Fuzzy logic-based temperature controller nonlinear compensation control method and system

Abstract

The application relates to the technical field of temperature control, in particular to a temperature controller nonlinear compensation control method and system based on fuzzy logic, which comprises the following steps: a double closed-loop control architecture of a temperature control system is constructed; main control data is generated through an outer ring fuzzy decision layer; feedforward compensation and lag compensation processing are performed on the main control data through an inner ring compensation execution layer to obtain a final control quantity; and the operation parameters of the temperature control system are adjusted according to the final control quantity. Through the double compensation mechanism of feedforward compensation and lag compensation, accurate prediction and adaptive adjustment of control data are realized, and the control lag and nonlinear instability problems caused by sensor delay, inertia of an execution mechanism and environmental interference in the temperature control system are systematically solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of temperature control, in particular to a fuzzy logic-based temperature controller nonlinear compensation control method and system. BACKGROUND

[0002] With the rapid development of industrial automation and intelligence, temperature controllers are increasingly widely used in various systems. However, traditional temperature controllers often have insufficient nonlinear compensation under complex working conditions, resulting in decreased control accuracy, slower response speed, and increased energy consumption, etc. Especially in dynamic environmental changes, the performance of the temperature controller will be significantly affected, making it difficult to meet the modern industrial demand for high precision and high efficiency.

[0003] After searching, a Chinese invention patent with publication number CN110426950B discloses an intelligent robot based on fuzzy logic. The patent adjusts the parameters of the neural network module through the fuzzy logic module to achieve precise control of the speed of the robot drive wheels. However, this technical solution is mainly aimed at robot motion control, and the design of the fuzzy logic module does not fully consider the compensation of the unique nonlinear characteristics of the temperature controller, and lacks an optimization mechanism for dynamic response to temperature changes. In addition, this solution has limited real-time adaptability in complex environments, which may result in ineffective response to rapidly changing temperature conditions in temperature control scenarios.

[0004] After searching, a Chinese invention patent with publication number CN103823368B discloses a PID-type fuzzy logic control method based on a weight rule table. The patent simplifies the implementation process of fuzzy logic control through the weight rule table and optimizes the overshoot and oscillation of the control system. However, this technical solution is not specifically designed for the nonlinear compensation needs of temperature controllers, and the setting of the weight rule table relies on expert experience, which may lack sufficient flexibility and adaptive ability when facing complex temperature control scenarios. In addition, this solution does not fully consider the impact of temperature sensor data delay on control accuracy, which may result in large control deviations in actual applications.

[0005] The above problems show that existing fuzzy logic-based control technology has insufficient nonlinear compensation, lacks dynamic response optimization, and has limited adaptability to complex environments when applied to temperature controllers. Therefore, the present application provides a fuzzy logic-based temperature controller nonlinear compensation control method and system, aiming to introduce a fuzzy logic optimization mechanism specific to temperature controller characteristics to improve the control accuracy, response speed, and energy efficiency of temperature controllers under complex working conditions, thereby meeting the demand for efficient and intelligent temperature controllers in modern industry. SUMMARY

[0006] To solve the above problems, the application provides a fuzzy logic-based temperature controller nonlinear compensation control method and system, which realizes accurate prediction and adaptive adjustment of control data through a double compensation mechanism of feedforward compensation and lag compensation, and systematically solves the control lag and nonlinear instability problems caused by sensor delay, actuator inertia and environmental interference in the temperature control system.

[0007] The object of the application can be achieved by the following technical solutions:

[0008] In a first aspect, the application provides a fuzzy logic-based temperature controller nonlinear compensation control method, comprising the steps of:

[0009] S1, a double-loop control architecture of the temperature control system is constructed, the double-loop control architecture comprising an outer loop fuzzy decision layer and an inner loop compensation execution layer;

[0010] S2, main control data is generated through the outer loop fuzzy decision layer, and the main control data is subjected to feedforward compensation and lag compensation processing through the inner loop compensation execution layer to obtain a final control quantity;

[0011] S3, the operating parameters of the temperature control system are adjusted according to the final control quantity;

[0012] The generation of the main control data through the outer loop fuzzy decision layer comprises the steps of:

[0013] The temperature and humidity deviation value is collected, and the weights of the temperature main control rule set and the humidity main control rule set are adjusted;

[0014] The temperature and humidity deviation value is subjected to first normalization processing based on the adjusted weights of the temperature main control rule set and the humidity main control rule set, and the obtained data is taken as an input variable;

[0015] The input variable is mapped to a fuzzy language variable as the main control data according to a membership function.

[0016] As a preferred technical solution of the application, the adjustment of the weights of the temperature main control rule set and the humidity main control rule set comprises the steps of:

[0017] The weights of the temperature main control rule set and the humidity main control rule set are adjusted according to a temperature and humidity coupling degree coefficient, specifically: when the temperature and humidity coupling degree coefficient is greater than a preset coupling threshold, the weight of the humidity main control rule set is increased and the weight of the temperature main control rule set is decreased; when the temperature and humidity coupling degree coefficient is less than or equal to the preset coupling threshold, the original weights are maintained;

[0018] The temperature and humidity coupling degree coefficient calculation formula is:

[0019] ;

[0020] The weight calculation formula of the temperature master control rule set is:

[0021] ;

[0022] The weight calculation formula of the humidity master control rule set is:

[0023] ;

[0024] In the formula, is the temperature deviation is the covariance of the humidity deviation , is the standard deviation of the temperature deviation, is the standard deviation of the humidity deviation, is the temperature-humidity coupling degree coefficient, is the weight of the temperature master control rule set before adjustment, is the weight of the temperature master control rule set after adjustment, is the weight of the humidity master control rule set after adjustment.

[0025] As a preferred technical solution of the present application, the first normalization processing includes the steps of:

[0026] According to the dynamic characteristics of the temperature control system, a plurality of fuzzy sets are set up, and the input variables are divided into the fuzzy sets; the fuzzy sets are used to refine the temperature-humidity deviation degree;

[0027] The first normalization processing formula is:

[0028] ;

[0029] In the formula, is the temperature deviation, indicating the deviation of the current temperature from the set temperature, is the minimum value of the temperature deviation, is the maximum value of the temperature deviation, is the humidity deviation, indicating the deviation of the current humidity from the set humidity, is the minimum value of the humidity deviation, is the maximum value of the humidity deviation, is the value obtained by the first normalization processing of the temperature-humidity deviation value.

[0030] As a preferred technical solution of the present application, the execution of the feedforward compensation and the lag compensation processing on the master control data by the inner loop compensation execution layer includes the steps of:

[0031] Extracting the heat source features that are strongly related to the temperature-humidity deviation value; the heat source features include the device start-stop state, the environmental temperature change trend, and the historical interference data;

[0032] The error of the historical main control data and the actual execution result is taken as a supervision signal, and the LSTM model is trained according to the supervision signal to generate a compensation amount of the actual execution result to the ideal historical main control data result;

[0033] The extracted heat source features are input into the LSTM model in a time sequence to generate an interference suppression amount for the actuator inertia and sensor delay; the interference suppression amount is taken as a pre-compensation amount of the main control data; the interference suppression amount is mapped into a fuzzy language variable according to an interference membership function to generate interference suppression data;

[0034] The interference suppression data and the main control data are superimposed to generate intermediate control data;

[0035] The lag time to be compensated is calculated, and the intermediate control data is dynamically corrected according to the lag time to be compensated to generate final control data.

[0036] As a preferred technical solution of the present application, the interference suppression data is generated by mapping the interference suppression amount into a fuzzy language variable according to an interference membership function, and the method comprises the following steps:

[0037] The interference suppression amount is mapped into an interference fuzzy set;

[0038] The interference suppression amount is mapped into the interval [0, 1] through a second normalization processing;

[0039] The interference suppression amount is generated into interference suppression data through an interference membership function.

[0040] As a preferred technical solution of the present application, the intermediate control data is generated by superimposing the interference suppression data and the main control data, and the method comprises the following steps:

[0041] The main control data generated by an outer loop fuzzy decision layer is obtained;

[0042] The dimensions of the main control data and the interference suppression data are unified;

[0043] The intermediate control data is generated by using a linear superposition formula;

[0044] The linear superposition formula is:

[0045] ;

[0046] Wherein, is the main control data; is the interference suppression data; is a superposition coefficient; is the intermediate control data.

[0047] As a preferred technical solution of the present application, the calculation of the to-be-compensated lag time comprises the following steps:

[0048] extracting a response sequence of the main control data and the intermediate control data;

[0049] calculating a phase lag angle between the main control data and the system response;

[0050] calculating a pure lag time according to the phase lag angle, and inversely deducing an actual lag time through a time sequence offset of the main control data and the intermediate control data;

[0051] differencing the actual lag time and the pure lag time to obtain the to-be-compensated lag time;

[0052] combining the intermediate control data and the to-be-compensated lag time to generate final control data; the final control data generation formula is:

[0053] ;

[0054] wherein, the to-be-compensated lag time, the final control data, the intermediate control data applied in advance time.

[0055] In a second aspect, the present application further provides a fuzzy logic-based temperature controller nonlinear compensation control system for executing the fuzzy logic-based temperature controller nonlinear compensation control method as described above, the system comprising a data acquisition module, an outer loop decision module, an inner loop compensation module and a strategy optimization module;

[0056] The data acquisition module is configured to acquire a temperature and humidity deviation value in real time and construct a multi-dimensional input data set.

[0057] The outer loop decision module is configured to execute fuzzy reasoning and decision generation based on a double closed-loop control architecture, and comprises a weight adjustment unit and a first normalization processing unit; the weight adjustment unit is configured to dynamically adjust weights of a temperature main control rule set and a humidity main control rule set to solve coupling interference during temperature and humidity joint debugging; and the first normalization processing unit is configured to eliminate dimension differences of the temperature and humidity deviation value through a nonlinear mapping algorithm.

[0058] The inner loop compensation module is configured to implement a double compensation mechanism for actuator inertia and sensor delay; and comprises a feedforward compensation unit and a lag compensation unit.

[0059] The strategy optimization module is configured to perform temperature control compensation according to an interference suppression amount and a to-be-compensated lag time.

[0060] As a preferred technical scheme of the present application, the feedforward compensation unit learns the error between the historical main control data and the actual execution effect through the LSTM model, and generates the interference suppression amount for the actuator inertia and sensor delay.

[0061] As a preferred technical scheme of the present application, the lag compensation unit generates the lag time to be compensated according to the phase lag angle calculation and pure lag time backstepping technology, and realizes lag compensation through time axis translation.

[0062] The present application provides a fuzzy logic-based temperature controller nonlinear compensation control method and system, which has the following beneficial effects:

[0063] The present application realizes accurate prediction and adaptive adjustment of control data through the double compensation mechanism of feedforward compensation and lag compensation, systematically solves the control lag and nonlinear instability problems caused by sensor delay, actuator inertia and environmental interference in the temperature control system, learns the error between the historical main control data and the actual execution effect through the LSTM model, generates the interference suppression amount for the actuator inertia and sensor delay, and offsets the control lag effect caused by physical delay; according to the phase lag angle calculation and pure lag time backstepping technology, the lag time to be compensated is generated, and lag compensation is realized through time axis translation, so as to offset the total lag effect of the system; effectively solve the limitation that the traditional fixed lag compensation cannot adapt to time-varying working conditions, and significantly improve the robustness and steady-state accuracy of the control system. BRIEF DESCRIPTION OF DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0065] Figure 1 The first flowchart of the fuzzy logic-based temperature controller nonlinear compensation control method provided by the embodiment of the present application is shown in the figure.

[0066] Figure 2 The second flowchart of the fuzzy logic-based temperature controller nonlinear compensation control method provided by the embodiment of the present application is shown in the figure.

[0067] Figure 3 The structure diagram of the fuzzy logic-based temperature controller nonlinear compensation control system provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0068] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described, obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work also belong to the scope of protection of the present application.

[0069] The best embodiments of the present application will be further described below with reference to the accompanying drawings;

[0070] Embodiment 1

[0071] Please refer to Figure 1 The embodiment provides a fuzzy logic-based temperature controller nonlinear compensation control method, which comprises the following steps:

[0072] S1, a double-loop control architecture of a temperature control system is constructed, the double-loop control architecture comprising an outer-loop fuzzy decision layer and an inner-loop compensation execution layer;

[0073] S2, main control data is generated by the outer-loop fuzzy decision layer, and the main control data is subjected to feedforward compensation and lag compensation processing by the inner-loop compensation execution layer to obtain a final control quantity;

[0074] S3, the running parameters of the temperature control system are adjusted according to the final control quantity.

[0075] It can be understood that the double-loop control architecture is composed of the outer-loop fuzzy decision layer and the inner-loop compensation execution layer, the outer-loop fuzzy decision layer is responsible for generating the main control data, and the inner-loop compensation execution layer is responsible for performing feedforward compensation and lag compensation processing on the main control data to obtain the final control quantity; the outer-loop fuzzy decision layer and the inner-loop compensation execution layer realize cooperative work through information flow transmission, wherein the outer-loop fuzzy decision layer transmits the main control data to the inner-loop compensation execution layer, the inner-loop compensation execution layer performs feedforward compensation and lag compensation processing according to the main control data to generate the final control quantity, the system adjusts the running parameters of the temperature control system according to the final control quantity, and real-time monitoring data is fed back to the outer-loop fuzzy decision layer to update the fuzzy rule base and the membership function parameters.

[0076] Specifically, the main control data is generated by the outer-loop fuzzy decision layer, comprising the following steps:

[0077] The fuzzy rule set comprises a temperature main control rule set and a humidity main control rule set;

[0078] The temperature and humidity deviation values are collected, and the weights of the temperature main control rule set and the humidity main control rule set are adjusted;

[0079] The temperature and humidity deviation values are subjected to first normalization processing based on the adjusted weights of the temperature main control rule set and the humidity main control rule set, and the obtained data is taken as an input variable.

[0080] According to the membership function, the input variable is mapped as a fuzzy language variable as the main control data.

[0081] Based on the foregoing, the weights of the temperature main control rule set and the humidity main control rule set are adjusted to solve the coupling interference in the temperature and humidity joint control, including the steps of:

[0082] The weight adjustment of the temperature main control rule set and the humidity main control rule set is based on a temperature and humidity coupling degree coefficient; when the temperature and humidity coupling degree coefficient is greater than a preset coupling threshold, the weight of the humidity main control rule set is increased and the weight of the temperature main control rule set is reduced; when the temperature and humidity coupling degree coefficient is less than or equal to the preset coupling threshold, the original weights are maintained.

[0083] The temperature and humidity coupling degree coefficient calculation formula is:

[0084]

[0085] The temperature main control rule set weight calculation formula is:

[0086]

[0087] The humidity main control rule set weight calculation formula is:

[0088]

[0089] wherein, is a covariance of the temperature deviation and the humidity deviation, is a standard deviation of the temperature deviation, is a standard deviation of the humidity deviation, is a temperature and humidity coupling degree coefficient, is a temperature main control rule set weight before adjustment, is a temperature main control rule set weight after adjustment, is a humidity main control rule set weight after adjustment.

[0090] Based on the foregoing, the first normalization processing is used to eliminate the dimension difference of the temperature and humidity deviation values and map them to a specified interval, including:

[0091] According to the dynamic characteristics of the temperature control system, a plurality of fuzzy sets are set up, and the input variable is divided into the fuzzy sets;

[0092] The membership function is used to convert the input variable into a fuzzy language variable and provides a basis for fuzzy reasoning; the fuzzy sets are used to refine the temperature and humidity deviation degree, so as to map the first normalized value of the temperature and humidity deviation value to the fuzzy sets.

[0093] ​​​The first normalization processing core formula is:

[0094] ;

[0095] wherein, is the deviation of the current temperature from the set temperature, is the minimum possible value of the temperature deviation, is the maximum possible value of the temperature deviation, is the deviation of the current humidity from the set humidity, is the minimum possible value of the humidity deviation, is the maximum possible value of the humidity deviation, is the value obtained by the first normalization of the temperature and humidity deviation values.

[0096] Based on the foregoing, the present embodiment maps the data obtained by the first normalization to the interval [-1, 1], and sets up five fuzzy sets, namely, negative large, negative small, zero, positive small, and positive large. When the input variable is [-1, -0.6), the fuzzy set is negative large; when the input variable is [-0.6, -0.2), the fuzzy set is negative small; when the input variable is [-0.2, 0.2), the fuzzy set is zero; when the input variable is [0.2, 0.6), the fuzzy set is positive small; and when the input variable is [0.6, 1], the fuzzy set is positive large.

[0097] Then, the membership function is used to calculate the membership of the input variable to each fuzzy set, so as to realize the fuzzification of the input variable.

[0098] When the input variable is [-1, -0.6), the membership is ;

[0099] When the input variable is [-0.6, -0.2), the membership is ;

[0100] When the input variable is [-0.2, 0.2), the membership is ;

[0101] When the input variable is [0.2, 0.6), the membership is ;

[0102] When the input variable is [0.6, 1], the membership is ;

[0103] wherein, , , and are function parameters for defining the boundary and slope of the fuzzy set, and x is the input variable.

[0104] At this time, the main control data is

[0105] It can be understood that the embodiment avoids the problem that the traditional single-layer rule base cannot distinguish between primary and secondary temperature and humidity interference by adjusting the weights of the temperature master control rule set and the humidity master control rule set, and further enhances the robustness of the system to complex working conditions; the first normalization processing eliminates the dimensional difference of the temperature and humidity deviation values, so that they can participate in operation on the same scale, and avoids control deviation caused by dimensional difference; the fuzzy input variable facilitates subsequent logical reasoning.

[0106] Specifically, the pre-feed compensation and lag compensation processing of the main control data by the inner loop compensation execution layer includes the steps of:

[0107] extracting heat source features strongly related to temperature and humidity deviation values; the heat source features include device start-stop state, environmental temperature change trend, and historical interference data;

[0108] The error between the historical main control data and the actual execution result is used as a supervision signal, and the LSTM model is trained according to the supervision signal to generate a compensation amount of the actual execution result to the ideal historical main control data result;

[0109] The extracted heat source features are input into the LSTM model in time sequence to generate an interference suppression amount for the inertia of the execution mechanism and the delay of the sensor; the interference suppression amount is used as a pre-compensation amount of the main control data; the interference suppression amount is mapped to a fuzzy language variable according to an interference membership function to generate interference suppression data;

[0110] The interference suppression data and the main control data are superimposed to generate intermediate control data;

[0111] The lag time to be compensated is calculated, and the intermediate control data is dynamically modified according to the lag time to be compensated to generate final control data.

[0112] Based on the foregoing, the interference suppression amount is mapped to a fuzzy language variable according to an interference membership function to generate interference suppression data, including the steps of:

[0113] The interference suppression amount is mapped to a fuzzy set of interference: the fuzzy set of interference includes no disturbance, low compensation, medium compensation, and high compensation; when there is no disturbance, no compensation is needed; when the compensation amount is small, it is suitable for small deviation; when the compensation amount is moderate, it is suitable for medium deviation; when the compensation amount is large, it is suitable for large deviation or emergency;

[0114] The interference suppression amount is mapped to the interval [0, 1] by the second normalization processing, for example:

[0115] When the interference suppression amount is [0, 0.4), the fuzzy set is no disturbance; the superposition coefficient , and the interference membership function is 0;

[0116] When the interference suppression amount is [0.4, 0.6), the fuzzy set is low compensation, the superposition coefficient , and the interference membership function is ;

[0117] When the interference suppression amount is [0.6, 0.8), the fuzzy set is medium compensation, the superposition coefficient , and the interference membership function is ;

[0118] When the interference suppression amount is [0.8, 1], the fuzzy set is high compensation, the superposition coefficient , and the interference membership function is ;

[0119] The interference suppression amount is generated into interference suppression data through the interference membership function.

[0120] Based on the foregoing, the interference suppression data is superposed with the main control data to generate intermediate control data, including the steps of:

[0121] Obtaining the main control data generated by the outer loop fuzzy decision layer;

[0122] Unifying the dimensions of the main control data and the interference suppression data;

[0123] Generating the intermediate control data using a linear superposition formula;

[0124] The linear superposition formula is:

[0125] ;

[0126] Wherein, is the main control data; is the interference suppression data; is the superposition coefficient; is the intermediate control data.

[0127] Based on the foregoing, the lag time to be compensated is calculated, and the intermediate control data is dynamically corrected according to the lag time to be compensated, including the steps of:

[0128] Extracting the response sequence of the main control data and the intermediate control data;

[0129] As , , , , wherein is the control period;

[0130] calculating a phase lag angle between the main control data and the system response, the phase lag angle being used to quantify a time delay caused by system inertia, delay or energy transfer characteristics, such that when the phase lag angle is 0°, the input and output are completely synchronized, and there is no time delay; and when the phase lag angle is 90°, the output is delayed by one quarter of a control period compared to the input;

[0131] calculating a pure lag time according to the phase lag angle, and simultaneously back-calculating an actual lag time through a time offset between the main control data and the intermediate control data, that is, a time difference between a response sequence of the main control data and a response sequence of the intermediate control data;

[0132] The pure lag time refers to a fixed time delay of an output signal relative to an input signal in a time dimension; and the actual lag time includes the pure lag time and a time delay caused by device start-stop, load sudden change and the like.

[0133] obtaining a lag time to be compensated by subtracting the actual lag time from the pure lag time;

[0134] generating final control data in combination with the intermediate control data and the lag time to be compensated; and a final control data generation formula is:

[0135] ;

[0136] wherein, the lag time to be compensated, the final control data, the intermediate control data applied in advance.

[0137] It can be understood that the embodiment realizes accurate prediction and adaptive adjustment of control data through a double compensation mechanism of feedforward compensation and lag compensation, and systematically solves the control lag and nonlinear instability problems caused by sensor delay, actuator inertia and environmental interference in the temperature control system; the LSTM model learns the error between the historical main control data and the actual execution effect, generates an interference suppression amount for the actuator inertia and the sensor delay, and offsets the control lag effect caused by physical delay; the lag time to be compensated is generated through the phase lag angle calculation and the pure lag time back-calculation technology, and lag compensation is realized through time axis translation, so as to offset the total lag effect of the system; the limitation that the traditional fixed lag compensation cannot adapt to time-varying working conditions is effectively solved, and the robustness and steady-state accuracy of the control system are significantly improved.

[0138] Embodiment 2

[0139] Please refer to Figure 3 ​The embodiment provides a fuzzy logic-based temperature controller nonlinear compensation control system, executes the fuzzy logic-based temperature controller nonlinear compensation control method, and the system comprises a data acquisition module, an outer loop decision module, an inner loop compensation module and a strategy optimization module.

[0140] The data acquisition module is used for acquiring a temperature and humidity deviation value in real time and constructing a multi-dimensional input data set.

[0141] The outer loop decision module performs fuzzy reasoning and decision generation based on a double closed-loop control architecture, comprises a weight adjustment unit and a first normalization processing unit; the weight adjustment unit is used for dynamically adjusting the weights of a temperature master control rule set and a humidity master control rule set, and solving coupling interference during temperature and humidity joint debugging; and the first normalization processing unit is used for eliminating dimension difference of the temperature and humidity deviation value through a nonlinear mapping algorithm.

[0142] The inner loop compensation module implements a double compensation mechanism for actuator inertia and sensor delay, and comprises a feedforward compensation unit and a lag compensation unit; the feedforward compensation unit learns the error between historical master control data and actual execution effect through an LSTM model, generates an interference suppression amount for actuator inertia and sensor delay, and offsets control lag effect caused by physical delay; and the lag compensation unit generates a lag time to be compensated according to phase lag angle calculation and pure lag time backstepping technology, and realizes lag compensation through time axis translation, so as to offset system total lag effect.

[0143] The strategy optimization module is used for temperature control compensation according to the interference suppression amount and the lag time to be compensated.

[0144] The above is merely a preferred embodiment of the application, and is not used to limit the application, and any modification, equivalent replacement and improvement made within the spirit and principle of the application should be included in the protection scope of the application.

Claims

1. A method for non-linear compensation control of a temperature controller based on fuzzy logic, characterized in that: The method comprises the following steps: S1, constructing a double-loop control architecture of the temperature control system, the double-loop control architecture comprising an outer-loop fuzzy decision layer and an inner-loop compensation execution layer; S2, generating main control data through the outer-loop fuzzy decision layer, and performing feedforward compensation and lag compensation processing on the main control data through the inner-loop compensation execution layer to obtain a final control quantity; S3, adjusting the operating parameters of the temperature control system according to the final control quantity; The generation of the main control data through the outer-loop fuzzy decision layer comprises the following steps: collecting the temperature and humidity deviation value, and adjusting the weights of the temperature main control rule set and the humidity main control rule set; performing first normalization processing on the temperature and humidity deviation value based on the adjusted weights of the temperature main control rule set and the humidity main control rule set, and taking the obtained data as input variables; mapping the input variables into fuzzy language variables as the main control data according to a membership function.

2. The fuzzy logic based thermostat non-linear compensation control method of claim 1, wherein: The adjustment of the weights of the temperature main control rule set and the humidity main control rule set comprises the following steps: adjusting the weights of the temperature main control rule set and the humidity main control rule set according to a temperature and humidity coupling degree coefficient, specifically, when the temperature and humidity coupling degree coefficient is greater than a preset coupling threshold, increasing the weight of the humidity main control rule set and reducing the weight of the temperature main control rule set; when the temperature and humidity coupling degree coefficient is less than or equal to the preset coupling threshold, maintaining the original weights; wherein the temperature and humidity coupling degree coefficient calculation formula is: ； the weight calculation formula of the temperature main control rule set is: ； the weight calculation formula of the humidity main control rule set is: ； wherein, temperature deviation humidity deviation covariance of temperature deviation and humidity deviation, standard deviation of temperature deviation, standard deviation of humidity deviation, temperature-humidity coupling coefficient, weight of temperature master control rule set before adjustment, weight of temperature master control rule set after adjustment, weight of humidity master control rule set after adjustment.

3. The fuzzy logic based thermostat non-linear compensation control method of claim 1, wherein: The first normalization processing comprises the following steps: according to the dynamic characteristics of the temperature control system, setting up a plurality of fuzzy sets, and dividing the input variables into the fuzzy sets; the fuzzy sets are used to refine the temperature and humidity deviation degree; the first normalization processing formula is: ； wherein, is a temperature deviation, representing a deviation of a current temperature from a set temperature, is a minimum value of the temperature deviation, is a maximum value of the temperature deviation, is a humidity deviation, representing a deviation of a current humidity from a set humidity, is a minimum value of the humidity deviation, is a maximum value of the humidity deviation, is a value obtained by first normalizing the temperature and humidity deviation values, is a weight of the adjusted temperature master rule set, is a weight of the adjusted humidity master rule set.

4. The fuzzy logic based thermostat non-linear compensation control method of claim 1, wherein: The feedforward compensation and lag compensation processing of the main control data through the inner-loop compensation execution layer comprises the following steps: extracting heat source features that are strongly related to the temperature and humidity deviation value; the heat source features include device start-stop state, environmental temperature change trend and historical interference data; taking the error between historical main control data and actual execution results as a supervision signal, training an LSTM model according to the supervision signal to generate a compensation amount of the actual execution results to the ideal historical main control data results; inputting the extracted heat source features into the LSTM model according to the time sequence to generate an interference suppression amount for the inertia of the execution mechanism and the delay of the sensor; taking the interference suppression amount as a pre-compensation amount of the main control data; mapping the interference suppression amount to a fuzzy language variable according to an interference membership function to generate interference suppression data; superimposing the interference suppression data and the main control data to generate intermediate control data; calculating a lag compensation time to be compensated, and dynamically correcting the intermediate control data according to the lag compensation time to be compensated to generate a final control quantity.

5. The fuzzy logic based thermostat non-linear compensation control method of claim 4, wherein: The mapping of the interference suppression amount to a fuzzy language variable according to the interference membership function to generate interference suppression data comprises the following steps: mapping the interference suppression amount to an interference fuzzy set; mapping the interference suppression amount to the [0, 1] interval through second normalization processing; generating interference suppression data from the interference suppression amount through the interference membership function.

6. The fuzzy logic based thermostat non-linear compensation control method of claim 5, wherein: The superimposing the interference suppression data and the main control data to generate intermediate control data comprises the steps of: obtaining the main control data generated by the outer ring fuzzy decision layer; unifying the dimensions of the main control data and the interference suppression data; generating the intermediate control data by using a linear superimposition formula; the linear superimposition formula is: ； wherein is main control data; is interference suppression data; is a superposition coefficient; is intermediate control data.

7. The fuzzy logic based thermostat non-linear compensation control method of claim 6, wherein: The calculation of the to-be-compensated lag time, dynamic correction of the intermediate control data according to the to-be-compensated lag time comprises the steps of: extracting the response sequence of the main control data and the intermediate control data; calculating the phase lag angle between the main control data and the system response; calculating the pure lag time according to the phase lag angle, and inversely deducing the actual lag time through the time sequence offset of the main control data and the intermediate control data; differencing the actual lag time and the pure lag time to obtain the to-be-compensated lag time; combining the intermediate control data and the to-be-compensated lag time to generate final control data; the final control data generation formula is: ； wherein is the time lag to be compensated, is the final control data, is the intermediate control data applied in advance of the time lag.

8. A fuzzy logic based thermostat nonlinear compensation control system implementing the fuzzy logic based thermostat nonlinear compensation control method of claim 7, characterized by: The system comprises a data acquisition module, an outer ring decision module, an inner ring compensation module and a strategy optimization module; The data acquisition module is used for acquiring the temperature and humidity deviation values in real time, and constructing a multi-dimensional input data set; The outer ring decision module performs fuzzy reasoning and decision generation based on a double closed-loop control architecture, and comprises a weight adjustment unit and a first normalization processing unit; the weight adjustment unit is used for dynamically adjusting the weights of the temperature main control rule set and the humidity main control rule set; and the first normalization processing unit is used for eliminating the dimension difference of the temperature and humidity deviation values by using a nonlinear mapping algorithm; The inner ring compensation module is used for implementing a double compensation mechanism for the inertia of the actuator and the sensor delay; and comprises a feedforward compensation unit and a lag compensation unit; The strategy optimization module is used for temperature control compensation according to the interference suppression amount and the to-be-compensated lag time.

9. The fuzzy logic based thermostat non-linear compensation control system of claim 8, wherein: The feedforward compensation unit learns the error between the historical main control data and the actual execution effect by using an LSTM model, and generates the interference suppression amount for the inertia of the actuator and the sensor delay.

10. The fuzzy logic based thermostat non-linear compensation control system of claim 8, wherein: The lag compensation unit generates the to-be-compensated lag time according to the phase lag angle calculation and pure lag time inverse deduction technology, and realizes lag compensation by time axis translation.

Images