Data acquisition control method and device based on intelligent temperature control equipment

Abstract

The invention provides a data acquisition control method and device based on intelligent temperature control equipment, and relates to the technical field of intelligent control. The method comprises the following steps: acquiring a PID parameter correction model; the material M and the pipe diameter D of the heated pipe are obtained; the temperature # imgabs0 # and the heating current # imgabs1 # of the heated pipe are obtained according to the data acquisition device, and the temperature difference # imgabs4 # and the temperature difference change rate # imgabs5 # between the # imgabs2 # and the preset target temperature # imgabs3 # are determined; constructing a first state vector # imgabs10 # comprising M, D, # imgabs6 #, # imgabs7 #, # imgabs8 # and # imgabs9 #, and constructing a second state vector # imgabs10 # comprising M, D, # imgabs6 #, # imgabs7 #, # imgabs8 # and # imgabs9 #; inputting the # imgabs11 # into a PID (Proportion Integration Differentiation) parameter correction model to obtain an action strategy # imgabs15 # comprising a proportion increment adjustment amount # imgabs12 #, an integral increment adjustment amount # imgabs13 # and a differential increment adjustment amount # imgabs14 #; inputting # imgabs16 # into a fuzzy PID controller, and controlling the temperature of the heated pipe by the fuzzy PID controller according to # imgabs17 # current. The method is fast in pipe heating temperature rise and accurate in temperature control.

Description

Background Art

[0002] In the field of intelligent control technology, during the process of heating a pipe to meet various processing requirements (such as annealing, softening, etc.), quickly and accurately heating the pipe to a preset temperature is the key in the pipe heating process.

[0003] In the related art, the pipe is placed in a constant temperature furnace, and the constant temperature furnace is used to heat the pipe, and the temperature of the constant temperature furnace is set to the preset temperature to heat the pipe to the preset temperature.

[0004] However, there are problems with slow heating and difficult temperature control of the pipe when using a constant temperature furnace to heat the pipe.

[0005] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present application, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The present application provides a data acquisition control method and device based on an intelligent temperature control device, which at least overcome the problems of slow heating and difficult temperature control of the pipe in the related art to a certain extent.

[0007] Other features and advantages of the present application will become apparent through the following detailed description, or be learned in part through the practice of the present application.

[0008] According to one aspect of the present application, there is provided a data acquisition control method based on an intelligent temperature control device. The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller, and includes: obtaining a PID (FuzzyPID, fuzzy proportional-integral-derivative control) parameter correction model; obtaining the material M and diameter D of the pipe to be heated; obtaining the temperature of the pipe to be heated, the heating current according to the data acquisition device, and determining the temperature difference and the temperature difference change rate between the and the preset target temperature, where the is the current flowing through the pipe to be heated controlled by the current heating device; constructing a first state vector including the M, the D, the, the, the, and the; inputting the into the PID parameter correction model to obtain a proportional increment adjustment amount, an integral increment adjustment amount. heating current and determining the and the preset target temperature temperature difference and the temperature difference change rate where the is the current flowing through the pipe to be heated controlled by the current heating device; constructing a first state vector including the M, the D, the , the , the and the first state vector ; inputting the into the PID parameter correction model to obtain a proportional increment adjustment amount , an integral increment adjustment amount And differential increment adjustment amount Action strategy ; Input the into the fuzzy PID controller, and the fuzzy PID controller adjusts the current flowing through the heated pipe according to the to control the temperature of the heated pipe.

[0009] The method of heating the pipe by using the current heating device can quickly increase the temperature of the pipe. By using reinforcement learning, the action strategy including the proportional increment adjustment amount, integral increment, and differential increment can be generated in real time according to the material, diameter, temperature, heating current, temperature difference between the preset target temperature, and the rate of change of the temperature difference of the pipe, so that the fuzzy PID controller can accurately control the current flowing through the heated pipe according to this action strategy, thereby accurately controlling the temperature of the heated pipe and improving the heating effect on the heated pipe.

[0010] Furthermore, by configuring the state of the pipe including the material and diameter, the applicability of this method can be improved.

[0011] Furthermore, compared with directly using the fuzzy PID controller to control the current flowing through the heated pipe, the method of using reinforcement learning to generate the action strategy to correct each increment in the fuzzy PID controller can improve the accuracy of current regulation, reduce the heating inertia temperature fluctuation after the heated pipe is heated to near the preset target temperature, and improve the heating effect.

[0012] In some embodiments, the intelligent temperature control device further includes an experience pool, and the method further includes: obtaining the corresponding second state vector , the including the material M, diameter D, temperature of the heated pipe after the preset time step of adjusting the current according to the , heating current , temperature difference , and rate of change of temperature difference ; Calculate the corresponding reward according to the following formula: :

[0013]

[0014] Wherein, , , are all weight coefficients, is the current flowing through the heated pipe at time ; Construct a historical sample ; The Store the historical sample group corresponding to the heated pipe in the experience pool.

[0015] By configuring the reward to be negatively correlated with the temperature difference and negatively correlated with the integral of the current over time, the action strategy output by the PID parameter correction model can not only accurately control the current flowing through the heated pipe to accurately control the temperature of the heated pipe, but also reduce the energy used to heat the heated pipe. In addition, by configuring in the reward, the probability that the temperature of the heated pipe becomes too high due to the adjustment of the current according to the action strategy can be reduced, and the accuracy of temperature control can be improved.

[0016] In some embodiments, multiple historical sample groups are stored in the experience pool, and each historical sample group includes multiple historical samples; the obtaining of the PID parameter correction model includes: obtaining an initial PID parameter correction model, the type of the initial PID parameter correction model is a PPO (Proximal Policy Optimization) model, and the initial PID parameter correction model includes an Actor (policy network); obtaining training samples from the experience pool ; updating the network parameters in the Actor according to the training samples to obtain the PID parameter correction model.

[0017] In some embodiments, the initial PID parameter correction model further includes a Critic (value network); the updating of the network parameters in the Actor according to the training samples includes: calculating the generalized advantage corresponding to the training sample according to the following formula :

[0018]

[0019]

[0020] where is the total number of historical samples included in the historical sample group where the training sample is located; is the discount factor; is the GAE (Generalized Advantage Estimation) parameter; is corresponding reward; is the function corresponding to the Critic; , are respectively the corresponding to the historical sample group where the training sample is located , corresponding state vectors at the Construct a first update formula and update the network parameters in the Actor according to the first update formula. The first update formula is as follows:

[0021]

[0022] where, is the network parameter in the Actor before update; is the network parameter in the Actor after update; is the learning rate of the Actor; is the gradient operator for the network parameter in the Actor; is as follows:

[0023]

[0024] where, the is used to limit the value of between ; is the empirical expectation representing the calculation time step ; is as follows:

[0025]

[0026] where, is the probability that when the network parameter in the Actor is , inputting the into the Actor, the Actor outputs ; is the probability that when the network parameter in the Actor is , inputting the into the Actor, the Actor outputs ;

[0027] In some embodiments, before updating the network parameter in the Actor according to the training sample, it further includes: calculating the target value of the according to the following formula:

[0028]

[0029] According to the construct a second update formula and update the network parameter in the Critic according to the second update formula. The second update formula is as follows:

[0030]

[0031] Among them, is the network parameter in the Critic before update; is the network parameter in the Critic after update; is the learning rate of the Critic; is the gradient operator for the network parameter in the Critic; as follows:

[0032]

[0033] Among them, is the function corresponding to the Critic before update.

[0034] In some embodiments, the material of the heated pipe is stainless steel, and the also includes the magnesium powder filling amount F.

[0035] By including F in , the applicability of this method can be improved.

[0036] In some embodiments, the way that the fuzzy PID controller adjusts the current flowing through the heated pipe includes: the fuzzy PID controller generates a basic adjustment parameter according to the and the and the , and the basic adjustment parameter includes a basic proportional increment , a basic integral increment and a basic differential increment ; the fuzzy PID controller calculates the final adjustment parameter according to the following formula:

[0037]

[0038]

[0039]

[0040] Among them, the is the final proportional increment included in the final adjustment parameter, the is the final integral increment included in the final adjustment parameter, is the final differential increment included in the final adjustment parameter; the fuzzy PID controller adjusts the current flowing through the heated pipe according to the final adjustment parameter.

[0041] Adjusting the basic parameters generated by the fuzzy PID controller by means of reinforcement learning, and adjusting the current with the finally adjusted parameters obtained, can improve the accuracy of current adjustment, and further improve the accuracy of controlling the temperature of the heated pipe material.

[0042] According to another aspect of the present application, there is also provided a data acquisition control device based on an intelligent temperature control device. The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller, including: a first acquisition module for acquiring a PID parameter correction model; a second acquisition module for acquiring the material M and diameter D of the heated pipe material; an acquisition and determination module for acquiring the temperature of the heated pipe material according to the data acquisition device , the heating current , and determining the between the preset target temperature and the temperature difference and the temperature difference change rate , where the is the current flowing through the heated pipe material controlled by the current heating device; a construction module for constructing a first state vector including the M, the D, the , the , the and the ; a first input module for inputting the into the PID parameter correction model to obtain an action policy including a proportional increment adjustment amount , an integral increment adjustment amount , and a differential increment adjustment amount ; a second input module for inputting the into the fuzzy PID controller, and the fuzzy PID controller adjusts the current flowing through the heated pipe material according to the to control the temperature of the heated pipe material. ; a second input module for inputting the into the fuzzy PID controller, and the fuzzy PID controller adjusts the current flowing through the heated pipe material according to the

[0043] In some embodiments, the intelligent temperature control device further includes an experience pool, and the device further includes: a historical sample construction module for acquiring the corresponding second state vector , where the includes the material M, diameter D, temperature of the heated pipe material, the heating current , the temperature difference , and the temperature difference change rate after a preset time step of adjusting the current according to the ; calculating the according to the following formulaCorresponding reward :

[0044]

[0045] Among them, 、 、 are all weight coefficients, is the current flowing through the heated pipe at time; construct a historical sample ; store the into the historical sample group corresponding to the heated pipe in the experience pool.

[0046] In some embodiments, multiple historical sample groups are stored in the experience pool, and each historical sample group includes multiple historical samples; the first acquisition module is used to acquire an initial PID parameter correction model, the type of the initial PID parameter correction model is a PPO model, and the initial PID parameter correction model includes an Actor; obtain training samples from the experience pool ; update the network parameters in the Actor according to the training samples to obtain the PID parameter correction model.

[0047] In some embodiments, the initial PID parameter correction model further includes a Critic; the first acquisition module is used to calculate the generalized advantage corresponding to the training sample according to the following formula :

[0048]

[0049]

[0050] Among them, is the total number of historical samples included in the historical sample group where the training sample is located; is the discount factor; is the GAE parameter; is the corresponding reward; is the function corresponding to the Critic; 、 are respectively the th moments in the historical sample group corresponding to the training sample, and the state vectors corresponding to the 、 th moments; construct a first update formula according to the , and update the network parameters in the Actor according to the first update formula, and the first update formula is:

[0051]

[0052] Among them, is the network parameter in the aforementioned Actor before update; is the network parameter in the aforementioned Actor after update; is the learning rate of the Actor; is the gradient operator for the network parameter in the aforementioned Actor; as follows:

[0053]

[0054] Among them, the is used to limit the value of between ; represents the empirical expectation of the computational time step ; as follows:

[0055]

[0056] Among them, when the network parameter in the aforementioned Actor is , inputting the into the aforementioned Actor, the Actor outputs with a probability; when the network parameter in the aforementioned Actor is , inputting the into the aforementioned Actor, the Actor outputs with a probability.

[0057] In some embodiments, the first acquisition module is further configured to calculate the target value of the according to the following formula:

[0058]

[0059] Construct a second update formula according to the , and update the network parameter in the Critic according to the second update formula. The second update formula is:

[0060]

[0061] Among them, is the network parameter in the aforementioned Critic before update; is the network parameter in the aforementioned Critic after update; is the learning rate of the Critic; is the gradient operator for the network parameters in the Critic; as follows:

[0062]

[0063] wherein, is the function corresponding to the Critic before update.

[0064] According to another aspect of the present application, there is also provided an electronic device, which includes: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the data acquisition control method based on the intelligent temperature control device as described in any one of the above by executing the executable instructions.

[0065] According to another aspect of the present application, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the data acquisition control method based on the intelligent temperature control device as described in any one of the above.

[0066] According to another aspect of the present application, there is also provided a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the data acquisition control method based on the intelligent temperature control device as described in any one of the above.

[0067] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0069] Figure 1 shows a schematic diagram of a data acquisition control system based on an intelligent temperature control device in an embodiment of the present application;

[0070] Figure 2 shows a flowchart of a data acquisition control method based on an intelligent temperature control device in an embodiment of the present application;

[0071] Figure 3 shows a flowchart of constructing a historical sample in an embodiment of the present application;

[0072] Figure 4 shows a flowchart of obtaining a PID parameter correction model in an embodiment of the present application;

[0073] Figure 5 A flowchart showing how to update network parameters in a Critic in an embodiment of the present application;

[0074] Figure 6 A schematic diagram showing a data acquisition control device based on an intelligent temperature control device in an embodiment of the present application;

[0075] Figure 7 A schematic diagram showing the structure of an electronic device in an embodiment of the present application. Detailed implementation manners

[0076] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments.

[0077] In addition, the accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0078] It should be noted that in the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0079] The following will describe in detail the specific implementation manners of the embodiments of the present application with reference to the accompanying drawings.

[0080] Figure 1 A schematic diagram of a data acquisition control system based on an intelligent temperature control device in an embodiment of the present application is shown. As Figure 1 shown, the system may include an intelligent temperature control device 11 and a processing device 12.

[0081] Among them, the intelligent temperature control device 11 includes a data acquisition device 111, a current heating device 112, and a fuzzy PID controller 113.

[0082] The data acquisition device 111 may include an infrared thermometer, and use the infrared thermometer to collect the temperature of the heated pipe in real time. The data acquisition device 111 may be connected to the current heating device 112 in communication to obtain the heating current applied by the current heating device 112 to the heated pipe in real time.

[0083] The fuzzy PID controller 113 may generate basic adjustment parameters according to the temperature difference between the temperature of the heated pipe and the preset target temperature and the rate of change of the temperature difference.

[0084] The processing device 12 can obtain the material M and diameter D of the heated pipe and connect to the data acquisition device 111 to obtain the temperature of the heated pipe. , Heating current , and calculate With preset target temperature The temperature difference between and temperature change rate , thus constructing a system including M, D, , , and The first state vector , and the Input into the PID parameter correction model, and the PID parameter correction model output includes the proportional increment adjustment amount , integral increment and differential increment Action strategy , and then The fuzzy PID controller 113 is used to control the The current flowing through the heated pipe is adjusted to control the temperature of the heated pipe.

[0085] The processing device 12 may be a variety of electronic devices, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0086] The processing device 12 may also be a server that provides various services. Optionally, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0087] In one embodiment, the processing device 12 belongs to the intelligent temperature control device 11 .

[0088] Under the above system architecture, in an embodiment of the present application, a data acquisition control method based on an intelligent temperature control device is provided, and this method can be executed by any electronic device with computing and processing capabilities. For example, the electronic device is a processing device.

[0089] Figure 2 The flowchart of a data acquisition control method based on an intelligent temperature control device in an embodiment of the present application is shown. As Figure 2 shown, the data acquisition control method based on an intelligent temperature control device provided in an embodiment of the present application includes the following S201 to S206. The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller.

[0090] S201, obtain a PID parameter correction model.

[0091] Among them, the PID parameter correction model is used to generate an action strategy including a proportional increment adjustment amount , an integral increment adjustment amount and a differential increment adjustment amount according to the state information of the pipe to be heated. . The PID parameter correction model can be any kind of reinforcement learning model.

[0092] The , , are respectively used to adjust the basic proportional increment, basic integral increase, and basic differential increment generated in the fuzzy PID controller.

[0093] In one embodiment, obtaining the PID parameter correction model may include: obtaining the PID parameter correction model from other network devices.

[0094] S202, obtain the material M and diameter D of the pipe to be heated.

[0095] The M and D of the pipe to be heated can be directly input into the processing device through an input device.

[0096] The embodiment of the present application does not limit the specific material of the pipe to be heated.

[0097] S203, obtain the temperature , heating current of the pipe to be heated according to the data acquisition device, and determine the temperature difference between this and a preset target temperature and the temperature difference change rate . This is the current flowing through the pipe to be heated controlled by the current heating device.

[0098] The data acquisition device may include an infrared thermometer and use the infrared thermometer to collect the temperature of the heated pipe in real time. The data acquisition device may be communicatively connected to the current heating device to obtain in real time the heating current applied by the current heating device to the heated pipe.

[0099] The processing device may obtain the temperature from the data acquisition device and the heating current , and calculate based on a preset target temperature stored in advance the temperature difference between and the rate of change of the temperature difference .

[0100] S204, construct a first state vector including the M, the D, the , the , the and the . .

[0101] In one embodiment, .

[0102] By including and in , the applicability of the present method can be improved.

[0103] In another embodiment, the material of the heated pipe is stainless steel, and further includes a magnesium powder filling amount F, that is .

[0104] By including F in , the applicability of the present method can be improved.

[0105] S205, input the into the PID parameter correction model to obtain an action strategy including a proportional increment adjustment amount , an integral increment adjustment amount and a differential increment adjustment amount . .

[0106] S206, input the into the fuzzy PID controller, and the fuzzy PID controller adjusts the current flowing through the heated pipe according to the to control the temperature of the heated pipe.

[0107] In one embodiment, the fuzzy PID controller adjusts according to the The ways to adjust the current flowing through the heated pipe include:

[0108] The fuzzy PID controller generates basic adjustment parameters according to the and the The basic adjustment parameters include the basic proportional increment , the basic integral increment and the basic derivative increment ;

[0109] The fuzzy PID controller calculates the final adjustment parameters according to the following formulas 1 - 3:

[0110] (1)

[0111] (2)

[0112] (3)

[0113] Wherein, the is the final proportional increment included in the final adjustment parameter, the is the final integral increment included in the final adjustment parameter, is the final derivative increment included in the final adjustment parameter;

[0114] The fuzzy PID controller adjusts the current flowing through the heated pipe according to the final adjustment parameter.

[0115] Wherein, the way that the fuzzy PID controller adjusts the current flowing through the heated pipe according to the final adjustment parameter can be any way that a fuzzy PID controller controls a variable according to the proportional increment, integral increment and derivative increment. This application does not limit this.

[0116] The way of heating the pipe by the current heating device can quickly raise the temperature of the pipe. By using reinforcement learning to generate an action strategy including the proportional increment adjustment amount, integral increment and derivative increment in real time according to the material, diameter, temperature, heating current, temperature difference and temperature difference change rate between the pipe and the preset target temperature, the fuzzy PID controller can accurately control the current flowing through the heated pipe according to the action strategy, so as to accurately control the temperature of the heated pipe and improve the heating effect on the heated pipe.

[0117] Furthermore, by configuring the state of the pipe to include the material and diameter, the applicability of this method can be improved.

[0118] Further, compared with directly using a fuzzy PID controller to control the current flowing through the heated pipe, the method of using reinforcement learning to generate an action policy to correct each item in the fuzzy PID controller can improve the accuracy of current regulation, reduce the heating inertial temperature fluctuation after the heated pipe is heated to near the preset target temperature, and improve the heating effect.

[0119] In one embodiment, taking including as an example, the intelligent temperature control device further includes an experience pool. As Figure 3 shown, after generating , the following S301 to S304 may further be included.

[0120] S301. Obtain the second state vector corresponding to the . The includes the material M, diameter D, temperature of the heated pipe, the heating current , the temperature difference , and the temperature difference change rate after adjusting the preset time step of the current according to the .

[0121] S302. Calculate the reward corresponding to the .

[0122] In one implementation, the reward corresponding to the can be calculated according to the following formula (4):

[0123]

[0124] (4)

[0125] where , , are all weight coefficients, and is the current flowing through the heated pipe at time .

[0126] It should be noted that the expression of in formula (4) is only one implementation manner. Any other manner that can make negatively correlated with the temperature difference, negatively correlated with the integral of the current over time, and give a negative reward after temperature overshoot can be applied to .

[0127] S303. Construct a historical sample .

[0128] S304, store it into the historical sample group corresponding to the heated pipe in this experience pool.

[0129] By configuring the reward to be negatively correlated with the temperature difference and negatively correlated with the integral of the current over time, it can be ensured that the action strategy output by the PID parameter correction model can not only accurately control the current flowing through the heated pipe to accurately control the temperature of the heated pipe, but also reduce the energy used to heat the heated pipe. Additionally, by configuring in the reward, the probability that the temperature of the heated pipe becomes too high due to the adjustment of the current according to the action strategy can be reduced, improving the accuracy of temperature control.

[0130] In one embodiment, multiple historical sample groups are stored in this experience pool, and each historical sample group includes multiple historical samples. As Figure 4 shown, obtaining the PID parameter correction model may include the following S401 to S403.

[0131] S401, obtain an initial PID parameter correction model. The type of the initial PID parameter correction model is a PPO model, and the initial PID parameter correction model includes an Actor.

[0132] In one embodiment, obtaining the initial PID parameter correction model may include obtaining a PPO model from other devices through a network; or directly constructing a PPO model in the processing device.

[0133] S402, obtain training samples from this experience pool .

[0134] The training sample can be any one of the historical samples.

[0135] S403, update the network parameters in the Actor according to the training sample to obtain the PID parameter correction model.

[0136] In one embodiment, the initial PID parameter correction model further includes a Critic. Updating the network parameters in the Actor according to the training sample may include: calculating the generalized advantage corresponding to the training sample according to the following formulas 5 and 6 :

[0137] (5)

[0138] (6)

[0139] Wherein, is the total number of historical samples included in the historical sample group where the training sample is located; is the discount factor; is the Generalized Advantage Estimation (GAE) parameter; is the corresponding reward; is the function corresponding to this Critic; 、 are respectively the corresponding to the historical sample group where this training sample is located at the 、 state vectors corresponding to the

[0140] According to this construct the first update formula, and update the network parameters in this Actor according to this first update formula. The first update formula is shown as Formula 7 below:

[0141] (7)

[0142] Among them, are the network parameters in this Actor before the update; are the network parameters in this Actor after the update; is the learning rate of the Actor; is the gradient operator for the network parameters in this Actor; As shown in Formula 8 below:

[0143] (8)

[0144] Among them, this is used to limit the value of between ; is the empirical expectation representing the calculation time step ; As shown in Formula 9 below:

[0145] (9)

[0146] Among them, is the probability that when the network parameters in this Actor are , inputting this to this Actor, the Actor outputs ; is the probability that when the network parameters in this Actor are , inputting this to this Actor, the Actor outputs ;

[0147] Regarding specifically what value it is, the embodiments of this application do not make limitations. For example 。

[0148] In one embodiment, as Figure 5 shown, before updating the network parameters in the Actor according to the training sample, the following S501 - S502 may further be included.

[0149] S501, calculate the target value of 。

[0150] Calculate the target value of according to the following formula 10: :

[0151] (10)

[0152] S502, construct a second update formula according to the and update the network parameters in the Critic according to the second update formula.

[0153] The second update formula is shown as the following formula 11:

[0154] (11)

[0155] Wherein, is the network parameter in the Critic before update; is the network parameter in the Critic after update; is the learning rate of the Critic; is the gradient operator for the network parameters in the Critic; As shown in the following formula 12:

[0156] (12)

[0157] Wherein, is the function corresponding to the Critic before update.

[0158] Based on the same inventive concept, an embodiment of the present application further provides a data acquisition control device based on an intelligent temperature control device, as described in the following embodiment. Since the principle of solving problems in this device embodiment is similar to that in the above - mentioned method embodiment, the implementation of this device embodiment can refer to the implementation of the above - mentioned method embodiment, and repeated parts will not be elaborated.

[0159] Figure 6 shows a schematic diagram of a data acquisition control device based on an intelligent temperature control device in an embodiment of the present application. The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller, as Figure 6As shown, the device includes: a first acquisition module 61 for acquiring a PID parameter correction model; a second acquisition module 62 for acquiring the material M and pipe diameter D of the pipe to be heated; an acquisition and determination module 63 for acquiring the temperature of the pipe to be heated according to the data acquisition device , heating current , and determining the temperature difference between the preset target temperature and the temperature difference change rate , where the is the current flowing through the pipe to be heated controlled by the current heating device; a construction module 64 for constructing a first state vector including the M, the D, the , the , the and the ; a first input module 65 for inputting the into the PID parameter correction model to obtain an action strategy including a proportional increment adjustment amount , an integral increment adjustment amount and a differential increment adjustment amount ; a second input module 66 for inputting the into the fuzzy PID controller, and the fuzzy PID controller adjusts the current flowing through the pipe to be heated according to the to control the temperature of the pipe to be heated.

[0160] In some embodiments, the intelligent temperature control device further includes an experience pool, and the device further includes: a historical sample construction module for acquiring a second state vector corresponding to the , the including the material M, pipe diameter D, temperature of the pipe to be heated, heating current , temperature difference , heating current , temperature difference and temperature difference change rate after a preset time step of adjusting the current according to the ; calculating the reward corresponding to the as shown in Formula 4.

[0161] In some embodiments, a plurality of historical sample groups are stored in the experience pool, each historical sample group includes a plurality of historical samples; the first acquisition module 61 is used to acquire an initial PID parameter correction model, the type of the initial PID parameter correction model is a PPO model, and the initial PID parameter correction model includes an Actor; acquiring training samples from the experience pool ; Update the network parameters in the Actor according to the training sample to obtain the PID parameter correction model.

[0162] In some embodiments, the initial PID parameter correction model further includes a Critic; the first acquisition module 61 is configured to calculate the generalized advantage corresponding to the training sample according to Formula 5 and Formula 6 ; According to the Construct a first update formula, and update the network parameters in the Actor according to the first update formula, and the first update formula can be represented by Formula 7, Formula 8 and Formula 9.

[0163] In some embodiments, the first acquisition module 61 is further configured to calculate the target value of ; According to the Construct a second update formula, and update the network parameters in the Critic according to the second update formula, and the second update formula can be represented by Formula 11 and Formula 12.

[0164] It should be noted here that the above-mentioned first acquisition module 61, second acquisition module 62, acquisition and determination module 63, construction module 64, first input module 65 and second input module 66 correspond to S201-S206 in the method embodiment. The examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment. It should be noted that the above modules, as part of the device, can be executed in a computer system such as a set of computer executable instructions.

[0165] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module" or "system" here.

[0166] Next, refer to Figure 7 to describe the electronic device 700 according to this embodiment of the present application. Figure 7 The electronic device 700 shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present application.

[0167] As Figure 7 shown, the electronic device 700 is presented in the form of a general-purpose computing device. The components of the electronic device 700 may include, but are not limited to: at least one of the above-mentioned processing units 710, at least one of the above-mentioned storage units 720, and a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710).

[0168] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 710, so that the processing unit 710 executes the steps according to various exemplary embodiments of the present application described in the "Exemplary Method" section above of this specification. For example, the processing unit 710 can execute the following steps of the above method embodiments: S201-S206, S301-S304, S401-S403, S501-S502.

[0169] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7201 and / or a cache storage unit 7202, and may further include a read-only storage unit (ROM) 7203.

[0170] The storage unit 720 may also include a program / utilities 7204 having a set (at least one) of program modules 7205. Such program modules 7205 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0171] The bus 730 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0172] The electronic device 700 can also communicate with one or more external devices 740 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 750. And, the electronic device 700 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 760. As shown in the figure, the network adapter 760 communicates with other modules of the electronic device 700 through the bus 730. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0173] Those skilled in the art can easily understand from the description of the above embodiments that the exemplary embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0174] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer program product, which includes: a computer program that, when executed by a processor, implements the above-described data acquisition control method based on an intelligent temperature control device.

[0175] In an exemplary embodiment of the present application, there is also provided a computer-readable storage medium, which can be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present application is stored on the computer-readable storage medium.

[0176] In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0177] More specific examples of the computer-readable storage medium in the present application may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0178] In the present application, the computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program used by or in combination with an instruction execution system, apparatus, or device.

[0179] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0180] In a specific implementation, the program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0181] It should be noted that although several modules or units of the devices for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more of the above-described modules or units may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by multiple modules or units.

[0182] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that these steps must be performed in that specific order, or that all of the steps shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0183] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which may be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0184] Other embodiments of the present application will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present application are pointed out by the appended claims.

Claims

1. A data acquisition and control method based on intelligent temperature control equipment, characterized in that: The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller, including: Get PID parameter correction model; Obtain the material M and diameter D of the heated pipe; The temperature of the heated pipe is obtained by the data acquisition device , Heating current , and determine the With preset target temperature The temperature difference between and temperature change rate , Controlling the current flowing through the heated pipe for the current heating device; Constructing the M, D, , , and stated The first state vector ; The Input the PID parameter correction model to obtain the proportional increment adjustment , integral increment adjustment and differential increment adjustment Action strategy ; The The fuzzy PID controller is inputted, and the fuzzy PID controller is used according to the The current flowing through the heated pipe is adjusted to control the temperature of the heated pipe.

2. The method according to claim 1, characterized in that The intelligent temperature control device further includes an experience pool, and the method further includes: Get the The corresponding second state vector , Including according to the After adjusting the preset time step of the current, the material M, diameter D, and temperature of the heated pipe are , Heating current , temperature difference and temperature change rate ; Calculate the following formula Corresponding rewards : in, , , are weight coefficients, for a current constantly flowing through the heated pipe; Building a historical sample ; The The historical sample group corresponding to the heated pipe is stored in the experience pool.

3. The method according to claim 2, characterized in that The experience pool stores a plurality of historical sample groups, each of which includes a plurality of historical samples; The step of obtaining a PID parameter correction model comprises: Acquire an initial PID parameter correction model, wherein the type of the initial PID parameter correction model is a proximal policy optimization (PPO) model, and the initial PID parameter correction model includes a policy network Actor; Obtain training samples from the experience pool ; The network parameters in the Actor are updated according to the training samples to obtain the PID parameter correction model.

4. The method according to claim 2, characterized in that: The initial PID parameter correction model also includes a value network Critic; The updating of the network parameters in the Actor according to the training sample includes: The generalized advantage corresponding to the training sample is calculated according to the following formula : ； ； in, is the total number of historical samples included in the historical sample group where the training sample is located; is the discount factor; Estimate GAE parameters for generalized advantage; for Corresponding rewards; is the function corresponding to the Critic; , They are the historical sample groups corresponding to the training samples. In this moment , The state vector corresponding to the moment; According to the Construct a first update formula, and update the network parameters in the Actor according to the first update formula, where the first update formula is: ； in, To update the network parameters in the Actor mentioned above; The network parameters in the Actor after the update; is the learning rate of Actor; is the gradient operator for the network parameters in the Actor; As shown below: ； Among them, the Used to The value is limited to between; is the calculation time step Expectations of experience; As shown below: ； in, The network parameters in the Actor are In the case of , the Actor outputs The probability of The network parameters in the Actor are In the case of , the Actor outputs probability.

5. The method according to claim 4, characterized in that Before updating the network parameters in the Actor according to the training sample, the method further includes: Calculate the following formula Target value : ； According to the A second update formula is constructed, and the network parameters in the Critic are updated according to the second update formula, where the second update formula is: ； in, To update the network parameters in the Critic mentioned before; is the network parameter in the Critic after the update; is the learning rate of Critic; is the gradient operator for the network parameters in the Critic; As shown below: ； in, It is the function corresponding to the Critic before updating.

6. The method according to any one of claims 1 to 5, characterized in that: The material of the heated pipe is stainless steel. It also includes the magnesium powder filling amount F.

7. The method according to any one of claims 1 to 5, characterized in that: The fuzzy PID controller is based on The method of adjusting the current flowing through the heated pipe includes: The fuzzy PID controller is based on and stated Generate basic adjustment parameters, the basic adjustment parameters include basic proportional increment , basic points increment and basic differential increment ; The fuzzy PID controller calculates the final adjustment parameters according to the following formula: ； ； ； Among them, the The final adjustment parameter includes a final proportional increment, The final adjustment parameters include the final integral increment, A final differential increment included in the final adjustment parameter; The fuzzy PID controller adjusts the current flowing through the heated pipe according to the final adjustment parameter.

8. A data acquisition control device based on intelligent temperature control equipment, characterized in that: The intelligent temperature control device includes a data acquisition device, a current heating device, and a fuzzy PID controller, including: A first acquisition module is used to acquire a PID parameter correction model; The second acquisition module is used to obtain the material M and the diameter D of the heated pipe; The acquisition and determination module is used to obtain the temperature of the heated pipe according to the data acquisition device. , Heating current , and determine the With preset target temperature The temperature difference between and temperature change rate , Controlling the current flowing through the heated pipe for the current heating device; A construction module is used to construct the M, D, , , and stated The first state vector ; The first input module is used to Input the PID parameter correction model to obtain the proportional increment adjustment , integral increment adjustment and differential increment adjustment Action strategy ; The second input module is used to The fuzzy PID controller is inputted, and the fuzzy PID controller is used according to the The current flowing through the heated pipe is adjusted to control the temperature of the heated pipe.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the data acquisition control method based on the intelligent temperature control device as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the data acquisition control method based on the intelligent temperature control device described in any one of claims 1 to 7 is implemented.

Images