An intelligent automatic temperature control method and system for a temperature controller

Abstract

The present invention discloses an intelligent automatic temperature regulation method and system for a temperature controller, relating to the technical field of temperature control. The method divides the deviation value range within the historical period and tests the adjustment degree of the temperature controller under different deviation interval conditions, precisely constructing multiple sets of electric power Dgz. These electric power data provide a reliable basis for screening the optimal temperature control parameters, effectively improving the accuracy of temperature control and reducing the energy consumption waste caused by excessive or untimely adjustment. The deep learning technology is used to predict the temperature change in the future period, and the temperature controller is given a predictive response based on the prediction result. This adjustment method based on the future temperature value can anticipate the temperature change trend in advance and make optimized adjustments, thus avoiding the temperature runaway or energy waste caused by the response lag in the traditional control method. By matching the corresponding demand satisfaction degree according to the electric power Dgz value output by the temperature controller in the future period.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and specifically to an intelligent automatic temperature regulation method and system for a temperature controller. Background Art

[0002] Temperature controllers are core devices in multiple fields such as industrial automation and smart home. Their main function is to monitor and adjust the temperature of a specific space in real time to ensure that the equipment or environment is maintained within an appropriate temperature range. With the development of Internet of Things technology and artificial intelligence technology, traditional temperature control methods are gradually moving towards the intelligent direction. In this context, intelligent temperature controllers have become key components in multiple application scenarios such as industrial production, smart home, and precision instruments. Especially in the field of intelligent automatic temperature regulation, improving the response speed and energy-saving effect of temperature control through accurate temperature prediction and adaptive regulation methods has become the focus of industry attention.

[0003] Current temperature control systems usually rely on preset temperature thresholds and simple on-off control methods, lacking the ability of in-depth learning and prediction of environmental temperature changes. Such traditional control methods often face the following problems: First, the control response is lagged or overreactive, resulting in large temperature fluctuations; Second, due to the lack of effective utilization of historical data, the system cannot make predictive adjustments based on long-term temperature change trends.

[0004] The emergence of these existing defects stems from the working principle of traditional temperature control systems, whose core mainly relies on setting fixed temperature thresholds or simple feedback mechanisms, and fails to comprehensively consider multi-dimensional information such as the environment, user needs, and historical data. Due to the lack of learning and prediction of temperature fluctuation laws, the temperature control system often cannot make accurate responses at the right time, resulting in over-regulation or sluggishness. Specifically, over-regulation may lead to energy waste because the control system frequently starts and stops equipment, increasing energy consumption, while sluggishness may cause the temperature to deviate from the set target, affecting comfort and production efficiency. In addition, the lack of personalized and adaptive control strategies makes it difficult for the system to cope with diverse environmental needs, thus reducing user satisfaction and potentially having an adverse impact on temperature-sensitive equipment or processes. Ultimately, the performance bottleneck of the temperature control system not only increases operating costs but also affects the overall system stability and efficiency. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides an intelligent automatic temperature regulation method and system for a temperature controller, which solves the problems in the above background art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent automatic temperature regulation method for a temperature controller includes the following steps.

[0007] S1. First, extract relevant temperature data for the historical period from the cloud platform according to Internet of Things technology. After data preprocessing, generate a historical temperature set.

[0008] S2. Based on the historical temperature set and combined with user requirements, obtain the deviation value range within the historical period. By dividing the deviation value range within the historical period into several deviation intervals, and testing the different adjustment degrees output by the temperature controller for temperature control under the corresponding deviation interval conditions, to construct multiple groups of electric powers Dgz under the corresponding deviation interval conditions. Based on the multiple groups of electric powers Dgz, screen out the optimal parameter group within the temperature controller.

[0009] S3. Based on the content of S2, construct a parameter set, and use deep learning technology and the historical temperature set to predict the temperature change situation in the future period to generate a future temperature value Wwz. According to the future temperature value Wwz and combined with the parameter set, make a predictive response to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller in the future period.

[0010] S4. According to the magnitude of the electric power Dgz value output by the temperature controller in the future period, match the corresponding demand satisfaction degree.

[0011] Preferably, the specific steps of S1 include:

[0012] S11. Through Internet of Things technology and using the database query method, obtain the temperature change situation within the historical period from the cloud platform to obtain relevant temperature data for the historical period. Among them, the relevant temperature data for the historical period includes the actual monitored temperature value Wd and the deviation value Wc at different spatial positions within each historical period.

[0013] S12. Perform data preprocessing on the extracted relevant temperature data for the historical period to remove outliers, fill in missing values and perform data standardization. Then summarize the preprocessed relevant data into a historical temperature set, and combine with the dimensionless processing technology to remove the influence of dimensions on the relevant data within the historical temperature set.

[0014] Preferably, the specific steps of S2 include:

[0015] S21. First, obtain user requirements. The user requirements include the target temperature Mwz and the target electric power range Scope. Combine with the historical temperature set, sort the several groups of deviation values Wc within the historical temperature set in ascending order of magnitude to construct a sequence group, and evenly divide the temperature difference within the sequence group into several deviation intervals.

[0016] S211. Among them, the sorting method is: sort the several groups of deviation values Wc in ascending order of numerical magnitude in sequence.

[0017] S212. The method for obtaining the deviation value Wc is: Wc = |Wd - Mwz|; the range of deviation values within the historical period refers to the range of several groups of deviation values Wc within the historical temperature set.

[0018] Preferably, the specific steps of S2 further include:

[0019] S22. According to several groups of deviation intervals, test the different adjustment degrees output by the temperature controller during temperature control under the conditions of the corresponding deviation intervals, so as to construct several groups of electric powers Dgz under the conditions of the corresponding deviation intervals. The electric power Dgz is specifically obtained through the following formula:

[0020]

[0021] In the formula, Dgz(t) represents the output of the controller at the historical time period t under the conditions of the corresponding deviation interval, that is, the electric power; Wc(t) represents the deviation value at the historical time period t under the conditions of the corresponding deviation interval; Wc(τ) represents the deviation value at the historical time point τ under the conditions of the corresponding deviation interval; α1 represents the proportional gain; α2 represents the integral gain; α3 represents the derivative gain;

[0022] S23. Among them, a group of parameter sets are composed of the proportional gain α1, the integral gain α2 and the derivative gain α3. By randomly generating several groups of parameter sets and substituting the several groups of parameter sets into the formula for obtaining the electric power Dgz in S22, several groups of electric powers Dgz under the conditions of the corresponding deviation intervals are obtained.

[0023] Preferably, the specific steps of S2 further include:

[0024] S24. According to the several groups of electric powers Dgz under the conditions of the corresponding deviation intervals obtained in S23, monitor the influence of each group of parameter sets on temperature control under the conditions of the corresponding deviation intervals to obtain relevant debugging data. The relevant debugging data includes the average overshoot of the corresponding group of parameter sets tested under the conditions of the corresponding deviation intervals The average steady-state error of the corresponding group of parameter sets is tested under the conditions of the corresponding deviation intervals And the average response duration of the corresponding group of parameter sets is tested under the conditions of the corresponding deviation intervals

[0025] S25. Based on the relevant debugging data, measure the performance of the temperature controller, and after dimensionless processing, calculate and obtain the fitness Syd of each group of parameter sets for temperature control tested under the conditions of the corresponding deviation intervals. The specific formula for obtaining is as follows:

[0026]

[0027] In the formula, It represents the average deviation value of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals. It represents the average overshoot of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals. It represents the average response duration of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals. It represents the average steady-state error of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals; w1, w2, w3, and w4 all represent weight values; among them, the specific values of w1, w2, w3, and w4 are set by the user according to the situation.

[0028] Preferably, the specific steps of S2 further include:

[0029] S26. According to the fitness Syd of each group of parameter groups for temperature control tested under the conditions of the corresponding deviation intervals, extract the fitness Syd with the maximum value, and use the parameter group corresponding to the fitness Syd with the maximum value as the optimal parameter group in the temperature controller.

[0030] Preferably, the specific steps of S3 include:

[0031] S31. According to the content in S26, respectively obtain the optimal parameter groups in the temperature controller under the conditions of the corresponding deviation intervals, and after summarization, construct a parameter set;

[0032] S32. Use deep learning technology and combine the historical temperature set and temperature heat transfer to predict the temperature change situation in the future time period to construct the rate of change of temperature with respect to time The specific acquisition method is as follows:

[0033]

[0034] In the formula, Wd represents the actual monitored temperature value, and Wd(x, y, z) represents the temperature value at the spatial position (x, y, z) and time t; represents the rate of change of temperature with respect to time; and respectively represent the second-order partial derivatives of temperature with respect to the spatial coordinates x, y, and z; β represents the thermal diffusivity;

[0035] S33. Numerically transform the formula involved in S32 into a discrete form to obtain the future temperature value Wwz.

[0036] Preferably, the specific steps of S3 further include:

[0037] S34. Determine the future deviation value WPc based on the future temperature value Wwz. Lock the deviation interval corresponding to the future deviation value Wpc according to the numerical value of the future deviation value Wpc, and denote the deviation interval corresponding to the future deviation value Wpc as the future deviation interval. Perform a predictive response on the automatic temperature control of the temperature controller according to the optimal parameter set in the temperature controller within the future deviation interval. Substitute the optimal parameter set in the temperature controller within the future deviation interval into the formula involved in S22 to obtain the electric power Dgz output by the temperature controller in the future period.

[0038] Preferably, the specific steps of S4 include:

[0039] S41. Based on the numerical value of the electric power Dgz output by the temperature controller in the future period and in combination with the target electric power range Scope, match the corresponding demand satisfaction degree. The specific content is as follows:

[0040] If the numerical value of the electric power Dgz output by the temperature controller in the future period falls within the target electric power range Scope, it is determined that the electric power Dgz output by the temperature controller in the future period is in a qualified state. At this time, temperature control operations will be performed according to the current optimal parameter set.

[0041] If the numerical value of the electric power Dgz output by the temperature controller in the future period does not fall within the target electric power range Scope, it is determined that the electric power Dgz output by the temperature controller in the future period is not in a qualified state. At this time, the content of S23 will be executed again to regenerate the parameter set, and it will be determined again whether the numerical value of the electric power Dgz output by the temperature controller in the future period falls within the target electric power range Scope.

[0042] An intelligent automatic temperature control system for a temperature controller includes a data module, a test module, a prediction module, and an automatic temperature control module;

[0043] The data module is used to extract relevant temperature data of the historical period from the cloud platform in advance according to the Internet of Things technology, and generate a historical temperature set after data preprocessing;

[0044] The test module is used to obtain the deviation value range within the historical period according to the historical temperature set and in combination with the user requirements. Divide the deviation value range within the historical period into several groups of deviation intervals, and test the different adjustment degrees output when the temperature controller performs temperature control under the corresponding deviation interval conditions, so as to construct multiple groups of electric power Dgz under the corresponding deviation interval conditions. Based on the multiple groups of electric power Dgz, screen out the optimal parameter set in the temperature controller;

[0045] The prediction module is used to construct a parameter set, and use deep learning technology and historical temperature sets to predict the temperature change in the future period to generate future temperature values Wwz. According to the future temperature values Wwz and combined with the parameter set, a predictive response is made to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller in the future period;

[0046] The automatic temperature adjustment module is used to match the corresponding demand satisfaction according to the magnitude of the electric power Dgz value output by the temperature controller in the future period.

[0047] The present invention provides a method and system for intelligent automatic temperature adjustment of a temperature controller, having the following beneficial effects:

[0048] (1) By extracting and preprocessing the temperature data of the historical period from the cloud platform to generate a historical temperature set, and carrying out targeted optimization of the temperature controller in combination with user requirements and environmental characteristics, personalized adjustment strategies can be provided for different usage scenarios. This method solves the problem that traditional temperature control systems rely on fixed thresholds and simple feedback mechanisms, making the temperature control more intelligent and adaptable. By dividing the deviation value range in the historical period and testing the adjustment degree of the temperature controller under different deviation interval conditions, multiple groups of electric powers Dgz are accurately constructed. These electric power data provide a reliable basis for screening the optimal temperature control parameter group, effectively improving the accuracy of temperature control and reducing the energy consumption waste caused by excessive or untimely adjustment. Using deep learning technology to predict the temperature change in the future period and making a predictive response to the temperature controller based on the prediction result, this adjustment method based on future temperature values can anticipate the temperature change trend in advance and make optimized adjustments, thus avoiding temperature runaway or energy waste caused by response lag in traditional control methods. By matching the corresponding demand satisfaction according to the magnitude of the electric power Dgz value output by the temperature controller in the future period, the efficiency of the temperature control system and the satisfaction of users are ensured. This automatic temperature adjustment method based on precise adjustment and prediction not only meets the comfort requirements of users, but also effectively reduces energy consumption and improves the overall operation efficiency of the system. Generally speaking, this method can improve the adaptability, responsiveness and energy utilization efficiency of the system while ensuring precise temperature control, and has important practical application value.

[0049] (2) By conducting detailed tests on several groups of deviation intervals, the electric power Dgz output by the temperature controller under different deviation interval conditions can be accurately constructed. This process establishes a refined adjustment model of the temperature controller through formulas. Among them, the proportional gain, integral gain, and derivative gain, as key parameters, can adjust the power output by the controller according to the actual deviation situation. The specific formula calculation method makes the temperature control more precise and personalized, ensuring that the controller can provide appropriate electric power adjustment under different deviation conditions. By randomly generating several groups of parameter sets (including proportional gain, integral gain, and derivative gain) and substituting them into the formula to calculate the electric power Dgz, the present invention can obtain multiple different electric power combinations. These combinations can be used to meet different temperature control requirements and can adapt to changing environmental conditions. Based on the output of these multiple groups of electric power, the temperature controller can flexibly adjust its own adjustment strategy to achieve a relatively better temperature control effect and improve the adaptability and flexibility of the system.

[0050] (3) By testing the influence of each group of parameter sets on temperature control under different deviation interval conditions, detailed debugging data can be collected, including key indicators such as average overshoot, average steady-state error, and average response time. In this way, the specific influence of each group of parameters on temperature control can be comprehensively understood, ensuring that the temperature control system can exhibit stable and accurate temperature control performance in actual applications. This method effectively overcomes the traditional system's reliance on single feedback regulation or insufficiently refined debugging processes, improving the intelligent adjustment ability of the system. Based on the collected relevant debugging data, the present invention calculates the fitness Syd of each group of parameters through dimensionless processing. The fitness Syd combines multiple dimensions of performance indicators, such as average deviation, average overshoot, average response time, and average steady-state error, and comprehensively evaluates the performance of the temperature controller from multiple perspectives. Through this comprehensive evaluation method, the influence of each parameter combination on the system performance can be more objectively reflected, and a relatively better control strategy can be ensured to be selected.

[0051] (4) According to the predicted future deviation value, the system can select a relatively better control parameter set within the expected future deviation interval and calculate the corresponding electric power Dgz through this parameter set. This predictive electric power adjustment method based on the future deviation interval and the best parameter set can achieve more precise temperature control. By grasping the temperature change trend in advance, the temperature controller can reduce unnecessary energy waste, meet the temperature requirements while reducing energy consumption, thereby achieving an efficient energy-saving effect. Description of the Drawings

[0052] Figure 1 It is a schematic flow chart of an intelligent automatic temperature control method for a temperature controller of the present invention;

[0053] Figure 2 It is a block diagram of an intelligent automatic temperature control system for a temperature controller of the present invention. Detailed implementation manners

[0054] 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 only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , the present invention provides an intelligent automatic temperature control method for a temperature controller, including the following steps

[0057] S1. Pre-extract relevant temperature data of the historical period from the cloud platform according to the Internet of Things technology, and generate a historical temperature set after data preprocessing;

[0058] S2. According to the historical temperature set and combined with user requirements, obtain the deviation value range within the historical period. By dividing the deviation value range within the historical period into several deviation intervals, and testing the different adjustment degrees output by the temperature controller during temperature control under the corresponding deviation interval conditions, to construct multiple groups of electric powers Dgz under the corresponding deviation interval conditions. Based on the multiple groups of electric powers Dgz, screen out the best parameter group in the temperature controller;

[0059] S3. Based on the content of S2, construct a parameter set, and use deep learning technology and the historical temperature set to predict the temperature change situation in the future period to generate a future temperature value Wwz. According to the future temperature value Wwz and combined with the parameter set, make a predictive response to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller in the future period;

[0060] S4. Match the corresponding demand satisfaction degree according to the magnitude of the electric power Dgz value output by the temperature controller in the future period.

[0061] In this embodiment, by extracting the temperature data of the historical period based on the Internet of Things technology and performing data preprocessing, a historical temperature set is generated, enabling the system to comprehensively understand the historical laws of temperature changes. Combining with user requirements, the historical temperature deviation values are accurately divided and analyzed, and the adjustment power Dgz within the corresponding deviation range is used to optimize the controller parameters, enabling the temperature controller to achieve more accurate temperature control adjustment in practical applications, reducing unnecessary power consumption, and thus significantly improving the energy-saving effect of the system. With the help of deep learning technology and in-depth mining of historical temperature data, the present invention can predict the temperature change trend in the future period and generate future temperature values Wwz. Based on this prediction result, the temperature controller can optimize the adjustment parameters in advance to achieve anticipatory temperature adjustment response, which significantly improves the response speed of the temperature controller to complex environmental changes and avoids temperature adjustment deviation caused by hysteresis in traditional temperature control methods. An accurate mapping relationship is established between the output of the temperature control electric power and the demand satisfaction degree, enabling the temperature controller to flexibly adjust the output power according to different user requirements and meet personalized temperature control requirements. At the same time, by matching the electric power Dgz output by the temperature controller in the future period with the user demand satisfaction degree, the refined evaluation and optimization of the temperature control result are realized, improving the comprehensive satisfaction of users with the temperature control effect and further enhancing the practicability and user experience of the system.

[0062] Embodiment 2

[0063] Please refer to Figure 1 , specifically: The specific steps of S1 include:

[0064] S11. Through the Internet of Things technology and using the database query method, obtain the temperature change situation within the historical period from the cloud platform to obtain the relevant temperature data of the historical period. Among them, the relevant temperature data of the historical period includes the actual monitored temperature values Wd and deviation values Wc at different spatial positions within each historical period; connect to the cloud platform through Internet of Things devices (such as MQTT protocol, HTTP API, etc.) to pull data and extract temperature data for a specific time period (such as the past week, month, etc.).

[0065] S12. Perform data preprocessing on the extracted relevant temperature data of the historical period to remove outliers, fill in missing values, and perform data standardization, and then summarize the preprocessed relevant data into a historical temperature set. Combining with the dimensionless processing technology, remove the influence of the dimension (unit) on the relevant data within the historical temperature set.

[0066] The specific steps of S2 include:

[0067] S21. Pre-acquire user requirements, where the user requirements include the target temperature Mwz and the target electric power range Scope, and combine the historical temperature set to sort the magnitudes of several groups of deviation values Wc in the historical temperature set to construct a sequence group, and evenly divide the temperature differences in the sequence group into several deviation intervals;

[0068] S211. Among them, the sorting method is: sort several groups of deviation values Wc in ascending order of numerical magnitude;

[0069] S212. The acquisition method of the deviation value Wc is: Wc = |Wd - Mwz|; the deviation value range in the historical period refers to the range of several groups of deviation values Wc in the historical temperature set.

[0070] In this embodiment, through the Internet of Things technology, combined with the cloud platform and database query method, the actual monitored temperature values and deviation values Wc at different spatial positions within the historical period can be obtained. This data acquisition method can ensure a large amount of real and accurate temperature data, providing a solid data foundation for subsequent temperature control. At the same time, through the efficient connection of Internet of Things devices (such as MQTT protocol, HTTP API, etc.), real-time pulling of temperature data can be achieved, avoiding the time delay and human error that may occur in the traditional manual data acquisition process. In the data preprocessing stage, the present invention ensures the high quality and usability of the historical temperature set data through steps such as removing outliers, filling in missing values, and data standardization. Further combined with the dimensionless processing technology, the influence of dimension on data analysis and processing is removed, ensuring the consistency and accuracy of different data sources. This processing method can effectively solve the control error caused by data quality problems and improve the reliability and accuracy of temperature control. By pre-obtaining user requirements and combining historical temperature data, the present invention can construct a flexible temperature control strategy according to different target temperatures Mwz and target electric power ranges Scope. On this basis, the deviation values Wc in the historical temperature set are sorted by size, and the temperature difference is evenly divided into several deviation intervals to ensure that the temperature adjustment can be accurately adjusted according to different temperature fluctuations. The implementation of this step can customize the temperature control strategy according to the specific needs of users, improving the user experience and system operation efficiency. By sorting the deviation values Wc by size and dividing the deviation intervals, the present invention can identify the adjustment rules in different temperature intervals, thereby more accurately constructing a temperature control strategy suitable for different environments and requirements. This method is of great significance in solving the temperature fluctuation problem in different usage scenarios, can significantly improve the response speed and adaptability of the temperature control system, avoid the situation of overshooting or untimely adjustment of temperature, and ensure that the temperature operates stably within the set range. In summary, through precise data acquisition, intelligent data preprocessing, flexible adaptation of user requirements, and accurate temperature adjustment strategy, this method not only improves the overall performance of the system, but also significantly enhances the efficiency and stability of the temperature control process, with broad application prospects and practical value.

[0071] Embodiment 3

[0072] Please refer to Figure 1 , specifically: The specific steps of S2 further include:

[0073] S22. According to several groups of deviation intervals, test the different adjustment degrees output by the temperature controller during temperature control under the conditions of the corresponding deviation intervals to construct multiple groups of electric powers Dgz under the conditions of the corresponding deviation intervals. Specifically, the electric power Dgz is obtained through the following formula:

[0074]

[0075] Where, Dgz(t) represents the output of the controller at historical time t under the condition of the corresponding deviation interval, that is, the electric power; Wc(t) represents the deviation value at historical time t under the condition of the corresponding deviation interval; Wc(τ) represents the deviation value at historical time point τ under the condition of the corresponding deviation interval; α1 represents the proportional gain, which is the gain coefficient directly related to the deviation in the controller. The role of the proportional term is to adjust the control quantity based on the current deviation. A large proportional gain will make the system respond faster, but may cause overshoot or oscillation; a smaller proportional gain will make the system respond slower. α1*Wc(t) represents the proportional term; α2 represents the integral gain, which is the gain coefficient proportional to the integral of the deviation. The integral term considers the cumulative effect of the error and helps to eliminate the static error in the system. If there is a continuous deviation in the system, the integral term will gradually increase the output of the controller, thereby eliminating the steady-state error. The integral action may sometimes also cause overshoot or oscillation (due to excessive error accumulation). represents the accumulation of the deviation value Wc from time 0 to time t; α3 represents the derivative gain, which is the gain coefficient proportional to the rate of change of the error (i.e., the derivative of the error). The derivative term predicts the change trend of the error and is used to reduce the overshoot and oscillation of the system. The derivative term helps to reflect the change trend of the error in advance, especially effective in suppressing the sharp change and oscillation of the error. However, it may be more sensitive to noise because the derivative term is very sensitive to the rapid change of the error; represents the derivative term, that is, the rate of change of the deviation with respect to time; τ represents the historical time point;

[0076] S23. Among them, a set of parameter groups is composed of the proportional gain α1, the integral gain α2, and the derivative gain α3. By randomly generating several sets of parameter groups and substituting several sets of parameter groups into the formula for obtaining the electric power Dgz in S22, multiple sets of electric power Dgz under the condition of the corresponding deviation interval can be obtained.

[0077] In this embodiment, the method measures the electric power Dgz output by the temperature controller under different deviation intervals, and uses the PID control strategy to precisely adjust the output of the controller. The formula takes into account the deviation value, proportional gain, integral gain, and derivative gain to ensure that the output of the electric power can be adjusted in real time according to the current deviation and historical error. By constructing multiple sets of electric power Dgz, the present invention can flexibly adjust the power output of the controller under complex environmental conditions to achieve precise temperature control. This precise control strategy can effectively reduce the unstable factors caused by temperature fluctuations and improve the stability and accuracy of the system. The present invention performs dynamic adjustment of the system through a parameter group composed of proportional gain, integral gain, and derivative gain. In a specific implementation, the system adjusts the gain coefficient according to the current deviation and its change trend to respond to temperature changes. The proportional gain helps to quickly respond to temperature deviations, the integral gain can eliminate long-term static errors, and the derivative gain helps to predict the temperature change trend and avoid overshoot or oscillation. This adaptive gain adjustment mechanism ensures that the system can maintain relatively better adjustment performance within different deviation intervals, thereby improving the adaptability of the temperature control system, especially in an environment with large temperature fluctuations. By randomly generating multiple sets of parameter groups and substituting them into the PID control formula, the influence of different gain configurations on the output electric power of the temperature control system can be comprehensively evaluated. The randomly generated parameter groups provide a rich selection space for the system and further optimize the configuration of the controller parameters. This method enables the system to quickly screen out relatively better parameter groups under different control requirements and deviation intervals, thereby achieving better performance of the temperature control system. Through this optimization strategy, the temperature controller can provide personalized and flexible adjustment solutions in a complex environment. The PID control strategy can not only effectively respond to temperature deviations, but also reduce long-term errors and predict system fluctuations through the integral and derivative terms. The application of this method enhances the robustness of the temperature controller in a non-ideal environment. Especially in the face of sudden temperature fluctuations or system noise, it can effectively suppress over-adjustment through the derivative gain and avoid the occurrence of temperature runaway or oscillation. Therefore, during long-term operation, the system can stably maintain within the set temperature range, reducing energy waste and equipment damage. In summary, by introducing the PID control strategy and the optimization method of multiple parameter groups, the present invention not only improves the response speed and adjustment accuracy of the temperature controller, but also enhances the adaptability, stability, and robustness of the system, enabling intelligent and efficient temperature adjustment under changing environmental conditions, bringing significant technical advantages and practical benefits to the application of the temperature control system.

[0078] Embodiment 4

[0079] Please refer to Figure 1 , specifically: The specific steps of S2 further include:

[0080] S24. Based on multiple groups of electric powers Dgz under the corresponding deviation interval conditions obtained in S23, monitor the influence of each group of parameter sets on temperature control under the corresponding deviation interval conditions to obtain relevant debugging data. The relevant debugging data includes the average overshoot of the corresponding group of parameter sets tested under the corresponding deviation interval conditions. Under the corresponding deviation interval conditions, test the average steady-state error of the corresponding group of parameter sets. And under the corresponding deviation interval conditions, test the average response duration of the corresponding group of parameter sets.

[0081] S25. Based on the relevant debugging data, measure the performance of the temperature controller, and after dimensionless processing, calculate and obtain the fitness Syd of each group of parameter sets for temperature control under the corresponding deviation interval conditions. Specifically, it is obtained according to the following formula:

[0082]

[0083] In the formula, represents the average deviation value of the corresponding group of parameter sets tested under the corresponding deviation interval conditions; represents the average overshoot of the corresponding group of parameter sets tested under the corresponding deviation interval conditions; represents the average response duration of the corresponding group of parameter sets tested under the corresponding deviation interval conditions; represents the average steady-state error of the corresponding group of parameter sets tested under the corresponding deviation interval conditions; w1, w2, w3, and w4 all represent weight values. Among them, 0 < w1 < 1, 0 < w2 < 1, 0 < w3 < 1, 0 < w4 < 1, and the specific values of w1, w2, w3, and w4 are set by the user according to the situation.

[0084] Among them, overshoot: the percentage by which the maximum temperature in the control process exceeds the target temperature; response duration: the time required for the system to heat / cool from the start to approach the target temperature; steady-state error: the final error in the control process, defined as the difference between the final temperature of the system and the target temperature.

[0085] The specific steps of S2 also include:

[0086] S26. According to the fitness Syd of each group of parameter sets for temperature control under the corresponding deviation interval conditions, extract the fitness Syd with the maximum value, and use the parameter set corresponding to the fitness Syd with the maximum value as the best parameter set in the temperature controller.

[0087] In this embodiment, the method obtains multi-dimensional debugging data by testing different parameter groups under corresponding deviation interval conditions, including key performance indicators such as average overshoot, average steady-state error and average response time. Through comprehensive monitoring of these data, the adjustment performance of the temperature controller can be evaluated from multiple angles. This multi-dimensional optimization method enables the temperature controller to achieve relatively good performance under different usage environments, avoiding the imbalance and inadaptability that may be caused by single indicator optimization. Based on the obtained debugging data, the present invention introduces a calculation method for fitness Syd, combines dimensionless processing technology, and comprehensively evaluates the performance of each group of parameters through a formula. Fitness Syd takes into account multiple key factors such as deviation, overshoot, steady-state error and response time in temperature control, and combines weight values for weighted summation to ensure that the evaluation result is more in line with actual control requirements. This multi-dimensional weighted evaluation method enables the temperature controller to achieve more accurate adjustment and avoids problems such as temperature fluctuations and response lag. By evaluating the fitness Syd of each parameter group, the optimized best parameter group enables the temperature controller to respond quickly and accurately when facing different deviation intervals, thereby improving the stability and efficiency of temperature control. By selecting the best parameter group, the present invention ensures the efficient adaptability of the temperature controller in complex environments. Under different temperature fluctuation ranges and user demand conditions, the controller can automatically adjust and quickly enter a stable state, avoiding problems such as overshoot, overshoot or slow adjustment. This optimized temperature control system has stronger robustness and can effectively cope with the challenges of complex environments, such as industrial scenarios with drastic temperature changes or changing demands in smart home environments.

[0088] Example 5

[0089] Please refer to Figure 1 , specifically: S3 specific steps include:

[0090] S31, according to the content in S26, respectively obtain the optimal parameter groups in the temperature controller under the corresponding deviation interval conditions, and after summarizing, construct a parameter set;

[0091] S32. Use deep learning technology, combined with historical temperature sets and temperature heat transfer, to predict temperature changes in future time periods to construct the rate of change of temperature relative to time. The specific method is to obtain it according to the following formula:

[0092]

[0093] Where Wd represents the actual monitored temperature value, and Wd(x, y, z) represents the temperature value at the spatial position (x, y, z) and time t; Represents the rate of change of temperature with respect to time (i.e., the time derivative of temperature); and respectively represent the second-order partial derivatives of temperature with respect to the spatial coordinates x, y, and z, reflecting the distribution and variation of temperature in different directions in space; β represents the thermal diffusivity, which is a physical property of the material and is defined as: where k is the thermal conductivity, ρ is the density of the material, and C is the specific heat capacity. The thermal diffusivity describes the speed at which heat propagates in an object; this formula is used to describe the change of temperature over time in three-dimensional space in order to optimize energy usage efficiency and reduce the energy consumption of the system;

[0094] S33. Numerically transform the formula involved in S32 into a discrete form, and then solve it by computer to obtain the future temperature value Wwz.

[0095] Common numerical methods include the finite difference method (FDM), the finite element method (FEM), and the finite volume method (FVM). The finite difference method (FDM) approximately solves the above formula by discretizing space and time. In the heat conduction equation, the derivatives in time and space can be approximated by differences. Common time discretization methods include explicit methods and implicit methods.

[0096] S34. Determine the future deviation value WPc based on the future temperature value Wwz. Lock the deviation interval corresponding to the future deviation value Wpc according to the numerical value of the future deviation value Wpc, and record the deviation interval corresponding to the future deviation value Wpc as the future deviation interval. Anticipatorily respond to the automatic temperature control of the temperature controller according to the optimal parameter set in the temperature controller within the future deviation interval. Substitute the optimal parameter set in the temperature controller within the future deviation interval into the formula involved in S22 to obtain the electric power Dgz output by the temperature controller in the future period.

[0097] where the future deviation value WPc = |Wwz - Mwz|;

[0098] In this embodiment, by combining historical temperature data, spatial distribution information, and heat transfer laws, and adopting deep learning techniques and numerical solutions of heat transfer equations, it is possible to accurately predict the temperature changes in future time periods. This process not only considers the temperature changes over time but also reflects the temperature changes in space through the temperature partial derivatives in spatial coordinates, thereby improving the prediction accuracy. Through numerical methods (such as the finite difference method), complex partial differential equations are transformed into discrete forms that can be solved by a computer, achieving efficient and accurate calculation of future temperatures. After predicting the future temperature values through steps S32 and S33, the future deviation value WPc can be determined based on the prediction results, and the corresponding future deviation interval can be locked. By matching the future deviation interval with the optimal parameter group in the historical temperature controller, a predictive response strategy is provided for the temperature control system. This method can dynamically adjust the temperature control strategy according to the future temperature trend, ensuring that the temperature controller can adjust the output power in a timely and effective manner, avoiding the reaction lag or non-adaptation to future temperature changes that may occur in traditional methods. The intelligent predictive response of temperature control enables the temperature controller to respond to temperature changes in advance and accurately control the electric power output by substituting the optimal parameter group of the future deviation interval into the electric power calculation formula. This predictive response not only improves the temperature control accuracy but also significantly enhances the system response speed. Compared with the traditional adjustment method based on the current temperature deviation, the present invention adjusts the temperature more intelligently and efficiently through the prediction and optimization of the future deviation interval, thereby effectively avoiding problems such as overshoot, overregulation, and system oscillation. Due to the prediction of the future deviation interval, the temperature controller can adopt a relatively optimal electric power output strategy within a predetermined time, and the temperature control system avoids overregulation or slow reaction, reducing energy waste. Through the accurate prediction of future temperature changes, the time and power of the heating / cooling process can be controlled more precisely, ensuring the efficient use of energy and maintaining the stable operation of the system.

[0099] Embodiment 6

[0100] Please refer to Figure 1 , specifically: S41. According to the magnitude of the electric power Dgz output by the temperature controller in the future time period and in combination with the target electric power range Scope, the corresponding demand satisfaction degree is matched, and the specific content is as follows:

[0101] If the value of the electric power Dgz output by the temperature controller in the future time period falls within the target electric power range Scope, it is determined that the electric power Dgz output by the temperature controller in the future time period is in a qualified (satisfactory) state. At this time, the temperature control operation will be performed according to the current optimal parameter group.

[0102] If the value of the electric power Dgz output by the temperature controller in the future time period does not fall within the target electric power range Scope, it is determined that the electric power Dgz output by the temperature controller in the future time period is not in a qualified (unsatisfactory) state. At this time, the content of S23 will be re-executed to regenerate the parameter set, and it will be determined again whether the value of the electric power Dgz output by the temperature controller in the future time period falls within the target electric power range Scope.

[0103] In this embodiment, by comparing the electric power Dgz output by the temperature controller with the target electric power range Scope, the present invention can determine in real time whether the output of the control system meets the preset requirements. If the electric power Dgz falls within the target range, the system considers that the temperature control is in a satisfactory state and can continue to operate stably according to the current optimal parameter group. This precise electric power control mechanism ensures that while meeting the user's needs, the temperature control system avoids energy waste and over-regulation, thereby improving the stability and accuracy of the system operation. Optimize the adaptive adjustment ability of the system. If the electric power Dgz does not fall within the target electric power range Scope in the future time period, the system will re-execute step S23 according to the feedback, regenerate the parameter set and optimize the temperature control strategy. This mechanism enables the temperature control system to adjust in time when encountering abnormalities or demand changes, ensuring the self-adaptability of the system. Through this dynamic adjustment mechanism, the system can flexibly respond to environmental changes or external disturbances, ensuring that a more suitable temperature control solution can be provided in any situation. Improve energy efficiency and energy-saving effect. By precisely matching the electric power Dgz with the target electric power range Scope, the present invention avoids energy waste caused by too high or too low electric power. When the value of the electric power Dgz does not meet the target range, the system will automatically re-optimize the control parameters to ensure the effective use of energy. This energy-saving effect not only helps to reduce energy consumption, but also reduces the system operation cost, realizing the efficient and green operation of the temperature control system. In summary, through precise electric power control and automatic adjustment mechanism, the present invention not only improves the accuracy, energy-saving effect and adaptive adjustment ability of temperature control, but also greatly improves the intelligent level and user satisfaction of the system, providing an efficient, reliable, green and intelligent solution for the temperature control system.

[0104] Embodiment 7

[0105] Please refer to Figure 2 , specifically: a temperature controller intelligent automatic temperature control system, including a data module, a test module, a prediction module and an automatic temperature control module;

[0106] The data module is used to pre-extract relevant temperature data of the historical period from the cloud platform according to the Internet of Things technology, and generate a historical temperature set after data preprocessing;

[0107] The test module is used to obtain the deviation value range within the historical period according to the historical temperature set and in combination with user requirements. By dividing the deviation value range within the historical period into several groups of deviation intervals, and testing the different adjustment degrees output by the temperature controller during temperature control under the conditions of the corresponding deviation intervals, multiple groups of electric powers Dgz are constructed under the conditions of the corresponding deviation intervals. Based on the multiple groups of electric powers Dgz, the optimal parameter group within the temperature controller is screened out;

[0108] The prediction module is used to construct a parameter set, and use deep learning technology and the historical temperature set to predict the temperature change situation within the future time period to generate a future temperature value Wwz. According to the future temperature value Wwz and in combination with the parameter set, a predictive response is made to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller within the future time period;

[0109] The automatic temperature adjustment module is used to match the corresponding demand satisfaction degree according to the magnitude of the electric power Dgz value output by the temperature controller within the future time period.

[0110] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent automatic temperature regulation method for a temperature controller, characterized in that: including the following steps, S1. Extract relevant temperature data for the historical period from the cloud platform in advance according to Internet of Things technology, and generate a historical temperature set after data preprocessing; S2. According to the historical temperature set and combined with user requirements, obtain the deviation value range within the historical period. By dividing the deviation value range within the historical period into several groups of deviation intervals, and testing the different adjustment degrees output by the temperature controller during temperature control under the corresponding deviation interval conditions, to construct several groups of electric powers Dgz under the corresponding deviation interval conditions. Based on the several groups of electric powers Dgz, screen out the optimal parameter group in the temperature controller; The specific steps of S2 include: S21. Obtain user requirements in advance. The user requirements include the target temperature Mwz and the target electric power range Scope, and combined with the historical temperature set, sort the several groups of deviation values Wc in the historical temperature set in ascending order of magnitude to construct a sequence group, and evenly divide the temperature difference in the sequence group into several groups of deviation intervals; S211. Among them, the sorting method is: sort the several groups of deviation values Wc in ascending order of numerical magnitude; S212. The acquisition method of the deviation value Wc is: Wc = |Wd - Mwz|; the deviation value range within the historical period refers to the range of several groups of deviation values Wc in the historical temperature set, and Wd is the actual monitored temperature value; S22. According to several groups of deviation intervals, test the different adjustment degrees output by the temperature controller during temperature control under the corresponding deviation interval conditions, to construct several groups of electric powers Dgz under the corresponding deviation interval conditions. The electric power Dgz is specifically obtained through the following formula: In the formula, Dgz(t) represents the output of the controller at the historical time period t under the corresponding deviation interval condition, that is, the electric power; Wc(t) represents the deviation value at the historical time period t under the corresponding deviation interval condition; Wc(τ) represents the deviation value at the historical time point τ under the corresponding deviation interval condition; α1 represents the proportional gain; α2 represents the integral gain; α3 represents the derivative gain; S23. Among them, a group of parameter groups is composed of the proportional gain α1, the integral gain α2, and the derivative gain α3. By randomly generating several groups of parameter groups, and substituting the several groups of parameter groups into the formula for obtaining the electric power Dgz in S22, to obtain several groups of electric powers Dgz under the corresponding deviation interval conditions; S3. Based on the content of S2, construct a parameter set, and use deep learning technology and the historical temperature set to predict the temperature change situation in the future period to generate the future temperature value Wwz. According to the future temperature value Wwz and combined with the parameter set, make a predictive response to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller in the future period; S4. According to the magnitude of the electric power Dgz value output by the temperature controller in the future period, match the corresponding demand satisfaction degree.

2. The intelligent automatic temperature regulation method of a temperature controller according to claim 1, characterized in that: The specific steps of S1 include: S11. Obtain the temperature change situation within the historical period from the cloud platform through Internet of Things technology and using the database query method to obtain the relevant temperature data of the historical period. Among them, the relevant temperature data of the historical period includes the actual monitored temperature value Wd and the deviation value Wc at different spatial positions within each historical time period. S12. Perform data preprocessing on the extracted relevant temperature data of the historical period to remove outliers, fill in missing values, and perform data standardization. Then, summarize the preprocessed relevant data into a historical temperature set, and combine with the dimensionless processing technology to remove the influence of dimensions on the relevant data within the historical temperature set.

3. The intelligent automatic temperature control method of a temperature controller according to claim 2, characterized in that: The specific steps of S2 also include: S24. According to multiple groups of electric powers Dgz under the corresponding deviation interval conditions obtained in S23, monitor the influence of each group of parameter sets on temperature control under the corresponding deviation interval conditions to obtain relevant debugging data, where the relevant debugging data includes the average overshoot of the corresponding group of parameter sets tested under the corresponding deviation interval conditions The average steady-state error of the corresponding group of parameter sets is tested under the corresponding deviation interval conditions And the average response duration of the corresponding group of parameter sets is tested under the corresponding deviation interval conditions S25. Based on the relevant debugging data, measure the performance of the temperature controller, and after dimensionless processing, calculate and obtain the fitness Syd of each group of parameter sets for temperature control under the corresponding deviation interval conditions. Specifically, obtain it according to the following formula: In the formula, represents the average deviation value of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals; represents the average overshoot of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals; represents the average response duration of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals; represents the average steady-state error of testing the corresponding group of parameter groups under the conditions of the corresponding deviation intervals; w1, w2, w3, and w4 all represent weight values; Among them, the specific values of w1, w2, w3, and w4 are set by the user according to the situation.

4. A method for intelligent automatic temperature adjustment of a temperature controller according to claim 3, characterized in that: The specific steps of S2 also include: S26. According to the fitness Syd of each group of parameter sets for temperature control under the corresponding deviation interval conditions, extract the fitness Syd with the maximum value, and use the parameter set corresponding to the fitness Syd with the maximum value as the optimal parameter set within the temperature controller.

5. The intelligent automatic temperature control method of a temperature controller according to claim 4, characterized in that: The specific steps of S3 include: S31. According to the content in S26, obtain the optimal parameter sets within the temperature controller under the corresponding deviation interval conditions respectively. After summarization, construct a parameter set. S32. Using deep learning technology and combining with the historical temperature set and temperature heat transfer, predict the temperature change in the future time period to construct the rate of change of temperature with respect to time The specific acquisition method is as follows: Wherein, Wd represents the actually monitored temperature value, and Wd(x, y, z) represents the temperature value at the spatial position (x, y, z) and time t; represents the rate of change of temperature with respect to time; and respectively represent the second-order partial derivatives of temperature with respect to the spatial coordinates x, y, and z; β represents the thermal diffusivity; S33. Convert the formula involved in S32 into a discrete form by the numerical method to obtain the future temperature value Wwz.

6. A method for intelligent automatic temperature adjustment of a temperature controller according to claim 5, characterized in that: The specific steps of S3 also include: S34. According to the future temperature value Wwz, determine the future deviation value WPc. According to the numerical size of the future deviation value Wpc, lock the deviation interval corresponding to the future deviation value Wpc, and record the deviation interval corresponding to the future deviation value Wpc as the future deviation interval. According to the optimal parameter set within the temperature controller in the future deviation interval, perform a predictive response to the automatic temperature control of the temperature controller. By substituting the optimal parameter set within the temperature controller in the future deviation interval into the formula involved in S22, obtain the electric power Dgz output by the temperature controller in the future time period.

7. An intelligent automatic temperature regulation method for a temperature controller according to claim 6, characterized in that: The specific steps of S4 include: S41. According to the numerical size of the electric power Dgz output by the temperature controller in the future time period and in combination with the target electric power range Scope, match the corresponding demand satisfaction degree. The specific content is as follows: If the numerical value of the electric power Dgz output by the temperature controller in the future time period falls within the target electric power range Scope, it is judged that the electric power Dgz output by the temperature controller in the future time period is in a qualified state. At this time, temperature control operations will be carried out according to the current optimal parameter set. If the value of the electric power Dgz output by the temperature controller in the future time period does not fall within the target electric power range Scope, it is determined that the electric power Dgz output by the temperature controller in the future time period is not in a qualified state. At this time, the content of S23 will be re-executed to regenerate the parameter set, and it will be determined again whether the value of the electric power Dgz output by the temperature controller in the future time period falls within the target electric power range Scope.

8. An intelligent automatic temperature control system for a temperature controller, which is used to implement the intelligent automatic temperature control method for a temperature controller according to any one of claims 1 to 7 above, and is characterized in that: It includes a data module, a test module, a prediction module, and an automatic temperature control module; The data module is used to extract relevant temperature data of the historical period from the cloud platform in advance according to the Internet of Things technology, and generate a historical temperature set after data preprocessing; The test module is used to obtain the deviation value range within the historical period according to the historical temperature set and combined with user requirements. By dividing the deviation value range within the historical period into several deviation intervals, and testing the different adjustment degrees output by the temperature controller during temperature control under the corresponding deviation interval conditions, a plurality of groups of electric power Dgz are constructed under the corresponding deviation interval conditions. Based on the plurality of groups of electric power Dgz, the best parameter group in the temperature controller is selected; The prediction module is used to construct a parameter set, and use deep learning technology and the historical temperature set to predict the temperature change situation in the future time period to generate a future temperature value Wwz. According to the future temperature value Wwz and combined with the parameter set, a predictive response is made to the automatic temperature control of the temperature controller to obtain the electric power Dgz output by the temperature controller in the future time period; The automatic temperature control module is used to match the corresponding demand satisfaction degree according to the magnitude of the value of the electric power Dgz output by the temperature controller in the future time period.

Images