, pressure, flow, etc.; preprocess the collected data, including data cleaning (removing noise and outliers), data normalization (making the data on the same scale), etc., to improve data quality; extract key features from the preprocessed data through the built-in fourth deep learning model. The features include the rate of change of coolant temperature, the standard deviation of pressure fluctuations, the periodicity of flow, etc.; based on the extracted features, classify the system status using classification algorithms (such as support vector machines, decision trees, random forests, etc.). The classification results identify the current state of the system as normal operation, slight abnormality or serious fault; combine historical data and current data, and use time series analysis techniques (such as ARIMA, LSTM, etc.) to evaluate the system status in real time. It includes determining key indicators such as the health and stability of the system; predicting the operating status of the system in the future through prediction models (such as neural network prediction models) to identify potential risk points or abnormal trends; establishing a strategy library containing a variety of control strategies based on system characteristics and control requirements, including PID control, fuzzy control, neural network control, adaptive control, etc.; selecting the most appropriate control strategy from the strategy library based on the results of state classification and trend prediction. For example, under normal operating conditions, PID control is preferred to ensure the stability and response speed of the system; under minor abnormal conditions, fuzzy control is used to deal with uncertain factors; under serious fault conditions, the system is switched to an emergency protection strategy to prevent system damage; for the selected control strategy, its control parameters (such as the proportional, integral, and differential coefficients of PID control, the membership function and rule base of fuzzy control, etc.) are first initialized according to the default values; then, the control parameters are iteratively optimized using an optimization algorithm (such as a genetic algorithm, a particle swarm optimization algorithm, etc.) to find the optimal parameter combination so that the system can achieve the best control effect; based on the optimized control parameters, the control signal (such as voltage, current, frequency, etc.) is calculated and sent to the actuator (such as a pump, valve, etc.); the actuator adjusts the state of the water cooling system according to the received control signal; after executing the control strategy, the system state changes are continuously monitored in real time through sensors to obtain feedback data; the feedback data is evaluated using a data analysis algorithm to determine the execution effect of the control strategy; based on the control effect evaluation results, the control strategy is adjusted and optimized to further improve the control performance and stability of the system.

[0069] The effects of the above technical solution are as follows: through the built-in fourth deep learning model, key features can be extracted from the preprocessed data, and these features more accurately reflect the dynamic behavior and state changes of the system; the accuracy of feature extraction improves the accuracy of system state classification, which helps to discover potential problems in a timely manner; the classification algorithm is used to classify the system state, which can accurately identify whether the system is currently in normal operation, slight abnormality or serious fault state; the real-time and accuracy of system state identification are improved, providing a reliable basis for the selection of control strategies; combining historical data and current data, using time series analysis technology to evaluate the health and stability of the system in real time; it helps to discover the decline or abnormal changes in system performance in a timely manner, providing an important reference for system maintenance and management; through the prediction model, the operating state of the system in the future can be predicted, and potential risk points or abnormal trends can be identified; early warning of possible system failures provides a time window for adjustment and optimization of control strategies; according to system characteristics and control requirements, a strategy library containing multiple control strategies is established, which provides rich options for the selection of control strategies; the flexibility and adaptability of the control strategy are improved to meet the control requirements under different states; for the selected control strategy, its control parameters are initialized according to the default values, and iterative optimization is performed using the optimization algorithm; by continuously adjusting and optimizing the control parameters, the control performance and stability of the system are improved; through the above technical solutions, intelligent control of the water cooling system is realized; intelligent control improves the automation level and response speed of the system and reduces the need for manual intervention; in the case of minor abnormal conditions, fuzzy control and other strategies are adopted to deal with uncertain factors, which helps to avoid further development of faults; in the case of serious fault conditions, emergency protection strategies are switched to prevent system damage, which improves the reliability and safety of the system; through precise control strategies and optimized control parameters, precise adjustment of the system state is achieved; unnecessary energy waste and system loss are reduced, and the overall operation efficiency of the system is improved. The above formula combines historical data, prediction errors and future prediction values ​​together to provide a comprehensive score for the system state, making the state evaluation more accurate and better reflecting the actual operation of the system. By introducing weight coefficients (α, β, γ), the formula allows the importance of historical data, prediction errors and future predictions in the state score to be dynamically adjusted according to actual conditions. The formula combines the characteristics of the autoregressive (AR) and moving average (MA) models, so that the evaluation of the system status is not only based on current data, but also takes into account past trends and fluctuations, thereby improving the ability to capture the dynamic behavior of the system. Through real-time evaluation and trend prediction, the formula helps to identify potential risk points or abnormal trends in system operation, take measures in advance, reduce the probability of failure, and thus improve the reliability of the system. Using the historical data and error terms of the ARIMA model, the formula can more accurately predict future states, ensure that decisions are based on reliable forecast information, and thus improve management efficiency.By selecting appropriate control strategies from the strategy library, the formula not only evaluates the current state, but also provides a basis for the regulation of the system, ensuring that the control measures can respond to changes in the system state in a timely and effective manner. Real-time monitoring and evaluation of the system state, combined with the corresponding control strategy, helps to enhance the controllability of the system, reduce downtime, and improve overall operational efficiency. The implementation of the formula can provide a feedback mechanism for the system, continuously monitor the state score, and optimize it during the actual control process, thereby continuously improving the management and operation effects of the system. The design of the formula framework makes it easy to add other features or indicators in the future to adapt to different types of systems or new control requirements, and improve the applicability and scalability of the system. By integrating data analysis and prediction models, the formula provides strong support for data-driven decision-making, enabling managers to make decisions based on scientific evidence and reduce the risk of subjective judgment. Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. In this way, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A traction converter water cooling system test device, characterized in that: The device includes: a cooling liquid circulation system, a heat source power control system, a data acquisition and processing system, a cooling medium supply and recovery module, a monitoring and protection module and a control module; the heat source power control system is connected to the cooling liquid circulation system; the data acquisition and processing system is connected to the cooling liquid circulation system and the heat source power control system; the cooling medium supply and recovery module is connected to the cooling liquid circulation system; the monitoring and protection module and the cooling circulation system are connected to the control module.

2. A traction converter water cooling system test device according to claim 1, characterized in that: The cooling liquid circulation system circulates through heat exchange between liquid and liquid to provide cooling liquid for the tractor; The heat source power control system is used to adjust the heating power of the heat source and simulate the heat loss of the traction converter under different working conditions; The data acquisition and processing system is used to collect and process relevant data generated during the experiment, and evaluate the performance of the water cooling system based on the processing results; The coolant supply and recovery module is used to provide cooling medium to the traction converter and to recover the cooling medium after heat exchange; The monitoring and protection module is used to monitor the operating status of the cooling system in real time and take protective measures when abnormal conditions occur; The control module is used to control the operation of the entire cooling system.

3. The traction converter water cooling system test device according to claim 1, characterized in that: The coolant circulation system includes a pump, a heat exchanger, a water tank, a pipeline, various sensors and a control valve; the various sensors include a temperature sensor, a pressure sensor and a flow sensor; The heat source power control system includes a voltage-stabilized power supply, a switch, a voltage regulator, a voltmeter and an ammeter; The data acquisition and processing system includes a terminal device, a data collector and a thermocouple; The cooling medium supply and recovery device includes a liquid storage tank, a pipeline, a valve and a connecting piece; The monitoring and protection module includes a sensor, an alarm device and a cut-off valve; The control module includes a PLC controller and a relay.

4. The traction converter water cooling system test device according to claim 1, characterized in that: The heat source power control method of the heat source power control system comprises: Start the heat source power control system, initialize the hardware and software, calibrate the parameters of key components, and set the target heating power of the heat source according to the test requirements; The voltage of the input heat source is adjusted by the voltage regulator, and the input voltage and current of the heat source are monitored in real time by the voltage meter and the current meter, and the actual heating power is calculated and compared with the target power; Based on the real-time monitoring results, the voltage is fine-tuned through the control algorithm; Based on machine learning algorithms, the historical data of heat source power is learned and analyzed, and the power change trend in the future is predicted; Dynamically adjust the voltage regulation strategy according to the real-time changes in the heat source power; set an overheat protection device in the heat source power control system to automatically cut off the heat source power supply when the actual power exceeds the set threshold; Integrated fault self-diagnosis function to monitor the working status of each component in real time. If any abnormality is found, fault location and alarm will be issued. During the test, the changes in key parameters, the system's operating status and fault information are recorded in real time. The recorded data is deeply mined and analyzed based on the built-in first deep learning model to evaluate the performance and stability of the heat source power control system.

5. A traction converter water cooling system test device according to claim 4, characterized in that: The voltage is fine-tuned by a control algorithm according to the real-time monitoring result, including: Preprocess the voltage and current data monitored in real time by the voltmeter and ammeter, calculate the actual heating power in real time based on the preprocessed voltage and current data, and compare it with the preset target heating power to obtain the power error; According to the size and change trend of power error, the control strategy is selected, and the parameters of the control strategy are dynamically adjusted using genetic algorithm; Based on the selected control strategy and optimized parameters, the voltage of the input heat source is fine-tuned through the voltage regulator; during the fine-tuning process, the power error is continuously monitored through the real-time feedback mechanism, and the fine-tuning amplitude and frequency are dynamically adjusted according to the error changes; After voltage fine-tuning, stability verification is performed to verify whether the actual power fluctuates stably within the target power range; if there is a deviation, the control parameters are further fine-tuned based on the verification results to form a closed-loop feedback control.

6. The traction converter water cooling system test device according to claim 1, characterized in that: The data acquisition and processing method of the data acquisition and processing system comprises: The relevant data are collected in real time through various sensors, and the collected relevant data are transmitted to the data collector via wired or wireless means; The data collector preprocesses the received relevant data, caches the preprocessed relevant data in a storage unit of the data collector, and transmits the data stored in the storage unit to the data processing unit via wired or wireless means; The data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores it; The integrated data is deeply mined and analyzed through the built-in second deep learning model to extract key information. At the same time, the analysis results are intuitively displayed through data visualization technology; Based on the data analysis results, the performance of the water cooling system is evaluated. At the same time, fault diagnosis and early warning are carried out by combining historical data with abnormal data during the test process. Regularly conduct quality assessments on the collected and processed data, and adjust data collection and processing strategies based on the data quality assessment results.

7. A traction converter water cooling system test device according to claim 6, characterized in that: The data processing unit performs secondary processing on the received data, integrates the secondary processed data according to the test requirements, forms a complete data set, and archives and stores it, including: Identify and delete duplicate, invalid or obviously erroneous data records, check whether each data field is complete, and fill in missing values ​​using interpolation or mean substitution based on the context; and verify the logical relationship between data using preset thresholds and ranges; Unify the data formats output by different sensors into a standard format, and perform unit conversion for data involving different physical quantities; Through timestamp comparison and correction, the data is kept consistent in time. If the data needs to be analyzed in association, the data is aligned on the time axis through time windows or event trigger mechanisms. Aggregate data by time interval according to test requirements, and divide data into different groups according to test conditions, equipment status or data characteristics; Add labels to each data record and extract feature vectors of the data based on statistical analysis and machine learning algorithms; The data that has been preprocessed, time synchronized, aggregated and grouped, labeled, and feature extracted are integrated according to the experimental requirements to form a complete data set; the integrated data set is stored in the data storage system.

8. The traction converter water cooling system test device according to claim 1, characterized in that: The monitoring and protection method of the monitoring and protection module includes: The various operating data of the water cooling system are collected in real time through sensors, and the collected data are pre-processed; Performing in-depth analysis on the processed data based on a built-in third deep learning model to identify the operating state of the system, wherein the operating state includes normal operation, abnormal operation or fault state; When the system status analysis results show an abnormality or are close to the alarm threshold, the fault warning mechanism is triggered and feedback is given to relevant personnel in a variety of ways; According to the fault warning information, formulate corresponding protection strategies, and send the formulated protection strategies to the control system, which will execute corresponding protection measures; The fault diagnosis algorithm is used to locate the fault and determine the specific location or component where the fault occurred. The cause of the fault is analyzed by combining historical data and real-time data to determine the type, cause and impact of the fault. According to the fault diagnosis results, take corresponding repair measures, and optimize the system based on the cause of the fault and the repair process.

9. The traction converter water cooling system test device according to claim 1, characterized in that: The control method of the control module includes: The various operating data of the water cooling system are collected in real time through sensors, and the collected data are pre-processed; Evaluate the preprocessed data through data analysis algorithms to determine the current state of the system, and select the control strategy based on the current state of the system and the control objectives; According to the control strategy, the control parameters are calculated, and the calculated control parameters are converted into control signals, which are sent to the actuators to adjust the state of the system; After executing the control strategy, continue to monitor the state changes of the system in real time through sensors, obtain feedback data, use data analysis algorithms to evaluate the feedback data, and determine the execution effect of the control strategy; According to the control effect evaluation results, the control strategy is adjusted and optimized.

10. A traction converter water cooling system test device according to claim 9, characterized in that: The pre-processed data is evaluated by a data analysis algorithm to determine the current state of the system, and a control strategy is selected according to the current state of the system and the control target, including: The built-in fourth deep learning model extracts key features from the preprocessed data. Based on the extracted features, the classification algorithm is used to classify the system status to identify whether the system is currently in normal operation, slight abnormality or serious fault state; Combine historical data with current data, use time series analysis to evaluate the system status in real time, use prediction models to predict the system's operating status in the future, and identify potential risk points or abnormal trends; According to system characteristics and control requirements, a strategy library containing multiple control strategies is established, and control strategies are selected from the strategy library based on the results of state identification and trend prediction; For the selected control strategy, its control parameters are initialized according to the default values, and the control parameters are iteratively optimized using the optimization algorithm.

Images