Intelligent optimization control method and device for mold cooling system

Abstract

The invention provides an intelligent optimization control method and device for a mold cooling system, and relates to the field of intelligent optimization control devices. The intelligent optimization control device based on the mold cooling system comprises a hardware part, a software control system, a model calculation module and an optimization algorithm, the hardware part comprises a temperature sensor, a flow sensor, a controller, a cooling liquid pump, a cooling loop and an actuator, the software control system is used for receiving and processing real-time data from the sensors, and the model calculation module is used for calculating the model calculation module according to the real-time data. The model calculation module is used for analyzing temperature and flow changes in the cooling process. High-precision and low-delay temperature and flow sensors are utilized, and sensor data are corrected in real time through an error correction module, so that the measurement precision and the response speed are greatly improved, and the problem that the precision and the response speed of the sensors are limited is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent optimization control devices, and in particular to an intelligent optimization control method and device for a mold cooling system. Background Art

[0002] The intelligent optimization control device of the mold cooling system is mainly composed of the following parts: temperature sensor, flow sensor, controller, coolant pump, cooling circuit, actuator and related communication modules. The temperature sensor and flow sensor are responsible for real-time monitoring of the temperature of the mold and the flow of the coolant, and transmit the data to the controller. According to the set optimization algorithm, the controller dynamically adjusts the flow rate and temperature of the coolant by analyzing the data sent back by the sensor. The coolant pump and actuator perform corresponding operations according to the control signal to ensure maximum cooling efficiency while avoiding overheating or insufficient cooling of the mold. The system also has a feedback mechanism that can adjust the cooling strategy according to the actual temperature changes to achieve intelligent optimization control.

[0003] Although the intelligent optimization control device of the mold cooling system can effectively improve the cooling efficiency, it also has some shortcomings. The limited sensor accuracy and response speed may lead to inaccurate temperature control, especially when the ambient temperature changes greatly, the system response lags. The control algorithm is more complex, and the setting of the optimization strategy requires professional debugging, which increases the maintenance cost and operation difficulty of the system. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent optimization control method and device for a mold cooling system, which solves the problem that the temperature control is not precise enough due to the limited accuracy and response speed of the sensor; the control algorithm is highly complex, which increases the maintenance cost and operation difficulty of the system.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent optimization control device for a mold cooling system, comprising a hardware part, a software control system, a model calculation module and an optimization algorithm, wherein the hardware part comprises a temperature sensor, a flow sensor, a controller, a coolant pump, a cooling circuit and an actuator, the software control system is used to receive and process real-time data from the sensor, the model calculation module is used to analyze the temperature and flow changes during the cooling process, the optimization algorithm dynamically adjusts the flow and temperature of the coolant based on the prediction results of the model, the temperature sensor and the flow sensor adopt high-precision, low-latency composite sensors, and are corrected in real time through an integrated error correction module to eliminate environmental interference and improve measurement accuracy and response speed;

[0008] The control algorithm adopts an intelligent adaptive algorithm based on the combination of fuzzy control and neural network, which can automatically learn and adjust control parameters without manual intervention, simplifying the system debugging process and reducing maintenance costs.

[0009] Preferably, the neural network model in the optimization algorithm is trained with a large amount of cooling data, and can accurately predict the temperature change of the mold under different cooling conditions, and adjust the flow of the coolant in advance according to the prediction results to avoid overcooling or overheating of the mold. The device includes an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to different production stages of the mold, thereby improving the cooling efficiency and avoiding the problem of inaccurate temperature control caused by fixed thresholds in traditional systems.

[0010] Preferably, the correction module of the composite sensor adopts a multi-channel data fusion algorithm to perform weighted averaging processing on the output data of multiple sensors, thereby reducing the measurement error caused by a single sensor and further improving the control accuracy of the cooling temperature. A real-time communication protocol is adopted between the controller and the actuator, which can dynamically adjust the power output of the cooling pump according to the actual flow and temperature changes of the coolant, and combine PID control with adaptive fuzzy control to ensure control accuracy and response speed and improve system stability.

[0011] The intelligent optimization control method of the mold cooling system includes the following steps:

[0012] a. Install temperature sensors, flow sensors, coolant pumps, cooling circuits and actuators in the mold cooling system to form a complete hardware system;

[0013] b. Use temperature sensors and flow sensors to monitor the temperature and flow data in the mold cooling system in real time;

[0014] c. Transmit the data collected by the sensor to the controller through the software control system;

[0015] d. In the controller, the temperature and flow changes during the cooling process are analyzed through the model calculation module, and the following temperature prediction model is established:

[0016]

[0017] Where T(t) represents the mold temperature at time t, T0 is the initial temperature, Q in is the input heat, Q out is the heat output, C m is the heat capacity of the mold;

[0018] e) Using the prediction results of the model calculation module, dynamically adjust the flow and temperature of the coolant. The cooling flow control model is:

[0019] F(t)=F0+k·(T set -T(t)

[0020] Where F(t) is the coolant flow rate at time t, F0 is the initial flow rate, T set is the set temperature, k is the adjustment coefficient; f. Through the intelligent adaptive algorithm combined with fuzzy control and neural network, the control parameters of the coolant are optimized to improve the cooling efficiency;

[0021] g. Use the error correction module to correct the sensor data in real time, reduce the impact of environmental factors on sensor data, and improve measurement accuracy and response speed;

[0022] h. The neural network is trained through historical data of the cooling process to predict temperature changes under different cooling conditions and optimize the control strategy;

[0023] I. The system has an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to the different production stages of the mold;

[0024] j. Use multi-channel data fusion algorithm to perform weighted average processing on multiple sensor data to further improve data accuracy;

[0025] k. The controller and actuator transmit data through a real-time communication protocol to ensure real-time adjustment of the power output of the coolant pump and achieve efficient control.

[0026] Preferably, the temperature sensor and flow sensor are high-precision, low-latency composite sensors that can accurately monitor the mold temperature and coolant flow in real time, and use the error correction module to perform error compensation using the following formula:

[0027] E(t)=E0+α·ΔT+β·ΔF

[0028] Among them, E(t) is the correction error at time t, E0 is the initial error, ΔT is the temperature deviation, ΔF is the flow deviation, α and β are correction coefficients to eliminate the influence of environmental interference on sensor data.

[0029] Preferably, the control algorithm uses a combination of fuzzy control and neural network, and the fuzzy controller is based on the following membership function:

[0030] μ(T,F)=min(μ T (T),μ F (F)

[0031] Among them, μ(T,F) is the output of fuzzy control, μ T (T) and μ F(F) is the fuzzy membership function of temperature and flow.

[0032] Preferably, the neural network can continuously optimize the control strategy according to historical data through an adaptive learning mechanism, reduce manual intervention, and improve the intelligence level of the system.

[0033] Preferably, the control algorithm calculates an advance adjustment value of the coolant flow rate based on historical data to avoid insufficient cooling or overcooling.

[0034] (III) Beneficial effects

[0035] The present invention provides an intelligent optimization control method and device for a mold cooling system, which has the following beneficial effects:

[0036] The use of high-precision, low-latency temperature and flow sensors and real-time correction of sensor data through the error correction module greatly improves measurement accuracy and response speed, solving the problem of limited sensor accuracy and response speed;

[0037] The intelligent adaptive algorithm based on the combination of fuzzy control and neural network can automatically learn and adjust the control parameters, reducing the complexity of the control algorithm, reducing the system maintenance cost and operation difficulty; in addition, the temperature prediction model and flow control model of the cooling system are established through the model calculation module, and the flow and temperature of the coolant can be dynamically adjusted according to the real-time data, thereby effectively avoiding the phenomenon of overcooling or overheating of the mold;

[0038] The present invention also introduces an adaptive threshold adjustment function and a multi-channel data fusion algorithm, which can flexibly adjust the cooling target value in different production stages, and perform weighted average processing on multiple sensor data to further improve data accuracy and ensure the stability and efficiency of system control; the system dynamically adjusts the power output of the cooling pump by combining PID control with adaptive fuzzy control, ensuring the response speed and precise control of the cooling system under different working conditions, thereby improving the cooling efficiency as a whole and reducing energy consumption in the cooling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the internal structure of the present invention. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present invention are described clearly and completely. 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.

[0041] like Figure 1As shown, an embodiment of the present invention provides an intelligent optimization control device for a mold cooling system, including a hardware part, a software control system, a model calculation module and an optimization algorithm. The hardware part includes a temperature sensor, a flow sensor, a controller, a coolant pump, a cooling circuit and an actuator. The software control system is used to receive and process real-time data from the sensor. The model calculation module is used to analyze the temperature and flow changes in the cooling process. The optimization algorithm dynamically adjusts the flow and temperature of the coolant based on the prediction results of the model. The temperature sensor and the flow sensor use high-precision, low-latency composite sensors, and are corrected in real time through an integrated error correction module to eliminate environmental interference and improve measurement accuracy and response speed. The neural network model in the optimization algorithm is trained through a large amount of cooling data, and can accurately predict the temperature changes of the mold under different cooling conditions, and adjust the flow of the coolant in advance according to the prediction results to avoid overcooling or overheating of the mold. The device includes an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to different production stages of the mold, thereby improving cooling efficiency and avoiding the problem of inaccurate temperature control caused by fixed thresholds in traditional systems.

[0042] The control algorithm adopts an intelligent adaptive algorithm based on the combination of fuzzy control and neural network. It can automatically learn and adjust control parameters without manual intervention, simplify the system debugging process, and reduce maintenance costs. The correction module of the composite sensor adopts a multi-channel data fusion algorithm to perform weighted average processing on the output data of multiple sensors, thereby reducing the measurement error caused by a single sensor and further improving the control accuracy of the cooling temperature. A real-time communication protocol is used between the controller and the actuator, which can dynamically adjust the power output of the cooling pump according to the actual flow and temperature changes of the coolant, and combine PID control with adaptive fuzzy control to ensure control accuracy and response speed and improve system stability.

[0043] The intelligent optimization control method of the mold cooling system includes the following steps:

[0044] a. Install temperature sensors, flow sensors, coolant pumps, cooling circuits and actuators in the mold cooling system to form a complete hardware system.

[0045] b. Use temperature sensors and flow sensors to monitor the temperature and flow data in the mold cooling system in real time. The temperature sensor and flow sensor are high-precision, low-latency composite sensors that can accurately monitor the mold temperature and coolant flow in real time. Use the error correction module to perform error compensation using the following formula:

[0046] E(t)=E0+α·ΔT+β·ΔF

[0047] Among them, E(t) is the correction error at time t, E0 is the initial error, ΔT is the temperature deviation, ΔF is the flow deviation, α and β are correction coefficients to eliminate the influence of environmental interference on sensor data.

[0048] c. The data collected by the sensor is transmitted to the controller through the software control system.

[0049] d. In the controller, the temperature and flow changes during the cooling process are analyzed through the model calculation module, and the following temperature prediction model is established:

[0050]

[0051] Where T(t) represents the mold temperature at time t, T0 is the initial temperature, Q in is the input heat, Q out is the heat output, C m is the heat capacity of the mold.

[0052] e) Using the prediction results of the model calculation module, dynamically adjust the flow and temperature of the coolant. The cooling flow control model is:

[0053] F(t)=F0+k·(T set -T(t)

[0054] Where F(t) is the coolant flow rate at time t, F0 is the initial flow rate, T set is the set temperature, k is the adjustment coefficient. f. Through the intelligent adaptive algorithm combined with fuzzy control and neural network, the control parameters of the coolant are optimized to improve the cooling efficiency. The control algorithm combines fuzzy control with neural network. The fuzzy controller is based on the following membership function:

[0055] μ(T,F)=min(μ T (T),μ F (F)

[0056] Among them, μ(T,F) is the output of fuzzy control, μ T (T) and μ F (F) is the fuzzy membership function of temperature and flow. The control algorithm calculates the advance adjustment value of the coolant flow according to historical data to avoid insufficient cooling or overcooling.

[0057] g. The error correction module is used to perform real-time correction on sensor data, reduce the impact of environmental factors on sensor data, and improve measurement accuracy and response speed.

[0058] h. The neural network is trained through historical data of the cooling process to predict temperature changes under different cooling conditions and optimize the control strategy. Through the adaptive learning mechanism, the neural network can continuously optimize the control strategy based on historical data, reduce manual intervention, and improve the intelligence level of the system.

[0059] I. The system has an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to the different production stages of the mold.

[0060] j. Use multi-channel data fusion algorithm to perform weighted average processing on multiple sensor data to further improve data accuracy.

[0061] k. The controller and actuator transmit data through a real-time communication protocol to ensure real-time adjustment of the power output of the coolant pump and achieve efficient control.

[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent optimization control device for a mold cooling system, comprising a hardware part, a software control system, a model calculation module and an optimization algorithm, wherein the hardware part comprises a temperature sensor, a flow sensor, a controller, a coolant pump, a cooling circuit and an actuator, the software control system is used to receive and process real-time data from the sensor, the model calculation module is used to analyze temperature and flow changes during the cooling process, and the optimization algorithm dynamically adjusts the flow and temperature of the coolant based on the prediction results of the model. Features: The temperature sensor and flow sensor adopt high-precision, low-latency composite sensors, and perform real-time correction through an integrated error correction module to eliminate environmental interference and improve measurement accuracy and response speed; The control algorithm adopts an intelligent adaptive algorithm based on the combination of fuzzy control and neural network, which can automatically learn and adjust control parameters without manual intervention, simplifying the system debugging process and reducing maintenance costs.

2. The intelligent optimization control device for mold cooling system according to claim 1, Features: The neural network model in the optimization algorithm is trained with a large amount of cooling data, and can accurately predict the temperature changes of the mold under different cooling conditions, and adjust the flow of the coolant in advance according to the prediction results. The device includes an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to different production stages of the mold.

3. The intelligent optimization control device for mold cooling system according to claim 1, Features: The correction module of the composite sensor adopts a multi-channel data fusion algorithm to perform weighted average processing on the output data of multiple sensors. A real-time communication protocol is adopted between the controller and the actuator, which can dynamically adjust the power output of the cooling pump according to the actual flow and temperature changes of the coolant, and combine PID control with adaptive fuzzy control.

4. Intelligent optimization control method of mold cooling system, Features: The following steps are involved: a. Install temperature sensors, flow sensors, coolant pumps, cooling circuits and actuators in the mold cooling system to form a complete hardware system; b. Use temperature sensors and flow sensors to monitor the temperature and flow data in the mold cooling system in real time; c. Transmit the data collected by the sensor to the controller through the software control system; d. In the controller, the temperature and flow changes during the cooling process are analyzed through the model calculation module, and the following temperature prediction model is established: Where T(t) represents the mold temperature at time t, T 0 is the initial temperature, Qi n is the input heat, Q out is the heat output, C m is the heat capacity of the mold; e) Using the prediction results of the model calculation module, dynamically adjust the flow and temperature of the coolant. The cooling flow control model is: F(t)=F 0 +k·(T set -T(t)) Where F(t) is the coolant flow rate at time t, F 0 is the initial flow rate, T set is the set temperature, k is the adjustment coefficient; f. Through the intelligent adaptive algorithm combined with fuzzy control and neural network, the control parameters of the coolant are optimized to improve the cooling efficiency; g. Use the error correction module to correct the sensor data in real time, reduce the impact of environmental factors on sensor data, and improve measurement accuracy and response speed; h. The neural network is trained through historical data of the cooling process to predict temperature changes under different cooling conditions and optimize the control strategy; I. The system has an adaptive threshold adjustment function, which can automatically adjust the target values ​​of temperature and flow according to the different production stages of the mold; j. Use multi-channel data fusion algorithm to perform weighted average processing on multiple sensor data to further improve data accuracy; k. The controller and actuator transmit data through a real-time communication protocol to ensure real-time adjustment of the power output of the coolant pump and achieve efficient control.

5. According to claim 4, the intelligent optimization control method of the mold cooling system, Features: The temperature sensor and flow sensor are high-precision, low-latency composite sensors that can accurately monitor the mold temperature and coolant flow in real time. The error correction module is used to perform error compensation using the following formula: E(t)=E 0 +α·ΔT+β·ΔF Where E(t) is the correction error at time t, E 0 is the initial error, ΔT is the temperature deviation, ΔF is the flow deviation, and α and β are correction coefficients to eliminate the influence of environmental interference on sensor data.

6. The intelligent optimization control method for the mold cooling system according to claim 4, Features: The control algorithm uses a combination of fuzzy control and neural network. The fuzzy controller is based on the following membership function: μ(T, F)=min(μ T (T),m F (F)) Among them, μ(T, F) is the output of fuzzy control, μ T (T) and μ F (F) is the fuzzy membership function of temperature and flow.

7. The intelligent optimization control method for the mold cooling system according to claim 4, Features: The neural network can continuously optimize the control strategy according to historical data through an adaptive learning mechanism, reduce manual intervention, and improve the intelligence level of the system.

8. The intelligent optimization control method for the mold cooling system according to claim 4, Features: The control algorithm calculates the advance adjustment value of the coolant flow rate based on historical data to avoid insufficient cooling or overcooling.

Images