Temperature control PID tuning method and device based on edge computing

Abstract

The present invention discloses a temperature control PID tuning method and device based on edge computing, including: a data acquisition module, a data processing module and a control module; it relates to the field of temperature control technology, and solves the technical problem that the current way of obtaining PID parameters easily leads to a smaller heating power output when the difference between the target temperature and the actual temperature value of the controlled object is closer, resulting in a longer time required to reach the target temperature; a reference temperature value is set by the target temperature value, the actual temperature value and the temperature difference, and when the subsequent PID tuning model is calculated, the reference temperature value is used as one of the input data, and the PID tuning model can obtain the corresponding PID parameters based on the reference temperature value. When the temperature difference is large, the reference temperature value at this time is greater than the target temperature value, and after the generated PID parameters are input into the PID controller, the speed at which the actual temperature value reaches the target temperature value can be accelerated.

Description

Technical Field

[0001] The present invention belongs to the technical field of temperature control, and in particular to a temperature control PID tuning method and device based on edge computing. Background Art

[0002] The PID control algorithm in the control algorithm is one of the most important control methods for various industrial controls; with the continuous development of social economy and the continuous improvement of people's quality of life, the temperature control requirements in household appliances are also increasing, which requires the introduction of new control algorithms; because the traditional PID control algorithm will be combined with the dynamic characteristics of the controlled object, its parameter adjustment requires experienced engineers to adjust it, and the parameters will no longer change after adjustment, resulting in its use and development space being limited. It is mostly used for industrial heating control and cannot be well applied in environments requiring medium and low precision temperature control.

[0003] A Chinese patent discloses a self-tuning PID energy-saving temperature control method and module (publication number: CN109839967A). The patent adjusts and calculates the PID control parameters through a PSO-DE algorithm that combines a particle swarm algorithm (PSO) and a differential evolution algorithm (DE), and then adjusts the duty cycle of a control cycle output pulse according to the calculation result, thereby adjusting the heating power output so that the sampled temperature sampling value is approximately equal to the actual temperature value of the controlled object. The PID parameters obtained by the above algorithm are still controlled based on the target temperature, which results in a smaller heating power output when the target temperature is closer to the actual temperature value of the controlled object, resulting in a longer time to reach the target temperature. In addition, since the temperature control has a certain hysteresis, when the actual temperature value of the controlled object is approximately equal to the temperature sampling value, even if the load power is zero, the temperature control will fluctuate greatly. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a temperature control PID tuning method and device based on edge computing, which is used to solve the technical problem that the current way of obtaining PID parameters easily leads to a small heating power output when the difference between the target temperature and the actual temperature value of the controlled object is large, resulting in a long time required to reach the target temperature. The present invention sets a reference temperature value through the target temperature value, the actual temperature value and the temperature difference, and then uses the reference temperature value as one of the input data when calculating through the subsequent PID tuning model. At this time, the PID tuning model can obtain the corresponding PID parameters based on the reference temperature value to solve the above problem.

[0005] To achieve the above object, a first aspect of the present invention provides a temperature control PID tuning method based on edge computing, comprising the following steps:

[0006] Step 1: extract the target temperature value and the actual temperature value, calculate the difference between the target temperature value and the actual temperature value, and obtain the temperature difference;

[0007] Step 2: Setting a reference temperature value based on the target temperature value, the actual temperature value and the temperature difference;

[0008] Step 3: Input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; wherein the PID tuning model is obtained based on the training of the artificial intelligence model;

[0009] Step 4: Input PID parameters into the PID controller to adjust the load heating power output;

[0010] Step 5: Update the actual temperature value after the preset period and determine whether the updated actual temperature value reaches the target temperature value; if yes, adjust the PID parameters in the PID controller to the preset parameter values; if no, update the temperature difference, obtain the updated PID parameters based on the updated actual temperature value, the temperature difference and the target temperature value, and jump to step 4; wherein the preset period is determined based on the temperature difference, the actual temperature value and the target temperature value.

[0011] It should be noted that the actual temperature value is the current temperature value, and the actual initial temperature value is the initial temperature value when running with the current PID parameters or PID update parameters.

[0012] The reference temperature value is set by the target temperature value, the actual temperature value and the temperature difference. When the temperature difference is large, the reference temperature value is greater than the target temperature value. After the generated PID parameters are input into the PID controller, the speed at which the actual temperature value reaches the target temperature value can be accelerated. When the temperature difference is small, the reference temperature value is less than the target temperature value. The hysteresis of temperature heating can reduce the temperature fluctuation of the controlled object.

[0013] Preferably, setting the reference temperature value based on the target temperature value, the actual temperature value and the temperature difference value includes:

[0014] Extract target temperature value, actual temperature value and temperature difference;

[0015] The upper limit floating value Tf is calculated by the formula Tf=a×Tc / Ts-b; where Ts is the actual temperature value, Tc is the temperature difference, a is the weight coefficient, b is the correction value, and a>0;

[0016] The sum of the upper limit floating value Tf and the target temperature value is calculated to obtain the reference temperature value.

[0017] Specifically, the correction value b is set according to the temperature difference and the actual temperature value, and b is a constant. By setting the correction value b by the target temperature value, when the temperature difference is small, the reference temperature value can be lower than the target temperature value to adapt to the hysteresis of the temperature, thereby reducing the temperature fluctuation of the controlled object.

[0018] Preferably, the PID tuning model is obtained based on artificial intelligence model training, including:

[0019] Extracting several groups of historical setting data from the database; wherein the historical setting data group includes PID parameters and target temperature values, actual temperature values, and temperature difference values ​​corresponding to the PID parameters; and obtaining a temperature change curve according to the change of the actual temperature;

[0020] Filter historical setting data based on the temperature change curve to obtain a standard data group;

[0021] Integrate several groups of standard data groups and corresponding reference temperature values ​​into several training data and test data; use several training data to train the artificial intelligence model, test the trained artificial intelligence model through the test data, and adjust the artificial intelligence model according to the test results; finally, a PID tuning model is obtained, whose input is the reference temperature value, the actual temperature value and the temperature difference, and the output is the PID parameter.

[0022] The historical tuning data is screened through the temperature change curve, so that the PID parameters corresponding to the optimal result are used as the standard data group. In the subsequent training process, since the PID tuning model is obtained based on the optimal result, the PID parameters output by the PID tuning model have this advantage; specifically, the optimal result is the one with the fastest temperature rise of the controlled object within the same time, and the PID parameters output by the PID tuning model also have the advantage of fast temperature rise within the same time.

[0023] Preferably, the screening of historical setting data based on the temperature change curve includes:

[0024] Grouping historical setting data groups with the same target temperature value and actual temperature value to obtain a number of identical data groups;

[0025] The temperature change curves corresponding to several historical setting data groups in the same data group are extracted, and several integral values ​​are obtained by integrating the temperature change curves in the same time period; the temperature change curve corresponding to the maximum integral value, the target temperature value, the actual temperature value, the temperature difference and the corresponding PID parameters are marked as the standard data group.

[0026] Specifically, through the above method, a historical setting data group with the largest heating amount and the fastest temperature rise in the same time can be obtained.

[0027] Preferably, obtaining the PID update parameter based on the updated actual temperature value, the temperature difference value and the target temperature value includes:

[0028] Extract the updated actual temperature value, temperature difference value and target temperature value;

[0029] The updated reference temperature value Tk is calculated by the formula Tk=a×Txc / Txs-b+Tm, where Txc is the updated temperature difference value, Txs is the updated actual temperature value, and Tm is the target temperature value;

[0030] The updated reference temperature value Tk, the updated actual temperature value Txs and the updated temperature difference value Txc are input into the PID tuning model to obtain updated PID parameters.

[0031] After the load power is regulated according to the PID parameters, in order to reduce the temperature fluctuation and the influence of the temperature control hysteresis, the actual temperature value, the temperature difference and the target temperature value are updated to obtain new PID parameters, thereby solving the above problems.

[0032] Preferably, the preset period is determined based on the temperature difference, the actual temperature value and the target temperature value, including:

[0033] Extract temperature difference and actual temperature value;

[0034] The preset period f is calculated by the formula f=Tc / c×Ts, where c is a weight coefficient and c≥1.

[0035] It should be noted that c is proportional to Ts, that is, the larger the actual temperature value, the larger the value of c.

[0036] The preset period f obtained in this way can adjust the length of the preset period according to the actual changes, so as to ensure that the preset period is as long as possible without affecting the temperature of the controlled object. When the actual temperature value is closer to the target temperature value, the preset period f is shorter, so as to minimize the temperature fluctuation of the controlled object.

[0037] Preferably, the method for obtaining the weight coefficient a includes:

[0038] S1: extract the actual temperature value and the target temperature value;

[0039] S2: By formula a=(Tm / Ts) 1 / 3 Calculate the weight coefficient a;

[0040] S3: Determine whether the preset cycle is over; if yes, extract the updated actual temperature value and target temperature value, and jump to S2; if no, re-enter S3.

[0041] The present invention also discloses a temperature control PID setting device based on edge computing, comprising: a data acquisition module, a data processing module and a control module;

[0042] The data acquisition module is used to extract the target temperature value and the actual temperature value;

[0043] The data processing module is used to calculate the difference between the target temperature value and the actual temperature value to obtain the temperature difference; set the reference temperature value based on the target temperature value, the actual temperature value and the temperature difference; input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; and,

[0044] After a preset period, the actual temperature value is updated and it is determined whether the updated actual temperature value reaches the target temperature value; if yes, the PID parameters in the PID controller are adjusted to the preset parameter values; if no, the temperature difference is updated, and the updated PID parameters are obtained based on the updated actual temperature value, the temperature difference and the target temperature value;

[0045] The control module is used to input PID parameters into the PID controller to adjust the load heating power output;

[0046] Preferably, the PID tuning device also includes a storage module, which is used to store PID parameters, target temperature values ​​corresponding to the PID parameters, actual temperature values, temperature differences and a program for running the PID tuning model. Edge computing is achieved through the storage module without uploading data to the cloud for computing operations.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] In the present invention, a reference temperature value is set by a target temperature value, an actual temperature value and a temperature difference value. When a subsequent PID tuning model is calculated, the reference temperature value is used as one of the input data. At this time, the PID tuning model can obtain corresponding PID parameters based on the reference temperature value. When the temperature difference value is large, the reference temperature value at this time is greater than the target temperature value. After the generated PID parameters are input into the PID controller, the speed at which the actual temperature value reaches the target temperature value can be accelerated.

[0049] In the present invention, the upper limit floating value Tf is calculated by the formula Tf=a×Tc / Ts-b, and then the reference temperature value is calculated by the upper limit floating value Tf and the target temperature value. In order to avoid the influence of temperature hysteresis, by setting the constant b, when the temperature difference is small, the reference temperature value can be made lower than the target temperature value to adapt to the temperature hysteresis, thereby reducing the temperature fluctuation of the controlled object. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a flow chart of the temperature control PID tuning method of the present invention;

[0052] Figure 2 It is a schematic diagram of the flow chart of obtaining the PID tuning model of the present invention. DETAILED DESCRIPTION

[0053] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1-Figure 2 The first embodiment of the present invention provides a temperature control PID tuning method based on edge computing, comprising the following steps:

[0055] Step 1: extract the target temperature value and the actual temperature value, calculate the difference between the target temperature value and the actual temperature value, and obtain the temperature difference;

[0056] Step 2: Setting a reference temperature value based on the target temperature value, the actual temperature value and the temperature difference;

[0057] Step 3: Input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; wherein the PID tuning model is obtained based on the training of the artificial intelligence model;

[0058] Step 4: Input PID parameters into the PID controller to adjust the load heating power output;

[0059] Step 5: Update the actual temperature value after the preset period and determine whether the updated actual temperature value reaches the target temperature value; if yes, adjust the PID parameters in the PID controller to the preset parameter values; if no, update the temperature difference, obtain the updated PID parameters based on the updated actual temperature value, the temperature difference and the target temperature value, and jump to step 4; wherein the preset period is determined based on the temperature difference, the actual temperature value and the target temperature value.

[0060] It should be noted that the actual temperature value is the current temperature value, and the actual initial temperature value is the initial temperature value when running with the current PID parameters or PID update parameters.

[0061] When heating water with a gas water heater, the priority should be to quickly raise the low-temperature water in the water inlet pipe to the target temperature value; for example, when the user takes a bath with a gas water heater, if the temperature cannot quickly reach near the target temperature value, it will affect the user's experience.

[0062] In the present application, the reference temperature value is set by using the target temperature value, the actual temperature value and the temperature difference. When the temperature difference is large, the reference temperature value is greater than the target temperature value. After the generated PID parameters are input into the PID controller, the load power can be significantly increased, and the speed at which the actual temperature value reaches the target temperature value can be accelerated. When the temperature difference is small, the reference temperature value is less than the target temperature value. Through the hysteresis of temperature heating, the temperature fluctuation degree of the controlled object can be reduced, and the problem of excessive temperature difference of the water temperature output by the gas water heater can be avoided.

[0063] In this embodiment, the reference temperature value is set based on the target temperature value, the actual temperature value and the temperature difference value, including:

[0064] Extract target temperature value, actual temperature value and temperature difference;

[0065] The upper limit floating value Tf is calculated by the formula Tf=a×Tc / Ts-b; where Ts is the actual temperature value, Tc is the temperature difference, a is the weight coefficient, b is the correction value, and a>0;

[0066] The sum of the upper limit floating value Tf and the target temperature value is calculated to obtain the reference temperature value.

[0067] In order to achieve that when the temperature difference is small, the reference temperature value is less than the target temperature value; when the temperature difference is large, the reference temperature value is greater than the target temperature value; the correction value b is set according to the temperature difference and the actual temperature value. Specifically, in this embodiment, the mapping relationship of the correction value b is: b=2.2-0.8×Tc / Ts, and b is a constant. By setting the correction value b to adapt to the hysteresis of temperature, the temperature fluctuation of the controlled object can be reduced.

[0068] For example, when the target temperature value Tm is 50°C, the temperature difference value Tc is 40°C, and the actual temperature value Ts is 10°C, a= (Tm / Ts) 1 / 3 ≈1.71, b=-1, then Tf=7.84, and the corresponding reference temperature value is 57.84℃.

[0069] When the target temperature is still 50°C, the temperature difference Tc is 5°C, and the actual temperature value Ts is 45°C, according to the formula, it can be calculated that the reference temperature value at this time is approximately 48°C, and a≈1.0357 and b≈2.1111.

[0070] As the most important in this embodiment, the PID tuning model is obtained based on artificial intelligence model training, including:

[0071] Extracting several groups of historical setting data from the database; wherein the historical setting data group includes PID parameters and target temperature values, actual temperature values, and temperature difference values ​​corresponding to the PID parameters; and obtaining a temperature change curve according to the change of the actual temperature;

[0072] Filter historical setting data based on the temperature change curve to obtain a standard data group;

[0073] Integrate several groups of standard data groups and corresponding reference temperature values ​​into several training data and test data; use several training data to train the artificial intelligence model, and test the trained artificial intelligence model through the test data; for the PID parameters and the corresponding PID parameters in the test data, when the difference between the two is within the threshold range, there is no need to adjust the artificial intelligence model; if the difference is not within the threshold range, adjust the artificial intelligence model until the PID parameters of the corresponding test data are within the threshold range; the threshold range can be set according to demand or experience, when the number of test data with PID parameters within the threshold range obtained from all test data accounts for 95% or more of the total test data, a PID tuning model with reference temperature value, actual temperature value and temperature difference as input and PID parameters as output is obtained.

[0074] It should be noted that the artificial intelligence model can be a RBF neural network model or a BP neural network model.

[0075] Based on the characteristics of the artificial intelligence model, the historical tuning data is screened through the temperature change curve, so that the PID parameters corresponding to the optimal result are used as the standard data group. In the subsequent training process, since the PID tuning model is used as the basis for obtaining the optimal result, the PID parameters output by the PID tuning model have this advantage;

[0076] Furthermore, historical setting data is screened based on the temperature change curve, including:

[0077] Grouping historical setting data groups with the same target temperature value and actual temperature value to obtain a number of identical data groups;

[0078] The temperature change curves corresponding to several historical setting data groups in the same data group are extracted, and several integral values ​​are obtained by integrating the temperature change curves in the same time period; the temperature change curve corresponding to the maximum integral value, the target temperature value, the actual temperature value, the temperature difference and the corresponding PID parameters are marked as the standard data group.

[0079] In the actual application of gas water heaters, the optimal result is that the temperature rise of the controlled object is the fastest within the same time. The PID parameters output by the PID tuning model also have the advantage of fast temperature rise within the same time.

[0080] Specifically, through the above method, a historical setting data group with the largest heating amount and the fastest temperature rise in the same time can be obtained.

[0081] In this embodiment, the PID update parameters are obtained based on the updated actual temperature value, the temperature difference value and the target temperature value, including:

[0082] Extract the updated actual temperature value, temperature difference value and target temperature value;

[0083] The updated reference temperature value Tk is calculated by the formula Tk=a×Txc / Txs-b+Tm, where Txc is the updated temperature difference value, Txs is the updated actual temperature value, and Tm is the target temperature value;

[0084] The updated reference temperature value Tk, the updated actual temperature value Txs and the updated temperature difference value Txc are input into the PID tuning model to obtain updated PID parameters.

[0085] After the load power is regulated according to the PID parameters, in order to reduce the temperature fluctuation and the influence of the temperature control hysteresis, the actual temperature value, the temperature difference and the target temperature value are updated to obtain new PID parameters, thereby solving the above problems.

[0086] Exemplarily, the updated temperature difference value Txc is 10° C., the updated actual temperature value Txs is 40° C., b=2, then a≈1.08, and TK=48.27° C. at this time.

[0087] As another preferred embodiment of the present invention, the preset period is determined based on the temperature difference, the actual temperature value and the target temperature value, including:

[0088] Extract temperature difference and actual temperature value;

[0089] The preset period f is calculated by the formula f=Tc / c×Ts, where c is a weight coefficient and c≥1.

[0090] It should be noted that c is proportional to Ts, that is, the larger the actual temperature value, the larger the value of c.

[0091] For example, when the target temperature value Tm is 50° C., the temperature difference value Tc is 40° C., the actual temperature value Ts is 10° C., c=1.05, then f=3.08.

[0092] The preset period f obtained in this way can adjust the length of the preset period according to the actual changes, so as to ensure that the preset period is as long as possible without affecting the temperature of the controlled object. When the actual temperature value is closer to the target temperature value, the preset period f is shorter, so as to minimize the temperature fluctuation of the controlled object.

[0093] Furthermore, the method of obtaining the weight coefficient a includes:

[0094] S1: extract the actual temperature value and the target temperature value;

[0095] S2: By formula a=(Tm / Ts) 1 / 3 Calculate the weight coefficient a;

[0096] S3: Determine whether the preset cycle is over; if yes, extract the updated actual temperature value and target temperature value, and jump to S2; if no, re-enter S3.

[0097] The present invention also discloses a temperature control PID setting device based on edge computing, comprising: a data acquisition module, a data processing module and a control module;

[0098] The data acquisition module is used to extract the target temperature value and the actual temperature value;

[0099] The data processing module is used to calculate the difference between the target temperature value and the actual temperature value to obtain the temperature difference; set the reference temperature value based on the target temperature value, the actual temperature value and the temperature difference; input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; and,

[0100] After a preset period, the actual temperature value is updated and it is determined whether the updated actual temperature value reaches the target temperature value; if yes, the PID parameters in the PID controller are adjusted to the preset parameter values; if no, the temperature difference is updated, and the updated PID parameters are obtained based on the updated actual temperature value, the temperature difference and the target temperature value;

[0101] The control module is used to input PID parameters into the PID controller to adjust the load heating power output;

[0102] Preferably, the PID tuning device also includes a storage module, which is used to store PID parameters, target temperature values ​​corresponding to the PID parameters, actual temperature values, temperature differences and a program for running the PID tuning model. Edge computing is achieved through the storage module, and there is no need to upload data to the cloud for computing operations.

[0103] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0104] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The temperature control PID tuning method based on edge computing is characterized by: The following steps are involved: Step 1: extract the target temperature value and the actual temperature value, calculate the difference between the target temperature value and the actual temperature value, and obtain the temperature difference; Step 2: Setting a reference temperature value based on the target temperature value, the actual temperature value and the temperature difference; Step 3: Input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; wherein the PID tuning model is obtained based on the training of the artificial intelligence model; Step 4: Input PID parameters into the PID controller to adjust the load heating power output; The step of setting a reference temperature value based on the target temperature value, the actual temperature value and the temperature difference value comprises: Extract target temperature value, actual temperature value and temperature difference; The upper limit floating value Tf is calculated by the formula Tf=a×Tc / Ts-b; where Ts is the actual temperature value, Tc is the temperature difference, a is the weight coefficient, b is the correction value, and a>0; The mapping relationship of the correction value b is: b=2.2-0.8×Tc / Ts; The method of obtaining the weight coefficient a includes: S1: extract the actual temperature value and the target temperature value; S2: By formula a=(Tm / Ts) 1 / 3 Calculate the weight coefficient a; S3: Determine whether the preset cycle is over; if yes, extract the updated actual temperature value and target temperature value, and jump to S2; if no, re-enter S3; The sum of the upper limit floating value Tf and the target temperature value is calculated to obtain the reference temperature value.

2. The temperature control PID tuning method based on edge computing according to claim 1 is characterized in that: The method further comprises step 5: updating the actual temperature value after a preset period and determining whether the updated actual temperature value reaches the target temperature value; Yes, adjust the PID parameters in the PID controller to the preset parameter values; No, update the temperature difference, obtain updated PID parameters based on the updated actual temperature value, temperature difference and target temperature value, and jump to step 4; wherein the preset period is determined based on the temperature difference, actual temperature value and target temperature value.

3. The temperature control PID tuning method based on edge computing according to claim 1 is characterized in that: The PID tuning model is obtained based on artificial intelligence model training, including: Extracting several groups of historical setting data from the database; wherein the historical setting data group includes PID parameters and target temperature values, actual temperature values, and temperature difference values ​​corresponding to the PID parameters; and obtaining a temperature change curve according to the change of the actual temperature; Filter historical setting data based on the temperature change curve to obtain a standard data group; Integrate several groups of standard data groups and corresponding reference temperature values ​​into several training data and test data; use several training data to train the artificial intelligence model, test the trained artificial intelligence model through the test data, and adjust the artificial intelligence model according to the test results; finally, a PID tuning model is obtained, whose input is the reference temperature value, the actual temperature value and the temperature difference, and the output is the PID parameter.

4. The temperature control PID tuning method based on edge computing according to claim 3 is characterized in that: The screening of historical setting data based on the temperature change curve includes: Grouping historical setting data groups with the same target temperature value and actual temperature value to obtain a number of identical data groups; The temperature change curves corresponding to several historical setting data groups in the same data group are extracted, and several integral values ​​are obtained by integrating the temperature change curves in the same time period; the temperature change curve corresponding to the maximum integral value, the target temperature value, the actual temperature value, the temperature difference and the corresponding PID parameters are marked as the standard data group.

5. The temperature control PID tuning method based on edge computing according to claim 2 is characterized in that: The step of obtaining updated PID parameters based on the updated actual temperature value, the temperature difference value and the target temperature value comprises: Extract the updated actual temperature value, temperature difference value and target temperature value; The updated reference temperature value Tk is calculated by the formula Tk=a×Txc / Txs-b+Tm, where Txc is the updated temperature difference value, Txs is the updated actual temperature value, and Tm is the target temperature value; The updated reference temperature value Tk, the updated actual temperature value Txs and the updated temperature difference value Txc are input into the PID tuning model to obtain updated PID parameters.

6. The temperature control PID tuning method based on edge computing according to claim 2 is characterized in that: The preset period is determined based on the temperature difference, the actual temperature value and the target temperature value, and includes: Extract temperature difference and actual temperature value; The preset period f is calculated by the formula f=Tc / c×Ts, where c is a weight coefficient and c≥1.

7. A temperature control PID tuning device based on edge computing, applied to a temperature control PID tuning method based on edge computing according to any one of claims 1 to 6, characterized in that: include: Data acquisition module, data processing module and control module; The data acquisition module is used to extract the target temperature value and the actual temperature value; The data processing module is used to calculate the difference between the target temperature value and the actual temperature value to obtain the temperature difference; Setting a reference temperature value based on a target temperature value, an actual temperature value, and a temperature difference value; Input the reference temperature value, the actual temperature value and the temperature difference into the PID tuning model to obtain the PID parameters; as well as, updating the actual temperature value after a preset period and determining whether the updated actual temperature value reaches the target temperature value; Yes, adjust the PID parameters in the PID controller to the preset parameter values; If no, the temperature difference is updated, and updated PID parameters are obtained based on the updated actual temperature value, the temperature difference and the target temperature value.

Images