Temperature control method in plate production process

Through the combination of intelligent sensor network and multiple control algorithms, the problems of uneven temperature control and slow response in plate production are solved, efficient and stable temperature control is achieved, and the overall benefits and product quality of plate production are improved.

CN119065413APending Publication Date: 2024-12-03JIANGXI TONGYI POLYMER MATERIAL TECH CO LTD
View PDF 0 Cites 8 Cited by

Patent Information

Application Number
CN202411166544.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

During the traditional plate production process, single-point temperature monitoring cannot fully reflect the temperature distribution of the entire production line, resulting in uneven temperature control. In addition, traditional PID control is less efficient when dealing with nonlinear and uncertainty problems, and cannot respond quickly to burst temperatures. change.

Method used

Adopt intelligent sensor network and distributed data processing, combining fuzzy control, PID control and adaptive neural network, use machine learning algorithms to establish temperature prediction models, and achieve real-time and accurate through multi-objective optimization control and intelligent feedback and self-repair systems. Temperature monitoring and flexible control strategy adjustment.

Benefits of technology

It significantly improves the accuracy and response speed of temperature control, optimizes the temperature control strategy, reduces temperature fluctuations, improves production efficiency and product quality, and ensures high efficiency, stability and continuity of the production process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065413A_ABST
    Figure CN119065413A_ABST
Patent Text Reader

Abstract

The invention discloses a temperature control method in a plate production process, and particularly relates to the technical field of industrial automatic manufacturing, S1, a temperature sensor is deployed on a plate production line, the sensor discovers and is connected with other sensor nodes, a dynamically adjusted and self-repaired sensor network is formed, low-delay data transmission is realized, and through dynamic reconfiguration, the temperature of the plate production process is controlled; the integrity of the sensor network and the continuity of data transmission are ensured; firstly, through deployment of an intelligent sensor network and distributed data processing and analysis, the system can accurately monitor temperature changes on a production line in real time, and accuracy and timeliness of temperature data are improved. And secondly, three algorithms of fuzzy control, PID control and an adaptive neural network are combined, so that the system has the capability of flexibly coping with different production conditions, the accuracy and response speed of temperature control are remarkably improved, and integration of intelligent feedback and a self-repairing system is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automated manufacturing, and more specifically, to a temperature control method in a plate production process. Background Art

[0002] In the board production process, traditional temperature control methods usually rely on single-point temperature monitoring and simple PID control, but this has significant limitations when facing complex production environments and dynamically changing temperature requirements. Single-point temperature monitoring cannot fully reflect the temperature distribution of the entire production line, resulting in uneven temperature control, which affects the quality of the board. Traditional PID control is less efficient in dealing with nonlinear and uncertain problems and cannot respond quickly to sudden temperature changes. In order to overcome these problems, a temperature control method for the board production process is proposed. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the embodiment of the present invention provides a temperature control method for the plate production process. Through the above-mentioned innovative temperature control technical solution, the plate production process achieves significant beneficial effects; first, through the deployment of intelligent sensor networks and distributed data processing and analysis, the system can monitor the temperature changes on the production line in real time and accurately, and improve the accuracy and timeliness of temperature data. Secondly, by combining the three algorithms of fuzzy control, PID control and adaptive neural network, the system has the ability to flexibly respond to different production conditions, and significantly improves the accuracy and response speed of temperature control. Thirdly, the temperature prediction model established by the machine learning algorithm is used to predict the temperature change trend in advance, optimize the temperature control strategy, reduce temperature fluctuations, and improve production efficiency and product quality. In addition, through multi-objective optimization control, the system can comprehensively consider temperature uniformity, energy consumption minimization and production efficiency maximization, achieve global optimal control, and ensure the efficiency and stability of the production process. Finally, the integration of intelligent feedback and self-repairing system enhances the fault diagnosis and self-repairing capabilities of the system, ensures the continuity and stability of the production process, and reduces production interruptions and quality problems caused by faults. Overall, this innovative temperature control method greatly improves the overall benefits and product quality of plate production.

[0004] To achieve the above object, the present invention provides the following technical solution: The temperature control of the plate production process includes the following steps:

[0005] S1: Deploy temperature sensors on the sheet production line. The sensors discover and connect to other sensor nodes to form a dynamically adjusted and self-healing sensor network to achieve low-latency data transmission. Through dynamic reconfiguration, the integrity of the sensor network and the continuity of data transmission are ensured.

[0006] S2: Integrate a distributed data processing unit in each temperature sensor node to perform real-time data analysis and preprocessing, and only transmit key data to the central control system; through data filtering, smoothing and anomaly detection preprocessing steps, reduce the load of the central system and improve data processing efficiency and response speed;

[0007] S3: The central control system combines three algorithms, fuzzy control, PID control and adaptive neural network, to automatically adjust control parameters and optimize temperature regulation strategy according to real-time monitoring data. The fuzzy controller handles temperature deviation, the PID controller adjusts proportional, integral and differential parameters, and the adaptive neural network performs online training and parameter optimization. Through comprehensive control output and dynamic weight adjustment, multi-algorithm collaborative optimization control is achieved;

[0008] S4: Use LSTM machine learning algorithm to establish a prediction model for temperature changes, predict temperature change trends in advance, generate optimized temperature control strategies, and reduce temperature fluctuations; collect and preprocess historical temperature data, train prediction models, predict future temperature changes in real time, and dynamically adjust control parameters based on prediction results to achieve precise temperature control;

[0009] S5: In the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered simultaneously, global optimal control is achieved through dynamic weight adjustment, a multi-objective optimization function is constructed, the objective function is optimized using genetic algorithms, dynamic optimization control is performed based on real-time data, and comprehensive balance of various optimization objectives is achieved;

[0010] S6: Integrated real-time feedback control system, rapid response to temperature changes, equipped with fault diagnosis and self-repair module, real-time detection of system status, automatic repair of faults found, real-time monitoring of sensor data and control instructions, closed-loop feedback control and fault diagnosis, start-up of self-repair mechanism for fault isolation and network reorganization, to ensure continuous and stable operation of the system;

[0011] In a preferred embodiment: the temperature control method for a sheet material production process according to claim 1 is characterized in that: a temperature sensor T is arranged on the production line i , where i represents the sensor number, T1, T2, ..., T n , arrange T in the cooling zone n +1, T n+2 , ..., T m ; The sensor nodes use Zigbee wireless communication protocol; Each sensor node T i Equipped with wireless communication module, using ad hoc network protocol P mesh Establish a network connection: N(T) = {T i |i∈[1,n]}; where N(T) represents the sensor network, Ti Represents a node in the network; when a sensor node T i When a failure occurs, the network N(T) automatically reconfigures the other nodes T j (j≠i) reconnect to ensure the integrity of the network and the continuity of data transmission.

[0012] In a preferred embodiment: a data processing unit is integrated in each temperature sensor node to perform real-time analysis and preliminary processing on the collected temperature data, and only transmit key data to the central control system; data collection is performed through each sensor T i Collect temperature data D i (t), where t represents time: D i (t) = {T i (t)}; initial processing by sensor node T i Perform data preprocessing F i , including filter F filter , Smooth F smooth and anomaly detection F detect :D′ i (t) = F i (D i (t)) = F smooth (F filter (D i (t))); key data transmission is transmitted through sensor node T i Only the processed key data D′ is transmitted i (t) To the central control system C: D' i (t)→C.

[0013] In a preferred embodiment: the central control system adopts a combination of fuzzy control, PID control and adaptive neural network control, automatically adjusts the control parameters according to real-time monitoring data, and optimizes the temperature adjustment strategy to adapt to the changing environment and needs in the production process. First, a fuzzy rule base is established to define the fuzzy rule base for temperature control: if e(t) = A and Δe(t) = B, then Δu(t) = C, where e(t) = T set -T i (t) is the temperature deviation, Δe(t) = e(t) - e(t-1) is the deviation change rate, and Δu(t) is the control output change; then fuzzy reasoning is performed based on the fuzzy rule base and the current temperature deviation and deviation change rate to calculate the control output change: Δu fuzzy (t)=∑ i w i ·C i , where w i is the weight of the fuzzy rule, C i is the output corresponding to the fuzzy rule; first define the output of the PID controller: Among them, K p , K i , K d They are proportional, integral and differential gains respectively; Parameter adjustment: adjust the parameters of the PID controller according to the output changes of the fuzzy controller: A neural network model NN is established, with the input being the current temperature data and historical data, and the output being the adjustment value of the control parameter: Δθ(t)=NN(D total (t), H(t)), where Δθ(t) is the adjustment value of the control parameter. Online training uses real-time monitoring data and control output for online training to update the weights of the neural network model: Update weights Among them, W is the weight of the neural network, η is the learning rate, and E is the error function; finally, according to the output of each algorithm, the comprehensive control output is calculated: u total (t) = w1u fuzzy (t)+w2u PID (t)+w3u NN (t), where w1, w2, and w3 are the weights of each algorithm; Weight adjustment: Dynamically adjust the weights of each algorithm based on the control effect and real-time feedback: Among them, w1(t+1)=w1(t)+Δw1(t): at time t+1, the weight w1 of fuzzy control is its weight w1(t) at time t plus the weight adjustment Δw1(t), w2(t+1)=w2(t)+Δw2(t): at time t+1, the weight w2 of PID control is its weight w2(t) at time t plus the weight adjustment Δw2(t), w3(t+1)=w3(t)+Δw3(t): at time t+1, the weight w3 of adaptive neural network control is its weight w3(t) at time t plus the weight adjustment Δw3(t).

[0014] In a preferred embodiment: a prediction model of temperature change is established using a machine learning algorithm to predict the temperature change trend in advance, generate an optimized temperature control strategy, and reduce temperature fluctuations. Historical data collection: historical temperature data H(t) is collected from the sensor network of the production line, including the temperature measurement value T i (t), control parameters θ(t), and production environment variables E(t): Where H(t) is the historical temperature data, T i (t) is the temperature measurement value of sensor i at time t, θ(t) is the control parameter at time t, and E(t) is the production environment variable at time t; then the historical data is preprocessed, including missing value filling, data normalization and noise filtering; missing values ​​are filled by interpolation, and data normalization is achieved by the following formula: Among them, T′ i(t) is the temperature measurement value after preprocessing, T min and T max Select models for the minimum and maximum values ​​of temperature data respectively: Predict temperature change trend through machine learning model LSTM: M = LSTM (H (t)), where M is the temperature prediction model trained by LSTM, H (t) is the historical temperature data, use the preprocessed historical data to train the model, and optimize the model parameter θ M : Among them, θ M is the optimized model parameter, T pred (t) is the predicted temperature value, T actual (t) is the actual temperature value; Real-time data input: input the real-time data into the trained model for prediction: T pred (t+Δt)=M(D total (t)) where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; predict the temperature trend of the future time period t+Δt and generate the temperature prediction value T pred (t+Δt):T pred (t+Δt)=M(D total (t)), where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; according to the prediction result T pred (t+Δt), the central control system C adjusts the control parameter θ(t) and optimizes the temperature control strategy: θ(t+Δt)=optimize(T pred (t+Δt)), where θ(t+Δt) is the control parameter at time t+Δt, optimize is the optimization function, T pred (t+Δt) is the predicted temperature value at time t+Δt; a new control instruction U(t) is generated to reduce temperature fluctuations and maintain temperature stability: U(t)=f(θ(t+Δt)), where U(t) is the control instruction at time t, f is the control function, and θ(t+Δt) is the control parameter at time t+Δt.

[0015] In a preferred embodiment: in the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered simultaneously, and global optimal control is achieved through dynamic weight adjustment; temperature uniformity target G1: ensure uniform temperature throughout the production line to avoid local overheating and overcooling: Where G1 is the temperature uniformity target, n is the number of sensors, T i(t) is the temperature measurement value T of sensor i at time t set is the set temperature; energy consumption minimization goal G2: reduce energy consumption while meeting the temperature control requirements: G2 = E(t), where G2 is the energy consumption minimization goal, and E(t) is the energy consumption at time t; production efficiency maximization goal G3: improve production speed and efficiency while ensuring product quality: G3 = η(t), where G3 is the production efficiency maximization goal, and η(t) is the production efficiency at time t; comprehensive optimization objective function G: G = α1G1+α2G2+α3G3, where G is the comprehensive optimization objective function, α1, α2, α3 are the weight coefficients of each optimization objective, corresponding to the temperature uniformity objective G1, energy consumption minimization objective G2 and production efficiency maximization objective G3 respectively; then use the multi-objective optimization algorithm to optimize the objective function: Among them, θ opt is the optimized control parameter, G(θ) is the optimization objective function; dynamic optimization is performed based on real-time data: during the production process, temperature data and energy consumption data are monitored in real time, and the weight coefficient α of the optimization objective function is dynamically adjusted i , to achieve global optimal control: α i (t) = adjust(α i , D total (t)), where αi(t) is the weight coefficient at time t, adjust is the weight adjustment function, and D total (t) is the real-time data at time t; finally, the decision rule is established:

[0016] If the temperature deviation |T i (t)-T set |>∈1, then adjust the heating power and cooling intensity P c (t):

[0017]

[0018] Among them, U(t) is the control instruction at time t, P y (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP ∈ is the adjustment amount, T i (t) is the temperature measurement value of sensor i at time t, T set is the set temperature, ∈1 is the temperature deviation threshold;

[0019] If energy consumption E(t)>E max , then optimize energy consumption regulation and reduce heating and cooling frequency:

[0020]

[0021] Among them, U(t) is the control instruction at time t, P y (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP c is the adjustment amount, and is the threshold of heating power and cooling intensity, E(t) is the energy consumption at time t, E max is the maximum energy consumption;

[0022] If production efficiency η(t)<η min , then adjust the temperature control strategy to increase the production line speed:

[0023] U(t)=optimize(T i (t), η(t))

[0024] Among them, U(t) is the control instruction at time t, optimize is the optimization function, T i (t) is the temperature measurement value of sensor i at time t, η(t) is the production efficiency at time t, η min The minimum production efficiency.

[0025] In a preferred embodiment: an integrated real-time feedback control system that quickly responds to temperature changes, equipped with a fault diagnosis and self-repair module, real-time detection of system status, automatic repair of faults found; real-time monitoring of sensor data D′ i (t) and control command U(t), conduct closed-loop feedback control F, and adjust control parameters in time θ (t): F = {D i ′(t),U(t), θ (t)}, where D′ i (t) is the processed data of sensor i at time t, U(t) is the control instruction at time t, θ(t) is the control parameter at time t, and F is the feedback control signal; Fault diagnosis algorithm D(F): Real-time detection of sensor T i and control system C, and find abnormal situation E i :E i =D(F), where D(F) is the fault diagnosis algorithm, E i is the abnormal situation detected at time t, T i is the sensor, C is the control system; the self-repair mechanism R(E i ): When fault E is detected i After that, perform fault isolation and system reorganization:

[0026] Among them, R(Ei ) is the self-repair mechanism, T i is the faulty sensor and N(T) is the sensor network.

[0027] Technical effects and advantages of the present invention: Through the above-mentioned innovative temperature control technical solution, the board production process has achieved significant beneficial effects. First, through the deployment of intelligent sensor networks and distributed data processing and analysis, the system can monitor the temperature changes on the production line in real time and accurately, improving the accuracy and timeliness of temperature data. Secondly, by combining the three algorithms of fuzzy control, PID control and adaptive neural network, the system has the ability to flexibly respond to different production conditions, significantly improving the accuracy and response speed of temperature control. Thirdly, the temperature prediction model established by machine learning algorithm is used to predict the temperature change trend in advance, optimize the temperature control strategy, reduce temperature fluctuations, and improve production efficiency and product quality. In addition, through multi-objective optimization control, the system can comprehensively consider temperature uniformity, energy consumption minimization and production efficiency maximization, achieve global optimal control, and ensure the efficiency and stability of the production process. Finally, the integration of intelligent feedback and self-repair system enhances the system's fault diagnosis and self-repair capabilities, ensures the continuity and stability of the production process, and reduces production interruptions and quality problems caused by faults. Overall, this innovative temperature control method greatly improves the overall benefits and product quality of board production. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the working steps of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Example embodiments will now be described more fully with reference to the accompanying drawings, a method for temperature control of a sheet production process, the temperature control of a sheet production process comprising the following steps: S1: deploying temperature sensors on a sheet production line, the sensors discovering and connecting to other sensor nodes to form a dynamically adjusted and self-healing sensor network to achieve low-latency data transmission, and ensuring the integrity of the sensor network and the continuity of data transmission through dynamic reconfiguration;

[0031] S2: Integrate a distributed data processing unit in each temperature sensor node to perform real-time data analysis and preprocessing, and only transmit key data to the central control system; through data filtering, smoothing and anomaly detection preprocessing steps, reduce the load of the central system and improve data processing efficiency and response speed;

[0032] S3: The central control system combines three algorithms, fuzzy control, PID control and adaptive neural network, to automatically adjust control parameters and optimize temperature regulation strategy according to real-time monitoring data. The fuzzy controller handles temperature deviation, the PID controller adjusts proportional, integral and differential parameters, and the adaptive neural network performs online training and parameter optimization. Through comprehensive control output and dynamic weight adjustment, multi-algorithm collaborative optimization control is achieved;

[0033] S4: Use LSTM machine learning algorithm to establish a prediction model for temperature changes, predict temperature change trends in advance, generate optimized temperature control strategies, and reduce temperature fluctuations; collect and preprocess historical temperature data, train prediction models, predict future temperature changes in real time, and dynamically adjust control parameters based on prediction results to achieve precise temperature control;

[0034] S5: In the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered simultaneously, global optimal control is achieved through dynamic weight adjustment, a multi-objective optimization function is constructed, the objective function is optimized using genetic algorithms, dynamic optimization control is performed based on real-time data, and comprehensive balance of various optimization objectives is achieved;

[0035] S6: Integrated real-time feedback control system, rapid response to temperature changes, equipped with fault diagnosis and self-repair module, real-time detection of system status, automatic repair of faults found, real-time monitoring of sensor data and control instructions, closed-loop feedback control and fault diagnosis, start self-repair mechanism for fault isolation and network reorganization, to ensure continuous and stable operation of the system; temperature sensor T is arranged on the production line i , where i represents the sensor number, T1, T2, ..., T n , arrange T in the cooling zone n +1, T n+2 , ..., T m ; The sensor nodes use Zigbee wireless communication protocol; Each sensor node T i Equipped with wireless communication module, using ad hoc network protocol P mesh Establish a network connection: N(T) = {T i |i∈[1,n]}; where N(T) represents the sensor network, T i Represents a node in the network; when a sensor node T i When a failure occurs, the network N(T) automatically reconfigures the other nodes T i(j≠i) reconnection to ensure the integrity of the network and the continuity of data transmission; on the plate production line, high-precision temperature sensors need to be deployed at key locations, and these sensors must have self-organizing network functions. This means that each sensor can automatically discover and connect to other sensor nodes to form a dynamically adjusted and self-healing sensor network. The application of self-organizing network technology enables the sensor network to quickly reorganize when any node fails or fails, ensuring the continuity of data transmission and the integrity of the network. In order to achieve low-latency data transmission, each sensor node is equipped with a wireless communication module and uses a specific self-organizing network protocol for communication. This protocol allows sensor nodes to quickly transmit data and dynamically adjust the network topology as needed to adapt to changes and needs of the production line. In this way, the entire sensor network can monitor temperature changes on the production line in real time and provide accurate temperature data. These data are crucial for subsequent temperature control and optimization strategies because they directly affect production efficiency and product quality. In addition, the use of high-precision temperature sensors ensures the accuracy of the data and further improves the accuracy of temperature control. The dynamic adjustment capability and self-healing function of the entire sensor network greatly improve the reliability and stability of the system and reduce production interruptions and quality problems caused by sensor failures or data transmission problems.

[0036] Secondly, a data processing unit is integrated in each temperature sensor node to perform real-time analysis and preliminary processing on the collected temperature data, and only transmit key data to the central control system; data collection is done through each sensor T i Collect temperature data D i (t), where t represents time: D i (t) = {T i (t)}; initial processing by sensor node T i Perform data preprocessing F i , including filter F filter , Smooth F smooth and anomaly detection F detect :D′ i (t) = F i (D i (t)) = F smooth (F filter (D i (t))); key data transmission is transmitted through sensor node T i Only the processed key data D′ is transmitted i (t) To the central control system C: D' i(t)→C; A distributed data processing unit is integrated in each temperature sensor node. This design enables real-time analysis and preprocessing of data to be completed on the sensor node, thereby reducing the load on the central control system. Each sensor node is not only responsible for collecting temperature data, but also for preliminary data processing, including filtering, smoothing, and anomaly detection. Filtering technology can remove noise from the collected data to ensure the purity of the data; smoothing technology can reduce data fluctuations to make the temperature data more stable; anomaly detection technology is used to identify and exclude abnormal data points to prevent false alarms and misoperations. After these preprocessing steps, only the processed key data is transmitted to the central control system. This method not only reduces the amount of data transmission and transmission delay, but also improves the efficiency of data processing. After receiving the processed data, the central control system can respond and make decisions more quickly, thereby achieving more efficient temperature control. This distributed data processing design ensures the real-time and flexibility of the system, enabling temperature control to respond to various changes and emergencies on the production line in a timely manner. Through distributed data processing and analysis, the response speed and processing capacity of the entire system have been significantly improved, which helps to improve production efficiency and product quality.

[0037] Next, the central control system adopts a combination of fuzzy control, PID control and adaptive neural network control to automatically adjust the control parameters according to real-time monitoring data and optimize the temperature adjustment strategy to adapt to the changing environment and needs in the production process. First, a fuzzy rule base is established to define the fuzzy rule base for temperature control: if e(t) = A and Δe(t) = B, then Δu(t) = C, where e(t) = T set -T i (t) is the temperature deviation, Δe(t) = e(t) - e(t-1) is the deviation change rate, and Δu(t) is the control output change; then fuzzy reasoning is performed based on the fuzzy rule base and the current temperature deviation and deviation change rate to calculate the control output change: Δu fuzzy (t)=∑ i w i ·C i , where w i is the weight of the fuzzy rule, C i is the output corresponding to the fuzzy rule; first define the output of the PID controller: Among them, K p , K i , K d They are proportional, integral and differential gains respectively; Parameter adjustment: adjust the parameters of the PID controller according to the output changes of the fuzzy controller: A neural network model NN is established, with the input being the current temperature data and historical data, and the output being the adjustment value of the control parameter: Δλ(t)=NN(Dtotal (t), H(t)), where Δλ(t) is the adjustment value of the control parameter. Online training uses real-time monitoring data and control output to perform online training and update the weights of the neural network model: Update weights Among them, W is the weight of the neural network, η is the learning rate, and E is the error function; finally, according to the output of each algorithm, the comprehensive control output is calculated: u total (t) = w1u fuzzy (t)+w2u PID (t)+w3u NN (t), where w1, w2, and w3 are the weights of each algorithm; Weight adjustment: Dynamically adjust the weights of each algorithm based on the control effect and real-time feedback: Among them, w1(t+1)=w1(t)+Δw1(t): at time t+1, the weight w1 of fuzzy control is its weight w1(t) at time t plus the weight adjustment Δw1(t), w2(t+1)=w2(t)+Δw2(t): at time t+1, the weight w2 of PID control is its weight w2(t) at time t plus the weight adjustment Δw2(t), w3(t+1)=w3(t)+Δw3(t): at time t+1, the weight w3 of adaptive neural network control is its weight w3(t) at time t plus the weight adjustment Δw3(t); The central control system combines fuzzy control, PID control and adaptive neural network three control algorithms to achieve precise control of temperature. The fuzzy control algorithm is used to process temperature deviation. Through the pre-set fuzzy rule base, the temperature data is fuzzified and inferred to generate the corresponding control output. On this basis, the PID control algorithm further adjusts the proportional, integral and differential parameters to achieve fast response and stable control. The adaptive neural network continuously optimizes the control parameters through the learning of real-time data and historical data to adapt to the dynamic changes in the production process. The combination of these three control algorithms enables the system to flexibly respond to different production conditions and achieve the best control effect. Specifically, fuzzy control handles nonlinear and uncertain problems, PID control responds quickly and stabilizes the system, and adaptive neural networks perform well in dealing with complex and dynamically changing systems. Through the comprehensive control output, the system can dynamically adjust the weights of each algorithm to achieve multi-algorithm collaborative optimization control. For example, when the fuzzy control effect is good, its weight can be increased; when the PID control effect is not good, its weight can be reduced. In this way, the system can flexibly adjust the control strategy according to the real-time situation to ensure the accuracy and stability of temperature control. This combination of multiple adaptive control algorithms not only improves the intelligence level of the system, but also enhances the adaptability and robustness of the system.

[0038] In addition, a prediction model of temperature change is established using machine learning algorithms to predict temperature change trends in advance, generate optimized temperature control strategies, and reduce temperature fluctuations. Historical data collection: Historical temperature data H(t) is collected from the sensor network of the production line, including temperature measurement values ​​T j (t), control parameters θ(t), and production environment variables E(t): Where H(t) is the historical temperature data, T i (t) is the temperature measurement value of sensor i at time t, θ(t) is the control parameter at time t, and E(t) is the production environment variable at time t; then the historical data is preprocessed, including missing value filling, data normalization and noise filtering; missing values ​​are filled by interpolation, and data normalization is achieved by the following formula: Among them, T′ i (t) is the temperature measurement value after preprocessing, T min and T max Select models for the minimum and maximum values ​​of temperature data respectively: Predict temperature change trend through machine learning model LSTM: M = LSTM (H (t)), where M is the temperature prediction model trained by LSTM, H (t) is the historical temperature data, use the preprocessed historical data to train the model, and optimize the model parameter θ M : Among them, θ M is the optimized model parameter, T pred (t) is the predicted temperature value, T actual (t) is the actual temperature value; Real-time data input: input the real-time data into the trained model for prediction: T pred (t+Δt)=M(D total (t)) where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; predict the temperature trend of the future time period t+Δt and generate the temperature prediction value T pred (t+Δt):T pred (t+Δt)=M(D total (t)), where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; according to the prediction result T pred (t+Δt), the central control system C adjusts the control parameter θ(t) and optimizes the temperature control strategy: θ(t+Δt)=optimize(T pred(t+Δt)), where θ(t+Δt) is the control parameter at time t+Δt, optimize is the optimization function, T pred (t+Δt) is the predicted temperature value at time t+Δt; a new control instruction U(t) is generated to reduce temperature fluctuations and maintain temperature stability: U(t)=f(θ(t+Δt)), where U(t) is the control instruction at time t, f is the control function, and θ(t+Δt) is the control parameter at time t+Δt; by using machine learning algorithms to establish a prediction model for temperature changes, the temperature change trend can be predicted in advance, and an optimized temperature control strategy can be generated, thereby effectively reducing temperature fluctuations. In this process, it is first necessary to collect historical temperature data from the sensor network of the production line, including temperature measurements, control parameters, and production environment variables. The collected historical data is preprocessed, including missing value filling, data normalization, and noise filtering to ensure the integrity and accuracy of the data. Then, the machine learning model LSTM is selected for training. When training the model, the preprocessed historical data is used for optimization to minimize the error between the predicted temperature value and the actual temperature value. The trained model can predict the temperature trend based on the real-time input data. Specifically, the real-time data is input into the trained model to predict the temperature change trend in the future time period. Based on the prediction results, the central control system can dynamically adjust control parameters, optimize temperature control strategies, generate new control instructions, reduce temperature fluctuations, and maintain temperature stability. This predictive model control based on machine learning can better cope with temperature fluctuations and changes that may occur during the production process by predicting temperature changes in advance, improving the accuracy and response speed of temperature control, and further improving production efficiency and product quality.

[0039] It should be noted that in the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered at the same time, and global optimal control is achieved through dynamic weight adjustment; temperature uniformity target G1: ensure uniform temperature on the entire production line to avoid local overheating and overcooling: Where G1 is the temperature uniformity target, n is the number of sensors, T i (t) is the temperature measurement value T of sensor i at time t setis the set temperature; energy consumption minimization goal G2: reduce energy consumption while meeting the temperature control requirements: G2 = E(t), where G2 is the energy consumption minimization goal, and E(t) is the energy consumption at time t; production efficiency maximization goal G3: improve production speed and efficiency while ensuring product quality: G3 = η(t), where G3 is the production efficiency maximization goal, and η(t) is the production efficiency at time t; comprehensive optimization objective function G: G = α1G1+α2G2+α3G3, where G is the comprehensive optimization objective function, α1, α2, α3 are the weight coefficients of each optimization objective, corresponding to the temperature uniformity objective G1, energy consumption minimization objective G2 and production efficiency maximization objective G3 respectively; then use the multi-objective optimization algorithm to optimize the objective function: Among them, θ opt is the optimized control parameter, G(θ) is the optimization objective function; dynamic optimization is performed according to real-time data: during the production process, temperature data and energy consumption data are monitored in real time, and the weight coefficient αi of the optimization objective function is dynamically adjusted to achieve global optimal control: α i (t) = adjust(α i , D total (t)), where α i (t) is the weight coefficient at time t, adjust is the weight adjustment function, D total (t) is the real-time data at time t; finally, the decision rule is established:

[0040] If the temperature deviation |T i (t)-T set |>∈1, then adjust the heating power and cooling intensity P c (t):

[0041]

[0042] Among them, U(t) is the control instruction at time t, P y (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP ∈ is the adjustment amount, T i (t) is the temperature measurement value of sensor i at time t, T set is the set temperature, ∈1 is the temperature deviation threshold;

[0043] If energy consumption E(t)>E max , then optimize energy consumption regulation and reduce heating and cooling frequency:

[0044]

[0045] Among them, U(t) is the control instruction at time t, Py (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP c is the adjustment amount, and is the threshold of heating power and cooling intensity, E(t) is the energy consumption at time t, E max is the maximum energy consumption;

[0046] If production efficiency η(t)<η min , then adjust the temperature control strategy to increase the production line speed:

[0047] U(t)=optimize(T i (t), η(t))

[0048] Among them, U(t) is the control instruction at time t, optimize is the optimization function, T i (t) is the temperature measurement value of sensor i at time t, η(t) is the production efficiency at time t, η min is the minimum value of production efficiency; in the temperature control process, the three optimization objectives of temperature uniformity, energy consumption minimization and production efficiency maximization are considered at the same time, and global optimal control is achieved through dynamic weight adjustment. First, three optimization objectives are determined: temperature uniformity ensures that the temperature on the entire production line is as uniform as possible to avoid local overheating or overcooling; energy consumption minimization minimizes energy consumption while meeting the temperature control requirements; production efficiency maximization improves production speed and efficiency while ensuring product quality. Then, a comprehensive optimization objective function is constructed to combine the weight coefficients of these three objectives to form a multi-objective optimization function. Next, a multi-objective optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm) is used to optimize this objective function and find the best control parameters. In the actual production process, dynamic optimization is performed according to real-time data, temperature data and energy consumption data are monitored in real time, and the weight coefficient of the optimization objective function is dynamically adjusted to achieve global optimal control. For example, when energy consumption exceeds the set threshold, the frequency of heating or cooling can be reduced; when production efficiency is lower than the set value, the temperature control strategy can be adjusted to increase the speed of the production line. In this way, the system can flexibly respond to changes in the production process, achieve optimization and balance of temperature control, and ensure the efficiency and stability of the production process.

[0049] Finally, the integrated real-time feedback control system can quickly respond to temperature changes, and is equipped with a fault diagnosis and self-repair module to detect the system status in real time and automatically repair faults; real-time monitoring of sensor data D′ i (t) and control command U(t), perform closed-loop feedback control F, and adjust the control parameter θ(t) in time: F={D i′(t), U(t), θ(t)}, where D i (t) is the processed data of sensor i at time t, U(t) is the control instruction at time t, θ(t) is the control parameter at time t, and F is the feedback control signal; Fault diagnosis algorithm D(F): Real-time detection of sensor T i and control the status of the control system C, and find abnormal situation E i :E i =D(F), where D(F) is the fault diagnosis algorithm, E i is the abnormal situation detected at time t, T i is the sensor, C is the control system; the self-repair mechanism R(E i ): When fault E is detected i After that, perform fault isolation and system reorganization:

[0050] Among them, R(E i ) is the self-repair mechanism, T i is the fault sensor, and N(T) is the sensor network; in the intelligent feedback and self-repairing system, real-time feedback control and fault diagnosis and self-repairing modules are integrated to achieve rapid response to temperature changes and real-time monitoring of system status. First, the system monitors sensor data and control instructions in real time, performs closed-loop feedback control, and adjusts control parameters in time to ensure temperature stability. When temperature changes are detected, the feedback control system can respond quickly, adjust the operating status of the heating or cooling equipment, and maintain the temperature within the set range. At the same time, the fault diagnosis algorithm integrated in the system can detect the status of the sensor and control system in real time and find abnormal conditions, such as sensor failure or data anomaly. When a fault occurs, the self-repairing mechanism automatically starts to isolate the faulty sensor and reorganize the sensor network to ensure the continuity of data transmission and the normal operation of the system. For example, when a sensor node fails, the system automatically reconfigures the network, and other nodes will reconnect to ensure the integrity of the network and the accuracy of the data. In this way, the system can not only respond and adjust temperature control in real time, but also has powerful fault diagnosis and self-repairing capabilities, greatly improving the reliability and stability of the system. This intelligent feedback and self-repair system design ensures the continuity and stability of the production process, reduces production interruptions and quality problems caused by failures, and further improves production efficiency and product quality.

[0051] The above embodiments can be implemented in whole or in part by software, hardware, firmware and any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions and computer programs. When the computer instructions and computer programs are loaded and executed on a computer, the processes and functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server and data center to another website, computer, server and data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server, data center, etc. that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0052] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0053] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0054] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0055] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0056] If the functions are implemented in the form of software functional units and sold and used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, optical disk, and other media that can store program codes.

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes and substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A temperature control method for a sheet production process, characterized in that: The temperature control of the sheet production process comprises the following steps: S1: Deploy temperature sensors on the sheet production line. The sensors discover and connect to other sensor nodes to form a dynamically adjusted and self-healing sensor network to achieve low-latency data transmission. Through dynamic reconfiguration, the integrity of the sensor network and the continuity of data transmission are ensured. S2: Integrate a distributed data processing unit in each temperature sensor node to perform real-time data analysis and preprocessing, and only transmit key data to the central control system; through data filtering, smoothing and anomaly detection preprocessing steps, reduce the load of the central system and improve data processing efficiency and response speed; S3: The central control system combines three algorithms, fuzzy control, PID control and adaptive neural network, to automatically adjust control parameters and optimize temperature regulation strategy according to real-time monitoring data. The fuzzy controller handles temperature deviation, the PID controller adjusts proportional, integral and differential parameters, and the adaptive neural network performs online training and parameter optimization. Through comprehensive control output and dynamic weight adjustment, multi-algorithm collaborative optimization control is achieved; S4: Use LSTM machine learning algorithm to establish a prediction model for temperature changes, predict temperature change trends in advance, generate optimized temperature control strategies, and reduce temperature fluctuations; collect and preprocess historical temperature data, train prediction models, predict future temperature changes in real time, and dynamically adjust control parameters based on prediction results to achieve precise temperature control; S5: In the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered simultaneously, global optimal control is achieved through dynamic weight adjustment, a multi-objective optimization function is constructed, the objective function is optimized using genetic algorithms, dynamic optimization control is performed based on real-time data, and comprehensive balance of various optimization objectives is achieved; S6: Integrated real-time feedback control system, rapid response to temperature changes, equipped with fault diagnosis and self-repair modules, real-time detection of system status, automatic repair of faults found, real-time monitoring of sensor data and control instructions, closed-loop feedback control and fault diagnosis, self-repair mechanism activated for fault isolation and network reorganization, to ensure continuous and stable operation of the system.

2. A temperature control method for a sheet material production process according to claim 1, characterized in that: Arrange temperature sensor T on the production line i , where i represents the sensor number, and T1, T2, …, T n , arrange T in the cooling zone n +1,T n+2 ,…,T m ; The sensor nodes use Zigbee wireless communication protocol; Each sensor node T i Equipped with wireless communication module, using ad hoc network protocol P mesh Establish a network connection: N(T) = {T i |i∈[1,n]}; where N(T) represents the sensor network, T i Represents a node in the network; when a sensor node T i When a failure occurs, the network N(T) automatically reconfigures the other nodes T j (j≠i) reconnect to ensure the integrity of the network and the continuity of data transmission.

3. The temperature control method for a sheet material production process according to claim 1, characterized in that: The data processing unit is integrated in each temperature sensor node to perform real-time analysis and preliminary processing on the collected temperature data, and only transmit key data to the central control system; data collection is done through each sensor T i Collect temperature data D i (t), where t represents time: D i (t) = {T i (t)}; initial processing by sensor node T i Perform data preprocessing F i , including filter F filter , Smooth F smooth and anomaly detection F detect :D′ i (t) = F i (D i (t)) = F smooth (F filter (D i (t))); key data transmission is transmitted through sensor node T i Only the processed key data D′ is transmitted i (t) to the central control system C:D′ i (t)→C.

4. The temperature control method for a sheet material production process according to claim 1, characterized in that: The central control system adopts a combination of fuzzy control, PID control and adaptive neural network control. It automatically adjusts the control parameters according to real-time monitoring data and optimizes the temperature adjustment strategy to adapt to the changing environment and needs in the production process. First, a fuzzy rule base is established to define the fuzzy rule base for temperature control: if e(t) = A and Δe(t) = B, then Δu(t) = C, where e(t) = T set -T i (t) is the temperature deviation, Δe(t) = e(t) - e(t-1) is the deviation change rate, and Δu(t) is the control output change; then fuzzy reasoning is performed based on the fuzzy rule base and the current temperature deviation and deviation change rate to calculate the control output change: Δu fuzzy (t)=∑ i w i ·C i , where w i is the weight of the fuzzy rule, C i is the output corresponding to the fuzzy rule; first define the output of the PID controller: Among them, K p ,K i ,K d They are proportional, integral and differential gains respectively; Parameter adjustment: adjust the parameters of the PID controller according to the output changes of the fuzzy controller: Establish a neural network model NN, the input is the current temperature data and historical data, and the output is the adjustment value of the control parameter: Δθ(t)=NN(D total (t),H(t)), where Δθ(t) is the adjustment value of the control parameter. Online training uses real-time monitoring data and control output for online training to update the weights of the neural network model: Update weights Among them, W is the weight of the neural network, η is the learning rate, and E is the error function; finally, according to the output of each algorithm, the comprehensive control output is calculated: u total (t) = w1u fuzzy (t)+w2u PID (t)+w3u NN (t), where w1, w2, and w3 are the weights of each algorithm; Weight adjustment: Dynamically adjust the weights of each algorithm based on the control effect and real-time feedback: Among them, w1(t+1)=w1(t)+Δw1(t): at time t+1, the weight w1 of fuzzy control is its weight w1(t) at time t plus the weight adjustment Δw1(t), w2(t+1)=w2(t)+Δw2(t): at time t+1, the weight w2 of PID control is its weight w2(t) at time t plus the weight adjustment Δw2(t), w3(t+1)=w3(t)+Δw3(t): at time t+1, the weight w3 of adaptive neural network control is its weight w3(t) at time t plus the weight adjustment Δw3(t).

5. The temperature control method for a sheet material production process according to claim 1, characterized in that: Use machine learning algorithms to establish a prediction model for temperature changes, predict temperature change trends in advance, generate optimized temperature control strategies, and reduce temperature fluctuations. Historical data collection: Collect historical temperature data H(t) from the sensor network of the production line, including temperature measurement values ​​T i (t), control parameters θ(t), and production environment variables E(t): Where H(t) is the historical temperature data, T i (t) is the temperature measurement value of sensor i at time t, θ(t) is the control parameter at time t, and E(t) is the production environment variable at time t; then the historical data is preprocessed, including missing value filling, data normalization and noise filtering; missing values ​​are filled by interpolation, and data normalization is achieved by the following formula: Among them, T i ′(t) is the temperature measurement value after preprocessing, T min and T max Select models for the minimum and maximum values ​​of temperature data respectively: Predict temperature change trend through machine learning model LSTM: M = LSTM (H (t)), where M is the temperature prediction model trained by LSTM, H (t) is the historical temperature data, use the preprocessed historical data to train the model, and optimize the model parameter θ M : Among them, θ M is the optimized model parameter, T pred (t) is the predicted temperature value, T actual (t) is the actual temperature value; Real-time data input: input the real-time data into the trained model for prediction: T pred (t+Δt)=M(D total (t)) where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; predict the temperature trend of the future time period t+Δt and generate the temperature prediction value T pred (t+Δt):T pred (t+Δt)=M(D total (t)), where T pred (t+Δt) is the predicted temperature value at time t+Δt, M is the trained temperature prediction model, and D total (t) is the real-time data at time t; according to the prediction result T pred (t+Δt), the central control system C adjusts the control parameter θ(t) and optimizes the temperature control strategy: θ(t+Δt)=optimize(T pred (t+Δt)), where θ(t+Δt) is the control parameter at time t+Δt, optimize is the optimization function, T pred (t+Δt) is the predicted temperature value at time t+Δt; a new control instruction U(t) is generated to reduce temperature fluctuations and maintain temperature stability: U(t)=f(θ(t+Δt)), where U(t) is the control instruction at time t, f is the control function, and θ(t+Δt) is the control parameter at time t+Δt.

6. The temperature control method for a sheet material production process according to claim 1, characterized in that: In the temperature control process, temperature uniformity, energy consumption minimization and production efficiency maximization are considered at the same time, and global optimal control is achieved through dynamic weight adjustment; Temperature uniformity goal G1: Ensure uniform temperature on the entire production line to avoid local overheating and overcooling: Where G1 is the temperature uniformity target, n is the number of sensors, T i (t) is the temperature measurement value T of sensor i at time t set is the set temperature; energy consumption minimization goal G2: reduce energy consumption while meeting the temperature control requirements: G2 = E(t), where G2 is the energy consumption minimization goal, and E(t) is the energy consumption at time t; production efficiency maximization goal G3: improve production speed and efficiency while ensuring product quality: G3 = η(t), where G3 is the production efficiency maximization goal, and η(t) is the production efficiency at time t; comprehensive optimization objective function G: G = α1G1+α2G2+α3G3, where G is the comprehensive optimization objective function, α1, α2, α3 are the weight coefficients of each optimization objective, corresponding to the temperature uniformity objective G1, energy consumption minimization objective G2 and production efficiency maximization objective G3 respectively; then use the multi-objective optimization algorithm to optimize the objective function: Among them, θ opt is the optimized control parameter, G(θ) is the optimization objective function; dynamic optimization is performed based on real-time data: during the production process, temperature data and energy consumption data are monitored in real time, and the weight coefficient α of the optimization objective function is dynamically adjusted i , to achieve global optimal control: α i (t) = adjust(α i ,D total (t)), where α i (t) is the weight coefficient at time t, adjust is the weight adjustment function, D total (t) is the real-time data at time t; finally, the decision rule is established: If the temperature deviation |T i (t)-T set |>∈1, then adjust the heating power and cooling intensity P c (t): Among them, U(t) is the control instruction at time t, P y (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP ∈ is the adjustment amount, T i (t) is the temperature measurement value of sensor i at time t, T set is the set temperature, ∈1 is the temperature deviation threshold; If energy consumption E(t)>E max , then optimize energy consumption regulation and reduce heating and cooling frequency: Among them, U(t) is the control instruction at time t, P y (t) and P c (t) are heating power and cooling intensity, ΔP y and ΔP c is the adjustment amount, and is the threshold of heating power and cooling intensity, E(t) is the energy consumption at time t, E max is the maximum energy consumption; If production efficiency η(t)<η min , then adjust the temperature control strategy to increase the production line speed: U(t)=optimize(T i (t),η(t)) Among them, U(t) is the control instruction at time t, optimize is the optimization function, T i (t) is the temperature measurement value of sensor i at time t, η(t) is the production efficiency at time t, η min The minimum production efficiency.

7. The temperature control method for a sheet material production process according to claim 1, characterized in that: Integrated real-time feedback control system, rapid response to temperature changes, equipped with fault diagnosis and self-repair modules, real-time detection of system status, automatic repair of faults found; real-time monitoring of sensor data D′ i (t) and control command U(t), perform closed-loop feedback control F, and adjust the control parameter θ(t) in time: F={D i ′(t),U(t),θ(t)}, where D′ i (t) is the processed data of sensor i at time t, U(t) is the control instruction at time t, θ(t) is the control parameter at time t, and F is the feedback control signal; Fault diagnosis algorithm D(F): Real-time detection of sensor T i and control system C, and find abnormal situation E i : E i =D(F), where D(F) is the fault diagnosis algorithm, E i is the abnormal situation detected at time t, T i is the sensor, C is the control system; Automatically start the self-repair mechanism R(E i ): When fault E is detected i After that, perform fault isolation and system reorganization: Among them, R(E i ) is the self-repair mechanism, T i is the faulty sensor, and N(T) is the sensor network.

Citation Information

Cited By

  • Insulator lead welding process for tantalum capacitor

    CN119635057A

  • Emulsion paint production temperature control management system and method

    CN119645154A

  • Energy-saving thermal management method and system for energy storage cabinet of phase change material

    CN119815811A

  • Intelligent temperature control system for whole cable production process

    CN119937688A

  • Temperature controller nonlinear compensation control method and system based on fuzzy logic

    CN120371044A