An intelligent high-temperature power supply temperature monitoring method and system

Abstract

The present invention relates to the technical field of power supply temperature anomaly recognition, and particularly to an intelligent high-temperature power supply temperature monitoring method and system. The method includes the following steps: obtaining temperature data of a power supply module; performing temperature heat dissipation processing and temperature change processing on the basis of the temperature data of the power supply module to obtain power supply module temperature heat dissipation data and power supply module temperature change data; performing a power supply module temperature heat dissipation anomaly determination based on the power supply module temperature heat dissipation data to obtain temperature heat dissipation anomaly data; performing a power supply module temperature change anomaly determination based on the power supply module temperature change data to obtain temperature change anomaly data; constructing a temperature anomaly curve based on the temperature heat dissipation anomaly data and the temperature change anomaly data to obtain temperature anomaly curve data for assisting in the operation of high-temperature power supply temperature monitoring. The present invention improves the accuracy of temperature anomaly determination, reduces false alarms and missed alarms based on temperature volatility analysis, heat transfer lag calculation, and time series prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply temperature anomaly identification, and particularly to an intelligent high-temperature power supply temperature monitoring method and system. Background Art

[0002] Power supply modules operating in high-temperature environments (such as industrial control systems, power electronics equipment, new energy battery management systems (BMS), server data centers, aerospace electronic equipment, etc.) have extremely strict requirements for temperature management. The temperature control of power supply modules not only affects their operating efficiency but also directly determines their reliability and service life. However, existing temperature monitoring methods have obvious deficiencies in the following aspects. Existing methods usually adopt a temperature acquisition strategy at fixed intervals, unable to perceive rapid temperature fluctuations in real time, lacking dynamic analysis of temperature change trends, and easily missing the precursor stage of anomalies, resulting in low heat dissipation management efficiency and lagging anomaly identification, making it difficult to meet the requirements of complex working environments. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes an intelligent high-temperature power supply temperature monitoring method and system to solve at least one of the above technical problems.

[0004] The present application provides an intelligent high-temperature power supply temperature monitoring method, including the following steps:

[0005] Step S1: Obtain power supply module temperature data;

[0006] Step S2: Perform temperature heat dissipation processing and temperature change processing on the power supply module temperature data to obtain power supply module temperature heat dissipation data and power supply module temperature change data;

[0007] Step S3: Judge the power supply module temperature heat dissipation anomaly based on the power supply module temperature heat dissipation data to obtain temperature heat dissipation anomaly data;

[0008] Step S4: Judge the power supply module temperature change anomaly based on the power supply module temperature change data to obtain temperature change anomaly data;

[0009] Step S5: Construct a temperature anomaly curve based on the temperature heat dissipation anomaly data and the temperature change anomaly data to obtain temperature anomaly curve data for assisting in high-temperature power supply temperature monitoring operations.

[0010] In the present invention, by measuring the temperature at the center and multiple points on the edge, the overall temperature distribution of the power module can be more accurately reflected, avoiding the error of single-point acquisition. The heat conduction capacity of the power module is calculated through the heat flux density model to identify the parts with insufficient heat dissipation, facilitating the optimization of the heat dissipation design. Combining with the temperature gradient analysis, the abnormal heat dissipation area is found to reduce the risk of local overheating. The heat dissipation performance is monitored in real time. When it is found that the temperature continues to rise but the heat dissipation power fails to increase correspondingly, the system can immediately give an alarm to prevent equipment damage caused by poor heat dissipation. By using the rate of change analysis, abnormal situations such as rapid temperature rise or fall can be identified, preventing equipment overheating or cooling failure caused by factors such as current fluctuations and abnormal loads. By comprehensively analyzing the abnormal data of temperature heat dissipation and the abnormal data of temperature change, a dynamic abnormal curve is constructed, which can not only identify the current abnormality but also predict future temperature abnormalities, thus realizing early warning and improving the operation and maintenance efficiency.

[0011] Preferably, step S1 is specifically as follows:

[0012] Step S11: Control the temperature sensor preset at the center position of the power module to collect the temperature of the power module, and obtain the central temperature data of the power module;

[0013] Step S12: Control the temperature sensor preset at the edge position of the power module to collect the temperature of the power module, and obtain the edge temperature data of the power module;

[0014] Step S13: Construct a spatial matrix for the central temperature data and the edge temperature data of the power module to obtain the temperature data of the power module.

[0015] In the present invention, a dual temperature sensor layout of the center + edge is adopted, which can simultaneously obtain the temperature information of the core components and the peripheral area, avoiding data errors caused by single-point monitoring. The central temperature data can reflect the heat load conditions of the power core components (such as power modules, converters), and the edge temperature data can evaluate the efficiency of the heat dissipation system to ensure a comprehensive grasp of the temperature status. By constructing a spatial matrix model, the temperature gradient distribution can be analyzed more precisely, improving the reliability of temperature monitoring.

[0016] Preferably, step S2 is specifically as follows:

[0017] Step S21: Perform temperature heat dissipation rate processing on the temperature data of the power module to obtain temperature heat dissipation rate data;

[0018] Step S22: Construct a spatial gradient map for the temperature heat dissipation rate data to obtain the temperature heat dissipation data of the power module;

[0019] Step S23: Perform a central-edge heat accumulation effect simulation based on the temperature heat dissipation data and the temperature data of the power module to obtain central-edge heat accumulation effect data;

[0020] Step S24: Perform temperature constant change calculation based on the central edge heat accumulation effect data to obtain the power supply module temperature change data.

[0021] In the present invention, the traditional method usually only monitors the temperature value, while this method dynamically evaluates the heat dissipation performance by calculating the temperature dissipation rate (i.e., the rate of temperature decrease over time). The sliding window calculation is adopted to smooth the dissipation rates in different time periods, identify the trend changes of the heat dissipation efficiency, and improve the data stability. If the dissipation rate shows an abnormal decrease (for example, the temperature remains high for a long time and cannot be effectively reduced), the system gives an early warning of heat dissipation failure, such as heat dissipation fan failure, cooling system efficiency decline, etc. Based on the temperature dissipation rate data, a spatial gradient map is constructed to analyze the heat dissipation capabilities of different regions. The heat conduction equation is used to calculate the heat flow situation and form a temperature distribution map to more accurately identify the regions of local overheating or insufficient heat dissipation. Combining with heat flow modeling, the heat accumulation situation inside the power supply module is simulated to predict whether there is a risk of continuous overheating. Compared with the traditional static temperature control strategy, this method can predict the temperature change trend, provide intelligent temperature control decisions, and improve the efficiency of temperature control management.

[0022] Preferably, step S3 is specifically as follows:

[0023] Step S31: Judge the abnormal heat dissipation of material properties according to the power supply module temperature dissipation data to obtain the abnormal heat dissipation data of material properties;

[0024] Step S32: Perform environmental temperature and humidity heat dissipation influence correction according to the abnormal heat dissipation data of material properties and the power supply module temperature dissipation data to obtain the environmental temperature and humidity heat dissipation correction data;

[0025] Step S33: Perform heat transfer medium interaction processing according to the environmental temperature and humidity heat dissipation correction data to obtain the abnormal temperature dissipation data.

[0026] In the present invention, the actual heat dissipation rate is calculated and compared with the theoretical heat dissipation rate. If the deviation is too large, it indicates that the material is aged, damaged or polluted (such as dust accumulation on the heat sink). The present invention introduces temperature and humidity correction to ensure accurate evaluation of heat dissipation abnormalities under different environmental conditions. Humidity affects the heat capacity and thermal conductivity of air. High humidity reduces the heat dissipation ability of air and even causes condensation phenomena that affect the power supply module. Through the environmental temperature and humidity heat dissipation influence correction, the dynamic adaptability is improved. Different heat transfer media (such as air, liquid coolant) have different heat dissipation characteristics, and deeper heat dissipation abnormality judgment is carried out according to the heat transfer medium interaction.

[0027] Preferably, step S4 is specifically as follows:

[0028] Step S41: Judge the abnormal temperature change of material properties according to the power supply module temperature change data to obtain the abnormal material temperature change data;

[0029] Step S42: Perform temperature, humidity and heat dissipation correction according to the abnormal temperature change data of the material to obtain the abnormal temperature change data.

[0030] The present invention improves the accuracy of abnormality detection based on parameters such as material thermal expansion coefficient and thermal conductivity, and adopts temperature and humidity correction to improve the accuracy of temperature anomaly detection under different environmental conditions.

[0031] Preferably, step S5 is specifically:

[0032] Step S51: constructing an abnormal curve according to the temperature heat dissipation abnormal data and the temperature change abnormal data to obtain abnormal curve data;

[0033] Step S52: Acquire standard power module temperature data;

[0034] Step S53: constructing a temperature curve according to the standard power module temperature data to obtain temperature curve data;

[0035] Step S54: extracting similarities and differences based on the abnormal curve data and the temperature curve data to obtain the temperature abnormal curve data to perform auxiliary work for high-temperature power supply temperature monitoring.

[0036] In the present invention, the temperature data of the power module under normal working conditions is selected to construct a standard curve. Hierarchical modeling is adopted to generate corresponding standard temperature curves for different ambient temperatures and different load conditions, so as to make a more accurate comparison. Historical data fitting (such as polynomial regression and Bayesian optimization) is adopted to improve the accuracy of the standard curve. As a reference benchmark for temperature anomaly analysis, it can be used to evaluate whether the current temperature curve is normal. Combined with the dynamic comparison mechanism, the appropriate standard curve is selected under different working conditions to improve the accuracy of anomaly detection. Traditional methods can often only provide a judgment of "whether it is abnormal", while this method can accurately analyze the type, severity and possible causes of the anomaly by extracting similarities and differences in features.

[0037] Preferably, the temperature heat dissipation rate processing is specifically as follows:

[0038] Performing heat dissipation rate processing of the original area temperature according to the temperature data of the power module to obtain first temperature heat dissipation rate data;

[0039] Perform cross-region temperature heat dissipation rate processing according to the power module temperature data to obtain cross-region temperature heat dissipation rate data;

[0040] The heat flow simulation of the heat dissipation medium is performed according to the cross-region temperature heat dissipation rate data to obtain the second temperature heat dissipation rate data.

[0041] In the present invention, traditional heat dissipation monitoring mainly focuses on overall temperature changes. However, the present invention conducts independent heat dissipation rate analysis for local areas of the power module (such as power modules, heat sinks, air ducts, etc.), improving the accuracy of local heat dissipation monitoring. For example, the temperature of power components in the power module changes faster than that in the heat sink area. Analyzing the heat dissipation rate in this area can identify hot spots in advance. Traditional methods are difficult to accurately analyze the heat flow between different regions, while this method can provide more accurate cross-region temperature heat dissipation data by calculating the heat dissipation rate across regions. If the temperature drop rate in a certain area is slower than that in the adjacent area, it represents heat retention in this area, and it is judged that the heat dissipation design needs to be optimized. From this perspective, a more refined data view is provided. Based on heat flow simulation (such as CFD computational fluid dynamics simulation), by simulating the heat flow of the heat dissipation medium, the heat transfer path can be more accurately optimized, improving the heat dissipation efficiency.

[0042] Preferably, the central-edge heat accumulation effect simulation is specifically as follows:

[0043] Extract the volatility characteristics from the temperature data of the power module to obtain temperature volatility characteristic data;

[0044] Calculate the central-edge temperature transfer lag based on the temperature volatility characteristic data to obtain central-edge lag coefficient data;

[0045] Perform heat balance processing based on the central-edge lag coefficient data and the temperature heat dissipation data of the power module to obtain power module heat balance data;

[0046] Calculate the heat accumulation effect based on the power module heat balance data and the temperature heat dissipation data of the power module to obtain central-edge heat accumulation effect data.

[0047] In the present invention, by extracting temperature fluctuation characteristics, short-term temperature anomalies, sudden temperature rises, and long-term temperature fluctuations can be identified, improving the anomaly detection ability. There is a lag effect in the heat transfer from the center to the edge of the power module. If the lag time is too long, heat accumulation will occur, reducing the heat dissipation efficiency. By analyzing the temperature fluctuation characteristics, the sensitivity of temperature anomaly detection is improved, ensuring that the heat dissipation system can accurately respond to short-term and long-term temperature changes. This method optimizes the heat transfer process by calculating the center-edge temperature lag coefficient, and improves the ability to optimize the heat dissipation path by calculating the temperature transfer lag, ensuring that heat can be evenly diffused and preventing local heat accumulation. The present invention achieves the accuracy of central-edge heat accumulation effect simulation through heat balance processing, thereby providing accurate data support. According to the heat accumulation effect calculation, the heat distribution can be predicted and optimized, preventing local overheating and improving the long-term stability of the equipment.

[0048] Preferably, the central-edge temperature transfer lag calculation is specifically as follows:

[0049] Perform central peak-valley calculation and edge peak-valley calculation based on the temperature volatility characteristic data to obtain central peak-valley data and edge peak-valley data respectively;

[0050] Obtain power supply heat dissipation data, where the power supply heat dissipation data includes power supply heat dissipation position data and power supply heat dissipation power data;

[0051] Calculate the heat dissipation effect lag time for the temperature position data corresponding to the power module temperature data according to the power supply heat dissipation data to obtain heat dissipation effect time coefficient data;

[0052] Select the adjacent peak-valley transfer influence for the central peak-valley data and the edge peak-valley data according to the heat dissipation effect time coefficient data to obtain adjacent peak-valley transfer data;

[0053] Calculate the lag coefficient according to the adjacent peak-valley transfer data to obtain the central-edge temperature transfer lag data.

[0054] In the present invention, by calculating the peak-valley data of the center and the edge, the periodicity, amplitude and time delay of temperature fluctuations can be accurately monitored, improving the accuracy of temperature anomaly detection. There is a time lag for heat to spread from the center to the edge of the power module. By calculating the heat dissipation effect time coefficient, the heat dissipation effect can be more accurately reflected. Traditional heat dissipation management strategies do not consider the transfer relationship between temperature peaks and valleys, which easily leads to overcooling or insufficient heat dissipation. Or, traditional temperature control methods only focus on single-point temperature over-limit alarms or overall temperature mean analysis, ignoring the time transfer relationship between peaks and valleys. This method constructs a mathematical model by calculating the peak-valley time difference, transfer amplitude ratio, and similarity distribution between the central temperature and the edge temperature, accurately calculates the lag coefficient, making the temperature control more precise and the heat dissipation system more intelligent. The present invention accurately depicts the temperature response delay between the center and the edge of the power module, deeply reflects the heat transfer path, and improves the accuracy and dynamic adaptability of heat dissipation anomaly judgment.

[0055] Preferably, the present invention also provides an intelligent high-temperature power supply temperature monitoring system for executing the intelligent high-temperature power supply temperature monitoring method as described above. The intelligent high-temperature power supply temperature monitoring system includes:

[0056] A power module temperature data acquisition module for obtaining power module temperature data;

[0057] A power module temperature analysis module for performing temperature heat dissipation processing and temperature change processing on the power module temperature data to obtain power module temperature heat dissipation data and power module temperature change data;

[0058] A power module temperature heat dissipation anomaly judgment module for judging the power module temperature heat dissipation anomaly according to the power module temperature heat dissipation data to obtain temperature heat dissipation anomaly data;

[0059] A power module temperature change anomaly judgment module, which is used to judge the anomaly of the power module temperature change according to the power module temperature change data, and obtain the temperature change anomaly data;

[0060] A temperature anomaly curve construction module, which is used to construct a temperature anomaly curve according to the temperature heat dissipation anomaly data and the temperature change anomaly data, and obtain the temperature anomaly curve data for auxiliary operation of high-temperature power supply temperature monitoring.

[0061] The beneficial effects of the present invention are as follows: By combining the central position temperature data and the edge temperature data to construct a spatial temperature matrix, local temperature hotspots, heat dissipation paths, and overall temperature distributions can be accurately captured. By calculating the local area temperature heat dissipation rate and the cross-area temperature heat dissipation rate, the heat dissipation efficiency of different parts can be analyzed, and high-temperature accumulation areas can be accurately identified. Combining thermal fluid simulation (CFD) to optimize the heat dissipation path of the air-cooled or liquid-cooled system, improve heat dissipation uniformity, and avoid local overheating problems. By analyzing parameters such as the thermal conductivity, thermal expansion coefficient, and specific heat capacity of the power module material, heat dissipation anomalies caused by material aging or deformation can be identified. Combining temperature and humidity compensation calculations to avoid misjudgment caused by changes in environmental temperature or humidity and improve the accuracy of anomaly judgment. Through anomaly curve modeling, the long-term characteristics of temperature heat dissipation anomalies and temperature change anomalies can be comprehensively analyzed, and the visualization of temperature anomaly trends can be realized. By comparing with the standard temperature curve, it can be identified whether the current temperature curve deviates from the normal working range, and the accuracy of anomaly judgment can be improved. Description of the Drawings

[0062] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes, and advantages of the present application will become more obvious:

[0063] Figure 1 Shows the step flow chart of a method for monitoring the temperature of an intelligent high-temperature power supply according to an embodiment;

[0064] Figure 2 Shows the step flow chart of a method for collecting power module temperature data according to an embodiment;

[0065] Figure 3 Shows the step flow chart of a method for analyzing the temperature of a power module according to an embodiment;

[0066] Figure 4 Shows the step flow chart of a method for judging the anomaly of power module temperature heat dissipation according to an embodiment;

[0067] Figure 5 Shows the step flow chart of a method for constructing a temperature anomaly curve according to an embodiment. Detailed Embodiments

[0068] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative work belong to the scope of protection of the present invention.

[0069] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0070] It should be understood that although terms such as "first" and "second" may be used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0071] Please refer to Figures 1 to 5 , this application provides an intelligent high-temperature power supply temperature monitoring method, including the following steps:

[0072] Step S1: Obtain the temperature data of the power supply module;

[0073] In one embodiment, temperature sensors (such as thermocouples, PT100, NTC thermistors, etc.) are arranged at multiple key parts of the power supply module (such as power devices, heat sinks, PCB boards), and the temperature data is collected through an A / D converter. In an extremely high-temperature environment (such as above 175°C), a fiber Bragg grating (FBG) temperature sensor is used to collect the temperature data to improve the measurement accuracy and anti-interference ability. For power supply modules that are not suitable for wiring, wireless temperature sensors (such as Bluetooth, Zigbee, LoRa, etc.) are used to transmit the temperature data to the main control unit.

[0074] In one embodiment, temperature sensors are arranged at key positions of the power supply module, for example, directly installed on the top of the package of the power module (MOSFET / IGBT). Installed on the heat sink, and the heat sink is located in the area where the heat flow is most concentrated, such as the center and edge positions of the heat sink. Installed on the PCB thermal-sensitive area, the area where the copper foil on the power PCB board is thicker (such as the high-power circuit). Using an NTC thermistor or a K-type thermocouple, the measurement range can reach , accuracy 。The sensor is connected to a 24-bit ADC (such as ADS1115) for high-precision data acquisition. At 10 Hz (10 acquisitions per second), the temperature response speed is ensured. It is transmitted to the microcontroller (such as STM32) via the I²C or SPI bus. If the environment is not suitable for wiring, a LoRa / Zigbee wireless temperature sensor can be used to transmit data.

[0075] Step S2: Perform temperature heat dissipation processing and temperature change processing based on the power module temperature data to obtain the power module temperature heat dissipation data and the power module temperature change data;

[0076] In one embodiment, based on finite element analysis (FEA) or heat transfer models (such as Fourier's heat conduction equation), the theoretical heat dissipation performance under different working conditions is calculated and compared with the measured data. The fan speed is controlled by PWM (pulse width modulation) to increase or decrease the heat dissipation capacity. The coolant flow rate is monitored, and the flow rate is adjusted according to the temperature change to improve the heat dissipation efficiency. When the temperature is too high, the PWM control signal of the power module is adjusted to reduce the output power to prevent thermal runaway.

[0077] In one embodiment, the real-time heat dissipation efficiency is calculated. The thermal resistance is equal to the module temperature minus the ambient temperature divided by the power consumption. If the thermal resistance is greater than 1.5 K / W (standard value), it indicates poor heat dissipation. The fan is controlled by PWM to adjust the speed. When T < 60°C, the fan speed is maintained at 40%. When 60°C ≤ T < 80°C, the fan speed linearly increases to 100%. When T ≥ 80°C, the fan runs at full speed and an alarm is triggered. The coolant flow rate is monitored to ensure that the flow rate ≥ 1.5 L / min for normal system operation. When the flow rate < 1.5 L / min, the coolant pump is triggered to boost the pressure. When the flow rate < 0.5 L / min, an alarm is given and the power output is reduced.

[0078] Step S3: Judge whether there is an abnormality in the power module temperature heat dissipation based on the power module temperature heat dissipation data to obtain the temperature heat dissipation abnormality data;

[0079] In one embodiment, based on the temperature heat dissipation curve under normal operating conditions, a threshold is set. When the actual heat dissipation speed is lower than the preset standard (such as the cooling rate < 5°C / min), it is determined that there is a heat dissipation abnormality. By calculating the ratio ( T = T_module - T_environment) of the temperature difference ( T / P) to the power consumption P, it is judged whether there is a decrease in the heat dissipation performance. When the thermal resistance exceeds the design value (such as Rth > 1.5 K / W), it indicates poor heat dissipation. The fan speed is monitored. If the speed drops by more than 30% or stops rotating, it is judged that the air-cooling system is abnormal. The coolant temperature and flow rate are monitored. If the flow rate drops or the temperature continues to rise, it is judged that the liquid-cooling system fails.

[0080] Step S4: Determine whether there is an abnormal change in the power supply module temperature based on the power supply module temperature change data to obtain temperature change abnormal data;

[0081] In one embodiment, calculate the temperature rise rate (dT / dt) per unit time. If the temperature rise rate exceeds the safety value (e.g., >10°C / min), it is determined that the temperature is abnormal. Determine whether there is abnormal temperature fluctuation through the sliding window method (e.g., the temperature change range in the past 5 minutes > 20°C). If the temperature exceeds a certain threshold (e.g., T > 150°C), trigger an alarm or automatically reduce the frequency. If the temperature exceeds the limit (e.g., T > 175°C), trigger an emergency shutdown.

[0082] Step S5: Construct a temperature abnormal curve based on the temperature heat dissipation abnormal data and the temperature change abnormal data to obtain temperature abnormal curve data for assisting in the monitoring of the high-temperature power supply temperature.

[0083] In one embodiment, based on the collected temperature abnormal data, algorithms such as polynomial regression, neural network, or support vector regression (SVR) are used to construct a temperature abnormal curve. Combining historical fault data, machine learning models (such as LSTM, CNN) are used to identify potential abnormal patterns. Predict future temperature abnormal situations and take countermeasures in advance. When the temperature abnormal curve exceeds the set range, the system automatically sends an alarm message (such as a text message, APP notification). Link the temperature protection mechanism, such as adjusting the heat dissipation strategy or triggering an emergency power-off.

[0084] In one embodiment, polynomial regression is used to fit the temperature abnormal curve by the least squares method: , where is the temperature abnormal curve data, is the temperature heat dissipation abnormal data, is the temperature change abnormal data, is the acceleration data of the temperature change abnormal data, is the cubic term of the temperature change abnormal data, representing the high-order nonlinear influence, which represents the violent fluctuation of the temperature change rate, is the time parameter term. For being too high, the linear temperature rise rate increases, indicating a decrease in heat dissipation capacity. It is necessary to increase the fan speed to improve the heat dissipation capacity, or increase the coolant flow rate to improve the heat exchange efficiency. For being too high, the heat accumulation accelerates. Due to the aging of the heat dissipation material or environmental impact, it is necessary to replace the heat sink with a higher thermal conductivity (such as replacing aluminum with copper), or reduce the environmental temperature (such as increasing air flow). For being too high, the temperature curve fluctuates violently, which is a dynamic heat dissipation abnormality (such as fan fluctuation). It is necessary to stabilize the fan power supply to ensure a constant rotation speed, or use a coolant with a higher heat capacity to reduce local temperature changes.

[0085] Preferably, step S1 is specifically as follows:

[0086] Step S11: Control the temperature sensor preset at the center position of the power module to collect the temperature of the power module, and obtain the central temperature data of the power module;

[0087] In one embodiment, a K-type thermocouple (measurement range -40°C to 175°C, accuracy ±1°C) or an NTC thermistor (suitable for high-temperature environments) is selected. For extremely high-temperature environments (such as >175°C), a fiber Bragg grating (FBG) sensor is used. Paste a thermocouple at the exact center of the power device (such as MOSFET, IGBT), and fix it using high-temperature-resistant silicone or welding to ensure optimal heat transfer. If a PCB-embedded temperature sensor is used, reserve a sensor pad at the central power path copper layer position of the PCB, and collect data through the I²C or SPI interface. Read the temperature signal through a 24-bit ADC (such as ADS1115), sample 10 times per second (10Hz) to ensure sufficient response speed. If the sensor uses wireless transmission, use the ZigBee / LoRa protocol to collect temperature data and send it to the control unit.

[0088] Step S12: Control the temperature sensor preset at the edge position of the power module to collect the temperature of the power module, and obtain the edge temperature data of the power module;

[0089] In one embodiment, the same K-type thermocouple, NTC thermistor, or FBG fiber temperature sensor as that at the center position is selected. Install one sensor at each of the four edge corners of the power module to monitor the temperature in a uniformly distributed manner. Install it by means of bolt fixation, thermal conduction glue bonding, or direct embedding in the PCB to ensure that the temperature sensor can stably sense. Sample 10 times per second (10Hz). Send it to the control unit through I²C / SPI or LoRa / ZigBee.

[0090] Step S13: Construct a spatial matrix for the central temperature data and the edge temperature data of the power module to obtain the temperature data of the power module.

[0091] In one embodiment, set the matrix form: , where is the temperature data of the power module, is the temperature data of the first edge sensor, is the temperature data of the second edge sensor, is the temperature data of the third edge sensor, is the temperature data of the fourth edge sensor, where the first edge sensor, the second edge sensor, the third edge sensor, and the fourth edge sensor are sensors installed at different edge orientations of the power module. is the temperature data of the central sensor.

[0092] Preferably, step S2 is specifically as follows:

[0093] Step S21: Perform temperature heat dissipation rate processing on the power module temperature data to obtain temperature heat dissipation rate data;

[0094] In one embodiment, the central difference method is used to calculate the temperature heat dissipation rate, that is, with a sampling interval of 1 second, the temperature data of this sampling minus the temperature data of the previous sampling interval divided by the sampling interval to obtain the temperature heat dissipation rate data.

[0095] Step S22: Construct a spatial gradient map for the temperature heat dissipation rate data to obtain power module temperature heat dissipation data;

[0096] In one embodiment, the finite difference method is used to calculate the gradient, that is, along the X direction: , and along the Y direction: , where is the distance between the temperature data of the first edge sensor and the temperature data of the second edge sensor, is the distance between the temperature data of the second edge sensor and the temperature data of the fourth edge sensor.

[0097] Step S23: Perform central-edge heat accumulation effect simulation based on the power module temperature heat dissipation data and the power module temperature data to obtain central-edge heat accumulation effect data;

[0098] In one embodiment, calculate the temperature difference between the center and the edge : . If , it indicates that heat accumulates in the center and the heat dissipation is uneven; if , it indicates that the heat distribution is uniform and there is no obvious heat accumulation effect. Calculate the heat flow per unit area : , is the thermal conductivity, which is obtained by querying through a database based on material properties. is the temperature gradient, that is, the power module temperature heat dissipation data. Finite element analysis (FEA) is used for heat flow simulation to generate an isothermal line diagram to visually display the heat accumulation area and calculate the temperature distribution under different environmental conditions (wind speed, coolant flow rate).

[0099] Step S24: Perform temperature constant change calculation based on the central-edge heat accumulation effect data to obtain power module temperature change data.

[0100] In one embodiment, the power supply module mainly transfers heat to the environment in the form of convection, satisfying the temperature change law under Newton cooling conditions: , where is the current temperature (instantaneous temperature) of the power supply module, that is, the module temperature observed at a certain moment, is the convective heat transfer coefficient (W / m²·K). is the ambient temperature, is approximated in the form of difference in the actual system. Set the steady-state temperature formula: , is the heat generation power per unit surface area of the module (unit: W / m²), which can be obtained by converting the input power and the heat generation area. If , it is considered to reach the steady state.

[0101] Preferably, step S3 is specifically:

[0102] Step S31: Judge the abnormal heat dissipation of material properties according to the heat dissipation data of the power supply module temperature, and obtain the abnormal heat dissipation data of material properties;

[0103] In one embodiment, calculate the thermal resistance of the material : , where is the power supply module temperature, is the ambient temperature, is the module power consumption, is the thickness of the material. Calculate the thermal conductivity of the module material (such as aluminum, copper, ceramic substrate): , where is the thermal conductivity (W / m·K), such as 385 W / m·K for copper and 205 W / m·K for aluminum, is the heat dissipation area, is the temperature gradient. Set the reference thermal conductivity. If the calculated thermal resistance is more than 10% higher than the design value, it is judged that the material thermal resistance is abnormal (caused by material aging, oxidation, surface contamination).

[0104] Step S32: Correct the influence of ambient temperature and humidity on heat dissipation according to the abnormal heat dissipation data of material properties and the heat dissipation data of the power supply module temperature, and obtain the corrected data of ambient temperature and humidity on heat dissipation;

[0105] In one embodiment, calculate the air convection heat transfer coefficient ( ): , where is the convective heat transfer constant measured by experiment, is the ambient temperature, is the surface temperature of the power supply module, is the temperature correction coefficient, which is used to adjust the temperature dependence of the heat transfer coefficient, taking into account the influence of temperature on air flow characteristics (such as changes in Reynolds number and Prandtl number). The empirical value is taken as , specifically depending on the heat dissipation conditions. Natural convection: , Forced convection: , is the wind speed. Calculate the influence of humidity on the thermal conductivity. At high humidity (>70%), if the surface of the radiator is wet, the thermal conductivity will decrease by 5% - 15%. If the humidity H > 80%, the thermal resistance increases by 10%, resulting in a decrease in the heat dissipation capacity. High humidity affects the thermal conductivity of the radiator: , where is the influence of high humidity on the thermal conductivity of the radiator, is the thermal conductivity of the heat dissipation material under normal environmental conditions (such as aluminum ), is the humidity influence factor (range 5% - 15%, depending on the humidity). Under normal circumstances: . If the humidity H = 80%: . The thermal conductivity drops by 10%, that is, the heat dissipation capacity decreases.

[0106] Step S33: Perform heat transfer medium interaction processing according to the environmental temperature and humidity heat dissipation correction data to obtain temperature heat dissipation abnormal data.

[0107] In one embodiment, calculate the heat capacity of the coolant: , where is the mass of the coolant (kg), is the specific heat capacity of the coolant (J / kg·K), is the temperature difference between the inlet and outlet of the coolant (°C). Monitor the coolant flow rate. If the flow rate < 1.5 L / min, it is determined that the coolant flow rate is too low. If the temperature difference < 3°C, it is determined that the heat exchange efficiency of the coolant decreases. Calculate the efficiency of the air-cooled system: , is the heat dissipation power, is the convective heat transfer coefficient, is the heat dissipation area, which refers to the heat dissipation surface area where the power module contacts the air, including the surface areas of the heat sink and heat pipes, is the surface temperature of the power module, is the surrounding air temperature. If the wind speed decreases and causes to drop by 10%, it is determined that there is a heat dissipation abnormality. If any of the above conditions is triggered (including: too low flow rate, too small liquid-cooled temperature difference, decreased air-cooled power), the system will generate temperature heat dissipation abnormal data and mark it according to the abnormal type as: liquid-cooled heat dissipation abnormality; air-cooled heat dissipation efficiency abnormality; multi-mode heat exchange cooperation failure abnormality.

[0108] Preferably, step S4 is specifically:

[0109] Step S41: Determine whether there is an abnormal temperature change in the material properties based on the temperature change data of the power supply module to obtain the abnormal material temperature change data;

[0110] In one embodiment, the central difference method is used to calculate the temperature change rate per unit time. Calculate the thermal expansion rate of the material , where is the length change (m) of the material due to temperature change, is the initial length (m) of the material, is the temperature change data. If the temperature change rate |dT / dt| > 10 °C / s and the thermal expansion rate of the material exceeds the standard range by 10%, the material is determined to be abnormal. Determine the abnormal temperature change of the material and set the material stress calculation: , where is the internal thermal stress (Pa) of the material, is the elastic modulus of the material (such as copper Pa). If > 108 Pa (material stress limit), it will cause the material to crack or be damaged, and it is determined that the material temperature change is abnormal.

[0111] Step S42: Perform temperature and humidity heat dissipation correction based on the abnormal material temperature change data to obtain the abnormal temperature change data.

[0112] In one embodiment, the system obtains the environmental humidity data H (unit: %), which is regularly sampled by the humidity sensor deployed on the outer shell of the power supply module or in the cooling channel (for example, updated every 10 s) to sense the humidity level of the air or cooling medium in real time. According to the humidity value, the system sets the humidity influence factor , which is used to reflect the degree of weakening of the humidity on the heat conduction ability of the material. The specific setting is as follows: , , . Then, the system calculates the corrected thermal conductivity according to the reference thermal conductivity (for example: aluminum material = 205 W / m·K): , where is the corrected thermal conductivity (W / m·K), is the thermal conductivity of the material in the standard dry environment, is the humidity influence factor (5% - 15%, depending on the humidity ).

[0113] Preferably, step S5 is specifically:

[0114] Step S51: Construct an abnormal curve based on the temperature heat dissipation abnormal data and the abnormal temperature change data to obtain the abnormal curve data;

[0115] In one embodiment, the temperature heat dissipation abnormal data and temperature change abnormal data in the last 30 minutes are selected, the time is aligned, and a smooth abnormal curve is generated using cubic spline interpolation: ,in is the temperature anomaly curve data, For temperature heat dissipation abnormal data, is the abnormal temperature change data, is the acceleration data of abnormal temperature change data, is the cubic term of abnormal temperature change data, a high-order nonlinear effect, representing the dramatic fluctuation of the temperature change rate. It is the time parameter item.

[0116] Step S52: Acquire standard power module temperature data;

[0117] In one embodiment, normal operating data with similar ambient temperature and humidity and the same load power are selected, and a moving window method (10-minute window) is used to obtain short-term standard temperature data.

[0118] Step S53: constructing a temperature curve according to the standard power module temperature data to obtain temperature curve data;

[0119] In one embodiment, the standard temperature curve is calculated: , is the smoothing factor, take 0.3, for Standard power module temperature data at the moment, for Standard power module temperature data at the moment.

[0120] Step S54: extracting similarities and differences based on the abnormal curve data and the temperature curve data to obtain the temperature abnormal curve data for auxiliary operation of high-temperature power supply temperature monitoring.

[0121] In one embodiment, the error between the abnormal curve and the standard curve is calculated, the mean square error is calculated, the data segment with an error less than or equal to a threshold is marked as convergent feature data, the data segment with an error greater than the threshold is marked as significant abnormal feature data, and the two are combined to obtain temperature anomaly curve data.

[0122] In one embodiment, further, time-frequency quantization analysis is performed based on the abnormal curve data and the temperature curve data to obtain time-frequency quantum data; a fusion network is constructed based on the time-frequency quantum data to obtain temperature curve fusion network data; entropy flow dynamics evolution is performed based on the temperature curve fusion network data to obtain temperature curve entropy flow data; phase change detection is performed on the temperature curve entropy flow data to obtain temperature anomaly curve data, so as to perform auxiliary operations for high-temperature power supply temperature monitoring.

[0123] Map the temperature signal to a quantum state through wavelet transform: ; where is the quantum state corresponding to the temperature signal, is the normalization factor, is the wavelet component index (representing different frequency levels), is the base of the natural logarithm, is the imaginary unit, is the frequency of the -th level wavelet component, is the time variable, is the energy ground state corresponding to the abnormal curve data / temperature curve data. Let the abnormal event be the observation operator and calculate its collapse probability distribution: , where is the projection probability of the quantum state on the ground state . Extract the signal frequency information through wavelet transform and map it to a quantum state. The probability distribution of the quantum state reflects the contribution of the temperature signal in different frequencies and energy modes. Calculate the probability of the abnormal event and detect high-probability abnormal points. Combine wavelet transform to accurately locate the time scale of the abnormal occurrence.

[0124] Construct a third-order tensor: time × temperature gradient × abnormal level, and use Tucker decomposition to extract the core features: , is a data structure containing three dimensions: time (T) × temperature gradient (G) × abnormal level (L), is (mode product) which represents matrix multiplication of the tensor along the -th dimension, and the value is 1, 2, 3, is the core tensor, the compressed low-dimensional representation, containing the main feature information, is the time-mode feature matrix (i.e., time-frequency quantum data), describing the features of the temperature signal in the time dimension, is the temperature-gradient-mode feature matrix, describing the pattern of the temperature change rate, is the abnormal-level-mode feature matrix, reflecting the feature distribution of the abnormal level, , is the spatio-temporal correlation map tensor, the data after removing the abnormal level, only containing the core features of time and temperature gradient.

[0125] , is the total entropy of the system, the total amount of disorder or information entropy of the system, used to measure the change trend of the system state, is the time variable of the system evolution, describing the change of entropy over time, The heat transferred to the system, used to calculate the contribution of thermal entropy. The temperature corresponding to the heat transfer, which affects the change in thermal entropy. For the state in the system The probability of occurrence, used to calculate the information entropy. The anomalous correlation tensor, representing the interaction strength between anomalous energies. The energy of the anomalous event, representing the energy of a certain anomalous state. The energy of the anomalous event, the energy of another anomalous state, which Interacts with The thermodynamic entropy term, describing the entropy change due to heat transfer. The information entropy term, describing the uncertainty of the system state. The parameters in the entropy term are directly or indirectly calculated from the data of the temperature curve fusion network.

[0126] , The order parameter, used to detect the sensitivity of the entropy to the phase transition with respect to temperature And energy Change. The system entropy, the total amount of disorder or information entropy of the system, used to measure the change in the system state during the phase transition. The temperature of the system, one of the main variables controlling the phase transition. The total energy or anomalous event energy of the system, which together with the temperature affects the change in entropy. , The phase transition threshold. Phase transition detection , Calculate the entropy With respect to temperature And energy The second-order partial derivative of, reflecting whether the system is in a phase transition state. If Suddenly changes, indicating that a phase transition has occurred in the system. Set the phase transition threshold , When Exceeds , The system enters an abnormal temperature state, thereby realizing anomaly detection for the convergence feature analysis based on quantum computing, used to detect the key points of temperature anomalies and judge whether the heat dissipation system is stable.

[0127] Preferably, the temperature heat dissipation rate processing is specifically as follows:

[0128] Perform the original area temperature heat dissipation rate processing based on the temperature data of the power supply module to obtain the first temperature heat dissipation rate data;

[0129] In one embodiment, the original region refers to the temperature change rate of a single component (such as a certain region of a MOSFET, IGBT, or heat sink). It is calculated using the central difference method, that is, the temperature difference of the original region divided by the sampling time. Calculate the spatial variation of the heat dissipation rate, that is, calculate the temperature gradient of the original region, calculate the temperature gradient along the X direction and the temperature gradient along the Y direction respectively, and obtain the first temperature heat dissipation rate data.

[0130] Perform cross-region temperature heat dissipation rate processing based on the power module temperature data to obtain cross-region temperature heat dissipation rate data;

[0131] In one embodiment, by analyzing the temperature change behaviors between multiple spatially adjacent devices (such as multiple MOSFETs, IGBT chips, and heat dissipation structures), quantify the heat dissipation efficiency differences between components, so as to identify risk points such as uneven heat dissipation and heat accumulation. The system is based on a high-precision temperature sensing network, collects the temperature time series data of each adjacent region, and calculates the difference in their temperature change rates: , where is the temperature curve of the th adjacent device region, is the temperature curve of the th adjacent device region, is the temperature change rate obtained by forward difference or moving average calculation, is the difference in the temperature rise rate of adjacent regions. The larger it is, the more uneven the heat diffusion is, and there may be a heat barrier potentially. The system constructs a cross-region temperature gradient model and calculates the average temperature difference in the spatial direction: , where is the physical distance (unit: m) between the th and th devices, used to estimate the directional temperature change. The system introduces Fourier's law of heat conduction to calculate the cross-region heat flux density: , is the cross-region heat flux density (unit: W / m²) between the th and th devices, is the thermal conductivity of the corresponding material (unit: W / m·K), which is determined by the properties of the structural material. The system integrates the calculation results of the heat flux density between all adjacent regions into cross-region temperature heat dissipation rate data.

[0132] Perform heat flow simulation of the heat dissipation medium based on the cross-region temperature heat dissipation rate data to obtain the second temperature heat dissipation rate data.

[0133] In one embodiment, calculate the medium flow rate and heat transfer ability: , is the numerical value of convective heat transfer, is the convective heat transfer coefficient (W / m²·K), is the heat dissipation surface area (m²), is the surface temperature (°C), is the cooling medium or ambient temperature (°C). The system calculates the temperature dissipation rate per unit mass (i.e., the second temperature dissipation rate data) based on the mass and specific heat capacity of the heat dissipation medium: This parameter reflects the heat dissipation ability of the cooling medium under the conditions of unit mass and unit specific heat, and is an important indicator for evaluating the heat flow efficiency. To further determine the flow state of the cooling medium, the system calculates the Reynolds number (Re) as follows: where is the density of the coolant (kg / m³), is the flow velocity of the coolant (m / s), is the pipe diameter (m), which is calculated from the inner diameter of the pipe through which the coolant or air flows, is the dynamic viscosity (Pa·s). If Re < 2300, it is judged as laminar flow with low heat dissipation efficiency. If Re > 4000, it is judged as turbulent flow with high heat dissipation efficiency. If Re is between the two, it is in the transition interval, and its trend can be dynamically evaluated. Calculate the heat transfer efficiency, which is obtained by dividing the heat dissipation ability actually calculated from the current flow velocity, medium properties and temperature difference by the ideal maximum heat exchange ability calculated based on the optimal working conditions of the cooling system design (which can be preset or obtained through simulation).

[0134] Preferably, the central-edge heat accumulation effect simulation is specifically as follows:

[0135] Extract the volatility characteristic data from the temperature data of the power module to obtain the temperature volatility characteristic data;

[0136] In one embodiment, extract the temperature fluctuation characteristics: where, is the temperature volatility characteristic data, is the sampling quantity data, is the sampling sequence term, is the th measured temperature value, is the average temperature within the window.

[0137] Calculate the central-edge temperature transfer lag based on the temperature volatility characteristic data to obtain the central-edge lag coefficient data;

[0138] In one embodiment, the system sets the approximate description of the edge temperature response of the power module as a time-delay expression form of the central temperature, that is: where is the edge temperature, is the central temperature, is the sampling time, is the temperature transfer lag time (seconds). For a preliminary estimate of the lag time, the thermal diffusion theory formula is used: , where is the estimated value of the basic lag time under physical model derivation, is the physical distance from the center to the edge (m), is the thermal diffusion coefficient of the material (m² / s). To enhance the adaptability of the model under complex working conditions, the system further introduces a statistical correlation analysis between the center-edge temperature curves. Define the cross-correlation coefficient of the center temperature sequence and the edge temperature sequence as: , is the center temperature of the power supply module, is the average center temperature of the power supply module, is the edge temperature of the power supply module, is the average edge temperature of the power supply module, is the temperature volatility characteristic data of the center temperature of the power supply module, is the temperature volatility characteristic data of the edge temperature of the power supply module, , is approximately equal to the reciprocal of, , , is the empirical correction coefficient (taking 1-2), indicating that when the temperature changes at the center and the edge are highly synchronized (i.e., →1), then →0; if the temperature changes at the two are not correlated ( approaches 0), then the system determines that there is a significant lag in the thermal response.

[0139] Based on the center-edge lag coefficient data and the power supply module temperature heat dissipation data, heat balance processing is performed to obtain the power supply module heat balance data;

[0140] In one embodiment, the heat conduction equation is used: , where, is the input heat (W) (i.e., obtained by power calculation), is the heat dissipation (W) (i.e., obtained by temperature induction calculation through a sensor), is the heat capacity (J / K). To accurately estimate , a heat transfer rate estimation model (such as one-dimensional steady-state heat conduction) is further introduced: , where, is the heat transfer rate, is the thermal conductivity of the material (W / m·K), approximately regarded as , is the center temperature of the power supply module, is the heat transfer area (m²), is the temperature at the edge of the power supply module, is the heat transfer path (m). The system calculates the difference between the input and output heat at the current moment according to the above model and makes a relative error judgment: , is the threshold data for thermal balance judgment. If the heat income and expenditure are basically the same (the error is less than 5%), the system judges it as a thermal balance state and records the current state to enter the temperature stability trend modeling module.

[0141] Calculate the heat accumulation effect based on the thermal balance data of the power supply module and the temperature dissipation data of the power supply module to obtain the center-edge heat accumulation effect data.

[0142] In one embodiment, to identify the heat concentration phenomenon (heat accumulation effect) existing inside the power supply module, the system calculates the heat accumulation effect in a multi-dimensional manner based on the thermal balance data and the temperature dissipation data, and outputs the center-edge heat accumulation effect data as the key basis for anomaly judgment and temperature control strategy optimization. The system calculates the temperature at the center temperature measurement point of the power supply module in real time and the temperature difference between the edge temperature measurement points : , if , it is determined that there is a heat accumulation trend, where is the temperature difference threshold (such as 5°C) set according to the system materials, environment, and load conditions, supporting static setting or dynamic adjustment trained by historical data. Calculate the heat flux intensity between each temperature measurement point using Fourier's Law: , where is the heat flux intensity, is the material thermal conductivity (W / m·K), is the temperature gradient vector, obtained by dividing the temperature change in the center-edge direction by the distance difference. Further calculate the difference in heat flux intensity between the center and the edge: , where is the center-edge heat flux intensity difference, is the heat flux density in the center region, is the heat flux density in the edge region. If , it means that the heat conduction efficiency in the center region is much lower than that in the edge, and there is heat flux accumulation, which can be determined as a significant heat accumulation phenomenon. The heat flux difference judgment threshold can be set based on the system heat load capacity.

[0143] In high-performance application scenarios, the system calls the heat conduction finite element analysis module to construct a temperature field simulation model based on the current temperature distribution, material properties, and boundary conditions, and simulate the temperature evolution trend in the short term in the future. Starting from the current moment, the system predicts the temperature field changes in the next 5 minutes. If it is found in the simulation results that the temperature in the central region increases by more than 10% relative to the current value, it is determined that there is an enhanced heat accumulation trend, and the heat dissipation strategy adjustment and safety warning mechanism can be triggered in advance. The central-edge heat accumulation effect data may include parameters such as the central-edge temperature difference value, heat flux difference value, predicted temperature rise percentage, etc., and supports being input into the abnormal curve construction module and the temperature control strategy optimization module in the form of graphs, matrices, or structured data, for intelligent scheduling of air-cooled / liquid-cooled systems, adjustment of heat dissipation path design, or output of user warning information.

[0144] Preferably, the calculation of the central-edge temperature transfer lag is specifically as follows:

[0145] Perform central peak-valley calculation and edge peak-valley calculation based on the temperature volatility characteristic data to obtain central peak-valley data and edge peak-valley data respectively;

[0146] In one embodiment, the sliding window method is used to extract the temperature data in the last 10 minutes, the window size is set to 60 seconds, the first derivative is used to detect the extreme points, and the temperature change rate is calculated. If the temperature change rate changes sign (from positive to negative) before and after the peak point, it is identified as the peak point. If the temperature change rate changes sign (from negative to positive) before and after the valley point, it is identified as the valley point.

[0147] Obtain the power supply heat dissipation data, where the power supply heat dissipation data includes the power supply heat dissipation position data and the power supply heat dissipation power data;

[0148] In one embodiment, obtain the positions of the radiators of the air-cooled system or the liquid-cooled system, and record the heat dissipation power of each heat dissipation point.

[0149] Calculate the heat dissipation effect lag time for the temperature position data corresponding to the power module temperature data according to the power supply heat dissipation data to obtain the heat dissipation effect time coefficient data;

[0150] In one embodiment, to model and compensate for the temperature response lag effect of different temperature measurement points of the power module, the system is based on the heat diffusion theory and uses the heat transfer time delay model to calculate the heat dissipation response time. Specifically, based on the spatial distribution relationship of the temperature measurement points relative to the heat source (i.e., the heat dissipation position), define: , is the distance (m) from the heat dissipation point to the temperature measurement point, is the thermal diffusivity (m² / s). By calculating for each temperature measurement point in the power module , a time-delay response model between temperature changes and actual heat dissipation behavior can be established. This model is not only used to judge whether the temperature responses at the center and the edge are synchronized, but also can be used as a dynamic correction factor in subsequent peak-valley analysis and lag coefficient judgment to adjust the time series of the temperature curve and improve the accuracy of lag judgment. In addition, to ensure the calculation accuracy, the system supports real-time updating of the dynamic parameters of the heat diffusion path based on the thermal sensing network. When the system detects a high-load mutation or a large change in ambient temperature and humidity, it automatically recalculates , so as to adapt to the influence of the change of the heat dissipation medium state on the heat transfer rate and achieve accurate temperature prediction and abnormal warning in the time domain.

[0151] Select the adjacent peak-valley transfer influence for the center peak-valley data and the edge peak-valley data according to the heat dissipation effect time coefficient data to obtain the adjacent peak-valley transfer data;

[0152] In one embodiment, to identify whether there is a temperature peak-valley transfer effect between the central region and the edge region of the power module, the system selects the adjacent peak-valley transfer influence for the center peak-valley data and the edge peak-valley data based on the principle of time series comparison and adjacent matching. The system extracts the peak points and valley points (i.e., local maximum and minimum values) from the temperature data at the center position, and searches for the peak-valley points in the temperature data of the corresponding edge region within a ±5-second time window centered on the peak-valley time point. To ensure accurate comparison, the center and edge temperature data have been processed by sampling synchronization, and interpolation is introduced for time alignment when necessary. The system calculates the center-edge peak-valley time difference: , where is the center peak-valley data, is the edge peak-valley data, seconds, it is considered that there is an effective heat response transfer effect between this center peak-valley and the edge peak-valley, and it is recorded as the effective adjacent peak-valley transfer data. In the case where one center peak-valley point corresponds to multiple candidate edge peak-valley points, the system selects the pair with the smallest time difference for matching to construct the peak-valley transfer mapping relationship between the center and the edge.

[0153] Calculate the lag coefficient according to the adjacent peak-valley transfer data to obtain the center-edge temperature transfer lag data.

[0154] In one embodiment, to further judge the heat conduction state between the central region and the edge region of the power module, the system calculates the relative lag ratio of the center and edge temperature responses based on the aforementioned obtained adjacent peak-valley transfer data, , to characterize the heat diffusion efficiency and the degree of heat retention. Calculate the relative lag ratio is the length of a single temperature fluctuation cycle in the central temperature curve of the power supply module, that is, the time required to drop from the peak to the valley or rise from the valley to the next peak, where specifically represents the average time difference between the central peak and valley relative to the edge peak and valley (i.e., the thermal response time delay), which is calculated through multiple matched adjacent peak and valley pairs: , is the number of valid peak and valley pairs, is the serial number index of the peak and valley pair, is the th central peak and valley point timestamp, representing the time point (unit: second) of the th peak or valley identified in the temperature curve of the central region of the power supply module, is the th edge peak and valley point timestamp, representing the time point (unit: second) of the peak or valley obtained by time window matching adjacent to the th central peak and valley point in the temperature curve of the edge region of the power supply module, is the relative rate of the central thermal response rhythm and the heat diffusion to the edge. The larger the value, the more serious the lag and the more difficult it is for the central heat to diffuse. When the system judges > 1.5, it is considered that there is obvious heat retention in the center, and the response of the edge region is slow, which is caused by problems such as local blockage of the heat conduction structure, deviation of the cooling system, and decrease in the thermal diffusion coefficient of the material. At this time, the system will mark this value as the central-edge temperature transfer lag data; record the abnormal event, and start the temperature control strategy adaptive adjustment module, such as increasing the rotation speed of the edge fan, adjusting the liquid cooling flow distribution, etc.; provide input to the temperature anomaly curve modeling module for optimizing the response timing of the temperature anomaly judgment model; issue a heat dissipation warning to the user terminal, prompting to check the local heat dissipation system or material status. The threshold 1.5 can be dynamically configured based on experimental data, device model or operating environment. The system supports training with historical data to optimize this value, and dynamically adjusts the judgment criteria according to the material properties (such as copper, aluminum, ceramic) and layout structure of different power supply modules to ensure the applicability and robustness of the model.

[0155] Calculate the relative lag ratio of the central temperature to the edge temperature , is the lag degree of the central temperature change relative to the edge temperature, is the time interval for the central temperature of the power supply module to drop from the peak to the valley or rise from the valley to the peak. If > 1.5, it indicates that there is serious heat retention in the center and uneven heat dissipation problem.

[0156] Preferably, the present invention also provides an intelligent high-temperature power supply temperature monitoring system for executing the intelligent high-temperature power supply temperature monitoring method as described above. The intelligent high-temperature power supply temperature monitoring system includes:

[0157] A power module temperature data acquisition module, which is used to obtain power module temperature data;

[0158] A power module temperature analysis module, which is used to perform temperature heat dissipation processing and temperature change processing according to the power module temperature data to obtain power module temperature heat dissipation data and power module temperature change data;

[0159] A power module temperature heat dissipation anomaly judgment module, which is used to judge the power module temperature heat dissipation anomaly according to the power module temperature heat dissipation data to obtain temperature heat dissipation anomaly data;

[0160] A power module temperature change anomaly judgment module, which is used to judge the power module temperature change anomaly according to the power module temperature change data to obtain temperature change anomaly data;

[0161] A temperature anomaly curve construction module, which is used to construct a temperature anomaly curve according to the temperature heat dissipation anomaly data and the temperature change anomaly data to obtain temperature anomaly curve data for assisting in the monitoring of high-temperature power supply temperature.

[0162] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended application documents rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0163] The above are only the specific embodiments of the present invention, which enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent high-temperature power supply temperature monitoring method, characterized in that: The following steps are involved: Step S1: Control the temperature sensor preset at the center position of the power module to collect the temperature of the power module to obtain the center temperature data of the power module; control the temperature sensor preset at the edge position of the power module to collect the temperature of the power module to obtain the edge temperature data of the power module; construct a spatial matrix for the center temperature data of the power module and the edge temperature data of the power module to obtain the power module temperature data; Step S2: Process the temperature heat dissipation rate according to the power module temperature data and construct a spatial gradient map to obtain the power module temperature heat dissipation data; perform center-edge temperature transfer hysteresis calculation according to the power module temperature data to obtain center-edge hysteresis coefficient data; perform heat accumulation effect calculation according to the center-edge hysteresis coefficient data and the power module temperature heat dissipation data to obtain center-edge heat accumulation effect data; perform temperature constant change calculation according to the center-edge heat accumulation effect data to obtain power module temperature change data; Step S3: judging abnormality of heat dissipation of the power module temperature according to the heat dissipation data of the power module temperature, and obtaining abnormal heat dissipation data of the power module temperature; Step S4: judging abnormal temperature change of the power module according to the temperature change data of the power module, and obtaining abnormal temperature change data; Step S5: constructing a temperature anomaly curve according to the temperature heat dissipation abnormality data and the temperature change abnormality data to obtain temperature anomaly curve data for performing auxiliary work of high-temperature power supply temperature monitoring; The calculation of center-edge temperature transfer hysteresis is as follows: Perform central peak-valley calculation and edge peak-valley calculation according to the temperature fluctuation characteristic data to obtain central peak-valley data and edge peak-valley data respectively; Acquire power heat dissipation data, wherein the power heat dissipation data includes power heat dissipation position data and power heat dissipation power data; According to the power supply heat dissipation data, the heat dissipation effect hysteresis time is calculated for the temperature position data corresponding to the power supply module temperature data to obtain the heat dissipation effect time coefficient data; According to the heat dissipation effect time coefficient data, the adjacent peak-valley transfer influence selection is performed on the central peak-valley data and the edge peak-valley data to obtain the adjacent peak-valley transfer data; The hysteresis coefficient is calculated based on the adjacent peak-valley transmission data to obtain the center edge hysteresis coefficient data.

2. The method according to claim 1, characterized in that Step S3 is specifically as follows: According to the power module temperature heat dissipation data, the material property heat dissipation abnormality is judged to obtain the material property heat dissipation abnormality data; Correct the heat dissipation effect of ambient temperature and humidity based on the abnormal heat dissipation data of material properties and the heat dissipation data of the power module temperature to obtain the corrected heat dissipation data of ambient temperature and humidity; According to the ambient temperature and humidity heat dissipation correction data, the heat transfer medium interaction processing is performed to obtain the temperature heat dissipation abnormality data.

3. The method according to claim 1, characterized in that Step S4 is specifically as follows: According to the temperature change data of the power module, the abnormal temperature change of the material property is judged to obtain the abnormal temperature change data of the material; Temperature and humidity heat dissipation correction is performed according to the abnormal temperature change data of the material to obtain the abnormal temperature change data.

4. The method according to claim 1, characterized in that: Step S5 is specifically as follows: An abnormal curve is constructed according to the temperature heat dissipation abnormal data and the temperature change abnormal data to obtain abnormal curve data; Get standard power module temperature data; Construct a temperature curve according to the temperature data of the standard power module to obtain temperature curve data; The difference and similarity features are extracted based on the abnormal curve data and the temperature curve data to obtain the temperature abnormal curve data for auxiliary work of high-temperature power supply temperature monitoring.

5. The method according to claim 1, characterized in that The specific temperature heat dissipation rate processing is: Performing heat dissipation rate processing of the original area temperature according to the temperature data of the power module to obtain first temperature heat dissipation rate data; Perform cross-region temperature heat dissipation rate processing according to the power module temperature data to obtain cross-region temperature heat dissipation rate data; The heat flow simulation of the heat dissipation medium is performed according to the cross-region temperature heat dissipation rate data to obtain the second temperature heat dissipation rate data.

6. The method according to claim 1, characterized in that The simulation of the center-edge heat accumulation effect is as follows: Extract fluctuation characteristics based on the temperature data of the power module to obtain temperature fluctuation characteristic data; The center-edge temperature transfer hysteresis is calculated based on the temperature fluctuation characteristic data to obtain the center-edge hysteresis coefficient data; Perform thermal balance processing according to the center edge hysteresis coefficient data and the power module temperature heat dissipation data to obtain the power module thermal balance data; The heat accumulation effect is calculated based on the thermal balance data of the power module and the temperature and heat dissipation data of the power module to obtain the center-edge heat accumulation effect data.

7. An intelligent high-temperature power supply temperature monitoring system, characterized in that: Used to execute the intelligent high-temperature power supply temperature monitoring method as claimed in claim 1, the intelligent high-temperature power supply temperature monitoring system comprises: The power module temperature data acquisition module is used to control the temperature sensor preset at the center of the power module to collect the power module temperature and obtain the power module center temperature data; control the temperature sensor preset at the edge of the power module to collect the power module temperature and obtain the power module edge temperature data; construct a spatial matrix for the power module center temperature data and the power module edge temperature data to obtain the power module temperature data; The power module temperature analysis module is used to process the temperature heat dissipation rate according to the power module temperature data and construct a spatial gradient map to obtain the power module temperature heat dissipation data; perform center-edge temperature transfer hysteresis calculation according to the power module temperature data to obtain center-edge hysteresis coefficient data; perform heat accumulation effect calculation according to the center-edge hysteresis coefficient data and the power module temperature heat dissipation data to obtain center-edge heat accumulation effect data; perform temperature constant change calculation according to the center-edge heat accumulation effect data to obtain the power module temperature change data; the center-edge temperature transfer hysteresis calculation is specifically: perform center peak-valley calculation and edge peak-valley calculation according to the temperature fluctuation characteristic data to obtain center peak-valley data and edge peak-valley data respectively; obtain power heat dissipation data, wherein the power heat dissipation data includes power heat dissipation position data and power heat dissipation power data; perform heat dissipation effect hysteresis time calculation on the temperature position data corresponding to the power module temperature data according to the power heat dissipation data to obtain heat dissipation effect time coefficient data; perform neighboring peak-valley transfer influence selection on the center peak-valley data and the edge peak-valley data according to the heat dissipation effect time coefficient data to obtain neighboring peak-valley transfer data; perform hysteresis coefficient calculation according to the neighboring peak-valley transfer data to obtain center-edge hysteresis coefficient data; A power module temperature heat dissipation abnormality judgment module is used to judge the power module temperature heat dissipation abnormality according to the power module temperature heat dissipation data to obtain the temperature heat dissipation abnormality data; A power module temperature change abnormality judgment module is used to judge the power module temperature change abnormality according to the power module temperature change data to obtain the temperature change abnormality data; The temperature anomaly curve construction module is used to construct the temperature anomaly curve according to the temperature heat dissipation anomaly data and the temperature change anomaly data to obtain the temperature anomaly curve data for auxiliary operation of high-temperature power supply temperature monitoring.

Images