An intelligent temperature control method for a test chamber

Abstract

The present invention relates to the field of temperature regulation, and particularly to an intelligent temperature regulation method and system for a test chamber. The method includes: calculating the optimal perturbation range in the simulated annealing algorithm, and obtaining the temperature inside the test chamber in the next time period by using the simulated annealing algorithm. The calculation method of the optimal perturbation range is as follows: obtaining a data set, where the data set includes multiple temperature data in the current time period, calculating the degree of dispersion of the data in the data set, calculating the perturbation range optimization factor for the current time period, the perturbation range optimization factor is positively correlated with the degree of dispersion, and taking the product of the perturbation range optimization factor and the preset perturbation range as the optimal perturbation range. The present invention has the effect of improving the calculation efficiency and control accuracy of the simulated annealing algorithm.

Description

Technical Field

[0001] The present invention relates to the field of temperature control, and particularly to an intelligent temperature control method for a test chamber. Background Art

[0002] A test chamber is a device used to test and simulate environmental conditions for materials, products, equipment, etc. The test chamber can simulate different environmental conditions, such as temperature, humidity, vibration, salt spray, etc., and is usually used to detect the performance, durability, and stability of products under specific environments. As a type of test chamber, an aging test chamber is applied in industries such as electronics, automotive, aviation, materials, and household appliances to simulate the long-term use environment of products and evaluate the reliability and durability of products. Traditional temperature control systems usually rely on simple thermostats or timing controls, and have problems such as low accuracy, slow response, and high energy consumption.

[0003] The Chinese patent application document with the patent publication number CN118655932A discloses a temperature control and monitoring system for the production process of fascia balls. The system includes a temperature real-time monitoring module, a temperature anomaly analysis module, a temperature control strategy module, a production scheduling optimization module, a temperature prediction model module, an equipment status diagnosis module, a parameter adjustment module, and a product quality inspection module. By introducing a long short-term memory network and a simulated annealing algorithm, the intelligent dynamic adjustment of the temperature control strategy is realized, allowing the system to intelligently judge the severity of the abnormal state according to the real-time data of temperature changes and adjust the temperature control strategy accordingly. For high-frequency fluctuations, the system can quickly adopt short-term high-power regulation, while for low-frequency fluctuations, long-term low-power regulation is implemented.

[0004] The simulated annealing algorithm can be used to control the temperature of the aging test chamber. When the simulated annealing algorithm performs intelligent control of the temperature, the perturbation range selected in each simulated annealing process (i.e., each temperature control) is a fixed value. If the perturbation range is too large, the search process is relatively rough, the convergence speed is slow, and it is impossible to quickly converge to the optimal solution. If the perturbation range is too small, the search process will become very detailed, and more iteration times are required to gradually optimize, resulting in low computational efficiency. Summary of the Invention

[0005] In order to solve the problem of low computational efficiency caused by the fixed perturbation range of the existing simulated annealing algorithm, the present invention provides an intelligent temperature control method and system for a test chamber.

[0006] The present invention provides an intelligent temperature control method for a test chamber, adopting the following technical solution:

[0007] Calculate the optimal perturbation range in the simulated annealing algorithm, and use the simulated annealing algorithm to obtain the temperature in the test chamber in the next time period;

[0008] Among them, the calculation method of the optimal perturbation range is as follows: obtain a data set, the data set includes multiple temperature data within the current time period, calculate the dispersion degree of the data in the data set, calculate the perturbation range optimization factor for the current time period, the perturbation range optimization factor is positively correlated with the dispersion degree, and take the product of the perturbation range optimization factor and the preset perturbation range as the optimal perturbation range.

[0009] Obtaining the perturbation range optimization factor based on the characteristics of the data set and further obtaining the optimal perturbation range can avoid the search process being too violent due to too large a perturbation amplitude and avoid the search being too slow due to too small a perturbation amplitude. Thus, while ensuring the search efficiency, it accelerates the convergence of the algorithm, enables each temperature control process to be more precise, avoids interference caused by data noise, and improves the stability and accuracy of temperature control. The optimization of the dynamic perturbation range based on the change characteristics of temperature data can better adapt to different temperature control scenarios, achieve more refined intelligent control, ultimately improve the computational efficiency and control accuracy of the entire system, reduce energy consumption, and enhance the repeatability and reliability of the experiment.

[0010] Preferably, the expression of the dispersion degree is:

[0011] ;

[0012] In the formula, represents the dispersion degree of the data set referred to during the s-th temperature control, represents the number of data points in the data set, represents the Z-Score value of the r-th data point in the data set referred to during the s-th temperature control, represents the information entropy value of the data set referred to during the s-th temperature control.

[0013] Through the above formula, the dispersion degree of the data in the data set can be calculated, improving the accuracy of the calculation result of the dispersion degree.

[0014] Preferably, the expression of the perturbation range optimization factor is:

[0015] ;

[0016] In the formula, represents the perturbation range optimization factor corresponding to the s-th temperature control, represents the dispersion degree of the data set referred to during the s-th temperature control, represents the maximum value of the number of monotonically increasing or monotonically decreasing data points in the data set referred to during the s-th temperature control, represents the number of data points in the data set, It represents the correlation coefficient preset for the data set referred to during the s-th temperature control. exp represents the exponential function with base e, and norm represents the normalization function.

[0017] By analyzing the characteristics of temperature data, noise data can be identified, facilitating the adjustment of the optimization strategy for the perturbation range on this basis, reducing the interference of noise data on the perturbation range optimization factor, and making it more in line with the actual requirements of the current temperature state.

[0018] Preferably, the expression of the perturbation range optimization factor is:

[0019] ;

[0020] In the formula, represents the perturbation range optimization factor corresponding to the s-th temperature control, represents the degree of dispersion of the data set referred to during the s-th temperature control, represents the maximum value of the number of monotonically increasing or decreasing data points in the data set referred to during the s-th temperature control, represents the number of data points in the data set, represents the correlation coefficient preset for the data set referred to during the s-th temperature control, represents the logarithmic function with base e, represents a preset constant, and norm represents the normalization function.

[0021] Preferably, the calculation method of the correlation coefficient is:

[0022] Calculate the first difference between each data point and its adjacent data point on the left, and calculate the second difference between the corresponding data point and its adjacent data point on the right; if the product of the first difference and the second difference is less than 0, then regard the corresponding data point as a reference data point, and take the number of reference data points as the correlation coefficient of the data set.

[0023] By calculating the correlation coefficient, the credibility of the data fluctuation range in the data set can be understood. The larger its value, the greater the possibility that the data fluctuation range in the data set is larger.

[0024] Preferably, the method for obtaining the temperature in the test chamber in the next time period using the simulated annealing algorithm includes:

[0025] Randomly generate a new solution within the best perturbation range of the current solution;

[0026] Construct an objective function, and use the objective function to calculate the objective function values of the current solution and the new solution;

[0027] Take the difference between the objective function values of the current solution and the new solution as the energy difference;

[0028] In response to the energy difference being less than or equal to 0, accept the new solution as the current solution; otherwise, accept the new solution with a certain probability.

[0029] Preferably, the expression of the objective function is: ;

[0030] In the formula, E represents the objective function value, τ represents the preset first weight, represents the preset second weight, q represents the partial discharge amplitude of the test product in the test chamber at the corresponding temperature during the simulated annealing process, v represents the partial discharge frequency of the test product in the test chamber at the corresponding temperature during the simulated annealing process, and N represents the energy consumption of the test chamber in the corresponding temperature state during the simulated annealing process.

[0031] By constructing the objective function value, it is convenient to understand the energy value of each new solution, so as to facilitate the calculation of the energy difference between the current solution and the new solution for judging whether to directly accept the new solution.

[0032] Preferably, the expression of the objective function is: ;

[0033] In the formula, E represents the objective function value, τ represents the preset first weight, represents the preset second weight, R represents the insulation resistance value of the test product in the test chamber at the corresponding temperature during the simulated annealing process, and N represents the energy consumption of the test chamber in the corresponding temperature state during the simulated annealing process.

[0034] The present invention has the following technical effects:

[0035] 1. Based on the characteristics of the data set, obtain the perturbation range optimization factor, and further obtain the optimal perturbation range, which can avoid the search process being too violent due to too large a perturbation amplitude and avoid the search being too slow due to too small a perturbation amplitude. Thus, while ensuring the search efficiency, it accelerates the convergence of the algorithm, can make each temperature control process more accurate, avoid interference caused by data noise, and improve the stability and accuracy of temperature control. The optimization of the dynamic perturbation range based on the temperature data change characteristics can better adapt to different temperature control scenarios, realize more refined intelligent control, ultimately improve the calculation efficiency and control accuracy of the simulated annealing algorithm, reduce the energy consumption of the aging test chamber, and enhance the reliability of the experiment.

[0036] 2. By the change characteristics of the temperature data in the test chamber and obtaining the perturbation range optimization factor for each temperature control, the accuracy and efficiency of the simulated annealing algorithm in temperature intelligent control can be significantly improved. By deeply analyzing the characteristics of the temperature data, noise data can be identified, and on this basis, the optimization strategy of the perturbation range can be adjusted to make it more in line with the actual needs of the current temperature state. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understandable. In the drawings, several embodiments of the present invention are shown by way of example and not limitation, and like or corresponding reference numerals represent like or corresponding parts.

[0038] Figure 1 is a flowchart of an intelligent temperature control method for a test chamber of the present invention. Detailed implementation manners

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0040] It should be understood that when terms such as "first" and "second" are used in the claims, the description, and the drawings of the present invention, they are only used to distinguish different objects and not to describe a specific order. The terms "including" and "comprising" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0041] An embodiment of the present invention discloses an intelligent temperature control method for a test chamber. Referring to Figure 1 , it includes steps S1 - S2, specifically as follows:

[0042] S1: Calculate the optimal perturbation range in the simulated annealing algorithm.

[0043] S11: Obtain a data set, where the data set includes multiple temperature data within the current time period.

[0044] Use a temperature sensor to collect the temperature data in the test chamber in real time. The collection duration is the entire aging test process of the aging test chamber, the collection frequency is once per second, the data set contains multiple data within the current time period, and the multiple data are arranged in chronological order. Exemplarily, the data set is the temperature data within the current 3 - minute time period.

[0045] S12: Calculate the degree of dispersion of the data in the data set.

[0046] Based on the data change characteristics of the temperature data in the data set, calculate the optimization amplitude of the perturbation range for each temperature control. First, calculate the degree of dispersion of the data in the data set.

[0047] The expression for the degree of dispersion is: ; where, represents the degree of dispersion of the data set referred to during the s-th temperature control, represents the number of data points in the data set, represents the Z-Score value of the r-th data point in the data set referred to during the s-th temperature control, which is calculated by the Z-Score model. The Z-Score model is a prior art, and the specific calculation steps are not elaborated here. represents the information entropy value of the data set referred to during the s-th temperature control. The data set referred to during the s-th temperature control is the temperature data within the time period where the s-th temperature control moment is located.

[0048] In the formula represents the distance of the r-th data point in the data set referred to during the s-th temperature control from the data mean value within the data set, represents the sum of the distances of all data points in the data set referred to during the s-th temperature control from the data mean value within the data set. The larger this value is, the more discrete the data distribution of the data set referred to during the s-th temperature control is, and the greater the corresponding degree of dispersion is. The larger it is, the more times different temperature values appear in the data set referred to during the s-th temperature control, indicating that the data distribution in the data set referred to during the s-th temperature control is more chaotic, and the degree of dispersion of the data set is greater.

[0049] S13: Calculate the disturbance range optimization factor for the current time period. The disturbance range optimization factor is positively correlated with the degree of dispersion.

[0050] There are noise data in the data set, and the noise data interfere with the optimization amplitude of the disturbance range during each temperature control. The difference between the noise data and the normal data lies in that: there is a stable change trend among the normal temperature data, while the noise data shows irregular and random fluctuations and usually deviates from the normal temperature change trend. Therefore, analyze the numerical change situation in the data set referred to during each temperature control to obtain the corresponding disturbance range optimization factor.

[0051] In the data set, calculate the first difference between each data point and the adjacent data point on the left, and calculate the second difference between the corresponding data point and the adjacent data point on the right; if the product of the first difference and the second difference is less than 0, then regard the corresponding data point as a reference data point, and regard the number of reference data points as the correlation coefficient of the data set.

[0052] In one embodiment, the expression of the disturbance range optimization factor is:

[0053] ;

[0054] where, represents the perturbation range optimization factor corresponding to the s-th temperature control represents the degree of dispersion of the data set referred to during the s-th temperature control represents the maximum value of the number of monotonically increasing or decreasing data points in the data set referred to during the s-th temperature control represents the number of data points in the data set represents the preset correlation coefficient of the data set referred to during the s-th temperature control, exp represents the exponential function with base e, and norm represents the normalization function

[0055] In the formula The larger it is, the more discrete the data distribution in the data set corresponding to the s-th temperature control is, and the larger the perturbation range required during temperature control is, so as to ensure that the flexibility of the search can be maintained under large temperature fluctuations, making it easier to find the global optimal solution or avoid the system falling into local extrema

[0056] In the formula quantifies the amplitude of data fluctuations in the data set referred to during the s-th temperature control. The larger this value is, the more noise data may exist in this data segment, and the greater the possibility that the degree of dispersion of the data set is affected by noise data. Then, the corresponding perturbation range during temperature control should be smaller, and the corresponding perturbation range optimization factor should also be smaller quantifies the positive and negative attribute situation of the numerical changes between data points in the data set. The smaller this value is, the fewer the number of continuously monotonically increasing or decreasing data points between data points in the data set, indicating that the amplitude of data fluctuations in the data set is larger, and the corresponding perturbation range optimization factor should also be smaller The larger it is, the greater the credibility that the amplitude of data fluctuations in the data set is larger, indicating that the corresponding perturbation range optimization factor is smaller

[0057] In one embodiment, the expression of the perturbation range optimization factor is

[0058] ;

[0059] In the formula represents the perturbation range optimization factor corresponding to the s-th temperature control represents the degree of dispersion of the data set referred to during the s-th temperature control represents the maximum value of the number of monotonically increasing or decreasing data points in the data set referred to during the s-th temperature control represents the number of data points in the data set represents the preset correlation coefficient of the data set referred to during the s-th temperature control represents the logarithmic function with base e M represents a preset constant. Exemplarily, the value of M is 10, and norm represents a normalization function.

[0060] S14: Use the product of the perturbation range optimization factor and the preset perturbation range as the optimal perturbation range.

[0061] Expression of the optimal perturbation range: ; In the formula, represents the optimal perturbation range during the s-th temperature control, represents the perturbation range set during the intelligent temperature control of the simulated annealing algorithm, represents the perturbation range optimization factor corresponding to the s-th temperature control.

[0062] S2: Use the simulated annealing algorithm to obtain the temperature inside the test chamber in the next time period.

[0063] S21: Construct the objective function.

[0064] In one embodiment, the expression of the objective function is: ;

[0065] In the formula, E represents the objective function value, τ represents the preset first weight, represents the preset second weight, q represents the partial discharge amplitude of the test product in the test chamber at the corresponding temperature during the simulated annealing process, v represents the partial discharge frequency of the test product in the test chamber at the corresponding temperature during the simulated annealing process, N represents the energy consumption of the test chamber in the corresponding temperature state during the simulated annealing process, where q and v are obtained from the tests of the corresponding test products during the historical test process.

[0066] In the objective function, the aging effect of a temperature value in an aging interval is quantified by (q×v). The smaller this value is, the worse the aging effect is, the larger the objective function value is, and the worse the priority of the corresponding temperature value in the selection process of the temperature optimal solution is; the larger N is in the objective function, the greater the energy consumption required for the corresponding temperature value is, the larger the objective function value is, and the worse the priority of the corresponding temperature value in the selection process of the temperature optimal solution is.

[0067] In one embodiment, the expression of the objective function is: ;

[0068] In the formula, E represents the objective function value, τ represents the preset first weight, represents the preset second weight, R represents the insulation resistance value of the test product in the test chamber at the corresponding temperature during the simulated annealing process, and N represents the energy consumption of the test chamber in the corresponding temperature state during the simulated annealing process.

[0069] In the objective function, the aging effect of a temperature value within an aging interval is quantified by the insulation resistance value R. The smaller this value is, the worse the aging effect, and the larger the objective function value is. The lower the priority of the corresponding temperature value in the selection process of the temperature optimal solution. The larger N is in the objective function, the greater the energy consumption required for the corresponding temperature value, the larger the objective function value, and the lower the priority of the corresponding temperature value in the selection process of the temperature optimal solution.

[0070] S22: Use the simulated annealing algorithm to calculate the temperature inside the test chamber in the next time period.

[0071] Set the initialization parameters in the simulated annealing algorithm. The initialization parameters include the initial solution, the initial temperature, the termination temperature, and the cooling rate. Starting from the initial solution and the initial temperature, enter the iterative loop until the temperature drops to the termination temperature. Exemplarily, the initial solution is set to the empirical value of 80 °C, the initial temperature is set to 100 °C, the termination temperature is preset to 50 °C, and the cooling rate is set to 0.96.

[0072] In the iterative loop, first take the initial solution as the current solution. Randomly select a new solution within the best perturbation range of the current solution. Take the objective function value of the new solution as the first function value, take the objective function value of the current solution as the second function value, and take the difference between the first function value and the second function value as the energy difference. In response to the energy difference being less than or equal to 0, accept the new solution as the current solution. Otherwise, accept the new solution with a certain probability to avoid premature convergence to a local optimal solution. Then update the temperature according to the set cooling rate and continue to search for a new solution. When the temperature drops to the termination temperature or reaches the maximum number of iterations, the algorithm ends and outputs the current solution as the optimal solution. The optimal solution is the best temperature inside the test chamber in the next time period.

[0073] Exemplarily, every 3 minutes is a temperature control cycle. At the end of the 3rd minute, calculate a best perturbation range based on the temperature data within 3 minutes obtained from the data set. Use the simulated annealing algorithm to search for the best temperature inside the test chamber in the next time period, that is, the best temperature inside the test chamber in the next temperature control cycle. Then, adjust the temperature inside the test chamber to the best temperature to conduct an aging test on the test product.

[0074] This solution can significantly improve the accuracy and efficiency of the simulated annealing algorithm in temperature intelligent control by analyzing the variation characteristics of the temperature data in the test chamber and obtaining the perturbation range optimization factor for each temperature control. Optimizing the perturbation range based on the data characteristics avoids overly large perturbations that may lead to a too violent search process, and also avoids overly small perturbations that may result in a slow search. Thus, while ensuring the search efficiency, it accelerates the convergence of the algorithm, enabling each temperature control process to be more precise, avoiding interference caused by data noise, and improving the stability and accuracy of temperature control. In addition, the optimization of the dynamic perturbation range based on the variation characteristics of the temperature data can better adapt to different temperature control scenarios, achieve more refined intelligent control, ultimately improve the computational efficiency and control accuracy of the entire system, reduce energy consumption, and enhance the repeatability and reliability of the experiment.

[0075] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many variations, changes, and alternative ways will occur to those skilled in the art without departing from the spirit and scope of the present invention. It should be understood that various alternative embodiments of the present invention described herein may be employed in the practice of the present invention.

[0076] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. An intelligent temperature control method for a test chamber, characterized in that, Including the steps: Calculating the optimal perturbation range in the simulated annealing algorithm and obtaining the temperature in the test chamber in the next time period by using the simulated annealing algorithm; Among them, the calculation method of the optimal perturbation range is as follows: obtaining a data set, the data set includes multiple temperature data in the current time period, calculating the dispersion degree of the data in the data set, calculating the perturbation range optimization factor in the current time period, the perturbation range optimization factor is positively correlated with the dispersion degree, and taking the product of the perturbation range optimization factor and the preset perturbation range as the optimal perturbation range; The expression of the perturbation range optimization factor is: ； In the formula, represents the disturbance range optimization factor corresponding to the s-th temperature control, represents the degree of dispersion of the data set referred to in the s-th temperature control, represents the maximum value of the number of monotonically increasing or monotonically decreasing data points in the data set referred to in the s-th temperature control, represents the number of data points in the data set, represents the preset correlation coefficient of the data set referred to in the s-th temperature control, exp represents the exponential function with base e, and norm represents the normalization function; The calculation method of the correlation coefficient is: Calculating the first difference between each data point and the adjacent data point on the left, and calculating the second difference between the corresponding data point and the adjacent data point on the right; if the product of the first difference and the second difference is less than 0, then taking the corresponding data point as a reference data point and taking the number of reference data points as the correlation coefficient of the data set.

2. The intelligent temperature control method for a test chamber according to claim 1, wherein The expression of the dispersion degree is: ； In the formula, represents the degree of dispersion of the data set referred to during the s-th temperature control, represents the number of data points in the data set, represents the Z-Score value of the r-th data point in the data set referred to during the s-th temperature control, represents the information entropy value of the data set referred to during the s-th temperature control.

3. The intelligent temperature control method for a test chamber according to claim 1, wherein The expression of the perturbation range optimization factor is: ； In the formula, represents the disturbance range optimization factor corresponding to the s-th temperature control, represents the degree of dispersion of the data set referred to during the s-th temperature control, represents the maximum value of the number of monotonically increasing or decreasing data points in the data set referred to during the s-th temperature control, represents the number of data points in the data set, represents the preset correlation coefficient of the data set referred to during the s-th temperature control, represents the logarithmic function with base e, represents a preset constant, and norm represents the normalization function.

4. The intelligent temperature control method for a test chamber according to claim 1, wherein The method for obtaining the temperature in the test chamber in the next time period by using the simulated annealing algorithm includes: Randomly generating a new solution within the optimal perturbation range of the current solution; Constructing an objective function and calculating the objective function values of the current solution and the new solution by using the objective function; Taking the difference between the objective function values of the current solution and the new solution as the energy difference; In response to the energy difference being less than or equal to 0, accepting the new solution as the current solution, otherwise accepting the new solution with a certain probability.

5. The intelligent temperature control method for a test chamber according to claim 4, wherein, The expression of the objective function is: ; where E represents the objective function value, τ represents the preset first weight, represents the preset second weight, q represents the partial discharge amplitude of the test product in the test chamber at the corresponding temperature during the simulated annealing process, v represents the partial discharge frequency of the test product in the test chamber at the corresponding temperature during the simulated annealing process, and N represents the energy consumption of the test chamber at the corresponding temperature state during the simulated annealing process.

6. The intelligent temperature control method for a test chamber according to claim 4, characterized in that, The expression of the objective function is as follows: ; where E represents the objective function value, τ represents the preset first weight, represents the preset second weight, R represents the insulation resistance value of the test product in the test chamber at the corresponding temperature during the simulated annealing process, and N represents the energy consumption of the test chamber in the corresponding temperature state during the simulated annealing process.

Images