A temperature control system

Abstract

The present invention discloses a temperature control system, which relates to the field of temperature control technology, and includes a target setting module, a comprehensive monitoring module, a central decision module, an optimization control module and a temperature control execution module; the target setting module considers environmental parameters based on an environmental correction strategy to generate a real-time target temperature table; the comprehensive monitoring module obtains and feeds back a real-time monitoring parameter table; the central decision module considers environmental parameter changes and real-time temperature changes of each key component based on a progressive change perception strategy to decide whether to update the target temperature table or perform temperature control; the optimization control module optimizes the control factor using a gray wolf optimization fuzzy PID algorithm to obtain a real-time optimal temperature control power adjustment scale; the temperature control execution module starts the temperature control device with a conventional temperature control power table, receives adjustment execution instructions and updates the real-time temperature control power, thereby realizing multi-component collaborative temperature control that dynamically responds to the environment and adjusts the total power to the minimum.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a temperature control system. Background Art

[0002] In industrial production, temperature control systems are widely used in various production processes, such as metallurgy, chemical industry, power generation, food processing, pharmaceutical industry, and electronics industry. In these processes, temperature changes can affect the operation and service life of production equipment. Therefore, precise temperature control is crucial to ensure product quality and improve production efficiency.

[0003] The existing patent application with publication number CN119087788A proposes a furnace tube heater heating control system based on the PID control algorithm, including a temperature sensor for real-time acquisition of the temperature inside the furnace tube; a PID controller for receiving temperature data from the temperature sensor and calculating the deviation between the set temperature and the measured temperature to output control instructions; and a regulating device for receiving control instructions from the PID controller and regulating the power of the heating element to achieve precise control of the heating temperature of the furnace tube heater and reduce temperature fluctuations.

[0004] However, the existing temperature control system has the following defects:

[0005] 1. Due to the different structures and functions of equipment, the corresponding temperature control requirements are also different. For example, a semi-solid die-casting machine requires simultaneous temperature control of the alloy furnace, pressure chamber, and mold, while a motor often only requires overall temperature control. Existing temperature control systems generally perform targeted temperature control on the entire controlled equipment or specific components, which is less versatile and does not consider the relationship between the overall and local parts of the equipment for coordinated temperature control.

[0006] 2. Existing temperature control technology does not consider the impact of external environmental factors on equipment heat exchange. Simply using real-time monitoring combined with prediction algorithms or control algorithms for temperature control may result in frequent temperature control adjustments for the equipment. For example, when the outside temperature is low and the humidity is high, some metal equipment will experience increased heat exchange with the outside world, causing rapid temperature loss. Frequent adjustment of heating power is required to maintain a stable temperature for the equipment.

[0007] 3. Existing temperature control technologies rarely consider cost and / or efficiency issues when performing temperature control. They only use control algorithms to obtain the operating power of the temperature control equipment to achieve constant temperature in production equipment, but ignore whether there is room for optimization in temperature control power and / or temperature control efficiency. Summary of the Invention

[0008] In view of the deficiencies in the prior art, the present invention proposes a temperature control system to provide a collaborative temperature control system that can dynamically respond to changes in the external environment and take into account the temperature requirements of different key components of the controlled equipment.

[0009] The technical solutions adopted to achieve the purpose of the present invention are:

[0010] A temperature control system includes a target setting module, a comprehensive monitoring module, a central decision module, an optimization control module and a temperature control execution module;

[0011] The target setting module stores the optimal temperature table and general parameter table ,take over Time adjustment instructions , based on the environmental correction strategy to consider real-time environmental parameter generation Target temperature table at each moment And feedback to the central decision-making module;

[0012] Integrated monitoring module receives Time monitoring instructions , get Monitoring parameter table at all times And feedback to the central decision-making module;

[0013] The central decision module sets the start time and based on the monitoring interval Set the subsequent time and send monitoring instructions at each time To the integrated monitoring module, receive and store Monitoring parameter table at all times , based on the progressive change perception strategy to consider the changes in environmental parameters and The real-time temperature change of each key component determines whether to send Instructions at all times;

[0014] Optimize control module reception Time control instructions , the Grey Wolf optimization fuzzy PID algorithm is used to optimize the control factors and obtain Optimal temperature control power adjustment scale at all times , and adjust the execution flag Packaging, generating, and adjusting execution instructions And send it to the temperature control execution module;

[0015] The temperature control execution module receives the execution instruction and uses the conventional temperature control power meter Run the temperature control equipment and receive Time adjustment execution instructions , each temperature control device The temperature control power at this moment is updated to Temperature control power at all times plus The optimal temperature control power adjustment at any time.

[0016] Further, the optimal temperature table ,in, The first Optimal temperature of key components, general parameter table ,in, and are normal ambient temperature and normal ambient humidity, respectively. For the The temperature control equipment corresponding to each key component is at normal ambient temperature and normal ambient humidity Next Key components reach optimal temperature The required conventional temperature control power, , The total number of key components of the controlled equipment.

[0017] Furthermore, the target setting module receives Time adjustment instructions , based on the environment correction strategy generation Target temperature table at each moment , including the following specific steps:

[0018] from Time adjustment instructions Get real-time ambient temperature changes and real-time ambient humidity changes And synchronize the input environment correction network group, output Real-time fitting temperature change table at each moment ;

[0019] From the optimal temperature table Extract the The optimal temperature of key components , set the The key components in Target temperature at the moment For the optimal temperature minus Real-time temperature change at each moment ;

[0020] statistics The key components in The target temperature at the moment, get Target temperature table at each moment .

[0021] Furthermore, the environmental correction network group includes The environment correction network with the same structure and requiring pre-training, where An environmental correction network is fitted under conventional temperature control power Next Temperature variation of key components Regarding the change in ambient temperature and ambient humidity changes The nonlinear mapping function, , Correct the total number of networks for the environment, and Equal in quantity.

[0022] Furthermore, The pre-training of an environment correction network includes the following specific steps:

[0023] Fixed The conventional temperature control power of the temperature control equipment corresponding to each key component , at different ambient temperatures and ambient humidity The following measurements are taken to obtain the Different temperatures of key components ;

[0024] Calculate the change in temperature for each pair of ambient temperatures , Change in ambient humidity Corresponding temperature change ;

[0025] Using several ambient temperature changes 、Several changes in ambient humidity and the corresponding temperature changes Build a dataset and divide it into training and test sets;

[0026] Select the environmental correction network to adjust the ambient temperature change and ambient humidity changes Defined as input, temperature change Defined as output;

[0027] The loss function is defined as mean square error, and Adam optimizer is used for multiple rounds of training to adjust the The environment modifies the network's hyperparameters;

[0028] After the Adam optimizer training is completed, the The hyperparameters of the environment correction network are used to adjust the ambient temperature change in the test set. and ambient humidity changes Enter An environment correction network is used to obtain the mean square error corresponding to the test set and determine whether it is less than or equal to the error threshold;

[0029] If it is less than or equal to the error threshold, The network pre-training for each environment correction is completed. If the error is greater than the threshold, the Adam optimizer is adjusted and re-trained.

[0030] Furthermore, the central decision module receives Monitoring parameter table at all times And decide whether to send it based on the progressive change perception strategy The instructions at this moment include the following specific steps:

[0031] Get Monitoring parameter table at all times And extract the real-time ambient temperature and real-time ambient humidity , call the general parameter table And extract the normal ambient temperature and normal ambient humidity ;

[0032] based on Whether the time is the start time to decide and compare the ambient temperature and compare ambient humidity Select normal ambient temperature and normal ambient humidity or Real-time ambient temperature at the moment and real-time ambient humidity , is the monitoring interval;

[0033] calculate Ambient temperature change gradient at each moment and environmental humidity gradient And determine whether they are all less than or equal to the change gradient threshold;

[0034] like Ambient temperature change gradient at each moment and environmental humidity gradient are all less than or equal to the change gradient threshold, and the Whether the time is the start time;

[0035] If it is the start time, the optimal temperature table As Target temperature table at each moment Store, generate execution markup , from the general parameter table Extract The conventional temperature control power corresponding to each key component constitutes the conventional temperature control power table , further package execution tags and conventional temperature control power meter generate Execution instructions at the time And send it to the temperature control execution module;

[0036] If it is not the start time, Target temperature table at each moment As Target temperature table at each moment Storage, from Monitoring parameter table at all times Extract real-time temperature table ;

[0037] Calculate separately The key components in Temperature gradient at each moment , determine whether they are all less than or equal to the change gradient threshold;

[0038] like The key components in Temperature gradient at each moment If both are less than or equal to the change gradient threshold, no action is required;

[0039] If there is a single component in The temperature change gradient at the moment is greater than the change gradient threshold, and a control mark is generated ,and Target temperature table at each moment Packaging and generating control instructions And send it to the optimization control module;

[0040] like Ambient temperature change gradient at each moment and / or ambient humidity gradient Greater than the gradient threshold, calculate Real-time ambient temperature change at the moment and real-time ambient humidity changes , with adjustment marks Packaging and generating adjustment instructions And send it to the target setting module, receive and store Target temperature table at each moment , with control marks Package generation Time control instructions And sent to the optimization control module.

[0041] Furthermore, the optimization control module uses the Grey Wolf optimization fuzzy PID algorithm to obtain Optimal temperature control power adjustment scale at all times , including the following specific steps:

[0042] Defining the solution space And initialize The position of the gray wolf, set the maximum optimization rounds , define the fitness function ;

[0043] Perform a single round of optimization and The positions of the gray wolves are substituted into the fuzzy PID algorithm and calculated Fitness function at the moment , select the first round of optimization Fitness function at the moment The three smallest gray wolves are Wolf, Wolf and Wolf, Wolf, Wolf and The positions of the wolves are recorded as 、 and ;

[0044] Random Generate a first random number and a second random number for the first round of optimization, calculate a first coefficient in the first round of optimization based on the optimization round number and the first random number, and calculate a second coefficient in the first round of optimization based on the second random number;

[0045] Based on the second coefficient in the first round of optimization and Wolf Position 、 Wolf Position and Wolf Position The product of the remaining The location of the gray wolf Wolf, Wolf and the distance of the wolf;

[0046] Further based on the first coefficient in the first round of optimization and each gray wolf's Wolf, Wolf and Wolf distance gets the updated position of each gray wolf;

[0047] Repeat the single round of optimization, reselecting in each round Wolf, Wolf and The wolf ordered the rest of the gray wolves to Wolf, Wolf and The wolves move closer until the number of optimization rounds equals the maximum number of optimization rounds. , will In round optimization Wolf's Position Substitute the fuzzy PID algorithm output Optimal temperature control power adjustment scale at all times .

[0048] Furthermore, the position of the single gray wolf Substitute the fuzzy PID algorithm and calculate the fitness function , including the following specific steps:

[0049] from Time control instructions Extract the target temperature table , call Monitoring parameter table at all times and Monitoring parameter table at all times , respectively extract Real-time temperature chart at all times and Real-time temperature chart at all times ;

[0050] The real-time temperature gauge Subtract target temperature table To obtain Real-time target temperature difference table at each moment ,Will Real-time temperature chart at all times minus Real-time temperature chart at all times and divided by the monitoring interval To obtain Real-time temperature change rate table at each moment ;

[0051] Will The key components in The real-time target temperature difference and the real-time temperature change rate at the moment are multiplied by the corresponding first quantization factor and the second quantization factor as the input of the fuzzy controller, and the output of the fuzzy controller is the proportional factor table. , Integral Factor Table and differential factor table ;

[0052] The membership function of the fuzzy controller is selected as a Gaussian membership function, fuzzy subsets are defined for the input and output of the fuzzy controller, and a fuzzy control rule table is established;

[0053] Select the centroid method as the defuzzification method and obtain the scale factor table , Integral Factor Table and differential factor table , through the PID algorithm to obtain each key component The temperature control power adjustment amount and control rounds corresponding to each moment;

[0054] Sum them separately The temperature control power adjustment amount and control round number of key components are obtained Total temperature control power adjustment at any moment and control the total number of rounds , further accumulate and obtain Fitness function at the moment .

[0055] Compared with the prior art, the present invention has the following significant advantages:

[0056] 1. Based on the synergy of the environmental correction strategy and the progressive change perception strategy, the real-time target temperature table is dynamically generated through the environmental correction network group, taking into account the changes in real-time environmental parameters relative to pre-stored conventional environmental parameters. The target temperature table always represents the operating temperature of the equipment or key components that best adapts to the real-time external environment. At system startup and non-startup times, it is determined in real time whether the environmental parameters and the real-time temperatures of all key components have changed. When the environmental parameters change, the real-time target temperature table is updated and the temperature control equipment is adjusted. When the environmental parameters do not change but the temperature of the key components changes, temperature control is performed to ensure that the equipment or key components always maintain the target temperature, and to achieve high-efficiency temperature control that adapts to changes in external environmental factors.

[0057] 2. Design the Gray Wolf optimization fuzzy PID algorithm. On the basis of the fuzzy PID algorithm, the Gray Wolf optimization is introduced. The Gray Wolf optimization searches for the optimal control factor based on the control rounds and the total amount of temperature control power adjustment fed back by the fuzzy PID algorithm, and obtains the optimal temperature control power adjustment scale with the highest real-time efficiency and the minimum total amount of temperature control power adjustment of each key component. It realizes the overall and local coordinated temperature control of the controlled equipment, reduces the temperature control cost and improves the temperature control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of a temperature control system of the present invention;

[0059] Figure 2 This is a flow chart of the progressive change perception strategy in the present invention;

[0060] Figure 3 This is the flow chart of the gray wolf optimized fuzzy PID algorithm in the present invention;

[0061] Figure 4 This is the fuzzy control rule table proposed in this invention. DETAILED DESCRIPTION

[0062] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0063] Example 1

[0064] like Figure 1 As shown, a specific embodiment of the present invention discloses a temperature control system, including a target setting module, a comprehensive monitoring module, a central decision module, an optimization control module and a temperature control execution module;

[0065] The target setting module stores the optimal temperature table and general parameter table ,take over Time adjustment instructions , based on environmental correction strategy considerations Real-time environmental parameter generation at every moment Target temperature table at each moment And feedback to the central decision-making module;

[0066] Integrated monitoring module receives Monitoring instructions at all times , acquired in real time through multiple sensors Monitoring parameter table at all times And feedback to the central decision module, where and They are Real-time ambient temperature and real-time ambient humidity at all times, They are controlled devices 1 to Real-time temperature of key components, is the total number of key components of the controlled equipment, and the number of sensors is equal to the total number of key components Add 2: Key components specifically refer to components whose real-time temperature can have a significant impact on the operation of the controlled equipment, and shall be determined by those skilled in the art;

[0067] The central decision module sets the start time when the system starts and based on the monitoring interval Periodically set subsequent moments and send monitoring instructions at each moment To the integrated monitoring module, receive and store Monitoring parameter table at all times , based on the progressive change perception strategy, comprehensively considers the changes in environmental parameters and controlled devices The real-time temperature change of each key component determines whether to send Instructions at the moment, including Time adjustment instructions , execute instructions and control instructions ;

[0068] Optimize control module reception Time control instructions , using the Grey Wolf optimization fuzzy PID algorithm to consider the control round and Total temperature control power adjustment at any moment Optimize the control factors of the fuzzy PID algorithm to obtain Time control rounds and temperature control power adjustment total Optimal temperature control power adjustment scale with minimum average Generate an adjustment execution tag that uniquely identifies the adjustment execution instruction And with the optimal temperature control power adjustment scale Packaging, obtaining adjustment execution instructions And sent to the temperature control execution module, where For the The temperature control equipment corresponding to each key component is The optimal temperature control power adjustment at any time, , The total number of key components of the controlled equipment;

[0069] The temperature control execution module includes multiple temperature control devices. The total number of temperature control devices and the total number of key components The same, respectively for the controlled device The key components are temperature controlled, and the execution instructions at the start time are received and the conventional temperature control power meter is used. Run the temperature control equipment and receive Time adjustment execution instructions And extract from them The temperature control equipment corresponding to each key component is The optimal temperature control power adjustment at all times, so that each temperature control device The temperature control power at this moment is updated to Temperature control power at all times plus The optimal temperature control power adjustment at any moment. The temperature control equipment includes heating equipment and cooling equipment.

[0070] Further, the optimal temperature table ,in, The first The optimal temperature of key components, the total number of key components Based on the controlled equipment of the temperature control system application, the optimal temperature table Record the optimal operating temperature of each key component of the controlled equipment. Taking the semi-solid die-casting machine as an example, the semi-solid die-casting machine includes 3 key components, that is, the total number of key components , the three key components are alloy furnace, pressure chamber and mold, then the optimal temperature table Record the best furnace temperature, pressure chamber temperature and mold temperature when the semi-solid die casting machine processes specific raw materials. For the semi-solid die casting machine, the best temperature table The optimal operating temperature of the three key components will also change with the change of raw materials.

[0071] Further, general parameter table ,in, and They are normal ambient temperature and normal ambient humidity, specifically referring to the ambient temperature and ambient humidity corresponding to the normal working environment of the controlled equipment. The first The temperature control equipment corresponding to each key component is at normal ambient temperature and normal ambient humidity Under the condition of Key components reach optimal temperature The required conventional temperature control power, which includes conventional heating power and conventional cooling power, is determined by the key components of the controlled equipment. Taking the semi-solid die-casting machine as an example, the three key components of the semi-solid die-casting machine all need to be heated. The alloy furnace melts the raw materials into soup material through heating, the pressure chamber ensures that the soup material can maintain a semi-solid state through heating, and the mold prevents the soup material from solidifying prematurely and affecting the final quality of the casting by heating. Therefore, the three conventional temperature control powers corresponding to the three key components of the semi-solid die-casting machine are all conventional heating powers.

[0072] Furthermore, the target setting module receives Time adjustment instructions , based on the environment correction strategy generation Target temperature table at each moment , including the following specific steps:

[0073] from Time adjustment instructions Get Real-time ambient temperature change at the moment and real-time ambient humidity changes , real-time ambient temperature change for Real-time ambient temperature at the moment Subtract normal ambient temperature , real-time environmental humidity change for Real-time ambient humidity at all times Subtract normal ambient humidity , An adjustment tag uniquely identifies an adjustment instruction;

[0074] Will Real-time ambient temperature change at the moment and real-time ambient humidity changes Synchronous input environment correction network group, output Real-time fitting temperature change table at each moment ,in, For the Real-time fitting temperature changes of key components;

[0075] From the optimal temperature table Extract the The optimal temperature of key components , to make up for the Real-time fitting temperature changes of key components , No. The key components in Target temperature at the moment Should be the optimal temperature minus Real-time temperature change at each moment ,Right now ;

[0076] Statistics of controlled equipment The key components in The target temperature at the moment, get Target temperature table at each moment .

[0077] Furthermore, the environmental correction network group includes The environmental correction network can be any feedforward neural network with nonlinear fitting capability and needs to be pre-trained. In this embodiment, the BP neural network is selected. An environmental correction network is fitted under conventional temperature control power Next Temperature variation of key components Regarding the change in ambient temperature and ambient humidity changes The nonlinear mapping function, , Correct the total number of networks for the environment, and Equal in quantity, taking the pressure chamber in the semi-solid die casting machine as an example, at normal ambient temperature and normal ambient humidity Heating the press chamber with conventional temperature control power can maintain the optimal press chamber temperature. When the ambient temperature and humidity change, although the conventional temperature control power of the press chamber remains unchanged, the heat exchange between the press chamber and the outside world changes, causing the press chamber temperature to change relative to the optimal press chamber temperature. The environmental correction network is used to fit the curve of the press chamber temperature changing with the ambient temperature and humidity.

[0078] Furthermore, The pre-training of an environment correction network includes the following specific steps:

[0079] Determine the The temperature control equipment corresponding to each key component is at normal ambient temperature and normal ambient humidity Next Key components reach optimal temperature Required conventional temperature control power ;

[0080] Fixed conventional temperature control power , at different ambient temperatures and ambient humidity The following measurements are taken to obtain the Different temperatures of key components ;

[0081] Calculate the change in temperature for each pair of ambient temperatures , Change in ambient humidity The corresponding Temperature variation of key components ;

[0082] Adopt the Several ambient temperature changes of key components 、Several changes in ambient humidity and the corresponding temperature changes Build a data set and Divide the training set and test set into the proportion of

[0083] Select the environmental correction network to adjust the ambient temperature change and ambient humidity changes Defined as the input of the environmental correction network, the temperature change Defined as the output of the environment correction network; the loss function is defined as the mean square error, that is, The fitted temperature change output by the environmental correction network The temperature change in the training set The error is adjusted by using Adam optimizer for multiple rounds of training. The hyperparameters of the network are modified in the environment, where the learning rate and training rounds of the Adam optimizer are initially set to 0.01 and 100;

[0084] After the Adam optimizer training is completed, the The hyperparameters of the environment correction network are used to adjust the ambient temperature change in the test set. and ambient humidity changes Enter An environment correction network is used to obtain the mean square error corresponding to the test set;

[0085] If the mean square error corresponding to the test set is less than or equal to the error threshold, then After the network pre-training is completed for each environment, if the mean square error corresponding to the test set is greater than the error threshold, the learning rate and training rounds of the Adam optimizer are adjusted to perform re-training.

[0086] like Figure 2 As shown, further, the central decision module receives Monitoring parameter table at all times And decide whether to send it based on the progressive change perception strategy The instructions at this moment include the following specific steps:

[0087] Get Monitoring parameter table at all times and extract Real-time ambient temperature at the moment and real-time ambient humidity , call the general parameter table stored in the target setting module and extract the normal ambient temperature from it and normal ambient humidity ;

[0088] judge Is the moment the start time? Time is the start time, the normal ambient temperature and normal ambient humidity As the comparison environment temperature and compare ambient humidity ,like The time is not the start time, Real-time ambient temperature at the moment and real-time ambient humidity As the comparison environment temperature and compare ambient humidity , is the monitoring interval;

[0089] calculate Ambient temperature change gradient at each moment and environmental humidity gradient , where the ambient temperature gradient is Shows that the ambient temperature To real-time ambient temperature Temperature fluctuation amplitude, environmental humidity change gradient Shows that the comparison of ambient humidity To real-time ambient humidity Humidity fluctuation range;

[0090] judge Ambient temperature change gradient at each moment and environmental humidity gradient Are they all less than or equal to the change gradient threshold?

[0091] like Ambient temperature change gradient at each moment and environmental humidity gradient are all less than or equal to the change gradient threshold, indicating that the ambient temperature To real-time ambient temperature The temperature has almost no fluctuation and the humidity is To real-time ambient humidity The humidity is almost unchanged, that is, the environmental parameters have not changed significantly. Whether the time is the start time Target temperature table at each moment And decide whether to generate execution instructions And sent to the temperature control execution module, where For the controlled device The key components in Target temperature at the moment;

[0092] when Time is the start time, because The environmental parameters at this moment have not changed significantly compared to the normal environmental parameters, and the optimal temperature table of the target setting module is directly called. and general parameter table and from the General Parameters table Extract Generate a table of conventional temperature control power corresponding to each key component ,in, For the The temperature control equipment corresponding to each key component is at normal ambient temperature and normal ambient humidity Under the condition of Key components reach optimal temperature The required conventional temperature control power is the optimal temperature table As Target temperature table at each moment And store, generate an execution tag for uniquely identifying the execution instruction , compared with conventional temperature control power meter Package generation Execution instructions at the time And send it to the temperature control execution module;

[0093] when The time is not the start time, because The environmental parameters at this moment are compared with There is no significant change in the environmental parameters at the time. Target temperature table at each moment Directly Target temperature table at each moment and store;

[0094] from Monitoring parameter table at all times Extract Real-time temperature chart at all times ,in, They are the 1st to the 2nd controlled devices respectively. Real-time temperature of key components;

[0095] Calculate separately The key components in Temperature gradient at each moment , among which, the controlled device The key components in Temperature gradient at each moment , For the controlled device The real-time temperature of each key component can be further judged. Whether there is a temperature change gradient of a single component greater than a change gradient threshold at a moment;

[0096] like The key components in Temperature gradient at each moment are all less than or equal to the change gradient threshold, that is, the controlled device The temperature of key components Time to If there is almost no change at any time, no action is required and the temperature control execution module continues to Real-time temperature control power meter at all times Just run it;

[0097] like There is a single component in the key components The temperature change gradient at the moment is greater than the change gradient threshold, and a control mark is generated to uniquely identify the control instruction. ,and Target temperature table at each moment Package generation Time control instructions And send it to the optimization control module;

[0098] like Ambient temperature change gradient at each moment and / or ambient humidity gradient Greater than the change gradient threshold, indicating that the temperature To real-time ambient temperature Temperature and / or humidity from the comparison To real-time ambient humidity There are large fluctuations in humidity, that is, the environmental parameters change significantly. Target temperature table at each moment Need to readjust the generation and calculation Real-time ambient temperature change at the moment and real-time ambient humidity changes , generate adjustment marks ,and Real-time ambient temperature change at the moment and real-time ambient humidity changes Package generation Time adjustment instructions And send it to the target setting module, receive and store the feedback from the target setting module Target temperature table at each moment , generate control mark ,and Target temperature table at each moment Package generation Time control instructions And sent to the optimization control module.

[0099] Specifically, taking the semi-solid die-casting machine as an example, the central decision module judges Whether the time is the start time of the temperature control system acting on the semi-solid die casting machine;

[0100] If it is the start time, based on Real-time ambient temperature at the moment , real-time ambient humidity With normal ambient temperature , normal ambient humidity Determine whether environmental parameters have changed significantly;

[0101] If the environmental parameters do not change significantly, the conventional temperature control power meter The alloy furnace, pressure chamber and mold can be heated separately. Achieve optimal furnace temperature, press chamber temperature and mold temperature at all times;

[0102] If the environmental parameters change significantly, the furnace, press chamber and mold will The target temperature at the moment needs to be re-determined through the target setting module. Target temperature table at each moment Through control instructions Tells the optimization control module to adjust the furnace, press chamber and mold Heating power at each moment;

[0103] If it is not the startup time, based on Real-time ambient temperature at the moment , real-time ambient humidity and Real-time ambient temperature at the moment , real-time ambient humidity Determine whether the environmental parameters have changed significantly. is the monitoring interval;

[0104] If the environmental parameters do not change, and The temperatures of the furnace, press chamber and mold must be maintained at the target temperature at all times. , further based on the furnace, press chamber and mold The temperature change gradient at each moment determines whether the furnace temperature, pressure chamber temperature and mold temperature have changed significantly;

[0105] If the furnace temperature, pressure chamber temperature and mold temperature are Significant changes will occur at any time Target temperature table at each moment As Target temperature table at each moment And through the control instructions Tells the optimization control module to adjust the furnace, press chamber and mold Heating power at each moment;

[0106] If the furnace temperature, pressure chamber temperature and mold temperature are There is no significant change at the moment, indicating that Time to At this moment, the furnace, press chamber and mold are still running stably at their respective target temperatures without any adjustment;

[0107] If the environmental parameters change, the furnace, press chamber and mold will The target temperature at the moment needs to be re-determined by the target setting module, and the new target temperature table is passed through Time control instructions Tells the optimization control module to adjust the furnace, press chamber and mold Heating power at all times.

[0108] like Figure 3 As shown, further, the optimization control module uses the gray wolf optimization fuzzy PID algorithm to obtain Optimal temperature control power adjustment scale at all times , including the following specific steps:

[0109] Defining the solution space And in the solution space Initialize the position of the gray wolf pack, which includes Gray wolves, the location of each gray wolf Both represent the solution space A set of control factors of the fuzzy PID algorithm, where The first among the gray wolves The location of the gray wolf, , is the total number of gray wolves, solution space The dimension is equal to the total number of control factors of the fuzzy PID algorithm. The control factors of the fuzzy PID algorithm include The first quantization factor corresponding to the key component and the second quantization factor , the control factor determines the output of the fuzzy PID algorithm;

[0110] Set the maximum number of optimization rounds ,definition Fitness function at the moment ,in, for The total number of control rounds at a time, for The total amount of temperature control power adjustment at any moment;

[0111] Perform a single round of optimization, the number of optimization rounds is 1, The positions of the gray wolves are substituted into the fuzzy PID algorithm and calculated Fitness function at the moment , select the fitness function in the first round of optimization The three smallest gray wolves are Wolf, Wolf and Wolf, Wolf, Wolf and The positions of the wolves are recorded as 、 and ,at this time, Wolf, Wolf and The wolves can be considered as the three best-positioned gray wolves in the first round of optimization;

[0112] Calculate the rest separately The location of the gray wolf Wolf, Wolf and The wolf's distance and the rest Gray wolf Wolf, Wolf and The wolf moves closer to get the rest The updated position of the first gray wolf, assuming The gray wolf is not Wolf, Wolf and Wolf, with The location of the gray wolf For example, after the first round of optimization Updated location of the gray wolf The specific calculation formula is as follows:

[0113] ;

[0114] in, is the first coefficient in the first round of optimization, The first coefficient in the round optimization , For the In the round optimization The first random number generated within, is the maximum optimization round, 、 and They are respectively The location of the gray wolf and Wolf, Wolf and The distance to the wolf's location is calculated as follows:

[0115] ;

[0116] ;

[0117] ;

[0118] in, is the second coefficient in the first round of optimization, The second coefficient in the round optimization , For the In the round optimization The second random number generated within, is the maximum optimization round;

[0119] Repeatedly perform a single round of optimization, reselecting in each round Wolf, Wolf and The wolf ordered the rest of the gray wolves to Wolf, Wolf and The wolves move closer until the number of optimization rounds equals the maximum number of optimization rounds. , will In round optimization Wolf's Position As the optimal control factor of the fuzzy PID algorithm, substitute the fuzzy PID algorithm output Optimal temperature control power adjustment scale at all times ,in, For the The key components corresponding to The temperature control equipment corresponding to each key component is The optimal temperature control power adjustment at any time.

[0120] Furthermore, the position of the single gray wolf Substitute the fuzzy PID algorithm and calculate the fitness function , including the following specific steps:

[0121] From the received Time control instructions Extract Target temperature table at each moment , call the central decision module to store Monitoring parameter table at all times and Monitoring parameter table at all times , respectively extract Real-time temperature chart at all times and Real-time temperature chart at all times , the real-time temperature table Subtract target temperature table To obtain Real-time target temperature difference table at each moment ,Will Real-time temperature chart at all times minus Real-time temperature chart at all times and divided by the monitoring interval To obtain Real-time temperature change rate table at each moment ,in, and They are Moment Real-time target temperature difference and real-time target temperature change rate of each key component;

[0122] Will Moment The real-time target temperature difference and real-time temperature change rate of each key component are multiplied by the corresponding first quantization factor and second quantization factor respectively and input into the fuzzy controller. The fuzzy controller is the first half of the fuzzy PID algorithm. The output of the fuzzy controller is the proportional factor table of the PID algorithm. , Integral Factor Table and differential factor table ,in, 、 and They are Moment The proportional factor, integral factor and differential factor of the key components of the PID algorithm are the second half of the PID fuzzy PID algorithm;

[0123] The membership function of the fuzzy controller is selected as the Gaussian membership function, and the fuzzy subsets are defined for the input and output of the fuzzy controller. ,in, 、 、 、 、 、 and Represented as a large negative number, a moderate negative number, a small negative number, 0, a small positive number, a moderate positive number, and a large positive number respectively;

[0124] A fuzzy control rule table is established based on the inference rules between the input and output of the fuzzy controller. The fuzzy control rule table is as follows: Figure 4 As shown, As an example, assume that the The key components in Real-time target temperature difference at the moment and real-time target temperature change rate All belong to ,According to the fuzzy rule table, the Scaling factors for key components , integrating factor and differential factors Belong to 、 and ;

[0125] Select the center of gravity method as the defuzzification method and obtain the proportional factor table of the PID algorithm , Integral Factor Table and differential factor table , and further through the PID algorithm to get each key component The temperature control power adjustment amount and control rounds corresponding to the time will be The temperature control power adjustment amount and control rounds of each key component are summed up to obtain Total temperature control power adjustment at any moment and control the total number of rounds , thereby obtaining Fitness function at the moment Among them, the center of gravity method and PID algorithm are existing methods and will not be elaborated in detail.

[0126] The present invention discloses a temperature control system, comprising a target setting module, a comprehensive monitoring module, a central decision module, an optimization control module and a temperature control execution module; the target setting module generates a real-time target temperature table based on an environmental correction strategy considering changes in environmental parameters; the comprehensive monitoring module obtains and feeds back a real-time monitoring parameter table; the central decision module decides whether to update the target temperature table or perform temperature control based on a progressive change perception strategy considering changes in environmental parameters and real-time temperature changes of each key component; the optimization control module optimizes the control factor using a gray wolf optimization fuzzy PID algorithm to obtain a real-time optimal temperature control power adjustment scale; the temperature control execution module starts the temperature control device with a conventional temperature control power table, receives adjustment execution instructions and updates the real-time temperature control power, thereby realizing multi-component collaborative temperature control that dynamically responds to the environment and adjusts the total power to the minimum.

[0127] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A temperature control system, characterized in that: It includes target setting module, comprehensive monitoring module, central decision-making module and optimization control module; The target setting module receives real-time adjustment instructions, generates a real-time target temperature table based on the environmental correction strategy and real-time environmental parameters, and feeds it back to the central decision module; The comprehensive monitoring module receives real-time monitoring instructions and feeds back a real-time monitoring parameter table to the central decision module; The central decision module periodically sends real-time monitoring instructions, stores a real-time monitoring parameter table, and decides whether to send real-time instructions based on a progressive change perception strategy taking into account changes in environmental parameters and real-time temperature changes of key components; The optimization control module receives real-time control instructions, optimizes the control factors using the Gray Wolf optimization fuzzy PID algorithm, obtains the real-time optimal temperature control power adjustment scale, and generates adjustment execution instructions; The decision of whether to send a real-time instruction comprises the following steps: Get the current real-time ambient temperature and real-time ambient humidity. If the current time is the startup time, use the normal ambient temperature and normal ambient humidity as the comparison ambient temperature and comparison ambient humidity respectively. If the current time is not the startup time, use the real-time ambient temperature and real-time ambient humidity of the previous time as the comparison ambient temperature and comparison ambient humidity respectively. Calculate the current ambient temperature change gradient and the ambient humidity change gradient and determine whether they are both less than or equal to the change gradient threshold; If the ambient temperature change gradient and / or ambient humidity change gradient at the current moment is greater than the change gradient threshold, the real-time ambient temperature change and the real-time ambient humidity change at the current moment are calculated, packaged with the adjustment mark to generate an adjustment instruction and sent to the target setting module, the target temperature table at the current moment is received and stored, packaged with the control mark to generate a control instruction at the current moment and sent to the optimization control module; If both are less than or equal to the change gradient threshold and the current moment is the startup moment, the optimal temperature table is used as the target temperature table at the current moment and stored, and the execution mark and the conventional temperature control power of all key components are packaged to generate the execution instruction at the current moment; If they are all less than or equal to the change gradient threshold and the current moment is not a startup moment, the target temperature table of the previous moment is used as the target temperature table of the current moment and stored, and the real-time temperature table of the current moment is obtained. The temperature change gradients of all key components at the current moment are calculated separately and it is determined whether they are all less than or equal to the change gradient threshold. If they are all less than or equal to the change gradient threshold, no operation is required. If there is a single component whose temperature change gradient is greater than the change gradient threshold at the current moment, a control mark is generated, packaged with the target temperature table at the current moment to generate a control instruction and sent to the optimization control module.

2. A temperature control system according to claim 1, characterized in that: The method of obtaining the real-time optimal temperature control power adjustment scale includes the following specific steps: Define the solution space and initialize the position of the gray wolf, set the maximum number of optimization rounds, and define the fitness function; Perform a single round of optimization, substitute the position of each gray wolf into the fuzzy PID algorithm and calculate the fitness function, select the three gray wolves with the smallest fitness function and record their positions; Randomly generate a first random number and a second random number for single-round optimization, calculate a first coefficient based on the number of optimization rounds and the first random number, and calculate a second coefficient based on the second random number; Calculate the distances of the remaining gray wolves to the three gray wolves with the smallest fitness function based on the second coefficient; Combining the first coefficient and the distance of each wolf to the three wolves with the smallest fitness function to obtain the updated position of each wolf; Repeat the single round of optimization. In each round of optimization, the three gray wolves with the smallest fitness function are reselected and the updated positions of the gray wolves are obtained until the maximum number of optimization rounds is reached. The positions of the gray wolves with the smallest fitness function are substituted into the fuzzy PID algorithm to output the real-time optimal temperature control power adjustment scale.

3. A temperature control system according to claim 2, characterized in that: Substituting the position of each gray wolf into the fuzzy PID algorithm and calculating the fitness function includes the following specific steps: Extract the current target temperature table, obtain the previous real-time temperature table and the current real-time temperature table; Subtract the current target temperature table from the current real-time temperature table to obtain the current real-time target temperature difference table; subtract the previous real-time temperature table from the current real-time temperature table and divide by the monitoring interval to obtain the current real-time temperature change rate table; The real-time target temperature difference and real-time temperature change rate of all key components at the current moment are multiplied by the corresponding first quantization factor and second quantization factor as the input of the fuzzy controller, and the output of the fuzzy controller is defined as a proportional factor table, an integral factor table, and a differential factor table; Select Gaussian membership function, define fuzzy subsets and establish fuzzy control rule table; The center of gravity method is selected as the defuzzification method to obtain the proportional factor table, integral factor table, and differential factor table. The PID algorithm is used to determine the temperature control power adjustment amount and control round number corresponding to each key component at the current moment. The temperature control power adjustment amounts and control rounds of all key components are summed to obtain the total temperature control power adjustment amount and total control rounds at the current moment, and the fitness function at the current moment is obtained by accumulating the sum.

4. A temperature control system according to claim 1, characterized in that: The target setting module receives the real-time adjustment instruction and generates a real-time target temperature table based on the environmental correction strategy and the real-time environmental parameters, including the following specific steps: Input the real-time ambient temperature change and the real-time ambient humidity change into the environmental correction network group, and output a real-time fitting temperature change table; Obtain the optimal temperature of a single key component and subtract the real-time temperature variation to obtain the real-time target temperature of the single key component; Count the real-time target temperatures of all key components and obtain a real-time target temperature table.

5. A temperature control system according to claim 4, characterized in that: The environmental correction network group includes environmental correction networks whose number is equal to the total number of key components and which need to be pre-trained, wherein a single environmental correction network fits a nonlinear mapping function of the temperature change of a single key component corresponding to conventional temperature control power with respect to the ambient temperature change and the ambient humidity change.

6. A temperature control system according to claim 5, characterized in that: The pre-training of the single environment correction network includes the following specific steps: Fix the conventional temperature control power of a single temperature control device and measure the different temperatures of a single key component under different ambient temperatures and ambient humidity; Calculate the temperature change corresponding to each pair of ambient temperature change and ambient humidity change; The data set is constructed using the ambient temperature change, ambient humidity change and corresponding temperature change and divided into training set and test set; Select the environmental correction network, define the input as the change in ambient temperature and humidity, the output as the change in temperature, define the loss function as mean square error, and use the Adam optimizer for training; After training is completed, the hyperparameters of the network are fixed in a single environment, and the test set is used to test to obtain the mean square error corresponding to the test set and determine whether it is less than or equal to the error threshold; If it is less than or equal to the error threshold, the single environment correction network pre-training is completed. If it is greater than the error threshold, the Adam optimizer is adjusted and re-trained.

7. A temperature control system according to claim 1, characterized in that: The target setting module stores an optimal temperature table and a conventional parameter table. The optimal temperature table includes the optimal temperatures of all key components. The conventional parameter table includes conventional ambient temperature, conventional ambient humidity, and conventional temperature control power of temperature control devices corresponding to all key components.

8. A temperature control system according to claim 1, characterized in that: The temperature control system further includes a temperature control execution module, which receives execution instructions and operates the temperature control device using a conventional temperature control power meter, receives real-time adjustment execution instructions and updates the real-time temperature control power of each temperature control device.

Images