Intelligent temperature control system for whole cable production process

Abstract

The invention relates to the technical field of temperature control, in particular to an intelligent temperature control system for the whole cable production process. Comprising a cable parameter acquisition module, a production process modeling module, a temperature control decision module, an execution control module and a monitoring early warning module. According to the system, cable production parameters are collected, and a graph neural network and a symbolic regression algorithm are used for modeling production temperature distribution and a temperature-quality relation. And based on the model, an optimal temperature control strategy is generated by adopting reinforcement learning, and precise temperature control is realized through adaptive fuzzy control. Meanwhile, the system monitors temperature parameters in real time, early warning signals are sent out when abnormal detection, over-limit detection or equipment failure are detected in combination with sparse coding and variation inference, and the production stability and the product quality are ensured. According to the invention, through intelligent modeling, decision making, control and monitoring means, the temperature control precision and efficiency of the whole cable production process are comprehensively improved.

Description

Technical Field

[0001] The invention relates to the technical field of temperature control, and in particular to an intelligent temperature control system for the entire cable production process. Background Art

[0002] With the continuous development of power systems and the widespread application of cable transmission technology, cables play an increasingly important role in modern power transmission. The long-term stable operation of cables is directly related to the safety and reliability of power systems. However, in actual operation, the temperature of the cable may change significantly due to changes in the load carried by the cable, fluctuations in ambient temperature, and differences in heat dissipation conditions. When the cable temperature is too high, it will accelerate the aging of the insulation material, shorten the life of the cable, and may even cause cable failures, seriously threatening the stable operation of the power system. At present, there are still the following problems: it is difficult for existing technologies to accurately model the temperature transfer path and dynamic changes in the entire cable production process, and it is impossible to achieve accurate prediction and control; it is difficult for existing methods to deeply explore the implicit physical laws between temperature and product quality, resulting in insufficient optimization of temperature control strategies; the existing technology is not accurate enough in temperature control execution and cannot meet the high quality requirements of cable production. Summary of the invention

[0003] To solve the above problems, the present invention provides an intelligent temperature control system for the entire cable production process, which solves the problem of how to accurately model the temperature transfer path and dynamic changes in the entire cable production process, deeply explore the implicit laws between temperature and quality, and realize high-precision temperature control execution to ensure cable production quality and operational reliability, thereby improving the temperature control accuracy and efficiency of the entire cable production process.

[0004] To achieve the above object, the technical solution adopted by the present invention is: An intelligent temperature control system for the entire cable production process, comprising a cable parameter acquisition module, a production process modeling module, a temperature control decision module, an execution control module and a monitoring and early warning module which are sequentially connected in communication; The cable parameter acquisition module is used to collect parameter information during the cable production process and build a parameter database; The production process modeling module is used to model the temperature transfer path and spatial distribution in the production process based on the parameter information using a graph neural network, generate a dynamic temperature distribution prediction model for the entire production process, and use a symbolic regression algorithm to extract implicit physical laws in the temperature-quality relationship; The temperature control decision module is used to generate an optimal temperature control strategy using a reinforcement learning algorithm based on the dynamic temperature distribution prediction model and the extracted implicit physical laws; The execution control module is used to receive the temperature control strategy generated by the temperature control decision module, and convert the control strategy into a precise control signal through an adaptive fuzzy control algorithm to drive the production equipment to complete temperature regulation; The monitoring and early warning module is used to monitor various temperature parameters in the production process in real time, use sparse coding and variational inference algorithms to detect potential anomalies, determine whether there are abnormal conditions, and issue an early warning signal when the temperature exceeds the set range or the equipment fails.

[0005] Furthermore, the parameter information includes ambient temperature, heat capacity of raw materials, heat transfer coefficient of cable surface, equipment temperature rise curve and dynamic production parameters.

[0006] Furthermore, the operation process of the production process modeling module includes the following steps: The parameter information is normalized, and outliers are removed through a noise reduction algorithm. A graph neural network is used to construct a temperature transfer topology map of the production equipment and cable production process, capturing the heat transfer paths and their relationships between nodes in the production process; Based on the temperature transfer topology map and combined with dynamic production parameters, the graph neural network model is trained to generate a dynamic temperature distribution prediction model for different production stages, and the temperature changes in the production process are predicted in real time. The symbolic regression algorithm is used to analyze the temperature data in the prediction model, to explore the implicit physical relationship between temperature change and product quality, and to generate a mathematical expression of the temperature-quality relationship; The generated temperature distribution prediction model and the extracted implicit physical laws are verified through historical production data and experimental data, and the model is optimized based on the verification results.

[0007] Furthermore, the formula of the dynamic temperature distribution prediction model is as follows:

[0008] in, represents the instantaneous temperature distribution of the system at time t; represents the amount of heat change; m represents the mass of the cable or related node; Indicates the specific heat capacity of the cable material; , , and They represent heat influence, heat conduction diffusion, external heat source and environmental benchmark influence respectively; Laplace operator representing temperature distribution; Represents the input power of external heat sources, including the dynamic heat input of production equipment.

[0009] Furthermore, the temperature-mass relationship mathematical expression is as follows:

[0010] in, It indicates the product quality index in the cable production process; T indicates the temperature of the production equipment and the cable surface; H Indicates the current heat of the system; It represents the temperature change per unit time; t represents the production time; Indicates the reference temperature; It represents the cable production process efficiency parameter; C represents the heat transfer coefficient of the cable surface; represents the temperature transfer time constant; , , , and represents the constant coefficient extracted by the symbolic regression algorithm; a and b represent the exponential parameters.

[0011] Furthermore, the operation process of the temperature control decision module includes the following steps: The dynamic temperature distribution data collected in real time during the production process and the extracted implicit physical laws are input into the temperature control decision module, and normalized and standardized based on historical data; Based on the dynamic temperature distribution prediction model, the objective function of the production process is defined using a reinforcement learning algorithm, including constraints such as maximizing product quality, minimizing temperature control energy consumption, and equipment operation stability. Generate a preliminary temperature control strategy through state space and action space, and use the policy gradient algorithm to optimize the strategy during training; Perform multi-objective optimization analysis on the generated temperature control strategy and output the optimal temperature control strategy.

[0012] Furthermore, the formula of the optimal temperature control strategy is as follows:

[0013] in, represents the optimal temperature control strategy; Indicates the energy consumption of temperature control; Represents the equipment operation stability function; Indicates the production equipment temperature T and the target temperature Deviation; , and represents the weight coefficient; Indicates the target temperature; T indicates the temperature of the production equipment and cable surface.

[0014] Furthermore, the execution control module adjusts the control rules and membership functions in real time based on an adaptive fuzzy control algorithm, and continuously optimizes the control parameters using production feedback data.

[0015] Furthermore, the monitoring and early warning module performs real-time analysis of production data based on a distributed computing architecture, and implements hierarchical push of remote early warning information through the industrial Internet of Things platform.

[0016] The beneficial effects of the present invention are: The present invention introduces a graph neural network to model the temperature transfer path and spatial distribution in the entire cable production process, generates a dynamic temperature distribution prediction model, realizes accurate prediction of temperature changes and optimizes the whole process, and improves production efficiency and product quality. The symbolic regression algorithm is used to extract the implicit physical laws in the relationship between temperature and quality, and provides deep physical mechanism support for the optimization of the temperature control strategy, ensuring that the temperature control adjustment is more scientific and accurate. The optimal temperature control strategy is generated based on the reinforcement learning algorithm, so that the system can adaptively adjust according to the dynamic prediction model and the extracted laws, avoid errors caused by human experience, and improve the scientificity and intelligence of decision-making. The temperature control strategy is converted into an accurate control signal through an adaptive fuzzy control algorithm to ensure that the production equipment can accurately execute the control instructions, maintain the temperature stability during the cable production process, and improve product consistency. The monitoring and early warning module realizes real-time monitoring and abnormal detection of the production process through sparse coding and variational inference algorithms, and can timely warn when the temperature exceeds the limit or the equipment fails, prevent the further expansion of potential problems, and ensure production safety and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a module schematic diagram of an intelligent temperature control system for the entire cable production process of the present invention.

[0018] Figure 2 It is a flowchart of the operation process of the production process modeling module provided by an embodiment of the present invention.

[0019] Figure 3 It is a flowchart of the operation process of the temperature control decision module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] See also Figure 1-3 As shown, the present invention relates to an intelligent temperature control system for the entire cable production process.

[0021] Example An intelligent temperature control system for the entire cable production process, comprising a cable parameter acquisition module, a production process modeling module, a temperature control decision module, an execution control module and a monitoring and early warning module which are sequentially connected in communication; The cable parameter acquisition module is used to collect parameter information during the cable production process and build a parameter database; the parameter information includes ambient temperature, raw material heat capacity, cable surface heat transfer coefficient, equipment temperature rise curve and dynamic production parameters.

[0022] It should be noted that high-precision temperature sensors and thermocouples are arranged at key positions of cable production equipment (such as extruders, cooling water tanks, wire drawing equipment, etc.) to collect dynamic production parameters such as ambient temperature, equipment temperature rise data, cable surface temperature, and cable internal temperature.

[0023] Equipped with high-precision temperature sensors, humidity sensors, heat flow sensors and photoelectric sensors to collect real-time information such as ambient temperature, heat capacity of raw materials and heat transfer coefficient of cable surface during the production process.

[0024] Temperature sensors: distributed at key nodes of the production line (such as extruder outlet, cooling tank inlet and cabling process) to achieve multi-point real-time monitoring.

[0025] Heat flow sensor: monitors the dynamic characteristics of heat exchange between the cable surface and the environment.

[0026] Dynamic parameter recording: collect the temperature rise curve of the equipment (such as extruder barrel, heater) and production line speed and tension.

[0027] The collected parameters are initially fused and processed through edge computing devices to achieve time synchronization and spatial alignment of multiple data sources, ensuring the consistency and accuracy of parameter data.

[0028] The construction of the parameter database is as follows: Static parameters: including physical properties such as heat capacity of raw materials and heat transfer coefficient of cable surface, obtained through laboratory measurement and literature data correction.

[0029] Dynamic parameters: including production line speed, raw material input, production environment temperature fluctuations, etc., obtained through real-time data acquisition systems (such as PLC or SCADA).

[0030] Data synchronization and storage: Use edge computing devices to synchronously process multi-sensor data, store the collected data in the parameter database through the Industrial Internet of Things (IIoT) platform, and support high-frequency (such as 100 Hz) data updates.

[0031] The production process modeling module is used to model the temperature transfer path and spatial distribution in the production process based on the parameter information using a graph neural network, generate a dynamic temperature distribution prediction model for the entire production process, and use a symbolic regression algorithm to extract implicit physical laws in the temperature-quality relationship; The operation process of the production process modeling module includes the following steps: The parameter information is normalized, and outliers are removed through a noise reduction algorithm. A graph neural network is used to construct a temperature transfer topology map of the production equipment and cable production process, capturing the heat transfer paths and their relationships between nodes in the production process; Specifically, a structured topology diagram of production equipment and environment is defined, including various production nodes (such as heat source, cooling equipment, transmission device) and their connection relationships. Each node represents a key position in the production process, such as cable preheating area, molding area, cooling area, etc.; the edge represents the temperature transfer path.

[0032] Node characteristics: Collect the temperature, heat flux density, material thermal conductivity and other characteristics of each node to construct a multi-dimensional feature vector.

[0033] Edge features: Calculate the thermal resistance, heat flow direction and time delay characteristics between nodes based on the laws of heat conduction.

[0034] The temperature transfer topology map is input into the network model using a graph convolutional network (GCN) or a graph attention network (GAT). The network captures the local and global temperature transfer relationships in the production process through layer-by-layer transfer and aggregation operations, generating a high-dimensional embedded representation.

[0035] Based on the temperature transfer topology map and combined with dynamic production parameters, the graph neural network model is trained to generate a dynamic temperature distribution prediction model for different production stages, and the temperature changes in the production process are predicted in real time. Specifically, real-time production parameters (such as feed rate, coolant flow rate, production time, etc.) are combined as dynamic inputs, and time series encoding methods (such as LSTM or time convolution network TCN) are used to process dynamic input information.

[0036] Define loss functions, such as temperature prediction error based on mean square error (MSE). Use self-supervised learning strategies to automatically label data during model training to improve training efficiency. Iterate through gradient descent algorithms (such as Adam optimizer) to adjust model weights to ensure efficient prediction performance of the model at each production stage.

[0037] The trained model is deployed to the production system, receiving real-time data input and generating temperature distribution prediction results for each production stage. The output includes node temperature distribution heat map and key node temperature change trend.

[0038] The symbolic regression algorithm is used to analyze the temperature data in the prediction model, explore the implicit physical relationship between temperature change and product quality, and generate a mathematical expression of the temperature-quality relationship; The generated temperature distribution prediction model and the extracted implicit physical laws are verified through historical production data and experimental data, and the model is optimized based on the verification results.

[0039] Specifically, the generated mathematical expressions are verified using experimental data and production history data to evaluate their accuracy and universality. The expression results are fed back to the production system for quality prediction and process optimization. The temperature distribution predicted by the model is compared with the temperature data actually collected in production to calculate the prediction error. The model performance is evaluated using indicators such as mean square error (MSE) and mean absolute error (MAE). Through simulation experiments or trial production, the temperature and quality data of key nodes are collected and compared with the prediction results. According to the verification results, the hyperparameters of the graph neural network (such as the number of layers, learning rate, and activation function) are adjusted. More constraints or features are introduced in the symbolic regression algorithm to improve the practical application effect of the expression.

[0040] Furthermore, the formula of the dynamic temperature distribution prediction model is as follows:

[0041] in, represents the instantaneous temperature distribution of the system at time t; represents the amount of heat change; m represents the mass of the cable or related node; Indicates the specific heat capacity of the cable material; , , and They represent heat influence, heat conduction diffusion, external heat source and environmental benchmark influence respectively; Laplace operator representing temperature distribution; Represents the input power of external heat sources, including the dynamic heat input of production equipment.

[0042] The temperature-mass relationship mathematical expression is as follows:

[0043] in, It indicates the product quality index in the cable production process; T indicates the temperature of the production equipment and the cable surface; H Indicates the current heat of the system; It represents the temperature change per unit time; t represents the production time; Indicates the reference temperature; It represents the cable production process efficiency parameter; C represents the heat transfer coefficient of the cable surface; represents the temperature transfer time constant; , , , and represents the constant coefficient extracted by the symbolic regression algorithm; a and b represent the exponential parameters.

[0044] The temperature control decision module is used to generate an optimal temperature control strategy using a reinforcement learning algorithm based on the dynamic temperature distribution prediction model and the extracted implicit physical laws; The operation process of the temperature control decision module includes the following steps: The dynamic temperature distribution data collected in real time during the production process and the extracted implicit physical laws are input into the temperature control decision module, and normalized and standardized based on historical data; Based on the dynamic temperature distribution prediction model, the objective function of the production process is defined using a reinforcement learning algorithm, including constraints such as maximizing product quality, minimizing temperature control energy consumption, and equipment operation stability. Specifically, based on the dynamic temperature distribution prediction model, the optimization objectives of the production process are clarified: Maximize product quality: Use predictive models and implicit physical laws to ensure that the production process achieves the optimal quality state, such as conductivity and insulation performance.

[0045] Minimize energy consumption for temperature control: Reduce energy consumption for heating, cooling and other temperature control measures, and improve energy efficiency in the production process.

[0046] Equipment operation stability: reduce temperature fluctuations during equipment operation, extend equipment life, and reduce failure rates.

[0047] According to the specific production needs, the weight of each optimization goal is assigned. For example, the high-quality production stage focuses on product quality; the energy-saving stage focuses more on minimizing energy consumption. Through the multi-objective optimization method, these goals are combined into a comprehensive decision-making criterion.

[0048] Generate a preliminary temperature control strategy through state space and action space, and use the policy gradient algorithm to optimize the strategy during training; Specifically, the state space is constructed by defining the state space of the production process, including: current dynamic temperature distribution data (such as the temperature of different nodes); current production parameters (such as production speed, coolant flow); production equipment status (such as the power level of the heating equipment).

[0049] Action space design defines the actions that the temperature control module can perform, such as: adjusting the power of the heating device (increasing or decreasing); changing the coolant flow rate or cooling time of the cooling device; changing the production line speed to adapt to the temperature control requirements.

[0050] Initialize the reinforcement learning model (such as a deep Q network or a policy gradient-based algorithm) and randomly generate a preliminary temperature control strategy based on the current state.

[0051] Using the dynamic temperature data and state space in the production process, we train the reinforcement learning algorithm and gradually optimize the temperature control strategy: Based on the results of the objective function, such as improved product quality, reduced energy consumption, and improved equipment stability, corresponding rewards or penalties are given. Use policy gradient algorithms (such as PPO or REINFORCE) to optimize the parameters of the policy network. Use ε-greedy strategies or random perturbations to achieve a dynamic balance between exploring new temperature control strategies and using existing strategies. Continuously iterate training and continuously optimize the execution effect of the temperature control strategy through a large amount of simulation and actual production process data. Dynamically adjust the learning rate and training parameters to avoid overfitting or slow policy updates.

[0052] Perform multi-objective optimization analysis on the generated temperature control strategy and output the optimal temperature control strategy.

[0053] Furthermore, the formula of the optimal temperature control strategy is as follows:

[0054] in, represents the optimal temperature control strategy; Indicates the energy consumption of temperature control; Represents the equipment operation stability function; Indicates the production equipment temperature T and the target temperature Deviation; , and represents the weight coefficient; Indicates the target temperature; T indicates the temperature of the production equipment and cable surface.

[0055] The execution control module is used to receive the temperature control strategy generated by the temperature control decision module, and convert the control strategy into a precise control signal through an adaptive fuzzy control algorithm to drive the production equipment to complete temperature regulation; the execution control module is based on the adaptive fuzzy control algorithm to adjust the control rules and membership functions in real time, and use production feedback data to continuously optimize the control parameters.

[0056] It should be noted that the temperature control strategy is converted into an executable command signal by the controller (such as PLC or industrial PC): For heating equipment: convert the temperature control strategy into PID signal output, such as controlling the input current of the heating resistor.

[0057] For the cooling system: adjust the cooling water valve opening, coolant flow or cooling power.

[0058] For traction equipment: Dynamically adjust the line speed to avoid overheating or insufficient cooling.

[0059] Signal interface: Analog signal: Use a DAC module to convert digital signals into analog signals (such as 4-20mA current).

[0060] Digital signals: Use industrial communication protocols such as Modbus or Profinet to send instructions to various devices.

[0061] The design of fuzzy control rules is as follows: Fuzzy control establishes a fuzzy rule base by associating input variables (such as temperature deviation and deviation change rate) with output variables (such as heating power and cooling flow).

[0062] Example rule: Rule 1: If the temperature deviation is large and the rate of change of the deviation is fast, the heating power should be increased quickly.

[0063] Rule 2: If the temperature is close to the target value and the deviation change rate is small, the heating power should be gradually reduced.

[0064] Membership function of input variables: Temperature deviation: divided into "large deviation", "medium deviation", "small deviation". Deviation change rate: divided into "fast change", "medium change", "slow change". Membership function of output variables (control signals): Heating power or cooling power: divided into "large power", "medium power", "small power".

[0065] Adjust the membership function based on real-time feedback data. For example, when the ambient temperature fluctuates drastically, expand the range of the "medium deviation" membership function to enhance the system's responsiveness to medium deviations. Continuously learn the effect of temperature control decisions and dynamically adjust the fuzzy rule base through reinforcement learning algorithms. For example, when the cooling efficiency is lower than expected, increase the priority of the cooling flow response.

[0066] The heating equipment control method achieves precise temperature control of the extruder barrel and wire drawing equipment by adjusting the heating power (by adjusting the current or voltage). When the temperature deviation is large, the power is increased quickly; when it is close to the target value, the power is gradually reduced to avoid overshoot.

[0067] The cooling system control method is to adjust the cooling water flow, coolant temperature or refrigerator operating power. When the cooling water temperature rises, the coolant flow is automatically increased or the cooling water temperature is reduced. When insufficient cooling causes the cable surface temperature to rise, the operating status of the cooling system is adjusted first.

[0068] The coordinated control of production line speed dynamically adjusts the production line speed (such as the motor speed of the traction equipment) to maintain the temperature stability of the cable at each stage of production. When the temperature at the extruder outlet is too high, the production line speed is temporarily reduced to extend the cooling time. After the temperature returns to normal, the production line speed is gradually increased to ensure production efficiency.

[0069] The monitoring and early warning module is used to monitor various temperature parameters in the production process in real time, use sparse coding and variational inference algorithms to detect potential anomalies, determine whether there are abnormal conditions, and issue an early warning signal when the temperature exceeds the set range or the equipment fails; the monitoring and early warning module performs real-time analysis of production data based on a distributed computing architecture, and realizes hierarchical push of remote early warning information through the industrial Internet of Things platform.

[0070] Specifically, sparse coding is used to construct the feature space of normal temperature data. The specific process is as follows: Using historical temperature data from normal production processes, a sparse coding-based model is trained to extract low-dimensional features of temperature parameters. In real-time monitoring, when the features of temperature data exceed the feature distribution range during training, it is marked as a potential anomaly.

[0071] Example application: If the cable surface temperature suddenly rises and exceeds the sparse characteristic distribution, it may indicate a cooling system failure.

[0072] Use variational inference to estimate the probability distribution of real-time data and identify data that does not conform to normal production status: Model the real-time temperature parameters as probability distribution (such as Gaussian distribution). When the temperature data deviates from the normal distribution (such as outside the mean + 3σ range), anomaly detection is triggered.

[0073] Based on comprehensive analysis of multiple parameters, anomalies are divided into the following categories: Slight abnormality: The temperature deviation is small but exceeds the set range, which may have a slight impact on product quality.

[0074] Major anomalies: Large temperature deviations may cause abnormal equipment operation or product failure.

[0075] Emergency Failure: A device failure (such as a cooling system stopping working or a heater power outage) requires immediate attention.

[0076] Based on the collected real-time data and combined with the anomaly detection results, set multi-level warning rules: Threshold warning: If a temperature parameter exceeds a set threshold (such as target temperature ±5°C), a warning is triggered.

[0077] Trend warning: If the temperature change rate exceeds the preset value (such as the heating rate exceeds 2°C / s), a trend warning will be issued in advance.

[0078] Composite warning: Combine multiple parameters (such as ambient temperature, equipment temperature rise curve and cable surface temperature) to determine whether there is a comprehensive risk.

[0079] The types of warning signals are as follows: Sound and light alarm: On the production line, the operator's attention is alerted by alarm lights and buzzers.

[0080] Remote notification: Push warning information to the terminal devices (such as mobile phones and tablets) of relevant personnel through the Industrial Internet of Things (IIoT) platform.

[0081] Production line control: In emergency situations, the production line shutdown protection function is automatically triggered, such as stopping heating when the extruder temperature is too high.

[0082] In summary, by integrating high-precision sensors, edge computing, graph neural networks, symbolic regression algorithms and reinforcement learning algorithms, the present invention enables the system to achieve comprehensive data collection, analysis and control from various dimensions from ambient temperature, equipment status to production parameters, builds intelligent temperature control closed-loop management, and improves the automation level of the production process. By introducing graph neural networks to construct a temperature transfer path topology map, and combining dynamic production parameters, the system can generate a dynamic temperature distribution prediction model, which greatly improves the accuracy of temperature prediction and avoids the problem of temperature control instability caused by prediction errors in traditional temperature control methods.

[0083] The present invention uses symbolic regression to extract implicit physical laws in the temperature-quality relationship, and combines it with a reinforcement learning algorithm to generate an optimal temperature control strategy, which can significantly reduce temperature control energy consumption and optimize production energy efficiency while ensuring product quality. Based on sparse coding and variational inference algorithms, it realizes accurate detection of potential anomalies in the production process, and combines the hierarchical early warning mechanism with the remote notification function of the industrial Internet of Things platform, which significantly improves the safety of equipment operation and the timeliness of fault response.

[0084] The present invention uses an adaptive fuzzy control algorithm to convert the temperature control strategy into an accurate equipment control signal. By adjusting the membership function and fuzzy rules in real time, the system can adapt to the complex requirements under different production conditions and ensure the efficiency and accuracy of temperature control execution. Dynamic adjustment of production line speed, heating power and cooling flow can quickly respond to temperature change requirements, reduce downtime and product scrap rate caused by overheating or insufficient cooling, and extend equipment service life and reduce maintenance costs.

[0085] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An intelligent temperature control system for the entire cable production process, characterized in that: It includes a cable parameter acquisition module, a production process modeling module, a temperature control decision module, an execution control module and a monitoring and early warning module which are sequentially connected in communication; The cable parameter acquisition module is used to collect parameter information during the cable production process and build a parameter database; The production process modeling module is used to model the temperature transfer path and spatial distribution in the production process based on the parameter information using a graph neural network, generate a dynamic temperature distribution prediction model for the entire production process, and use a symbolic regression algorithm to extract implicit physical laws in the temperature-quality relationship; The temperature control decision module is used to generate an optimal temperature control strategy using a reinforcement learning algorithm based on the dynamic temperature distribution prediction model and the extracted implicit physical laws; The execution control module is used to receive the temperature control strategy generated by the temperature control decision module, and convert the control strategy into a precise control signal through an adaptive fuzzy control algorithm to drive the production equipment to complete temperature regulation; The monitoring and early warning module is used to monitor various temperature parameters in the production process in real time, use sparse coding and variational inference algorithms to detect potential anomalies, determine whether there are abnormal conditions, and issue an early warning signal when the temperature exceeds the set range or the equipment fails.

2. According to claim 1, an intelligent temperature control system for the entire cable production process is characterized in that: The parameter information includes ambient temperature, raw material heat capacity, cable surface heat transfer coefficient, equipment temperature rise curve and dynamic production parameters.

3. The intelligent temperature control system for the entire cable production process according to claim 1 is characterized in that: The operation process of the production process modeling module includes the following steps: The parameter information is normalized, and outliers are removed through a noise reduction algorithm. A graph neural network is used to construct a temperature transfer topology map of the production equipment and cable production process, capturing the heat transfer paths and their relationships between nodes in the production process; Based on the temperature transfer topology map and combined with dynamic production parameters, the graph neural network model is trained to generate a dynamic temperature distribution prediction model for different production stages, and the temperature changes in the production process are predicted in real time. The symbolic regression algorithm is used to analyze the temperature data in the prediction model, to explore the implicit physical relationship between temperature change and product quality, and to generate a mathematical expression of the temperature-quality relationship; The generated temperature distribution prediction model and the extracted implicit physical laws are verified through historical production data and experimental data, and the model is optimized based on the verification results.

4. The intelligent temperature control system for the entire cable production process according to claim 3 is characterized in that: The formula of the dynamic temperature distribution prediction model is as follows: ； in, represents the instantaneous temperature distribution of the system at time t; represents the amount of heat change; m represents the mass of the cable or related node; Indicates the specific heat capacity of the cable material; , , and They represent heat influence, heat conduction diffusion, external heat source and environmental benchmark influence respectively; Laplace operator representing temperature distribution; Represents the input power of external heat sources, including the dynamic heat input of production equipment.

5. The intelligent temperature control system for the entire cable production process according to claim 3 is characterized in that: The temperature-mass relationship mathematical expression is as follows: ； in, It indicates the product quality index in the cable production process; T indicates the temperature of the production equipment and the cable surface; H Indicates the current heat of the system; It represents the temperature change per unit time; t represents the production time; Indicates the reference temperature; It represents the cable production process efficiency parameter; C represents the heat transfer coefficient of the cable surface; represents the temperature transfer time constant; , , , and represents the constant coefficient extracted by the symbolic regression algorithm; a and b represent the exponential parameters.

6. The intelligent temperature control system for the entire cable production process according to claim 1 is characterized in that: The operation process of the temperature control decision module includes the following steps: The dynamic temperature distribution data collected in real time during the production process and the extracted implicit physical laws are input into the temperature control decision module, and normalized and standardized based on historical data; Based on the dynamic temperature distribution prediction model, the objective function of the production process is defined using a reinforcement learning algorithm, including constraints such as maximizing product quality, minimizing temperature control energy consumption, and equipment operation stability. Generate a preliminary temperature control strategy through state space and action space, and use the policy gradient algorithm to optimize the strategy during training; Perform multi-objective optimization analysis on the generated temperature control strategy and output the optimal temperature control strategy.

7. The intelligent temperature control system for the entire cable production process according to claim 1 is characterized in that: The formula of the optimal temperature control strategy is as follows: ； in, represents the optimal temperature control strategy; Indicates the energy consumption of temperature control; Represents the equipment operation stability function; Indicates the production equipment temperature T and the target temperature Deviation; , and represents the weight coefficient; Indicates the target temperature; T indicates the temperature of the production equipment and cable surface.

8. The intelligent temperature control system for the entire cable production process according to claim 1 is characterized in that: The execution control module adjusts the control rules and membership functions in real time based on an adaptive fuzzy control algorithm, and continuously optimizes control parameters using production feedback data.

9. The intelligent temperature control system for the entire cable production process according to claim 1 is characterized in that: The monitoring and early warning module performs real-time analysis of production data based on a distributed computing architecture, and implements hierarchical push of remote early warning information through the industrial Internet of Things platform.

Images