A temperature parameter control method and system for a new energy motor bench test box

Abstract

The present invention relates to the field of temperature control, and in particular to a temperature parameter control method and system for a new energy motor bench test box. The method comprises the following steps: obtaining the real-time working temperature parameters of the test box and the test box structure diagram based on multiple sensor nodes; obtaining spatial temperature distribution data based on the real-time working temperature parameters of the test box; dynamically rendering the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field; performing position layout analysis on the test box structure diagram to obtain component position layout data; performing three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model; obtaining multiple temperature control area models based on the three-dimensional structural temperature change distribution model; performing segmented temperature control decisions on multiple temperature control area models to obtain a multi-order duty cycle temperature control strategy. The present invention achieves efficient and uniform temperature control.

Description

Technical Field

[0001] The present invention relates to the field of temperature control, and in particular to a temperature parameter control method and system for a new energy motor bench test box. Background Art

[0002] In recent years, with the rapid development of new energy motor technology, the demand for its performance testing and reliability verification has increased. New energy motors will generate a lot of heat during operation, and their temperature distribution characteristics directly affect the working efficiency and service life of the motor. It is very important to accurately control the temperature parameters of the new energy motor bench test chamber. Traditional temperature control methods are usually based on single-point temperature feedback and use a simple PID algorithm for adjustment. This method cannot fully reflect the complex temperature field distribution characteristics inside the test chamber, and often has problems such as uneven temperature control and low control accuracy. It is difficult to meet the needs of high-performance and high-reliability testing of new energy motors. Therefore, an intelligent new energy motor temperature control method is needed. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a temperature parameter control method and system for a new energy motor bench test box to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a temperature parameter control method for a new energy motor bench test box, comprising the following steps:

[0005] Step S1: obtaining the real-time working temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor nodes; obtaining the spatial temperature distribution data based on the real-time working temperature parameters of the test box; dynamically rendering the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field;

[0006] Step S2: Performing a position layout analysis on the test box structure diagram to obtain component position layout data; performing three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model;

[0007] Step S3: obtaining multiple temperature control area models based on the three-dimensional structure temperature change distribution model; performing segmented temperature control decisions on the multiple temperature control area models to obtain a multi-step duty cycle temperature control strategy;

[0008] Step S4: performing global balance analysis on multiple temperature control area models through a multi-step duty cycle temperature control strategy to obtain global balance data of the temperature control area; performing adaptive fine-tuning of PID parameters based on the global balance data of the temperature control area to construct a partition temperature PID fine-tuning strategy;

[0009] Step S5: Use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models, and generate temperature control area cooling capacity prediction data; perform power optimization adjustment on the temperature control area cooling capacity prediction data, and build an energy consumption dynamic optimization strategy;

[0010] Step S6: Perform abnormal temperature diagnosis decision on the three-dimensional structure temperature change distribution model and build an abnormal temperature decision engine; perform neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and build a temperature intelligent control model to perform temperature parameter control.

[0011] The present invention obtains the working temperature parameters and structure diagram of the test box in real time, provides real-time temperature data and structural information of the test box, and these data provide a basis for subsequent temperature parameter control. Based on the real-time working temperature parameters, spatial temperature distribution data is obtained to understand the temperature difference at different positions in the test box, provide spatial distribution information for temperature parameter control, perform dynamic rendering of change trajectory distribution, visualize spatial temperature distribution data, and form a dynamic temperature change distribution field, which provides an intuitive understanding of temperature changes and is helpful for further temperature parameter control and analysis. By performing position layout analysis on the structure diagram of the test box, the position information of each component in the test box is determined, and these position layout data are very important for subsequent temperature parameters. Control and model building are crucial. Based on the dynamic temperature change distribution field, the component position layout data is three-dimensionally interpolated and mapped, and the dynamic temperature change distribution field is associated with the structural diagram of the test chamber to obtain a three-dimensional structural temperature change distribution model. This model provides the temperature distribution of different components in the test chamber, providing a basis for temperature parameter control and analysis. According to the three-dimensional structural temperature change distribution model, the test chamber is divided into multiple temperature control areas. Each temperature control area has different temperature characteristics and control requirements. Segmented temperature control decisions are made for multiple temperature control area models to obtain a multi-stage duty cycle temperature control strategy. This strategy adjusts the duty cycle of the temperature controller according to the real-time temperature requirements of the temperature control area to achieve precise temperature control. The air-to-air temperature control strategy performs a global balance analysis on multiple temperature control area models and evaluates the temperature balance between temperature control areas, which helps to discover areas with uneven temperatures and make subsequent adjustments and improvements. It performs adaptive fine-tuning of PID parameters based on the global balance data of the temperature control area, and automatically adjusts the parameters of the PID controller according to the temperature differences between the temperature control areas to improve the accuracy and stability of temperature control. This partition temperature PID fine-tuning strategy helps to achieve more accurate temperature control. The partition temperature PID fine-tuning strategy is used to predict the cooling demand of multiple temperature control area models, and predict the cooling capacity required for each area according to the temperature control demand, which helps to plan and schedule cooling resources in advance. , optimize the power of the predicted data of the cooling capacity of the temperature control area, optimize the power adjustment strategy of the refrigeration equipment according to the real-time cooling demand and energy consumption, so as to improve the energy utilization efficiency and reduce the energy consumption cost, make abnormal temperature diagnosis decisions on the three-dimensional structural temperature change distribution model, detect the abnormal temperature in the test chamber, and take timely measures to deal with and correct it. By constructing an abnormal temperature decision engine, a neural network optimization and structural learning processing of the energy consumption dynamic optimization strategy and the partition temperature PID fine-tuning strategy, a temperature intelligent control model is constructed by comprehensively utilizing multiple control strategies and decision engines, which automatically adapts to different temperature control scenarios and executes corresponding temperature parameter control to achieve efficient and accurate temperature control.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: acquiring the real-time operating temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor node;

[0014] Step S12: Calculate the spatial position of the multi-sensor node to obtain the node spatial position coordinates;

[0015] Step S13: performing multi-position temperature calculation on the real-time working temperature parameters of the test box based on the node spatial position coordinates to obtain multiple node position temperature parameters;

[0016] Step S14: performing spatial temperature distribution analysis on temperature parameters at multiple node positions to obtain spatial temperature distribution data;

[0017] Step S15: performing multi-time-frequency decomposition processing on the temperature parameters of multiple node positions to obtain temperature change trajectories;

[0018] Step S16: dynamically rendering the temperature change trajectory distribution of the spatial temperature distribution data based on the temperature change trajectory to construct a dynamic temperature change distribution field.

[0019] The present invention provides real-time temperature data and structural information of the test box by acquiring the working temperature parameters and structural diagram of the test box in real time. The temperature parameters are used to monitor the temperature changes inside the test box to provide a basis for subsequent temperature control. The structural diagram of the test box is used to determine the positions and layouts of the internal components of the test box to provide a basis for subsequent temperature distribution analysis. The spatial position of multiple sensor nodes is calculated to determine the specific position of each sensor node in the test box. After obtaining the spatial position coordinates of the node, the temperature data of each node is associated with its position to provide accurate spatial information for subsequent temperature distribution analysis. Based on the spatial position coordinates of the node, the temperature sensor data in the test box is analyzed and calculated. Through multi-position temperature calculation, the temperature parameters of different positions are obtained, including the mean, maximum, minimum, etc. of the temperature distribution, to provide a test box. In order to understand the temperature conditions at different positions in the test chamber, the spatial temperature distribution analysis of the temperature parameters at multiple node positions is performed to understand the temperature differences and distribution conditions at different positions in the test chamber. After obtaining the spatial temperature distribution data, a temperature distribution diagram or a thermal diagram is drawn to intuitively display the spatial distribution characteristics of the temperature in the test chamber. By performing multi-time-frequency decomposition processing on the temperature parameters at multiple node positions, the temperature data is decomposed into components of different frequencies. After obtaining the temperature change trajectory, the change laws of different frequency components are analyzed to understand the periodic changes of temperature, which provides a reference for subsequent temperature control. Based on the temperature change trajectory, the spatial temperature distribution data is dynamically rendered, and the temperature changes are displayed in the form of animation or visualization. The dynamic temperature change distribution field intuitively displays the temperature change trend in the test chamber, helps to understand the temporal and spatial distribution characteristics of temperature, and provides an intuitive basis for temperature parameter control and analysis.

[0020] Preferably, the specific steps of step S15 are:

[0021] Perform time series temperature fitting identification on temperature parameters of multiple node positions to obtain a node time series temperature curve;

[0022] Perform temperature fluctuation analysis on the node timing temperature curve to obtain timing temperature change data;

[0023] Perform multi-time-frequency decomposition processing on the time-series temperature change data to obtain the temperature time-frequency domain; perform time-frequency period analysis on the temperature time-frequency domain to generate dynamic temperature change trend data;

[0024] The dynamic temperature change trend data is reconstructed through time series modeling to obtain the temperature change trajectory.

[0025] The present invention uses time-series temperature fitting to identify and curve fit the temperature parameters of each node to obtain the time-series temperature curve of the node. After obtaining the time-series temperature curve of the node, the temperature change trend and periodicity are further analyzed to provide a basis for subsequent temperature fluctuation analysis. Through temperature fluctuation analysis, the fluctuation amplitude and frequency of the node time-series temperature curve are understood, and the stability and degree of temperature change are evaluated. After obtaining the time-series temperature change data, the temperature change pattern and trend are analyzed to provide a basis for subsequent time-frequency decomposition processing. Through multi-time-frequency decomposition processing, the time-series temperature change data is decomposed into components of different frequencies to obtain the time-frequency domain expression of the temperature, and the temperature time-frequency domain expression is obtained. After the temperature is in the domain, the contribution and variation law of different frequency components are analyzed to understand the variation characteristics of temperature on different time scales. Through time-frequency periodic analysis, the periodic variation characteristics and frequency information of temperature in the time-frequency domain are determined. After generating dynamic temperature variation trend data, the periodic variation trend of temperature and the variation law of different frequency components are understood to provide more detailed information for temperature parameter control and analysis. Through time series modeling and reconstruction, the temperature variation trajectory is modeled and reconstructed based on the dynamic temperature variation trend data. After obtaining the temperature variation trajectory, the overall temperature variation trend, periodicity and trend mutation characteristics are analyzed to provide a comprehensive perspective for temperature control and analysis.

[0026] Preferably, the specific steps of step S2 are:

[0027] Step S21: performing component identification on the test box structure diagram to obtain test box component data;

[0028] Step S22: performing position layout analysis on the test box component data to obtain component position layout data;

[0029] Step S23: reconstructing the three-dimensional structure of the test box structure diagram based on the component position layout data to construct a three-dimensional structure model of the test box;

[0030] Step S24: performing three-dimensional interpolation mapping on the three-dimensional structural model of the test box based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model.

[0031] The present invention automatically identifies various components in the test box structure diagram, such as a chassis, a fan, a heat sink, etc., through component identification. After obtaining the test box component data, the function and characteristics of each component are further analyzed to provide a basis for subsequent position layout analysis and structural reconstruction. Through position layout analysis, the relative position relationship and layout mode of each component in the test box are determined. After obtaining the component position layout data, the spatial distribution and interaction between the various components are understood to provide a basis for subsequent structural reconstruction and temperature change distribution model construction. Through three-dimensional structural reconstruction, the test box structure diagram is converted into a three-dimensional structural model with spatial dimensions. After constructing the three-dimensional structural model of the test box, the geometric shape, size and component position of the test box are accurately represented to provide an accurate basis for subsequent temperature change distribution model construction. Through three-dimensional interpolation mapping, the dynamic temperature change distribution field is associated with the three-dimensional structural model of the test box to obtain a temperature distribution model in three-dimensional space. After obtaining the three-dimensional structural temperature change distribution model, the temperature change of different components and positions in the test box is understood to provide detailed spatial information for temperature parameter control.

[0032] Preferably, the specific steps of step S3 are:

[0033] Step S31: performing fine-grained regional division processing on the three-dimensional structure temperature change distribution model to obtain multiple temperature control area models;

[0034] Step S32: quantifying the regional temperature difference of multiple temperature control area models to obtain temperature control area temperature difference data;

[0035] Step S33: predicting the temperature difference change trend of the temperature difference data of the temperature control area to generate regional temperature difference trend prediction data;

[0036] Step S34: making segmented temperature control decisions on the regional temperature difference trend prediction data to obtain a multi-step duty cycle temperature control strategy.

[0037] The present invention divides the three-dimensional structural temperature change distribution model of the test box into multiple temperature control areas through fine-grained regional division processing. After obtaining multiple temperature control area models, the temperatures of different areas in the test box are independently controlled and adjusted to improve the accuracy and flexibility of temperature control. The temperature difference between different temperature control areas is quantified through regional temperature difference quantification. After obtaining the temperature difference data of the temperature control area, the temperature difference between each area is understood to provide a basis for subsequent temperature difference change trend prediction and temperature control decision-making. Through the temperature difference change trend prediction, the temperature difference data of the temperature control area is trend analyzed and predicted. After generating the regional temperature difference trend prediction data, the change law and trend of the temperature difference are understood to provide a prediction basis for temperature control decision-making to achieve more accurate temperature control. Through segmented temperature control decision-making, temperature control strategies for different stages are formulated according to the regional temperature difference trend prediction data. After obtaining the multi-stage duty cycle temperature control strategy, the duty cycle of the temperature controller is adjusted according to the temperature difference change trend and predicted value of the temperature control area to achieve accurate temperature control.

[0038] Preferably, the specific steps of step S4 are:

[0039] Step S41: performing regional temperature state evaluation processing on multiple temperature control area models based on the temperature difference data of the temperature control areas to obtain high temperature state areas and low temperature state areas;

[0040] Step S42: performing a step response demand analysis on the high temperature state area to obtain step response demand data of the high temperature area;

[0041] Step S43: Based on the step response demand data of the high temperature area, a high duty cycle hyper-parameter control process is performed on the high temperature state area through a multi-step duty cycle temperature control strategy to obtain the high temperature area hyper-parameter control data;

[0042] Step S44: performing low duty cycle gentle regulation processing on the low temperature state area through a multi-step duty cycle temperature control strategy to generate low temperature area gentle regulation data;

[0043] Step S45: performing global balance analysis on the low temperature area gentle control data and the high temperature area hyperparameter control data to obtain global balance data of the temperature control area;

[0044] Step S46: Adaptively fine-tune the PID parameters of multiple temperature control zone models based on the global balance data of the temperature control zones, and construct a zone temperature PID fine-tuning strategy.

[0045] The present invention evaluates the temperature state of each area according to the temperature difference data of the temperature control area through regional temperature state evaluation processing. After obtaining the high-temperature state area and the low-temperature state area, corresponding control strategies are formulated for the temperature states of different areas to achieve more accurate temperature control. Through step response demand analysis, the response speed and stability requirements of the high-temperature state area to temperature changes are determined. After obtaining the step response demand data of the high-temperature area, guidance is provided for the subsequent temperature control strategy design to ensure that the temperature regulation of the high-temperature area can meet the demand. Through high duty cycle hyper-parameter control processing, the hyper-parameters of the temperature controller, such as gain, integral time and differential time, are adjusted according to the temperature demand of the high-temperature state area. After obtaining the hyper-parameter control data of the high-temperature area, the controller is better adapted to the temperature regulation demand of the high-temperature area, and the response speed and stability of the temperature control are improved. The duty cycle smooth adjustment process adjusts the duty cycle of the temperature controller according to the temperature demand of the low-temperature state area to make the temperature change smoother. After generating the smooth control data of the low-temperature area, the temperature fluctuation in the low-temperature area is reduced to ensure that the temperature is controlled within an appropriate range. Through global balance analysis, the control strategies of the low-temperature area and the high-temperature area are comprehensively considered, and the temperature control balance of the entire temperature control area is evaluated. After obtaining the global balance data of the temperature control area, the temperature influence relationship between different areas is understood, which provides a reference for PID parameter fine-tuning and overall control strategy. Through PID parameter adaptive fine-tuning, the PID parameters of the temperature controller are fine-tuned according to the global balance data of the temperature control area. After constructing the partition temperature PID fine-tuning strategy, the PID controllers of each temperature control area are more optimized and adaptable, thereby improving the temperature parameter control performance of the entire test chamber.

[0046] Preferably, the specific steps of step S5 are:

[0047] Step S51: Calculate the target temperature of multiple temperature control area models using the zone temperature PID fine-tuning strategy to obtain the target temperature of the temperature control area;

[0048] Step S52: forecasting the cooling capacity demand for the target temperature of the temperature control area based on the temperature difference data of the temperature control area, and generating cooling capacity forecast data for the temperature control area;

[0049] Step S53: dynamically adjusting the temperature control loop power for the temperature control area cooling capacity prediction data to obtain loop power dynamic adjustment data;

[0050] Step S54: Optimize the power of multiple temperature control area models according to the loop power dynamic adjustment data to build a dynamic energy consumption optimization strategy.

[0051] The present invention adopts a zone temperature PID fine-tuning strategy, calculates the target temperature according to the PID parameters of each temperature control area, ensures the temperature control accuracy of each area, and after obtaining the target temperature of the temperature control area, provides an accurate target reference value for the next step of cooling capacity demand prediction and power optimization adjustment, predicts the cooling capacity demand of the temperature control area target temperature, predicts the cooling demand of each area according to the temperature difference data, and after generating the cooling capacity prediction data of the temperature control area, understands the cooling demand of each area, and provides a basis for subsequent temperature control and energy consumption optimization, dynamically adjusts the power of the temperature control loop according to the cooling capacity prediction data of the temperature control area, dynamically adjusts the power output of the loop according to the cooling demand, and after obtaining the dynamic adjustment data of the loop power, adjusts the power output of the loop according to the real-time cooling demand to meet the temperature control requirements and improve energy efficiency, and through power optimization adjustment, adjusts the power of multiple temperature control area models according to the dynamic adjustment data of the loop power to achieve dynamic optimization of energy consumption, and after constructing the dynamic optimization strategy of energy consumption, minimizes energy consumption and improves the energy efficiency performance of the entire test box under the premise of meeting the temperature control requirements.

[0052] Preferably, the specific steps of step S6 are:

[0053] Step S61: identifying abnormal temperature areas on the three-dimensional structure temperature change distribution model to generate abnormal temperature areas;

[0054] Step S62: accurately locate the fault in the abnormal temperature area and generate an abnormal temperature fault point;

[0055] Step S63: making abnormal temperature diagnosis decisions for abnormal temperature fault points and building an abnormal temperature decision engine;

[0056] Step S64: Perform neural network optimization and transformation learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy to build a temperature intelligent control model to execute temperature parameter control.

[0057] The present invention identifies abnormal temperature zones on a three-dimensional structural temperature variation distribution model, detects areas with abnormal temperatures in a test box, and after generating abnormal temperature zones, further analyzes temperature changes in these areas to provide a basis for subsequent fault diagnosis and decision-making. It accurately locates faults in abnormal temperature zones to determine specific fault points that cause temperature abnormalities. After generating abnormal temperature fault points, it accurately locates the problem to provide guidance for subsequent fault diagnosis and repair. It makes abnormal temperature diagnosis decisions on abnormal temperature fault points, determines possible fault causes according to the characteristics of the fault points and context information, and automatically performs fault diagnosis and decision-making after building an abnormal temperature decision engine to improve the efficiency and accuracy of fault handling. It optimizes the transformation learning process through a neural network, comprehensively considers information of the abnormal temperature decision engine, the dynamic optimization strategy of energy consumption, and the partition temperature PID fine-tuning strategy, and improves the accuracy and performance of temperature parameter control. After building a temperature intelligent control model, it automatically performs temperature parameter control according to real-time abnormal temperature diagnosis decisions, energy consumption optimization, and temperature control strategies to achieve intelligent control of the temperature of a new energy motor bench test box.

[0058] Preferably, the specific steps of step S63 are:

[0059] Get the historical operation log of the test chamber;

[0060] Based on the historical operation log of the test chamber, fault diagnosis and identification are performed on the abnormal temperature fault point to obtain the fault factor of the fault point; the fault factor of the fault point includes overtemperature of the fault point, abnormal electrical parameters and speed limit of the test chamber circuit;

[0061] When the fault factor of the fault point is overtemperature of the fault point, a fault judgment is performed on the sensor node of the fault point. When the sensor node of the fault point is normal, an emergency power-off process is performed and a power-off warning signal is generated;

[0062] When the sensor node at the fault point is abnormal, a signal fault warning is performed on the sensor node at the fault point to obtain a sensor fault signal;

[0063] When the fault factor of the fault point is abnormal electrical parameters, the line load is optimized for the abnormal temperature fault point to generate load optimization diagnostic data;

[0064] When the fault factor of the fault point is the speed limit of the test box circuit, the abnormal operation parameters of the motor are identified based on the historical operation log of the test box to obtain the abnormal operation data of the motor;

[0065] Make abnormal fault diagnosis decisions based on power outage warning signals, sensor fault signals, load optimization diagnosis data, and motor abnormal operation data, and build an abnormal temperature decision engine.

[0066] The present invention obtains the historical operation log of the test box to understand various operations and event records of the test box in the past operation process. The historical operation log provides detailed operation information of the test box, including data such as temperature, electrical parameters, and loop speed, which provides a basis for subsequent abnormal fault diagnosis and decision-making. By analyzing the historical operation log, the abnormal temperature fault point is diagnosed and identified, and the fault factor of the fault point is determined. After obtaining the fault factor of the fault point, the specific cause of the temperature abnormality is understood, and guidance is provided for subsequent fault processing. When the fault factor of the fault point is overtemperature of the fault point, the sensor node is judged to determine whether the sensor itself has a fault. Through fault judgment, it is determined whether the sensor node of the fault point is working normally, which provides a basis for subsequent processing decisions. When the sensor node of the fault point is judged to be normal, an emergency power-off process is performed to avoid further safety risks. After generating a power-off warning signal, an alarm is sent to relevant personnel to remind them to take appropriate measures to ensure the safety of the test box. When the sensor node of the fault point is judged to be abnormal, a signal fault warning is performed to timely discover the sensor fault. After obtaining the sensor fault signal, the relevant personnel are notified to perform sensor maintenance or replacement to ensure the accuracy and reliability of the temperature parameters. When the fault factor of the fault point is abnormal electrical parameters, line load optimization is performed to adjust the electrical parameters to stabilize temperature control. After generating load optimization diagnostic data, the optimized electrical parameter settings are understood to provide a reference for subsequent temperature parameter control. When the fault factor of the fault point is the speed limit of the test chamber circuit, the abnormality of the motor operating parameters is identified by analyzing the historical operation log. After obtaining the abnormal operation data of the motor, the operating status and performance of the motor are understood to provide a basis for subsequent fault diagnosis and repair. By making abnormal fault diagnosis decisions based on power-off warning signals, sensor fault signals, load optimization diagnostic data, and abnormal motor operation data, accurate diagnosis of abnormal temperature fault points is performed by comprehensively considering multiple factors. After building an abnormal temperature decision engine, fault diagnosis and decision-making are automatically performed, and corresponding measures are taken to repair the fault according to the diagnosis results to ensure the stability and reliability of the temperature parameter control of the test chamber.

[0067] In this specification, a temperature parameter control system of a new energy motor bench test box is provided, which is used to execute the temperature parameter control method of the new energy motor bench test box as described above, including:

[0068] The temperature change distribution module is used to obtain the real-time working temperature parameters of the test chamber and the structure diagram of the test chamber based on multiple sensor nodes; obtain the spatial temperature distribution data based on the real-time working temperature parameters of the test chamber; dynamically render the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field;

[0069] The three-dimensional interpolation module is used to perform position layout analysis on the test chamber structure diagram to obtain component position layout data; perform three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model;

[0070] The duty cycle temperature control module is used to obtain multiple temperature control area models based on the three-dimensional structure temperature change distribution model; perform segmented temperature control decisions on multiple temperature control area models to obtain multi-order duty cycle temperature control strategies;

[0071] The adaptive fine-tuning module is used to perform global balance analysis on multiple temperature control area models through multi-step duty cycle temperature control strategies to obtain global balance data of the temperature control areas; based on the global balance data of the temperature control areas, the PID parameters are adaptively fine-tuned to build a partition temperature PID fine-tuning strategy;

[0072] The power optimization module is used to use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models and generate the cooling capacity prediction data of the temperature control area; perform power optimization adjustment on the cooling capacity prediction data of the temperature control area and build a dynamic energy consumption optimization strategy;

[0073] The intelligent control module is used to make abnormal temperature diagnosis decisions on the three-dimensional structural temperature change distribution model and build an abnormal temperature decision engine; it performs neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and builds a temperature intelligent control model to execute temperature parameter control.

[0074] The present invention deploys multiple temperature sensors inside the test box to obtain real-time temperature data at various positions inside the test box, laying a foundation for subsequent temperature distribution modeling. Based on the collected temperature data, the temperature change trajectory inside the test box is dynamically rendered to construct a model that truly reflects the dynamic temperature field distribution. This dynamic and visualized temperature distribution field can more clearly reflect the transfer and change rules of temperature in the test box. Such a temperature distribution model provides a reliable reference basis for the subsequent precise temperature control strategy formulation, which helps to better understand the heat conduction and distribution characteristics of the test box. The two-dimensional temperature distribution field data is combined with the three-dimensional structural layout information of the test box to be mapped to a three-dimensional temperature change distribution model. This three-dimensional temperature change model The model not only retains the dynamic characteristics of temperature distribution, but also integrates the spatial information of the test chamber structure, making the corresponding relationship between the temperature change law and the specific component position more intuitive and clear. Based on this three-dimensional temperature change model, the temperature change of each part is analyzed more finely, and the heat transfer mechanism in the test chamber is deeply understood, laying the foundation for the subsequent regional temperature control. Through the analysis of the three-dimensional temperature change distribution model, the test chamber is divided into several relatively independent temperature control areas, each area has different temperature change characteristics. According to the temperature characteristics of different areas, a personalized multi-stage duty cycle temperature control strategy is formulated to achieve the temperature target of each area more accurately. Compared with the simple single temperature control strategy, the multi-stage duty cycle strategy can better adapt to the complex internal temperature of the test chamber. Complex temperature field distribution, improve the accuracy of temperature control, through the global balance analysis of the temperature control area of ​​the entire test chamber, dynamically adjust the PID control parameters of each area, ensure that the overall temperature field maintains a good balance state, adaptive adjustment of PID parameters can respond to changes in the temperature field inside the test chamber in a timely manner, continuously optimize the temperature control effect, and improve the stability and accuracy of control. Compared with the solution with fixed PID parameters, this adaptive adjustment strategy better adapts to the temperature change characteristics of the test chamber under different working conditions. Based on the prediction of the cooling capacity demand of each temperature control area, the power output of the refrigeration system is optimized and adjusted in real time. Under the premise of meeting the temperature control requirements, energy consumption is minimized. This dynamic energy consumption optimization strategy can be based on the actual temperature of the test chamber. The temperature load condition dynamically adjusts the working state of the refrigeration system, avoiding energy waste under the traditional constant power output mode. Through energy consumption optimization, it not only saves the operating cost of the test chamber, but also contributes positively to environmental protection, embodies the concept of high efficiency and energy saving, builds an abnormal temperature decision engine, automatically detects and diagnoses abnormal temperatures inside the test chamber, and provides a basis for subsequent troubleshooting and system maintenance. The optimization learning of the control strategy is completed by the neural network model, so that the entire temperature control system has the ability to continuously adapt, and can be continuously optimized and improved as the usage changes. This intelligent temperature control model greatly improves the autonomy and robustness of the temperature parameter regulation of the test chamber, and enhances the reliability and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A schematic flow chart of the steps of a temperature parameter control method of a new energy motor bench test box of the present invention;

[0076] Figure 2 Detailed implementation flow chart of step S1;

[0077] Figure 3 Detailed implementation flow chart of step S2;

[0078] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0079] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0080] The present application example provides a temperature parameter control method and system for a new energy motor bench test box. The execution subject of the temperature parameter control method and system for the new energy motor bench test box includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0081] See also Figures 1 to 4 The present invention provides a temperature parameter control method for a new energy motor bench test box, comprising the following steps:

[0082] Step S1: obtaining the real-time working temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor nodes; obtaining the spatial temperature distribution data based on the real-time working temperature parameters of the test box; dynamically rendering the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field;

[0083] Step S2: Performing a position layout analysis on the test box structure diagram to obtain component position layout data; performing three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model;

[0084] Step S3: obtaining multiple temperature control area models based on the three-dimensional structure temperature change distribution model; performing segmented temperature control decisions on the multiple temperature control area models to obtain a multi-step duty cycle temperature control strategy;

[0085] Step S4: performing global balance analysis on multiple temperature control area models through a multi-step duty cycle temperature control strategy to obtain global balance data of the temperature control area; performing adaptive fine-tuning of PID parameters based on the global balance data of the temperature control area to construct a partition temperature PID fine-tuning strategy;

[0086] Step S5: Use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models, and generate temperature control area cooling capacity prediction data; perform power optimization adjustment on the temperature control area cooling capacity prediction data, and build an energy consumption dynamic optimization strategy;

[0087] Step S6: Perform abnormal temperature diagnosis decision on the three-dimensional structure temperature change distribution model and build an abnormal temperature decision engine; perform neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and build a temperature intelligent control model to perform temperature parameter control.

[0088] The present invention obtains the working temperature parameters and structure diagram of the test box in real time, provides real-time temperature data and structural information of the test box, and these data provide a basis for subsequent temperature parameter control. Based on the real-time working temperature parameters, spatial temperature distribution data is obtained to understand the temperature difference at different positions in the test box, provide spatial distribution information for temperature parameter control, perform dynamic rendering of change trajectory distribution, visualize spatial temperature distribution data, and form a dynamic temperature change distribution field, which provides an intuitive understanding of temperature changes and is helpful for further temperature parameter control and analysis. By performing position layout analysis on the structure diagram of the test box, the position information of each component in the test box is determined, and these position layout data are very important for subsequent temperature parameters. Control and model building are crucial. Based on the dynamic temperature change distribution field, the component position layout data is three-dimensionally interpolated and mapped, and the dynamic temperature change distribution field is associated with the structural diagram of the test chamber to obtain a three-dimensional structural temperature change distribution model. This model provides the temperature distribution of different components in the test chamber, providing a basis for temperature parameter control and analysis. According to the three-dimensional structural temperature change distribution model, the test chamber is divided into multiple temperature control areas. Each temperature control area has different temperature characteristics and control requirements. Segmented temperature control decisions are made for multiple temperature control area models to obtain a multi-stage duty cycle temperature control strategy. This strategy adjusts the duty cycle of the temperature controller according to the real-time temperature requirements of the temperature control area to achieve precise temperature control. The air-to-air temperature control strategy performs a global balance analysis on multiple temperature control area models and evaluates the temperature balance between temperature control areas, which helps to discover areas with uneven temperatures and make subsequent adjustments and improvements. It performs adaptive fine-tuning of PID parameters based on the global balance data of the temperature control area, and automatically adjusts the parameters of the PID controller according to the temperature differences between the temperature control areas to improve the accuracy and stability of temperature control. This partition temperature PID fine-tuning strategy helps to achieve more accurate temperature control. The partition temperature PID fine-tuning strategy is used to predict the cooling demand of multiple temperature control area models, and predict the cooling capacity required for each area according to the temperature control demand, which helps to plan and schedule cooling resources in advance. , optimize the power of the predicted data of the cooling capacity of the temperature control area, optimize the power adjustment strategy of the refrigeration equipment according to the real-time cooling demand and energy consumption, so as to improve the energy utilization efficiency and reduce the energy consumption cost, make abnormal temperature diagnosis decisions on the three-dimensional structural temperature change distribution model, detect the abnormal temperature in the test chamber, and take timely measures to deal with and correct it. By constructing an abnormal temperature decision engine, a neural network optimization and structural learning processing of the energy consumption dynamic optimization strategy and the partition temperature PID fine-tuning strategy, a temperature intelligent control model is constructed by comprehensively utilizing multiple control strategies and decision engines, which automatically adapts to different temperature control scenarios and executes corresponding temperature parameter control to achieve efficient and accurate temperature control.

[0089] In the embodiment of the present invention, refer to Figure 1, is a schematic flow chart of the steps of a temperature parameter control method of a new energy motor bench test box of the present invention. In this example, the steps of the temperature parameter control method of the new energy motor bench test box include:

[0090] Step S1: obtaining the real-time working temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor nodes; obtaining the spatial temperature distribution data based on the real-time working temperature parameters of the test box; dynamically rendering the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field;

[0091] In this embodiment, multiple temperature sensor nodes are deployed at key locations (such as motors, frequency converters, and housings) inside the test box to collect temperature data from different areas in real time. The arrangement of the sensor nodes should fully consider the structural characteristics of the test box and cover the key monitoring areas inside the test box as much as possible. The collected multi-point temperature data is combined with the geometric size parameters and internal structure model of the test box to reconstruct the three-dimensional temperature distribution field inside the test box by using numerical simulation or interpolation methods. The temperature change trajectory of each position inside the test box is dynamically rendered through the time series temperature distribution field data to form a visualization model that reflects the dynamic characteristics of temperature. The simulation technology such as computational fluid dynamics (CFD) is used to further optimize the modeling accuracy of the temperature distribution field to make it closer to the actual working conditions. With the help of the visualized temperature distribution field model, the temperature change characteristics of different areas inside the test box are deeply analyzed to determine the overall distribution law of the temperature field. For the uneven areas or local high temperature points in the temperature field, the causes of their occurrence are further analyzed to provide a basis for the subsequent formulation of temperature control strategies. The dynamic change trend of the temperature field is understood through statistical analysis of the time series data of the temperature distribution field to provide a basis for predicting the temperature change trend.

[0092] Step S2: Performing a position layout analysis on the test box structure diagram to obtain component position layout data; performing three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model;

[0093] In this embodiment, according to the structural diagram of the test box, each key component inside the test box, such as a motor, a frequency converter, a cooling fan, etc., is identified and located, the specific positions of these key components are measured and recorded, and the three-dimensional position coordinate data of the components is established. In combination with the overall size parameters of the test box, the position data of the components is mapped to the three-dimensional space model of the test box to obtain accurate layout information of the components. The structural model of the test box and the temperature distribution data of the components are integrated using three-dimensional CAD modeling software to construct a three-dimensional structural temperature change distribution model. The model not only retains the geometric details of the test box, but also superimposes the dynamic temperature distribution information on the surface of the components, intuitively showing the temperature field characteristics inside the test box. The three-dimensional structural temperature change distribution model is simulated and solved, and its temperature field distribution is further optimized and corrected to improve the accuracy of the model. Through in-depth analysis of the model, the hot spot area inside the test box is identified to provide a reference basis for subsequent temperature control measures. The model is used to perform parameter sensitivity analysis to find out the key factors affecting the temperature distribution, providing guidance for the optimal design of the test box.

[0094] Step S3: obtaining multiple temperature control area models based on the three-dimensional structure temperature change distribution model; performing segmented temperature control decisions on the multiple temperature control area models to obtain a multi-step duty cycle temperature control strategy;

[0095] In this embodiment, the temperature control area inside the test box is divided into several relatively independent temperature control areas according to the characteristics of temperature distribution, such as motor area, inverter area, shell area, etc. The geometric boundary and volume parameters of each temperature control area are quantitatively described to provide a basis for the subsequent optimization of temperature control strategy. Corresponding temperature control strategies are formulated for each temperature control area, and differentiated temperature control schemes are adopted for areas with different characteristics. For hot spots, cooling control with a higher duty cycle can be adopted; for areas with lower temperatures, heating control with a lower duty cycle can be adopted. By adjusting the duty cycles of different temperature control areas in sections, refined control of the overall temperature field inside the test box can be achieved. According to the formulated multi-order duty cycle temperature control strategy, the corresponding temperature control system hardware circuit and control algorithm are designed, the temperature control system model is coupled with the constructed three-dimensional structural temperature change distribution model, and the simulation verification of the closed-loop temperature control system is carried out. Through simulation analysis, the temperature control parameters are optimized to ensure that the temperature control system can meet the precise control requirements of the temperature field inside the test chamber. According to the temperature control system scheme verified by simulation, the temperature control hardware system is actually constructed and software programming is performed. The temperature control system is integrated into the test chamber, and actual operation tests are carried out. The test results are compared and analyzed with the simulation model to further optimize the temperature control strategy. Through multiple rounds of testing and feedback optimization, it is ensured that the temperature control system can stably and efficiently achieve precise control of the temperature field inside the test chamber.

[0096] Step S4: performing global balance analysis on multiple temperature control area models through a multi-step duty cycle temperature control strategy to obtain global balance data of the temperature control area; performing adaptive fine-tuning of PID parameters based on the global balance data of the temperature control area to construct a partition temperature PID fine-tuning strategy;

[0097] In this embodiment, the formulated multi-order duty cycle temperature control strategy is applied to the three-dimensional structural temperature change distribution model for simulation, the temperature change of each temperature control area under the temperature control strategy is observed and analyzed, the overall uniformity of the temperature field is evaluated, and the temperature deviation index between each temperature control area is defined and calculated to quantify the global equilibrium performance of the temperature control system. For the case of poor global equilibrium, the cause of the temperature unevenness is analyzed to provide a basis for the subsequent PID parameter optimization. For areas with high temperature, the corresponding PID parameters are appropriately reduced to reduce the cooling power; for areas with low temperature, the PID parameters are appropriately increased to enhance the heating effect. Through the adaptive adjustment of the partitioned PID parameters, the temperature of each temperature control area is more balanced, and the global performance of the temperature control system is improved. The partition temperature PID fine-tuning strategy is integrated into the three-dimensional structural temperature change distribution model, and the simulation verification of the closed-loop temperature control system is carried out. The simulation results are observed and analyzed to check whether the temperature deviation of each temperature control area is significantly improved and whether the global balance is improved. If local temperature imbalance still exists, the PID parameters are further optimized and adjusted until the global temperature field balance that meets the requirements is achieved. The optimized partition temperature PID fine-tuning strategy is applied to the actual test chamber temperature control system, and the actual operation test of the test chamber is carried out. The actual temperature changes of each temperature control area are measured and compared with the simulation results for analysis. Through long-term actual operation verification, it is ensured that the partition temperature PID fine-tuning strategy can stably and efficiently achieve global balanced control of the temperature field inside the test chamber.

[0098] Step S5: Use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models, and generate temperature control area cooling capacity prediction data; perform power optimization adjustment on the temperature control area cooling capacity prediction data, and build an energy consumption dynamic optimization strategy;

[0099] In this embodiment, the instantaneous refrigeration capacity demand of each temperature control area during the dynamic temperature control process is monitored. Based on the historical refrigeration capacity data, a time series prediction model, such as an ARIMA model, is used to predict the refrigeration capacity demand within a certain period of time in the future, and a future refrigeration capacity prediction curve of each temperature control area is generated to provide a basis for the subsequent energy consumption optimization strategy. The refrigeration capacity prediction curve of each temperature control area is analyzed to find out the key areas with high refrigeration capacity demand. For these key areas, local power adjustment measures are taken, such as appropriately increasing the compressor speed or increasing the number of refrigeration modules. Through the dynamic optimization and adjustment of the refrigeration power of the key areas, it is ensured that the refrigeration demand of each temperature control area is met, and the overall energy consumption is reduced as much as possible. The optimized refrigeration power allocation scheme is coupled with the partition temperature PID fine-tuning strategy of step S4 to construct an energy consumption dynamic optimization strategy based on refrigeration capacity prediction and power optimization, so as to realize real-time dynamic control of the overall energy consumption of the test box. The strategy can adaptively adjust the PID parameters and refrigeration power ratio of each temperature control area according to the real-time refrigeration demand changes, and minimize the energy consumption under the premise of meeting the temperature control requirements.

[0100] Step S6: Perform abnormal temperature diagnosis decision on the three-dimensional structure temperature change distribution model and build an abnormal temperature decision engine; perform neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and build a temperature intelligent control model to perform temperature parameter control.

[0101] In this embodiment, a reasonable temperature abnormality threshold is defined. Once the temperature of a certain area is detected to exceed the threshold, it is determined to be abnormal temperature. A decision tree algorithm or Bayesian classifier is used to build an abnormal temperature diagnosis decision engine. The engine can quickly determine which areas have abnormal conditions based on the temperature data given by the temperature distribution model. The abnormal temperature diagnosis result will be used as a feedback signal to provide a basis for subsequent intelligent temperature control. The three submodules are jointly optimized using an optimized metamorphic learning method based on a neural network. The goal of neural network learning is to minimize the overall energy consumption while minimizing the probability of abnormal temperature while meeting the temperature control requirements. Through a large amount of simulation training and field test data, the structure and parameters of the neural network are continuously optimized so that it can adaptively adjust the control strategy of each submodule. The optimized neural network model is integrated as the core component of the temperature intelligent control model. The model can autonomously diagnose temperature abnormalities based on temperature distribution monitoring data, and dynamically adjust the partition temperature PID parameters and refrigeration power ratio to achieve intelligent closed-loop control of temperature parameters.

[0102] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0103] Step S11: acquiring the real-time operating temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor node;

[0104] Step S12: Calculate the spatial position of the multi-sensor node to obtain the node spatial position coordinates;

[0105] Step S13: performing multi-position temperature calculation on the real-time working temperature parameters of the test box based on the node spatial position coordinates to obtain multiple node position temperature parameters;

[0106] Step S14: performing spatial temperature distribution analysis on temperature parameters at multiple node positions to obtain spatial temperature distribution data;

[0107] Step S15: performing multi-time-frequency decomposition processing on the temperature parameters of multiple node positions to obtain temperature change trajectories;

[0108] Step S16: dynamically rendering the temperature change trajectory distribution of the spatial temperature distribution data based on the temperature change trajectory to construct a dynamic temperature change distribution field.

[0109] In this embodiment, multiple temperature sensor nodes are deployed inside the test box to cover all key temperature control areas, and the temperature data detected by each sensor node in real time is collected to build a real-time temperature parameter data set of the test box. The three-dimensional structural model diagram of the test box is obtained or drawn to provide a reference for the subsequent spatial temperature distribution analysis. The specific coordinate position of each sensor node in the three-dimensional space is measured using the known test box structure diagram, and the spatial coordinate (x, y, z) information of each sensor node is recorded to build a spatial position database of the sensor node. For each sensor node coordinate position, the corresponding real-time temperature value is extracted, and the temperature data of each node position is summarized to form a multi-point real-time temperature parameter set of the test box. The three-dimensional test box structure model and multi-point temperature data are used to calculate the temperature through interpolation and other numerical calculations. The calculation method is used to infer the overall temperature distribution inside the test box, and a data set describing the three-dimensional spatial temperature distribution of the test box is generated, which provides a basis for the subsequent construction of a dynamic temperature change distribution field. The time-frequency analysis method (such as wavelet transform) is used for multi-scale decomposition, and the temperature change characteristics of each sensor node in the time domain and frequency domain are extracted. The node temperature change trajectory is constructed, and the time-frequency characteristics of the temperature change trajectory of each node are analyzed to provide a basis for the construction of a dynamic temperature change distribution field. Through dynamic rendering technology, the temperature change trajectories of various areas inside the test box are visualized in the three-dimensional temperature distribution field, and a dynamic temperature change distribution field is constructed, which intuitively reflects the evolution of the temperature inside the test box over time. The dynamic temperature change distribution field provides a visualized temperature change reference for the subsequent temperature control optimization strategy.

[0110] In this embodiment, the specific steps of step S15 are:

[0111] Perform time series temperature fitting identification on temperature parameters of multiple node positions to obtain a node time series temperature curve;

[0112] Perform temperature fluctuation analysis on the node timing temperature curve to obtain timing temperature change data;

[0113] Perform multi-time-frequency decomposition processing on the time-series temperature change data to obtain the temperature time-frequency domain; perform time-frequency period analysis on the temperature time-frequency domain to generate dynamic temperature change trend data;

[0114] The dynamic temperature change trend data is reconstructed through time series modeling to obtain the temperature change trajectory.

[0115] In this embodiment, a curve fitting algorithm (such as polynomial fitting, spline interpolation, etc.) is used to perform time series fitting on real-time temperature data of multiple nodes, and the temperature curve of each sensor node changing with time, that is, the node time series temperature curve, is obtained by fitting. The time series temperature curve of each node is analyzed to extract the temperature fluctuation characteristics, including the temperature average value, fluctuation amplitude, fluctuation frequency, etc. These temperature fluctuation characteristic parameters are organized into time series temperature change data, which lays the foundation for subsequent time-frequency analysis. Time-frequency analysis methods (such as short-time Fourier transform, wavelet transform, etc.) are used to perform multi-scale decomposition on the time series temperature change data to obtain the distribution characteristics of temperature changes in the time domain and frequency domain. Characteristics, that is, the time-frequency domain characteristics of temperature. The time-frequency domain characteristics can reflect the periodicity and transient characteristics of temperature changes, etc., and provide a basis for the subsequent dynamic temperature trend analysis. The main time-frequency components in the temperature time-frequency domain are analyzed, and the main periodic characteristics of temperature changes are identified. According to the time-frequency domain characteristics, the temperature change trend on different time scales is calculated. The dynamic temperature change trend data obtained is predictively modeled using time series modeling methods (such as ARIMA model, neural network, etc.). Through time series modeling, the temperature change trajectory reflecting the overall temperature change trend is fitted, and the temperature change trajectory can be used to describe the evolution law of the temperature inside the test chamber in time and space.

[0116] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0117] Step S21: performing component identification on the test box structure diagram to obtain test box component data;

[0118] Step S22: performing position layout analysis on the test box component data to obtain component position layout data;

[0119] Step S23: reconstructing the three-dimensional structure of the test box structure diagram based on the component position layout data to construct a three-dimensional structure model of the test box;

[0120] Step S24: performing three-dimensional interpolation mapping on the three-dimensional structural model of the test box based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model.

[0121] In this embodiment, computer vision technology (such as image segmentation, object detection, etc.) is used to analyze and identify the structural image of the test box, automatically extract and identify the various components in the test box, such as the shell, partition, heat sink, sensor, etc., and organize the type, size, material and other information of each identified component into a test box component database. According to the test box component data, the specific placement position and relative position relationship of each component in the test box are analyzed, and a spatial relationship model between the components is established to describe the specific position coordinates of each component in three-dimensional space. The position information of these components is organized into component position layout data for guiding the construction of a three-dimensional model. Computer-aided design (CAD) technology is used to reconstruct the three-dimensional structural model of the test box in the three-dimensional modeling software according to the component data and position information obtained in steps S21 and S22. The components are accurately assembled into the three-dimensional model according to the size, material and position layout information of the components to construct a complete three-dimensional structure of the test box. The three-dimensional structure is mapped to the three-dimensional structural model of the test box constructed in step S23 by three-dimensional interpolation, and the temperature distribution field of each area inside the test box is established to form a three-dimensional structural temperature variation distribution model that reflects the three-dimensional dynamic change of temperature. The temperature variation distribution model can intuitively display the temperature distribution status inside the test box and its time evolution process.

[0122] In this embodiment, reference Figure 4 The above is a schematic flow chart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0123] Step S31: performing fine-grained regional division processing on the three-dimensional structure temperature change distribution model to obtain multiple temperature control area models;

[0124] Step S32: quantifying the regional temperature difference of multiple temperature control area models to obtain temperature control area temperature difference data;

[0125] Step S33: predicting the temperature difference change trend of the temperature difference data of the temperature control area to generate regional temperature difference trend prediction data;

[0126] Step S34: making segmented temperature control decisions on the regional temperature difference trend prediction data to obtain a multi-step duty cycle temperature control strategy.

[0127] In this embodiment, according to the three-dimensional structural temperature change distribution model, the internal space of the test box is divided into multiple relatively independent temperature control areas. According to the positions of different components, the distribution of heat input sources and other factors, the internal area of ​​the test box is divided into fine-grained areas. Each temperature control area has its own temperature distribution characteristics, forming multiple local temperature control area models. This fine-grained area division is conducive to the subsequent formulation of targeted temperature control strategies, analyzing the temperature distribution inside each temperature control area, calculating the temperature difference between the highest temperature and the lowest temperature in the area, and organizing the temperature difference values ​​of each temperature control area into temperature control area temperature difference data, reflecting the temperature difference between different areas. The temperature difference data can intuitively reflect the temperature inside the test box. The unevenness of temperature distribution provides a basis for subsequent temperature difference prediction and temperature control optimization. Time series analysis, machine learning and other methods are used to model and predict the temperature difference data of the temperature control area. The temperature difference change trend between each temperature control area in the future is predicted, and the regional temperature difference trend prediction data is obtained. The time axis is divided into multiple control stages. According to the temperature difference prediction of each stage, different duty cycle temperature control schemes are adopted to form a time-varying, multi-stage duty cycle temperature control strategy to achieve refined control of the temperature distribution inside the test chamber. This temperature control strategy can adaptively adjust the heating / cooling power of each area to maintain the temperature distribution of the entire test chamber in an ideal state.

[0128] In this embodiment, step S4 includes the following steps:

[0129] Step S41: performing regional temperature state evaluation processing on multiple temperature control area models based on the temperature difference data of the temperature control areas to obtain high temperature state areas and low temperature state areas;

[0130] Step S42: performing a step response demand analysis on the high temperature state area to obtain step response demand data of the high temperature area;

[0131] Step S43: Based on the step response demand data of the high temperature area, a high duty cycle hyper-parameter control process is performed on the high temperature state area through a multi-step duty cycle temperature control strategy to obtain the high temperature area hyper-parameter control data;

[0132] Step S44: performing low duty cycle gentle regulation processing on the low temperature state area through a multi-step duty cycle temperature control strategy to generate low temperature area gentle regulation data;

[0133] Step S45: performing global balance analysis on the low temperature area gentle control data and the high temperature area hyperparameter control data to obtain global balance data of the temperature control area;

[0134] Step S46: Adaptively fine-tune the PID parameters of multiple temperature control zone models based on the global balance data of the temperature control zones, and construct a zone temperature PID fine-tuning strategy.

[0135] In this embodiment, the temperature time series data of each temperature control area is extracted, the temperature difference changes between different areas are analyzed, and it is identified which areas belong to the high temperature state area and which areas belong to the low temperature state area. The step response characteristics of their temperature to the control quantity (such as duty cycle) are analyzed, and the ideal step response curve required for the high temperature area is determined, including indicators such as response time and overshoot. As the goal of temperature control strategy optimization, the step response demand data of these high temperature areas are organized into a database to provide a basis for the subsequent design of multi-order duty cycle temperature control strategies. A multi-order duty cycle temperature control algorithm is used to design a hyper-parameter control strategy suitable for the high temperature area according to the determined step response requirements of the high temperature area. The optimal duty cycle control parameters required for the high temperature area, such as proportional coefficient, integral coefficient, etc., are determined by simulation optimization and other means. For the identified low temperature state area, the Different from the temperature control strategy in the high-temperature area, a multi-order duty cycle temperature control algorithm suitable for the low-temperature area is designed to achieve smooth and stable temperature regulation, determine the optimal duty cycle control parameters required for the low-temperature area, and generate smooth control data for the low-temperature area. The temperature control requirements of the high-temperature area and the low-temperature area are comprehensively considered, and the balance between the two is analyzed to ensure that the temperature control strategy can achieve temperature balance in the global range to avoid local overheating or overcooling. For possible local imbalance problems, the temperature control parameters are further optimized and adjusted to obtain the global balance data of the temperature control area, and the proportional, integral, and differential parameters of the PID controller are adaptively fine-tuned to ensure that the temperature control effects between different temperature control areas are coordinated and consistent, to achieve global temperature balance, and to construct a partitioned temperature PID fine-tuning strategy to provide a reliable control algorithm for the subsequent implementation of the actual temperature control system.

[0136] In this embodiment, step S5 includes the following steps:

[0137] Step S51: Calculate the target temperature of multiple temperature control area models using the zone temperature PID fine-tuning strategy to obtain the target temperature of the temperature control area;

[0138] Step S52: forecasting the cooling capacity demand for the target temperature of the temperature control area based on the temperature difference data of the temperature control area, and generating cooling capacity forecast data for the temperature control area;

[0139] Step S53: dynamically adjusting the temperature control loop power for the temperature control area cooling capacity prediction data to obtain loop power dynamic adjustment data;

[0140] Step S54: Optimize the power of multiple temperature control area models according to the loop power dynamic adjustment data to build a dynamic energy consumption optimization strategy.

[0141] In this embodiment, the target temperature is calculated for each temperature control area. According to the overall target temperature set by the user and the real-time temperature difference data of each area, the PID control algorithm is used to determine the target temperature value that each temperature control area should reach, and the cooling capacity required for each area is predicted. Considering factors such as heat exchange and heat conduction, the heat balance model is used to predict and calculate the cooling capacity, and the predicted cooling capacity data of the temperature control area are organized into a cooling capacity prediction database to provide a basis for subsequent dynamic power adjustment. In combination with the performance parameters of the temperature control equipment, the power input required for each area is calculated, and the power input of the temperature control loop is dynamically adjusted to ensure that the cooling capacity of each area can meet the target temperature requirements. The loop power dynamic adjustment data is generated, and the power changes of the temperature control loop at each moment are recorded to identify the temperature control areas with higher energy consumption. For these high energy consumption areas, the power input is further optimized and adjusted to minimize energy consumption while meeting the target temperature. A set of energy consumption dynamic optimization strategies is constructed, which can dynamically adjust the power input of each temperature control area according to the real-time temperature difference and cooling requirements to maximize energy utilization efficiency.

[0142] In this embodiment, step S6 includes the following steps:

[0143] Step S61: identifying abnormal temperature areas on the three-dimensional structure temperature change distribution model to generate abnormal temperature areas;

[0144] Step S62: accurately locate the fault in the abnormal temperature area and generate an abnormal temperature fault point;

[0145] Step S63: making abnormal temperature diagnosis decisions for abnormal temperature fault points and building an abnormal temperature decision engine;

[0146] Step S64: Perform neural network optimization and transformation learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy to build a temperature intelligent control model to execute temperature parameter control.

[0147] In this embodiment, based on the three-dimensional temperature change distribution model, the temperature field inside the entire test box is monitored and analyzed in real time, and the abnormal detection algorithm is used to identify areas with significant deviations from the normal temperature distribution, namely abnormal temperature areas. These abnormal temperature areas may be caused by equipment failure, uneven distribution of cold and heat sources, etc. The position and temperature information of the identified abnormal temperature areas are recorded to provide a basis for subsequent fault location. For the identified abnormal temperature areas, the specific fault points that cause these anomalies are further located. The multi-sensor data fusion technology is used in combination with physical models such as heat conduction and heat convection to accurately analyze the causes of the abnormal temperature areas, locate the specific equipment failure points or heat source positions that cause local temperature anomalies, generate the position information of the abnormal temperature failure points, and combine the abnormal temperature failure Based on the analysis of the fault points, the expert experience knowledge is used to build an abnormal temperature diagnosis decision model. The model can quickly determine the type and severity of the fault according to the temperature change characteristics and location information of the fault point, and propose corresponding treatment measures, such as starting the backup equipment and adjusting the cooling capacity. The established abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy are integrated into an overall temperature intelligent control model. The neural network is used to optimize the metamorphic learning technology to continuously optimize and adjust these strategies and models so that they can better adapt to the actual operating environment. Through continuous machine learning and intelligent optimization, a complete set of temperature intelligent control model is constructed. The model can independently perform temperature partition control, energy consumption optimization and fault diagnosis according to real-time monitoring data, so as to realize intelligent control of the test chamber temperature.

[0148] In this embodiment, the specific steps of step S63 are:

[0149] Get the historical operation log of the test chamber;

[0150] Based on the historical operation log of the test chamber, fault diagnosis and identification are performed on the abnormal temperature fault point to obtain the fault factor of the fault point; the fault factor of the fault point includes overtemperature of the fault point, abnormal electrical parameters and speed limit of the test chamber circuit;

[0151] When the fault factor of the fault point is overtemperature of the fault point, a fault judgment is performed on the sensor node of the fault point. When the sensor node of the fault point is normal, an emergency power-off process is performed and a power-off warning signal is generated;

[0152] When the sensor node at the fault point is abnormal, a signal fault warning is performed on the sensor node at the fault point to obtain a sensor fault signal;

[0153] When the fault factor of the fault point is abnormal electrical parameters, the line load is optimized for the abnormal temperature fault point to generate load optimization diagnostic data;

[0154] When the fault factor of the fault point is the speed limit of the test box circuit, the abnormal operation parameters of the motor are identified based on the historical operation log of the test box to obtain the abnormal operation data of the motor;

[0155] Make abnormal fault diagnosis decisions based on power outage warning signals, sensor fault signals, load optimization diagnosis data, and motor abnormal operation data, and build an abnormal temperature decision engine.

[0156] In this embodiment, various log data generated by the test box during the previous operation process are collected and analyzed, including various operating indicators such as temperature, electrical parameters, and speed. Data mining and fault diagnosis algorithms are used to deeply analyze historical operation log data, identify fault points that cause abnormal temperatures, and determine the main factors causing these faults. For over-temperature fault points, check whether its sensor nodes are abnormal. If the sensor nodes are normal, emergency power-off processing is immediately performed to generate a power-off warning signal. If the sensor nodes are abnormal, a sensor fault warning signal is issued. Line load analysis and optimization are performed on the fault points that cause abnormal temperatures, and corresponding load optimization diagnostic data are generated to provide a basis for subsequent decision-making. According to historical operation logs, abnormal motor operating parameters are identified, and these motor abnormal operation data are recorded for fault diagnosis decisions. The aforementioned various abnormal fault diagnosis data, including power-off warning signals, sensor fault signals, load optimization diagnostic data, motor abnormal operation data, etc., are integrated. Expert systems or machine learning methods are used to construct an abnormal temperature decision engine that can quickly determine the fault type and provide treatment measures based on these diagnostic data. The decision engine provides important support for subsequent intelligent temperature control.

[0157] In this embodiment, a temperature parameter control system of a new energy motor bench test box is provided, which is used to execute the temperature parameter control method of the new energy motor bench test box as described above, including:

[0158] The temperature change distribution module is used to obtain the real-time working temperature parameters of the test chamber and the structure diagram of the test chamber based on multiple sensor nodes; obtain the spatial temperature distribution data based on the real-time working temperature parameters of the test chamber; dynamically render the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field;

[0159] The three-dimensional interpolation module is used to perform position layout analysis on the test chamber structure diagram to obtain component position layout data; perform three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model;

[0160] The duty cycle temperature control module is used to obtain multiple temperature control area models based on the three-dimensional structure temperature change distribution model; perform segmented temperature control decisions on multiple temperature control area models to obtain multi-order duty cycle temperature control strategies;

[0161] The adaptive fine-tuning module is used to perform global balance analysis on multiple temperature control area models through multi-step duty cycle temperature control strategies to obtain global balance data of the temperature control areas; based on the global balance data of the temperature control areas, the PID parameters are adaptively fine-tuned to build a partition temperature PID fine-tuning strategy;

[0162] The power optimization module is used to use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models and generate the cooling capacity prediction data of the temperature control area; perform power optimization adjustment on the cooling capacity prediction data of the temperature control area and build a dynamic energy consumption optimization strategy;

[0163] The intelligent control module is used to make abnormal temperature diagnosis decisions on the three-dimensional structural temperature change distribution model and build an abnormal temperature decision engine; it performs neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and builds a temperature intelligent control model to execute temperature parameter control.

[0164] The present invention deploys multiple temperature sensors inside the test box to obtain real-time temperature data at various positions inside the test box, laying a foundation for subsequent temperature distribution modeling. Based on the collected temperature data, the temperature change trajectory inside the test box is dynamically rendered to construct a model that truly reflects the dynamic temperature field distribution. This dynamic and visualized temperature distribution field can more clearly reflect the transfer and change rules of temperature in the test box. Such a temperature distribution model provides a reliable reference basis for the subsequent precise temperature control strategy formulation, which helps to better understand the heat conduction and distribution characteristics of the test box. The two-dimensional temperature distribution field data is combined with the three-dimensional structural layout information of the test box to be mapped to a three-dimensional temperature change distribution model. This three-dimensional temperature change model The model not only retains the dynamic characteristics of temperature distribution, but also integrates the spatial information of the test chamber structure, making the corresponding relationship between the temperature change law and the specific component position more intuitive and clear. Based on this three-dimensional temperature change model, the temperature change of each part is analyzed more finely, and the heat transfer mechanism in the test chamber is deeply understood, laying the foundation for the subsequent regional temperature control. Through the analysis of the three-dimensional temperature change distribution model, the test chamber is divided into several relatively independent temperature control areas, each area has different temperature change characteristics. According to the temperature characteristics of different areas, a personalized multi-stage duty cycle temperature control strategy is formulated to achieve the temperature target of each area more accurately. Compared with the simple single temperature control strategy, the multi-stage duty cycle strategy can better adapt to the complex internal temperature of the test chamber. Complex temperature field distribution, improve the accuracy of temperature control, through the global balance analysis of the temperature control area of ​​the entire test chamber, dynamically adjust the PID control parameters of each area, ensure that the overall temperature field maintains a good balance state, adaptive adjustment of PID parameters can respond to changes in the temperature field inside the test chamber in a timely manner, continuously optimize the temperature control effect, and improve the stability and accuracy of control. Compared with the solution with fixed PID parameters, this adaptive adjustment strategy better adapts to the temperature change characteristics of the test chamber under different working conditions. Based on the prediction of the cooling capacity demand of each temperature control area, the power output of the refrigeration system is optimized and adjusted in real time. Under the premise of meeting the temperature control requirements, energy consumption is minimized. This dynamic energy consumption optimization strategy can be based on the actual temperature of the test chamber. The temperature load condition dynamically adjusts the working state of the refrigeration system, avoiding energy waste under the traditional constant power output mode. Through energy consumption optimization, it not only saves the operating cost of the test chamber, but also contributes positively to environmental protection, embodies the concept of high efficiency and energy saving, builds an abnormal temperature decision engine, automatically detects and diagnoses abnormal temperatures inside the test chamber, and provides a basis for subsequent troubleshooting and system maintenance. The optimization learning of the control strategy is completed by the neural network model, so that the entire temperature control system has the ability to continuously adapt, and can be continuously optimized and improved as the usage changes. This intelligent temperature control model greatly improves the autonomy and robustness of the temperature parameter regulation of the test chamber, and enhances the reliability and adaptability of the system.

[0165] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0166] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A temperature parameter control method for a new energy motor bench test box, characterized in that: The following steps are involved: Step S1: obtaining the real-time working temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor nodes; obtaining the spatial temperature distribution data based on the real-time working temperature parameters of the test box; dynamically rendering the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field; Step S2: Performing a position layout analysis on the test box structure diagram to obtain component position layout data; performing three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model; Step S3: obtaining multiple temperature control area models based on the three-dimensional structure temperature change distribution model; performing segmented temperature control decisions on the multiple temperature control area models to obtain a multi-step duty cycle temperature control strategy; The multi-stage duty cycle temperature control strategy is specifically: dividing the time axis into multiple control stages, and adopting different duty cycle temperature control schemes according to the temperature difference prediction of each stage, forming a time-varying, multi-stage duty cycle temperature control strategy to achieve refined control of the temperature distribution inside the test chamber. Step S4: performing global balance analysis on multiple temperature control area models through a multi-step duty cycle temperature control strategy to obtain global balance data of the temperature control areas; Based on the global balance data of the temperature control area, the PID parameters are adaptively fine-tuned to build a zone temperature PID fine-tuning strategy; The global balance analysis specifically includes: comprehensively considering the temperature control requirements of high temperature areas and low temperature areas, analyzing the balance between the two, ensuring that the temperature control strategy can achieve temperature balance in the global range, and avoiding local overheating or overcooling; the global balance data of the temperature control area specifically includes: avoiding local overheating or overcooling, and further optimizing the adjustment temperature control parameters for possible local imbalance problems; Step S5: Use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models, and generate temperature control area cooling capacity prediction data; perform power optimization adjustment on the temperature control area cooling capacity prediction data, and build an energy consumption dynamic optimization strategy; Step S6: Perform abnormal temperature diagnosis decision on the three-dimensional structure temperature change distribution model and build an abnormal temperature decision engine; perform neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and build a temperature intelligent control model to perform temperature parameter control.

2. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: acquiring the real-time operating temperature parameters of the test box and the structure diagram of the test box based on the multi-sensor node; Step S12: Calculate the spatial position of the multi-sensor node to obtain the node spatial position coordinates; Step S13: performing multi-position temperature calculation on the real-time working temperature parameters of the test box based on the node spatial position coordinates to obtain multiple node position temperature parameters; Step S14: performing spatial temperature distribution analysis on temperature parameters at multiple node positions to obtain spatial temperature distribution data; Step S15: performing multi-time-frequency decomposition processing on the temperature parameters of multiple node positions to obtain temperature change trajectories; Step S16: dynamically rendering the temperature change trajectory distribution of the spatial temperature distribution data based on the temperature change trajectory to construct a dynamic temperature change distribution field.

3. The temperature parameter control method of the new energy motor bench test box according to claim 2 is characterized in that: The specific steps of step S15 are: Perform time series temperature fitting identification on temperature parameters of multiple node positions to obtain a node time series temperature curve; Perform temperature fluctuation analysis on the node timing temperature curve to obtain timing temperature change data; Perform multi-time-frequency decomposition on the time series temperature change data to obtain the temperature time-frequency domain; Perform time-frequency period analysis on the temperature time-frequency domain to generate dynamic temperature change trend data; The dynamic temperature change trend data is reconstructed through time series modeling to obtain the temperature change trajectory.

4. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: performing component identification on the test box structure diagram to obtain test box component data; Step S22: performing position layout analysis on the test box component data to obtain component position layout data; Step S23: reconstructing the three-dimensional structure of the test box structure diagram based on the component position layout data to construct a three-dimensional structure model of the test box; Step S24: performing three-dimensional interpolation mapping on the three-dimensional structural model of the test box based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model.

5. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: performing fine-grained regional division processing on the three-dimensional structure temperature change distribution model to obtain multiple temperature control area models; Step S32: quantifying the regional temperature difference of multiple temperature control area models to obtain temperature control area temperature difference data; Step S33: predicting the temperature difference change trend of the temperature difference data of the temperature control area to generate regional temperature difference trend prediction data; Step S34: making segmented temperature control decisions on the regional temperature difference trend prediction data to obtain a multi-step duty cycle temperature control strategy.

6. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: performing regional temperature state evaluation processing on multiple temperature control area models based on the temperature difference data of the temperature control areas to obtain high temperature state areas and low temperature state areas; Step S42: performing a step response demand analysis on the high temperature state area to obtain step response demand data of the high temperature area; Step S43: Based on the step response demand data of the high temperature area, a high duty cycle hyper-parameter control process is performed on the high temperature state area through a multi-step duty cycle temperature control strategy to obtain the high temperature area hyper-parameter control data; Step S44: performing low duty cycle gentle regulation processing on the low temperature state area through a multi-step duty cycle temperature control strategy to generate low temperature area gentle regulation data; Step S45: performing global balance analysis on the low temperature area gentle control data and the high temperature area hyperparameter control data to obtain global balance data of the temperature control area; Step S46: Adaptively fine-tune the PID parameters of multiple temperature control zone models based on the global balance data of the temperature control zones, and construct a zone temperature PID fine-tuning strategy.

7. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: Calculate the target temperature of multiple temperature control area models using the zone temperature PID fine-tuning strategy to obtain the target temperature of the temperature control area; Step S52: forecasting the cooling capacity demand for the target temperature of the temperature control area based on the temperature difference data of the temperature control area, and generating cooling capacity forecast data for the temperature control area; Step S53: dynamically adjusting the temperature control loop power for the temperature control area cooling capacity prediction data to obtain loop power dynamic adjustment data; Step S54: Optimize and adjust the power of multiple temperature control area models according to the loop power dynamic adjustment data to build a dynamic optimization strategy for energy consumption.

8. The temperature parameter control method of the new energy motor bench test box according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: identifying abnormal temperature areas on the three-dimensional structure temperature change distribution model to generate abnormal temperature areas; Step S62: accurately locate the fault in the abnormal temperature area and generate an abnormal temperature fault point; Step S63: making abnormal temperature diagnosis decisions for abnormal temperature fault points and building an abnormal temperature decision engine; Step S64: Perform neural network optimization and transformation learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy to build a temperature intelligent control model to execute temperature parameter control.

9. The temperature parameter control method of the new energy motor bench test box according to claim 8 is characterized in that: The specific steps of step S63 are: Get the historical operation log of the test chamber; Based on the historical operation log of the test chamber, fault diagnosis and identification are performed on the abnormal temperature fault point to obtain the fault factor of the fault point; the fault factor of the fault point includes overtemperature of the fault point, abnormal electrical parameters and speed limit of the test chamber circuit; When the fault factor of the fault point is overtemperature of the fault point, a fault judgment is performed on the sensor node of the fault point. When the sensor node of the fault point is normal, an emergency power-off process is performed and a power-off warning signal is generated; When the sensor node at the fault point is abnormal, a signal fault warning is performed on the sensor node at the fault point to obtain a sensor fault signal; When the fault factor of the fault point is abnormal electrical parameters, the line load is optimized for the abnormal temperature fault point to generate load optimization diagnostic data; When the fault factor of the fault point is the speed limit of the test box circuit, the abnormal operation parameters of the motor are identified based on the historical operation log of the test box to obtain the abnormal operation data of the motor; Make abnormal fault diagnosis decisions based on power outage warning signals, sensor fault signals, load optimization diagnosis data, and motor abnormal operation data, and build an abnormal temperature decision engine.

10. A temperature parameter control system for a new energy motor bench test box, characterized in that: The method for controlling the temperature parameters of the new energy motor test bench according to claim 1 comprises: The temperature change distribution module is used to obtain the real-time working temperature parameters of the test chamber and the structure diagram of the test chamber based on multiple sensor nodes; obtain the spatial temperature distribution data based on the real-time working temperature parameters of the test chamber; dynamically render the change trajectory distribution of the spatial temperature distribution data to construct a dynamic temperature change distribution field; The three-dimensional interpolation module is used to perform position layout analysis on the test chamber structure diagram to obtain component position layout data; perform three-dimensional interpolation mapping on the component position layout data based on the dynamic temperature change distribution field to obtain a three-dimensional structural temperature change distribution model; The duty cycle temperature control module is used to obtain multiple temperature control area models based on the three-dimensional structure temperature change distribution model; perform segmented temperature control decisions on multiple temperature control area models to obtain multi-order duty cycle temperature control strategies; The adaptive fine-tuning module is used to perform global balance analysis on multiple temperature control area models through multi-step duty cycle temperature control strategies to obtain global balance data of the temperature control areas; based on the global balance data of the temperature control areas, the PID parameters are adaptively fine-tuned to build a partition temperature PID fine-tuning strategy; The power optimization module is used to use the zone temperature PID fine-tuning strategy to predict the cooling capacity demand of multiple temperature control area models and generate the cooling capacity prediction data of the temperature control area; perform power optimization adjustment on the cooling capacity prediction data of the temperature control area and build a dynamic energy consumption optimization strategy; The intelligent control module is used to make abnormal temperature diagnosis decisions on the three-dimensional structural temperature change distribution model and build an abnormal temperature decision engine; it performs neural network optimization and structural learning processing on the abnormal temperature decision engine, energy consumption dynamic optimization strategy and partition temperature PID fine-tuning strategy, and builds a temperature intelligent control model to execute temperature parameter control.

Images