Heater temperature control performance detection method and system based on vacuum environment

Abstract

The invention provides a heat temperature control performance detection method and system based on a vacuum environment, and relates to the technical field of temperature control performance detection. A heat part in the vacuum chamber is activated based on an external power supply to carry out real-time operation monitoring; temperature change calculation is carried out according to the real-time operation data set, and temperature simulation control is carried out on the heat part; performing temperature control performance test on the heat part according to the temperature control suggestion, generating a temperature control performance score, and dynamically updating the temperature control suggestion; and the maintenance instruction is sent to a remote terminal for temperature intelligent control maintenance. The technical problem that in the prior art, due to the fact that the temperature control performance is not accurate in the vacuum environment, the operation efficiency of the heat part is low can be solved, the temperature control performance test is carried out in the vacuum environment, the operation efficiency of the heat part is improved, and the fault risk caused by temperature abnormity is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of temperature control performance detection, and in particular to a method and system for detecting the temperature control performance of a heater based on a vacuum environment. Background Art

[0002] Heater parts are key components used to heat and maintain target temperatures. They are widely used in fields that require precise temperature control, such as semiconductor manufacturing, optical coating, and high vacuum experiments. Especially in a vacuum environment, heater parts usually provide thermal energy through electric heating to meet the high temperature and high precision requirements of specific processes. In a vacuum environment, the temperature control performance testing of heater parts becomes more complicated due to the lack of air convection and different heat conduction mechanisms. Insufficient temperature control accuracy leads to large temperature fluctuations or local overheating; the heating rate is slow, which reduces the operating efficiency and production rhythm of the equipment; the lack of a real-time optimization mechanism makes it impossible to quickly respond to temperature control anomalies, increasing the risk of equipment failure and further affecting the operating efficiency and reliability of heater parts.

[0003] In summary, the prior art has technical problems such as inaccurate temperature control performance in a vacuum environment, slow heating rate, power waste or uneven heat distribution, resulting in low operating efficiency of heater parts. Summary of the invention

[0004] The purpose of this application is to provide a method and system for detecting the temperature control performance of a heater based on a vacuum environment, so as to solve the technical problems in the prior art that the temperature control performance is inaccurate in a vacuum environment, resulting in a slow heating rate, power waste or uneven heat distribution, leading to low operating efficiency of heater parts.

[0005] In view of the above problems, the present application provides a method and system for detecting the temperature control performance of a heater based on a vacuum environment.

[0006] In a first aspect, the present application provides a method for detecting the temperature control performance of a heater based on a vacuum environment, and the method is implemented by a temperature control performance detection system for a heater based on a vacuum environment, wherein the method comprises: evacuating a cavity by a molecular pump to construct a vacuum chamber, wherein the vacuum chamber contains heater parts; activating the heater parts in the vacuum chamber based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; performing temperature change calculations according to the real-time operation data set to obtain a plurality of temperature change coefficients, performing temperature simulation control on the heater parts according to the plurality of temperature change coefficients, and formulating temperature control recommendations; performing temperature control performance tests on the heater parts according to the temperature control recommendations to generate a temperature control performance score, dynamically updating the temperature control recommendations according to the temperature control performance score, and generating maintenance instructions; and sending the maintenance instructions to a remote terminal to perform intelligent temperature control maintenance on the heater parts.

[0007] In a second aspect, the present application further provides a heater temperature control performance detection system based on a vacuum environment, which is used to execute the heater temperature control performance detection method based on a vacuum environment as described in the first aspect, wherein the heater temperature control performance detection system based on a vacuum environment includes: a vacuum chamber construction module, the vacuum chamber construction module is used to evacuate the cavity through a molecular pump to construct a vacuum chamber, and the vacuum chamber contains a heater part; a real-time monitoring module, the real-time monitoring module is used to activate the heater part in the vacuum chamber based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; a temperature change calculation module, the temperature change calculation module is used to perform temperature change calculation according to the real-time operation data set to obtain multiple temperature change coefficients, perform temperature simulation control on the heater part according to the multiple temperature change coefficients, and formulate temperature control suggestions; a performance testing module, the performance testing module is used to perform temperature control performance testing on the heater part according to the temperature control suggestion, generate a temperature control performance score, dynamically update the temperature control suggestion according to the temperature control performance score, and generate a maintenance instruction; a temperature control maintenance module, the temperature control maintenance module is used to send the maintenance instruction to a remote terminal to perform temperature intelligent control maintenance on the heater part.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The cavity is evacuated by a molecular pump to construct a vacuum chamber, which contains a heater part; the heater part in the vacuum chamber is activated based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; temperature change calculation is performed based on the real-time operation data set to obtain multiple temperature change coefficients, and temperature simulation control is performed on the heater part according to the multiple temperature change coefficients to formulate temperature control suggestions; the temperature control performance of the heater part is tested according to the temperature control suggestions to generate a temperature control performance score, and the temperature control suggestion is dynamically updated according to the temperature control performance score to generate a maintenance instruction; the maintenance instruction is sent to a remote terminal to perform temperature intelligent control maintenance on the heater part. In other words, a vacuum chamber environment containing a heater part is constructed by evacuating a specific cavity by a molecular pump, the heater part is activated for real-time operation monitoring, and temperature change calculation is performed based on the real-time operation data set, so as to formulate corresponding temperature control suggestions and generate specific maintenance instructions, which not only improves the operation efficiency of the heater part, but also reduces the risk of failure caused by abnormal temperature.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a flow chart of a method for detecting the temperature control performance of a heater based on a vacuum environment in this application; Figure 2 This is a structural schematic diagram of the heater temperature control performance detection system based on a vacuum environment in this application.

[0012] Explanation of the reference numerals: vacuum chamber construction module 11 , real-time monitoring module 12 , temperature change calculation module 13 , performance testing module 14 , temperature control maintenance module 15 . DETAILED DESCRIPTION

[0013] This application solves the technical problem in the prior art that the inaccurate temperature control performance in a vacuum environment causes a slow heating rate, power waste or uneven heat distribution, resulting in low operating efficiency of heater parts by providing a method and system for detecting the temperature control performance of a heater based on a vacuum environment. A vacuum chamber environment containing heater parts is constructed by evacuating a specific cavity with a molecular pump, and the heater parts are activated for real-time operation monitoring. Based on the real-time operation data set, temperature change calculation is performed to formulate corresponding temperature control suggestions and generate specific maintenance instructions, which not only improves the operating efficiency of heater parts, but also reduces the risk of failure caused by abnormal temperature.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For example, please refer to the attached Figure 1 The present application provides a method for detecting the temperature control performance of a heater based on a vacuum environment, wherein the method for detecting the temperature control performance of a heater based on a vacuum environment is applied to a temperature control performance detection system of a heater based on a vacuum environment, and the method for detecting the temperature control performance of a heater based on a vacuum environment specifically comprises the following steps: S100: The cavity is evacuated by a molecular pump to construct a vacuum chamber, wherein the vacuum chamber includes a heater component.

[0016] Specifically, the molecular pump is connected to the cavity to gradually extract the gas molecules in the vacuum chamber. A molecular pump is a device that can effectively extract air molecules or gas molecules in a vacuum environment. It uses the collision and friction between molecules to capture and remove gas molecules, thereby effectively reducing the pressure in the cavity. A cavity refers to a container used for enclosed space in an experiment or device, usually a closed space used to create specific environmental conditions (such as vacuum, low temperature, etc.). In a vacuum experiment, a cavity generally refers to a pressurized and temperature-controlled device used to accommodate the equipment being tested (such as heater parts). The working principle of a molecular pump is to attract and discharge gas molecules from the cavity through the collision of a high-speed rotating impeller, molecules, and gas.

[0017] The process of using a molecular pump to evacuate air will form the required vacuum environment in the vacuum cavity, that is, the vacuum chamber. The constructed vacuum chamber contains the heater parts, which will operate in this environment to test the temperature control performance. At this time, the heater parts will start working in the vacuum environment, generating heat through electric heating to heat the surrounding environment or samples. In a vacuum environment, the heat conduction method is different from that in a conventional environment, and it mainly relies on thermal radiation rather than convection or heat conduction. By using a molecular pump to evacuate the cavity, the air pressure in the vacuum environment can be accurately controlled to ensure that the test is carried out under ideal vacuum conditions.

[0018] S200: activating a heater component in the vacuum chamber based on an external power source to perform real-time operation monitoring and determine a real-time operation data set.

[0019] Specifically, start the external power supply to provide power to the heater parts in the vacuum chamber, so that it starts to heat up and ensures that the heater parts enter the working state and start to operate. The real-time operation monitoring system starts to work, and uses multi-dimensional operation sensing technology to monitor the working state of the heater parts, including parameters such as temperature, current and voltage, to obtain a multi-dimensional operation data set. Traverse the multi-dimensional operation data set, mark the temperature rise according to the temperature change data, and add the marked multi-dimensional operation data set containing multiple temperature rise labels to the real-time operation data set. Through real-time operation monitoring, the real-time operation data set of the heater parts during the heating process is determined, providing detailed information on the performance of the heater parts, including the changes of parameters such as temperature, current and voltage over time.

[0020] S300: Perform temperature change calculation according to the real-time operation data set to obtain multiple temperature change coefficients, perform temperature simulation control on the heater parts according to the multiple temperature change coefficients, and formulate temperature control suggestions.

[0021] Specifically, temperature change calculation is performed based on the real-time operation data set, and the temperature change trend is analyzed to obtain multiple temperature change coefficients. Accurately identifying the dominant factors affecting temperature control performance is a key factor affecting temperature control accuracy and stability. Using multiple temperature rise tags as index data, traverse the real-time operation data set to extract multiple temperature rise features. Analyze the temperature fluctuation according to multiple temperature rise features, identify the unstable part of the temperature change, and find the temperature fluctuation node. The relationship between the temperature change rate and the fluctuation amplitude is analyzed by multivariate linear regression to determine the temperature change rate of each temperature fluctuation node. Partial least squares regression is used to optimize and extract the dominant temperature change coefficients to determine which factors (such as current, voltage, or environmental conditions) have the most important impact on temperature change. Once the dominant temperature change coefficients are extracted, the dominant temperature change coefficients need to be verified, usually through actual testing to check the accuracy of the model prediction results. Through regression analysis and verification process, multiple temperature change coefficients are finally determined.

[0022] According to the physical parameter set of the heater part, the finite element analysis software is used to model and construct a temperature simulation model. The vacuum chamber is analyzed to obtain the vacuum operating environment parameters. The vacuum operating environment parameters and multiple temperature variation coefficients are input into the temperature simulation model for simulation to calculate the temperature distribution of the heater part. The temperature distribution of the heater part under normal operating conditions is predicted through the temperature simulation distribution data. The operating temperature distribution is plotted as an operating temperature prediction distribution diagram, including a temperature curve diagram, to show the temperature change trend and predict whether the temperature meets the expected value. The operating temperature prediction distribution diagram is compared with the expected temperature curve diagram to extract all temperature nodes that do not meet the expected temperature value, which can be higher or lower than the expected value, and these temperature nodes are marked as temperature nodes to be adjusted. Temperature control suggestions are formulated based on multiple temperature nodes to be adjusted, including which nodes to adjust and how to adjust the nodes. For example, if the simulation shows that the temperature of the heater will exceed 180°C under high load, the temperature control suggestion may be to reduce the heating power or start the cooling system. Through temperature variation calculation and temperature simulation, the temperature changes of heater parts under different environments can be accurately predicted, and appropriate temperature control strategies can be formulated for different temperature change characteristics to avoid overheating or overcooling of the equipment.

[0023] S400: Performing a temperature control performance test on the heater parts according to the temperature control suggestion, generating a temperature control performance score, dynamically updating the temperature control suggestion according to the temperature control performance score, and generating a maintenance instruction.

[0024] Specifically, perform temperature control performance tests according to temperature control recommendations, and conduct experiments or simulation tests on heater parts to evaluate the actual performance of the device under temperature control recommendations, including indicators such as temperature stability, energy efficiency, and failure rate during operation. Assign weights to the importance of each indicator to the test results, perform weighted calculations on each test indicator, and obtain a comprehensive temperature control performance score. Based on the temperature control performance score, determine whether the current temperature control strategy has achieved the expected results. If the score is low (such as less than 80 points), the temperature control recommendations need to be optimized and related parameters adjusted. If the score is high, the existing strategy can be maintained or fine-tuned.

[0025] The temperature control performance score is a feedback mechanism that reflects the effect of the current temperature control strategy in actual operation. Reinforcement learning will use this score as a reward function to guide the optimization process. The reward function is the standard for evaluating the quality of actions in reinforcement learning. The temperature control performance score will be used as the input of the reward function. Reinforcement learning maximizes this score by adjusting the control strategy. If the temperature control system performs well and obtains a high temperature control performance score, the system will receive a positive reward, and such a behavior strategy will be strengthened. If the score is low, the system will receive a negative reward, indicating that the current strategy needs to be improved.

[0026] Through the process of reinforcement learning, the temperature control strategy is continuously adjusted until the ideal temperature control performance score is obtained. The core purpose of reinforcement learning is to optimize the temperature control strategy through a trial and error mechanism. Once the optimal strategy is determined through learning, the temperature control recommendations are updated, and these updated recommendations will become the basis for future operations. Maintenance instructions are generated based on the updated temperature control recommendations, including adjusting the heating power, changing the control cycle, and regularly checking the equipment. Reinforcement learning can automatically adjust the temperature control strategy based on the temperature control performance score, eliminate the subjective factors of manual intervention, and reduce errors in the adjustment process. By optimizing the temperature control strategy, heating energy consumption can be reduced, energy efficiency can be improved, and the temperature of the equipment can be stabilized, which helps to reduce unnecessary energy consumption and improve equipment efficiency.

[0027] S500: Send the maintenance instruction to the remote terminal to perform intelligent temperature control maintenance on the heater parts.

[0028] Specifically, maintenance instructions usually specify how to adjust the settings of the equipment to optimize its performance, extend its service life and reduce the occurrence of failures, including operations such as changing the heating power and adjusting the feedback cycle. Once the maintenance instruction is generated, the instruction is sent to the remote terminal through a network communication protocol (such as HTTP, etc.). Communication with the remote terminal is established through a secure network connection (such as VPN or encrypted channel). Once the maintenance instruction reaches the remote terminal, the control system on the terminal will automatically execute the instruction. According to the maintenance instruction, the remote terminal will adjust the output power of the heater, feedback cycle, etc. to ensure that the equipment is always in the best working condition. The remote terminal will continuously monitor the temperature of the equipment and feedback to the central control system. If the temperature of the equipment is too high or too low, the remote terminal can take action automatically, or alarm and inform the operator through the feedback reporting system.

[0029] After the maintenance instruction is executed, the equipment operation data will continue to be collected, and the temperature control status will be fed back to the central control center through the remote terminal to evaluate the effect of the current temperature control strategy and adjust the maintenance instruction when necessary. The remote terminal continues to monitor the temperature of the equipment in real time through sensors to ensure the effectiveness of the temperature control strategy. Real-time operation data will be fed back to the central control center to help understand whether the predetermined temperature control target has been achieved. By sending maintenance instructions to the remote terminal and performing intelligent temperature control maintenance on the heater parts, the temperature control strategy can be adjusted in real time to ensure that the equipment operates in the best temperature control state.

[0030] Further, the present application S200 includes: The external power supply is started to provide power to the heater part in the vacuum chamber to generate an activation instruction; multi-dimensional operation sensing is performed on the heater part through the activation instruction to obtain a multi-dimensional operation data set; the multi-dimensional operation data set is traversed to perform temperature rise identification to generate multiple temperature rise labels; and the multiple temperature rise labels are added to the real-time operation data set.

[0031] Specifically, the external power supply is started to provide electrical energy to activate the heater parts in the vacuum chamber, ensuring that the heater parts enter the working state and start running. The external power supply is usually used to provide the required current or voltage so that the heater parts can start and run to generate the required heat. The activation instruction is a command used to start or activate the device, which is triggered by an external power supply to ensure that the heater parts enter the working state and start running. Multi-dimensional operation sensing is used to monitor the working state of the heater parts, including parameters such as temperature, current and voltage, to form a multi-dimensional operation data set.

[0032] Traverse the multidimensional operation data set, identify the temperature rise situation for the temperature change data in the multidimensional operation data set, and generate multiple temperature rise labels. Temperature rise identification is the process of identifying and classifying the temperature change (heating process) of the heater parts during the heating process. By monitoring the temperature change, it is determined whether the heater reaches the predetermined heating rate or temperature change range, and corresponding labels are generated according to different heating behaviors.

[0033] Add multiple temperature rise labels to the real-time operation data set. The real-time operation data set not only includes parameters such as temperature, current, and voltage, but also can clearly identify the temperature rise behavior corresponding to the data point through the temperature rise label. Through multi-dimensional operation sensing, temperature, current, voltage and other data can be accurately obtained to fully reflect the working status of the heater. Through temperature rise identification and labels, different heating rates and temperature control behaviors can be identified, ensuring that the temperature control performance of heater parts in a vacuum environment can be accurately monitored and optimized.

[0034] Further, the present application S300 includes: The multiple temperature rise labels are used as index data, and the real-time operation data set is traversed and analyzed according to the index data to obtain multiple temperature rise characteristics; temperature fluctuation analysis is performed according to the multiple temperature rise characteristics to determine multiple temperature fluctuation nodes, and the multiple temperature fluctuation nodes contain multiple fluctuation amplitude data; multivariate linear regression is performed on the multiple temperature fluctuation nodes according to the multiple fluctuation amplitude data to obtain multiple temperature change rates, and the multiple temperature change rates correspond to the multiple temperature fluctuation nodes; partial least squares regression is performed according to the multiple temperature change rates and the multiple temperature fluctuation nodes for optimization, and the dominant temperature change coefficients are extracted; verification is performed based on the dominant temperature change coefficients to determine the multiple temperature change coefficients.

[0035] Specifically, multiple temperature rise tags are used as index data to traverse the real-time operation data set. The temperature rise tags essentially identify different temperature rise characteristics, such as rapid temperature rise or slow temperature rise, and can therefore be used as a basis for retrieving corresponding data in the real-time operation data set. The real-time operation data set is traversed and analyzed through the index data, key features are extracted, and multiple temperature rise features are obtained. The temperature rise features are key feature parameters extracted from the temperature rise process, which are usually related to factors such as the heating rate, temperature change process, and temperature rise mode.

[0036] Perform temperature fluctuation analysis on multiple temperature rise features to identify unstable parts of temperature changes and find temperature fluctuation nodes, that is, the moment or stage when the temperature changes significantly. Temperature fluctuation analysis is to analyze the temperature changes of the equipment and identify the fluctuations in the temperature change process (such as excessively high or low temperature fluctuations). Temperature fluctuation nodes refer to the time points or stages in the temperature change process when the temperature fluctuates significantly, which may be caused by certain factors (such as current fluctuations, uneven heat dissipation, etc.). Each temperature fluctuation node contains fluctuation amplitude data, that is, the amplitude or size of the temperature change at the temperature fluctuation node, which is used to measure the degree of temperature fluctuation.

[0037] Multivariate linear regression is performed on multiple temperature fluctuation nodes according to multiple fluctuation amplitude data, and a mathematical model is established through the relationship between the fluctuation amplitude data and the temperature change rate. In other words, for each temperature fluctuation node, the model will determine the correlation between the fluctuation amplitude and the temperature change rate at that node. Multivariate linear regression is a statistical method used to analyze the linear relationship between multiple independent variables (such as fluctuation amplitude data) and dependent variables (such as temperature change rate). Through multivariate linear regression analysis, the model will find the linear relationship between the fluctuation amplitude and the temperature change rate. For example, temperature change rate = a × fluctuation amplitude + b, where a and b are the coefficients obtained by regression analysis, and the corresponding temperature change rate is obtained by fitting these data. Through multivariate linear regression analysis, each fluctuation amplitude data point will obtain a corresponding temperature change rate, and these temperature change rates together constitute multiple temperature change rates, each of which corresponds to its own temperature fluctuation node.

[0038] Partial least squares regression (PLS regression) is used to optimize multiple temperature change rates and find the best linear relationship between multiple temperature change rates and fluctuation nodes. Since the temperature change rate may be affected by multiple factors (such as current fluctuations, ambient temperature, heating power, etc.), PLS regression helps to extract the most meaningful dominant temperature change coefficient among these high-dimensional factors. Partial least squares regression is a multivariate statistical analysis method that is often used to deal with situations with multicollinearity (correlation between multiple independent variables) or high independent variable dimensions. PLS regression uses dimensionality reduction technology to project the original high-dimensional data into a lower-dimensional space while retaining as much information as possible in order to find the best linear relationship between the independent variable and the dependent variable.

[0039] The dominant temperature variation coefficient refers to the most important factor or parameter that affects the temperature change process in the temperature control system. Through PLS regression analysis, the dominant temperature variation coefficient can help identify which variables have a decisive influence on temperature change, including current fluctuations, heating power, ambient temperature and other factors. The PLS regression analysis method is used to model the relationship between the temperature change rate (dependent variable) and the temperature fluctuation node (independent variable). PLS regression combines multiple independent variables (such as fluctuation amplitude at different time points, heating power, etc.) to extract the main components in a dimensionality reduction manner to ensure that the model does not lose its predictive ability due to high-dimensional data. The goal of PLS ​​regression is to express the relationship between the independent variable and the dependent variable by finding a linear equation. Assuming that there are multiple temperature fluctuation nodes and corresponding temperature change rate data, PLS regression optimizes the weights and reduces the impact of noise to obtain the optimal regression coefficient.

[0040] After the PLS regression is completed, a set of coefficients is obtained, which reflects the linear relationship between the temperature change rate and the temperature fluctuation node. The dominant temperature change coefficients are the most important coefficients extracted from this set of coefficients. These coefficients have the greatest impact on the stability of the temperature control process and the temperature change rate. The extracted dominant temperature change coefficients need to be verified through experiments or actual data. The verification process is usually to see whether the regression model can accurately predict the temperature change rate by comparing with the actual temperature control data. If the experimental results are close to the predicted results, it means that the dominant temperature change coefficient is valid. Through the regression analysis and verification process, multiple temperature change coefficients are finally determined. These coefficients will be used to optimize the temperature control strategy and ensure that the equipment can maintain temperature stability and precise control under different working environments.

[0041] Through temperature rise feature extraction and temperature fluctuation analysis, the key factors of temperature change in the heating process can be accurately identified. Through multivariate linear regression analysis, the relationship between temperature fluctuation and temperature change rate can be determined, unstable factors can be identified and eliminated, and the temperature control process can be optimized. Through PLS regression optimization of the dominant temperature change coefficient, the accuracy of temperature control can be further improved to ensure that the equipment can maintain stable operation under various environmental conditions.

[0042] Furthermore, the present application also includes the following steps: Retrieve a physical parameter set of the heater part, perform finite element analysis based on the physical parameter set, and construct a temperature simulation model of the heater part; perform environmental analysis based on the vacuum chamber to obtain vacuum operating environmental parameters, and according to the vacuum operating environmental parameters, input the multiple temperature variation coefficients into the temperature simulation model for simulation to obtain temperature simulation distribution data; predict the heater part according to the temperature simulation distribution data, and draw an operating temperature prediction distribution diagram, wherein the operating temperature prediction distribution diagram includes an operating temperature prediction curve diagram; construct a target temperature curve diagram, take the target temperature curve diagram as the expected temperature value, traverse the operating temperature prediction curve diagram and compare it with the expected temperature value, and extract multiple temperature nodes to be adjusted; add the multiple temperature nodes to be adjusted to the temperature control suggestion.

[0043] Specifically, the physical parameter set of the heater parts is obtained through technical documents, design manuals or experimental measurements. The physical parameter set refers to various parameters related to the physical properties of the heater parts, including the thermal conductivity, specific heat capacity, density, and geometric dimensions (such as length, width, thickness), etc. of the material. Finite element analysis is performed on the physical parameter set, and the geometric model of the heater parts is digitized and discretized to form a grid composed of multiple small units (such as cubes or tetrahedrons). Specifically, the geometric shape of the heater parts is divided into small units (such as tetrahedrons, hexahedrons, etc.), and each unit will be solved by an independent heat conduction equation. Set boundary conditions such as temperature, heat flow or heat source. Input the obtained physical parameter set (such as thermal conductivity, specific heat capacity, density, etc.) into the finite element analysis model. Use the heat conduction equation (such as the heat equation mentioned above) to solve the model to obtain the temperature distribution at different locations and different time points.

[0044] Finite element analysis is a numerical method used to solve complex physical problems. The entire model is divided into multiple small units (called finite elements), each small unit is analyzed, and finally the behavior of the entire system is synthesized. After the finite element analysis, a temperature simulation model is generated according to the set physical parameters, boundary conditions and material properties, which describes the temperature changes of the heater parts at different time points and different positions, and simulates the temperature changes of the heater parts during operation.

[0045] Perform environmental analysis on the vacuum chamber to obtain vacuum operating environment parameters, including vacuum degree, air pressure, temperature, thermal radiation, etc. Vacuum degree refers to the size of the gas pressure in the vacuum chamber, and the common unit is Pa (Pascal). When the vacuum degree is high, the gas molecules are scarce, the heat convection is weak, and the heat transfer method is mainly radiation; air pressure refers to the inner cavity pressure of the vacuum chamber, which is usually lower than the atmospheric pressure and may be at the mPa level; temperature refers to the temperature in the vacuum environment, which directly affects the heating process; due to the lack of air molecules in the vacuum, heat transfer mainly relies on radiation.

[0046] Combine the vacuum operating environment parameters with multiple temperature variation coefficients, input them into the temperature simulation model, and set boundary conditions. The simulation model will simulate the temperature distribution of the heater parts under the vacuum operating environment parameters, obtain the temperature distribution of the heater parts, and display the temperature conditions of each node. Based on the temperature simulation distribution data, estimate and infer the temperature behavior of the heater parts in actual operation. Analyze the temperature simulation distribution data to identify the key features of temperature changes, such as hot spots, temperature gradients, etc. Based on these features, predict the temperature behavior of the heater parts in actual operation, including the temperature change trend over time, possible temperature extremes, etc.

[0047] Convert the temperature prediction distribution data into a format suitable for display (such as a coordinate system, heat map grid, etc.), where each grid unit represents the temperature at a certain location on the heater surface. Use professional data visualization tools to draw the operating temperature prediction distribution map. Each location in the map will have a temperature value, and different colors will be used to identify it according to the temperature value (for example, red for high temperature and blue for low temperature). The operating temperature prediction curve is a component of the operating temperature prediction distribution map. It specifically shows the trend of temperature changes over time or location. It is usually represented by a curve, showing the temperature changes at different points or at different times, and helping to analyze the stability and consistency of temperature control performance.

[0048] Build a target temperature curve based on historical normal temperature or normal operation data, and use it as the expected temperature value. Extract the temperature nodes that do not meet the expected temperature value in the operating temperature prediction curve. They can be higher or lower than the expected value, or set a range. If the deviation is too large, it needs to be adjusted. Mark these nodes as temperature nodes to be adjusted. Collect multiple temperature nodes to be adjusted and include them in the temperature control suggestions. The temperature control suggestions include temperature nodes that need to be adjusted, adjusting heating power, modifying heating areas, or optimizing cooling systems.

[0049] By adjusting the temperature nodes that need to be adjusted, the temperature control performance of the heater is optimized to ensure that the temperature control performance of the heater parts in a vacuum environment is optimal. The simulation model is used to accurately predict the temperature distribution of the heater parts in a vacuum environment, and the operating temperature is compared with the target temperature to promptly discover and adjust the nodes that deviate from the normal operating temperature, thereby ensuring that the equipment works in an ideal state.

[0050] Furthermore, the present application also includes the following steps: A historical temperature record data set of a heater part is introduced to perform temperature control analysis, and multiple temperature control target values ​​are determined, wherein the multiple temperature control target values ​​include a temperature starting value and a temperature maximum value; the temperature starting value and the temperature maximum value are spline interpolated according to the operating time of the heater part to construct a target temperature curve; the target temperature curve is used as an expected temperature value to determine whether the operating temperature prediction curve meets the expected temperature value; if the operating temperature prediction curve does not meet the expected temperature value, the operating temperature prediction curve is traversed to perform deviation calculation with the expected temperature value to determine multiple deviation coefficients; a cluster analysis is performed on the operating temperature prediction curve according to the multiple deviation coefficients to obtain a first operating temperature prediction group and a second operating temperature prediction group; adjustment identifications are performed based on the first operating temperature prediction group and the second operating temperature prediction group according to the multiple deviation coefficients to generate the multiple temperature nodes to be adjusted.

[0051] Specifically, the historical temperature record data set of the heater parts is obtained, that is, the temperature change records of the heater parts under different working conditions in the past period of time, which reflects the temperature distribution and fluctuation of the heater parts under various operating conditions, including the starting temperature value, the maximum temperature value, and the temperature fluctuation under different working conditions. The temperature control analysis of the historical temperature record data set is performed, and statistical methods such as mean, median, standard deviation, etc. are used to determine the typical distribution and change trend of the temperature.

[0052] The temperature control target value refers to the actual temperature control operation guided by the set target temperature during the operation of the heater part. Multiple temperature control target values ​​include the starting temperature value and the maximum temperature value. The starting temperature value refers to the initial temperature when the heater part starts heating, ensuring that the heater part can be heated smoothly from the predetermined starting temperature; the maximum temperature value refers to the maximum temperature expected during the operation of the heater part. Exceeding this temperature may cause equipment damage, reduced efficiency or unsafe working conditions.

[0053] The temperature start value, maximum value and operation time are used as input to generate a smooth temperature curve through spline interpolation. The interpolation method is used to fill the gaps between data points so that the target temperature curve can reflect the temperature trend of the heater part during the entire operation process. Spline interpolation is a mathematical method that constructs a smooth curve through known discrete data points (such as temperature start value, maximum value and operation time) to fill the gaps between data points. The target temperature curve is a curve generated by interpolation based on the temperature control target value (such as temperature start value and temperature maximum value) and the historical temperature record data set, which describes the expected temperature change trend and fluctuation range of the heater part during operation.

[0054] The target temperature curve is taken as the expected temperature value, that is, the temperature curve under ideal conditions. The above operating temperature prediction curve is compared with the target temperature curve to determine whether the actual operating temperature of the heater part meets the expected temperature value. If the predicted curve does not meet the target temperature, it means that the temperature control performance of the heater part is abnormal. At this time, the operating temperature prediction curve is traversed to calculate the difference between the actual operating temperature and the target temperature value to obtain multiple deviation coefficients. The deviation coefficient represents the error between the actual temperature and the expected temperature at a specific time point or location. Usually, an upper and lower temperature range is set to indicate the degree to which the actual temperature is higher or lower than the target value.

[0055] According to multiple deviation coefficients, cluster analysis is performed on the operating temperature prediction curve graph to divide it into two categories, namely the first operating temperature prediction group and the second operating temperature prediction group. The first operating temperature prediction group is the node above the target temperature, and the second operating temperature prediction group is the node below the target temperature. The heater part is a heater. The temperature drop here may be caused by the abnormality of the heater or the heater is not working. Normally, the focus is on the temperature control of the temperature rise. Through cluster analysis, different deviation nodes can be grouped to better identify the temperature area that needs to be adjusted. Cluster analysis is a data analysis method that groups similar temperature data points to make it easier to identify patterns and trends. In temperature control analysis, cluster analysis can divide the actual temperature curve into different groups, such as groups above the target temperature and groups below the target temperature, to help judge the performance of the heater part.

[0056] According to the first operating temperature prediction group and the second operating temperature prediction group, temperature change sensitivity analysis is performed according to multiple deviation coefficients, and the temperature rise safety interval and the temperature drop safety interval are set. Nodes that are not in the safety range are extracted from the first operating temperature prediction group and the second operating temperature prediction group respectively, and they are used as temperature nodes to be adjusted. These nodes indicate that there is a large deviation between the actual operating temperature and the target temperature, and temperature control adjustment is required. By introducing historical temperature data and temperature control target values, the expected temperature curve can be accurately set, and by comparing the real-time temperature prediction with the target temperature, the temperature nodes that do not meet the expectations can be identified in time, and the temperature nodes to be adjusted are generated to avoid damage to the equipment due to excessively high or low temperatures.

[0057] Furthermore, the present application also includes the following steps: According to the first operating temperature prediction group, a temperature change sensitivity analysis is performed according to the multiple deviation coefficients to generate a first sensitivity; according to the first sensitivity, a temperature rise safety interval is set, and the operating temperature prediction data that is not in the temperature rise safety interval in the first operating temperature prediction group is extracted for adjustment identification to generate a first temperature node to be adjusted; according to the second operating temperature prediction group, a temperature change sensitivity analysis is performed according to the multiple deviation coefficients to generate a second sensitivity; according to the second sensitivity, a temperature drop safety interval is set, and the operating temperature prediction data that is not in the temperature drop safety interval in the second operating temperature prediction group is extracted for adjustment identification to generate a second temperature node to be adjusted; the first temperature node to be adjusted is integrated with the second temperature node to be adjusted to determine the multiple temperature nodes to be adjusted.

[0058] Specifically, the temperature change sensitivity analysis is performed on the first operating temperature prediction group (nodes above the target temperature), and the impact of temperature rise on the equipment is calculated through the deviation coefficient. The deviation coefficient (the amplitude of temperature change) will be used as an input parameter, and combined with the data of the first operating temperature prediction group, a sensitivity analysis is performed on each temperature node. Temperature sensitivity is usually obtained by the ratio of the change in equipment performance and the temperature change (i.e., the deviation coefficient). The higher the sensitivity, the greater the impact of temperature change on the equipment, and vice versa.

[0059] The temperature rise safety interval is set according to the first sensitivity, which reflects the tolerance of temperature rise to temperature control performance, that is, the safe range allowed during the temperature rise process. The first operating temperature prediction group is traversed, and all operating temperature prediction data that are not in the temperature rise safety interval are extracted, and the adjustment mark is made for them, and they are marked as the first temperature node to be adjusted, including all nodes in the first operating temperature prediction group that are not in the temperature rise safety interval.

[0060] Similar to the operation of the first operating temperature prediction group, the second operating temperature prediction group (nodes below the target temperature) is also subjected to temperature change sensitivity analysis to obtain the second sensitivity. The temperature drop safety range is set according to the second sensitivity. The temperature rise safety range is different from the temperature drop safety range. It is possible that a large temperature rise will not affect the operation, but the temperature drop will have a great impact, and vice versa. Depending on the specific situation, the interval can be changed dynamically. Traverse the second operating temperature prediction group, extract the nodes that do not meet the temperature drop safety range, and mark them as the second temperature nodes to be adjusted.

[0061] The first temperature node to be adjusted (high temperature point) and the second temperature node to be adjusted (low temperature point) are integrated to generate the final multiple temperature nodes to be adjusted. Through temperature change sensitivity analysis and safety interval setting, high temperature or low temperature risk points can be accurately identified, and the temperature nodes to be adjusted can be identified and adjusted to avoid equipment failure or performance degradation caused by excessively high or low temperatures.

[0062] Further, the present application S400 includes: A plurality of performance test indicators are set according to the temperature simulation distribution data, and temperature control suggestions are executed according to the plurality of performance test indicators to obtain a plurality of temperature control performance test results; weights are assigned to the plurality of temperature control performance test results based on the plurality of performance test indicators to determine a performance weight matrix; temperature control performance scores are scored for heater parts based on the performance weight matrix to generate a temperature control performance score; reinforcement learning is performed on the temperature control suggestions using the temperature control performance score as a reward function, and the temperature control suggestions are updated according to the learning results to generate the maintenance instructions.

[0063] Specifically, according to the temperature simulation distribution data, set multiple performance test indicators related to heater parts, including temperature stability, energy efficiency, failure rate, etc., to fully reflect the temperature control performance of heater parts. According to the set multiple performance test indicators, implement temperature control recommendations, conduct actual tests, and collect test data, such as temperature fluctuation range, energy consumption data, number of failures, etc. According to the importance of different performance test indicators, assign weights to multiple temperature control performance test results, and construct a performance weight matrix. Each element in the matrix corresponds to the weight of an indicator. For example, the weight of temperature stability is 50%, the weight of energy consumption is 30%, and the weight of failure rate is 20%.

[0064] The temperature control performance of the heater parts is scored according to the performance weight matrix. That is to say, each performance test result and its corresponding performance weight are weighted and summed to obtain the temperature control performance score. This score combines the numerical values ​​of the weights of various performance indicators and can reflect the overall performance of the heater parts.

[0065] The reward function is built around the temperature control performance score to guide reinforcement learning to optimize the temperature control recommendations. Reinforcement learning is a reward-based learning mechanism that obtains rewards or penalties by interacting with the environment and gradually learns the optimal strategy. In reinforcement learning, the reward function is used to evaluate the effect of each action (temperature control recommendation). The reward function is designed based on the temperature control performance score to derive a suitable temperature control strategy.

[0066] The goal of reinforcement learning is to optimize temperature control recommendations and improve temperature control performance scores. The parameter set of the current temperature control strategy is used as the state, the adjustment of temperature control parameters is used as the behavior action, the reward value calculated according to the temperature control performance score is used as the reward, and the behavior action taken under the state is determined as the strategy. The temperature control performance score will be used as a reward function and input into the reinforcement learning model (such as deep Q learning). The current temperature control strategy is adjusted according to this score, and how to improve the temperature control recommendations is learned to optimize the operating performance of the heater parts. For example, if the temperature control strategy causes excessive temperature fluctuations and a low score, the system will adjust the heating power through learning to reduce temperature fluctuations; if the energy efficiency is too low, the system will reduce power consumption to improve energy efficiency.

[0067] In the process of reinforcement learning, the system continuously optimizes the temperature control strategy and finally generates the optimal temperature control solution for heater parts. The optimal temperature control solution will serve as a specific maintenance instruction to guide operators to adjust the equipment according to the optimization strategy, thereby improving the temperature control effect and long-term operation stability of the equipment. Through reinforcement learning, the temperature control strategy is automatically adjusted to achieve the best performance. Through comprehensive evaluation of temperature control performance scores, temperature stability and energy efficiency are optimized to reduce equipment failures.

[0068] In summary, the heater temperature control performance detection method based on a vacuum environment provided by the present application has the following technical effects: The cavity is evacuated by a molecular pump to construct a vacuum chamber, which contains a heater part; the heater part in the vacuum chamber is activated based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; temperature change calculation is performed based on the real-time operation data set to obtain multiple temperature change coefficients, and temperature simulation control is performed on the heater part according to the multiple temperature change coefficients to formulate temperature control suggestions; the temperature control performance of the heater part is tested according to the temperature control suggestions to generate a temperature control performance score, and the temperature control suggestion is dynamically updated according to the temperature control performance score to generate a maintenance instruction; the maintenance instruction is sent to a remote terminal to perform temperature intelligent control maintenance on the heater part. In other words, a vacuum chamber environment containing a heater part is constructed by evacuating a specific cavity by a molecular pump, the heater part is activated for real-time operation monitoring, and temperature change calculation is performed based on the real-time operation data set, so as to formulate corresponding temperature control suggestions and generate specific maintenance instructions, which not only improves the operation efficiency of the heater part, but also reduces the risk of failure caused by abnormal temperature.

[0069] Embodiment 2, based on the same inventive concept as the method for detecting the temperature control performance of a heater in a vacuum environment in the aforementioned embodiment 1, the present application also provides a system for detecting the temperature control performance of a heater in a vacuum environment, please refer to the attached Figure 2 The heater temperature control performance detection system based on a vacuum environment includes: A vacuum chamber construction module 11, the vacuum chamber construction module 11 is used to perform a vacuum operation on the cavity through a molecular pump to construct a vacuum chamber, and the vacuum chamber contains a heater part; a real-time monitoring module 12, the real-time monitoring module 12 is used to activate the heater part in the vacuum chamber based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; a temperature change calculation module 13, the temperature change calculation module 13 is used to perform temperature change calculation according to the real-time operation data set to obtain multiple temperature change coefficients, perform temperature simulation control on the heater part according to the multiple temperature change coefficients, and formulate temperature control suggestions; a performance testing module 14, the performance testing module 14 is used to perform temperature control performance testing on the heater part according to the temperature control suggestion, generate a temperature control performance score, dynamically update the temperature control suggestion according to the temperature control performance score, and generate a maintenance instruction; a temperature control maintenance module 15, the temperature control maintenance module 15 is used to send the maintenance instruction to a remote terminal to perform temperature intelligent control maintenance on the heater part.

[0070] Furthermore, the real-time monitoring module 12 in the heater temperature control performance detection system based on a vacuum environment is also used for: The external power supply is started to provide power to the heater part in the vacuum chamber to generate an activation instruction; multi-dimensional operation sensing is performed on the heater part through the activation instruction to obtain a multi-dimensional operation data set; the multi-dimensional operation data set is traversed to perform temperature rise identification to generate multiple temperature rise labels; and the multiple temperature rise labels are added to the real-time operation data set.

[0071] Furthermore, the temperature change calculation module 13 in the heater temperature control performance detection system based on a vacuum environment is also used for: The multiple temperature rise labels are used as index data, and the real-time operation data set is traversed and analyzed according to the index data to obtain multiple temperature rise characteristics; temperature fluctuation analysis is performed according to the multiple temperature rise characteristics to determine multiple temperature fluctuation nodes, and the multiple temperature fluctuation nodes contain multiple fluctuation amplitude data; multivariate linear regression is performed on the multiple temperature fluctuation nodes according to the multiple fluctuation amplitude data to obtain multiple temperature change rates, and the multiple temperature change rates correspond to the multiple temperature fluctuation nodes; partial least squares regression is performed according to the multiple temperature change rates and the multiple temperature fluctuation nodes for optimization, and the dominant temperature change coefficients are extracted; verification is performed based on the dominant temperature change coefficients to determine the multiple temperature change coefficients.

[0072] Furthermore, the temperature change calculation module 13 in the heater temperature control performance detection system based on a vacuum environment is also used for: Retrieve a physical parameter set of the heater part, perform finite element analysis based on the physical parameter set, and construct a temperature simulation model of the heater part; perform environmental analysis based on the vacuum chamber to obtain vacuum operating environmental parameters, and according to the vacuum operating environmental parameters, input the multiple temperature variation coefficients into the temperature simulation model for simulation to obtain temperature simulation distribution data; predict the heater part according to the temperature simulation distribution data, and draw an operating temperature prediction distribution diagram, wherein the operating temperature prediction distribution diagram includes an operating temperature prediction curve diagram; construct a target temperature curve diagram, take the target temperature curve diagram as the expected temperature value, traverse the operating temperature prediction curve diagram and compare it with the expected temperature value, and extract multiple temperature nodes to be adjusted; add the multiple temperature nodes to be adjusted to the temperature control suggestion.

[0073] Furthermore, the temperature change calculation module 13 in the heater temperature control performance detection system based on a vacuum environment is also used for: A historical temperature record data set of a heater part is introduced to perform temperature control analysis, and multiple temperature control target values ​​are determined, wherein the multiple temperature control target values ​​include a temperature starting value and a temperature maximum value; the temperature starting value and the temperature maximum value are spline interpolated according to the operating time of the heater part to construct a target temperature curve; the target temperature curve is used as an expected temperature value to determine whether the operating temperature prediction curve meets the expected temperature value; if the operating temperature prediction curve does not meet the expected temperature value, the operating temperature prediction curve is traversed to perform deviation calculation with the expected temperature value to determine multiple deviation coefficients; a cluster analysis is performed on the operating temperature prediction curve according to the multiple deviation coefficients to obtain a first operating temperature prediction group and a second operating temperature prediction group; adjustment identifications are performed based on the first operating temperature prediction group and the second operating temperature prediction group according to the multiple deviation coefficients to generate the multiple temperature nodes to be adjusted.

[0074] Furthermore, the temperature change calculation module 13 in the heater temperature control performance detection system based on a vacuum environment is also used for: According to the first operating temperature prediction group, a temperature change sensitivity analysis is performed according to the multiple deviation coefficients to generate a first sensitivity; according to the first sensitivity, a temperature rise safety interval is set, and the operating temperature prediction data that is not in the temperature rise safety interval in the first operating temperature prediction group is extracted for adjustment identification to generate a first temperature node to be adjusted; according to the second operating temperature prediction group, a temperature change sensitivity analysis is performed according to the multiple deviation coefficients to generate a second sensitivity; according to the second sensitivity, a temperature drop safety interval is set, and the operating temperature prediction data that is not in the temperature drop safety interval in the second operating temperature prediction group is extracted for adjustment identification to generate a second temperature node to be adjusted; the first temperature node to be adjusted is integrated with the second temperature node to be adjusted to determine the multiple temperature nodes to be adjusted.

[0075] Furthermore, the performance testing module 14 in the heater temperature control performance testing system based on a vacuum environment is also used for: A plurality of performance test indicators are set according to the temperature simulation distribution data, and temperature control suggestions are executed according to the plurality of performance test indicators to obtain a plurality of temperature control performance test results; weights are assigned to the plurality of temperature control performance test results based on the plurality of performance test indicators to determine a performance weight matrix; temperature control performance scores are scored for heater parts based on the performance weight matrix to generate a temperature control performance score; reinforcement learning is performed on the temperature control suggestions using the temperature control performance score as a reward function, and the temperature control suggestions are updated according to the learning results to generate the maintenance instructions.

[0076] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The heater temperature control performance detection method based on a vacuum environment and the specific examples in Example 1 are also applicable to the heater temperature control performance detection system based on a vacuum environment in this embodiment. Through the above detailed description of the heater temperature control performance detection method based on a vacuum environment, those skilled in the art can clearly understand the heater temperature control performance detection system based on a vacuum environment in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0077] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0078] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting the temperature control performance of a heater based on a vacuum environment, characterized in that: include: The cavity is evacuated by a molecular pump to construct a vacuum chamber, wherein the vacuum chamber includes a heater component; Activate the heater component in the vacuum chamber based on an external power source to perform real-time operation monitoring and determine a real-time operation data set; Perform temperature change calculation according to the real-time operation data set to obtain multiple temperature change coefficients, perform temperature simulation control on the heater parts according to the multiple temperature change coefficients, and formulate temperature control suggestions; Performing a temperature control performance test on the heater parts according to the temperature control suggestions, generating a temperature control performance score, dynamically updating the temperature control suggestions according to the temperature control performance score, and generating a maintenance instruction; The maintenance instruction is sent to a remote terminal to perform intelligent temperature control maintenance on heater parts.

2. The method for detecting the temperature control performance of a heater based on a vacuum environment according to claim 1, characterized in that: Based on the external power supply, the heater parts in the vacuum chamber are activated to perform real-time operation monitoring, and a real-time operation data set is determined, including: Starting the external power supply to provide electrical energy to the heater parts in the vacuum chamber to generate an activation instruction; Perform multi-dimensional operation sensing on the heater parts through the activation instructions to obtain a multi-dimensional operation data set; Traversing the multidimensional operation data set to identify temperature rises and generate multiple temperature rise labels; The plurality of temperature rise tags are added to the real-time operation data set.

3. The method for detecting the temperature control performance of a heater based on a vacuum environment according to claim 2, characterized in that: Temperature variation calculation is performed according to the real-time operation data set to obtain multiple temperature variation coefficients, including: Using the multiple temperature rise tags as index data, traversing and analyzing the real-time operation data set according to the index data to obtain multiple temperature rise features; Perform temperature fluctuation analysis according to the multiple temperature rise characteristics to determine multiple temperature fluctuation nodes, wherein the multiple temperature fluctuation nodes include multiple fluctuation amplitude data; Perform multivariate linear regression on the multiple temperature fluctuation nodes according to the multiple fluctuation amplitude data to obtain multiple temperature change rates, wherein the multiple temperature change rates correspond to the multiple temperature fluctuation nodes; The multiple temperature variation coefficients are determined by performing partial least squares regression optimization according to the multiple temperature variation rates and the multiple temperature fluctuation nodes, extracting the dominant temperature variation coefficient, and performing verification based on the dominant temperature variation coefficient.

4. The method for detecting the temperature control performance of a heater based on a vacuum environment according to claim 1, characterized in that: Perform temperature simulation control on the heater parts according to the multiple temperature variation coefficients and formulate temperature control suggestions, including: Retrieving a physical parameter set of the heater part, performing finite element analysis based on the physical parameter set, and building a temperature simulation model of the heater part; Performing environmental analysis based on the vacuum chamber to obtain vacuum operating environmental parameters, and inputting the plurality of temperature variation coefficients into the temperature simulation model for simulation according to the vacuum operating environmental parameters to obtain temperature simulation distribution data; Predicting the heater parts according to the temperature simulation distribution data, and drawing an operating temperature prediction distribution diagram, wherein the operating temperature prediction distribution diagram includes an operating temperature prediction curve diagram; Constructing a target temperature curve graph, taking the target temperature curve graph as an expected temperature value, traversing the operating temperature prediction curve graph and comparing it with the expected temperature value, and extracting a plurality of temperature nodes to be adjusted; The multiple temperature nodes to be adjusted are added to the temperature control suggestion.

5. The method for detecting the temperature control performance of a heater based on a vacuum environment according to claim 4, characterized in that: The step of constructing a target temperature curve graph, taking the target temperature curve graph as an expected temperature value, traversing the operating temperature prediction curve graph and comparing it with the expected temperature value, and extracting a plurality of temperature nodes to be adjusted includes: Introducing a historical temperature record data set of a heater part to perform temperature control analysis and determine multiple temperature control target values, wherein the multiple temperature control target values ​​include a temperature start value and a temperature maximum value; Perform spline interpolation on the temperature starting value and the temperature maximum value according to the operation time of the heater component to construct a target temperature curve graph; Taking the target temperature curve as the expected temperature value, determining whether the operating temperature prediction curve meets the expected temperature value; If the operating temperature prediction curve does not conform to the expected temperature value, traversing the operating temperature prediction curve and the expected temperature value to perform deviation calculation and determine a plurality of deviation coefficients; Performing cluster analysis on the operating temperature prediction curve graph according to the multiple deviation coefficients to obtain a first operating temperature prediction group and a second operating temperature prediction group; Based on the first operating temperature prediction group and the second operating temperature prediction group, adjustment marks are performed according to the multiple deviation coefficients to generate the multiple temperature nodes to be adjusted.

6. The method for detecting the temperature control performance of a heater in a vacuum environment according to claim 5, characterized in that: The step of adjusting the identifications based on the first operating temperature prediction group and the second operating temperature prediction group according to the plurality of deviation coefficients to generate the plurality of temperature nodes to be adjusted includes: Performing temperature change sensitivity analysis according to the first operating temperature prediction group and the plurality of deviation coefficients to generate a first sensitivity; Setting a temperature rise safety interval according to the first sensitivity, extracting the operating temperature prediction data that is not in the temperature rise safety interval in the first operating temperature prediction group for adjustment identification, and generating a first temperature node to be adjusted; Performing temperature change sensitivity analysis according to the second operating temperature prediction group and the plurality of deviation coefficients to generate a second sensitivity; Setting a temperature drop safety interval according to the second sensitivity, extracting the operating temperature prediction data that is not in the temperature drop safety interval in the second operating temperature prediction group for adjustment identification, and generating a second temperature node to be adjusted; The first temperature node to be adjusted and the second temperature node to be adjusted are integrated to determine the plurality of temperature nodes to be adjusted.

7. The method for detecting the temperature control performance of a heater based on a vacuum environment according to claim 4, characterized in that: Performing a temperature control performance test on the heater parts according to the temperature control suggestion, generating a temperature control performance score, dynamically updating the temperature control suggestion according to the temperature control performance score, and generating a maintenance instruction, including: Setting a plurality of performance test indicators according to the temperature simulation distribution data, executing temperature control suggestions according to the plurality of performance test indicators, and obtaining a plurality of temperature control performance test results; Based on the multiple performance test indicators, weights are assigned to the multiple temperature control performance test results to determine a performance weight matrix; Performing a temperature control performance score on the heater parts based on the performance weight matrix to generate a temperature control performance score; The temperature control performance score is used as a reward function to perform reinforcement learning on the temperature control suggestion, and the temperature control suggestion is updated according to the learning result to generate the maintenance instruction.

8. A heater temperature control performance detection system based on a vacuum environment, characterized in that: The steps for implementing the method for detecting the temperature control performance of a heater based on a vacuum environment according to any one of claims 1 to 7, wherein the temperature control performance detection system for a heater based on a vacuum environment comprises: A vacuum chamber construction module, wherein the vacuum chamber construction module is used to evacuate the chamber through a molecular pump to construct a vacuum chamber, wherein the vacuum chamber includes a heater component; A real-time monitoring module, the real-time monitoring module is used to activate the heater parts in the vacuum chamber based on an external power supply to perform real-time operation monitoring and determine a real-time operation data set; A temperature change calculation module, the temperature change calculation module is used to perform temperature change calculation according to the real-time operation data set, obtain multiple temperature change coefficients, perform temperature simulation control on the heater parts according to the multiple temperature change coefficients, and formulate temperature control suggestions; A performance testing module, the performance testing module is used to perform a temperature control performance test on the heater parts according to the temperature control suggestion, generate a temperature control performance score, dynamically update the temperature control suggestion according to the temperature control performance score, and generate a maintenance instruction; A temperature control and maintenance module is used to send the maintenance instructions to a remote terminal to perform intelligent temperature control and maintenance on heater parts.

Images