Pressure regulating mechanism for plastic mold

Abstract

The application relates to the field of mold pressure regulation, in particular to a pressure regulation mechanism for a plastic mold, which comprises a pressure detection module and a temperature detection module that respectively transmit real-time monitored pressure signals and temperature signals to a data processing module. After receiving the signals from the pressure and temperature detection modules, the data processing module processes the signals through a pressure data analysis algorithm and a temperature trend prediction algorithm respectively to generate processed pressure signals and temperature signals. The processed pressure signals and temperature signals are respectively transmitted to a pressure control module and a temperature control module, which generate corresponding control instructions according to the received signals. The control modules send the generated control instructions to an execution mechanism to implement specific pressure and temperature regulation operations. The integrated control module integrates the outputs from the pressure control module and the temperature control module, generates optimized control instructions through a multivariable optimization control algorithm, and feeds back to the data processing module to form a closed-loop feedback.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mold pressure regulation, in particular to a pressure regulation mechanism for plastic mold. BACKGROUND

[0002] Plastic mold is an indispensable key equipment in the production process of plastic products. Its main function is to convert plastic raw materials into products with specific shape and size through processes such as heating, injection, pressure holding, and cooling. The quality of the plastic mold directly affects the appearance, dimensional accuracy, mechanical properties, and production efficiency of the final product. Therefore, the pressure and temperature control inside the mold play a crucial role in the entire production process.

[0003] In the process of plastic injection molding, pressure and temperature are two main parameters that affect product quality and production efficiency. Pressure control not only determines the injection speed and filling degree of plastic melt, but also relates to the holding time and pressure inside the mold, thereby affecting the compactness and dimensional accuracy of the product. Temperature control affects the flowability, cooling speed, and solidification process of the plastic melt, directly determining the surface quality and mechanical properties of the product. Therefore, accurate and stable pressure and temperature regulation is crucial for ensuring the production of high-quality plastic products.

[0004] Although the existing technology has achieved pressure regulation of plastic mold to some extent, there are still the following main defects:

[0005] Mechanical and simple electronic control systems have limitations in high-precision pressure regulation, making it difficult to meet the requirements of modern plastic products for high precision and consistency.

[0006] Traditional systems have slow response speed when dealing with rapidly changing production environments, leading to pressure fluctuations and instability, affecting production efficiency and product quality.

[0007] In a high-noise environment, the pressure sensor signal is easily disturbed, leading to inaccurate pressure estimation, further affecting the stability and precision of the control system.

[0008] Existing systems often only focus on pressure regulation, ignoring the linkage control of other key parameters such as temperature, leading to a lack of coordination between pressure and temperature, affecting the overall working state of the mold and product quality.

[0009] Traditional control systems mainly rely on real-time feedback, lacking the ability to predict and optimize future pressure and temperature changes, making it difficult to achieve proactive adjustment and closed-loop optimization control. SUMMARY

[0010] The purpose of the present application is to provide a pressure regulation mechanism for plastic mold to solve the technical problems raised in the background.

[0011] Based on the above idea, the application provides the following technical solutions:

[0012] A pressure adjusting mechanism for plastic mold, comprising:

[0013] A pressure detection module, a temperature detection module, a data processing module, a pressure control module, a temperature control module, an execution mechanism, a communication interface module and an integrated control module;

[0014] The pressure detection module is used for monitoring the pressure state inside the mold in real time and sending the monitored pressure signal to the data processing module;

[0015] The temperature detection module is used for monitoring the temperature state inside the mold in real time and sending the monitored temperature signal to the data processing module;

[0016] The data processing module is connected to the pressure detection module and the temperature detection module, used for receiving the pressure signal from the pressure detection module and the temperature signal from the temperature detection module, performing data processing, sending the processed pressure signal to the pressure control module and sending the processed temperature signal to the temperature control module;

[0017] The pressure control module is connected to the data processing module, used for receiving the pressure signal from the data processing module and adjusting the pressure inside the mold according to the received pressure signal, and sending the pressure control instruction to the execution mechanism;

[0018] The temperature control module is connected to the data processing module, used for receiving the temperature signal from the data processing module and adjusting the temperature inside the mold according to the received temperature signal, and sending the temperature control instruction to the execution mechanism;

[0019] The execution mechanism is connected to the pressure control module and the temperature control module, used for performing actual pressure and temperature adjusting operations according to the control instructions from the pressure control module and the temperature control module;

[0020] The communication interface module is used for data exchange and instruction transmission with an external control system, and the communication interface module and the data processing module are interconnected to realize bidirectional data communication;

[0021] The integrated control module is connected to the data processing module, the pressure control module and the temperature control module, used for integrating the pressure and temperature adjusting, forming a closed loop control, and feeding back the optimized control instruction to the data processing module to realize self-adaptive adjustment of the system.

[0022] The system monitors the pressure and temperature conditions inside the mold in real-time through the pressure detection module and temperature detection module, transmits the collected data to the data processing module for analysis and processing. The data processing module further transmits the processed pressure and temperature signals to the pressure control module and temperature control module respectively, generating corresponding control instructions. These instructions are implemented through actuators to perform specific pressure and temperature adjustment operations. At the same time, the communication interface module ensures that the system can communicate with external control systems for bidirectional data communication, realizing seamless information transmission. The integrated control module is responsible for integrating the adjustment signals of each module, forming a closed-loop control, and feeding back the optimized control instructions to the data processing module, forming a self-adaptive adjustment mechanism.

[0023] This overall structure design brings many technical advantages. First, the modular design makes the system parts clear in function, easy to maintain and upgrade. Second, the detailed data flow relationship ensures efficient information transmission and processing, improving the system's response speed and adjustment accuracy. In addition, the introduction of the closed-loop feedback mechanism greatly enhances the system's adaptive ability, allowing it to dynamically adjust control strategies based on real-time data, ensuring that the mold maintains the best pressure and temperature state under different working conditions. This design effectively solves the problem of traditional pressure regulation systems in complex production environments, significantly improving the production efficiency and product quality of plastic molds.

[0024] Preferably, the data processing module includes a pressure data analysis algorithm, which includes the following steps:

[0025] A1, receiving real-time pressure signals from the pressure detection module;

[0026] A2, applying Kalman filtering to the received pressure signals to eliminate noise interference and predict future pressure conditions;

[0027] A3, calculating the current pressure estimate based on the filtered pressure signal;

[0028] A4, outputting the calculated pressure estimate to the pressure control module.

[0029] The algorithm processes real-time pressure signals through Kalman Filtering technology. The specific process includes receiving real-time pressure signals transmitted by the pressure detection module, performing Kalman filtering to eliminate noise interference, predicting future pressure states, and finally outputting the current pressure estimate to the pressure control module. As a recursive filtering algorithm, Kalman filtering has the characteristics of strong real-time and high precision, and can effectively extract useful signals and suppress noise in a dynamically changing environment. By applying Kalman filtering, the pressure data analysis algorithm can accurately estimate the actual pressure state inside the mold, even in the case of high noise interference or unstable signals, it can provide reliable pressure estimation. This high-precision pressure estimation is crucial for subsequent pressure control, ensuring that the pressure regulation module can make accurate control decisions based on accurate data. In addition, the introduction of Kalman filtering makes the system have stronger prediction ability, which can predict the trend of pressure change in advance, so as to realize more proactive adjustment strategy. This not only improves the response speed of the system, but also optimizes the stability of pressure regulation, reduces overshoot and oscillation phenomenon, further improves the stability of the mold production process and the consistency of the product.

[0030] Preferably, the specific formula for pressure estimation in the pressure data analysis algorithm is:

[0031] ;

[0032] where P(t) is the pressure estimate at time t, is the predicted value based on the previous state, SP(t) is the actual measurement value of the pressure detection module at time t, K(t) is the Kalman gain, and H is the observation matrix.

[0033] The formula is based on the core principle of Kalman filtering, which dynamically updates the pressure estimate by combining the predicted value and the actual measurement value. The advantage of the formula design is its strong adaptability, which can automatically adjust the weight coefficient according to the real-time data changes, so as to maintain high estimation accuracy under different noise levels and system dynamics. The dynamic adjustment of Kalman gain ensures that the system relies more on the measurement value when the signal quality is good, and relies more on the predicted value when the signal noise is large, balancing the real-time and stability of the signal.

[0034] In addition, the pressure estimation formula can effectively suppress the influence of noise by coupling prediction and measurement, improving the sensitivity and response speed of the system to pressure changes. This high-precision pressure estimation not only improves the regulation accuracy of the pressure control module, but also further optimizes the performance of the entire pressure regulation system, ensuring that the mold maintains a stable pressure environment during the production process, thereby improving product quality and production efficiency.

[0035] Preferably, the data processing module further comprises a temperature trend prediction algorithm, which comprises the following steps:

[0036] B1, receiving historical temperature data from the temperature detection module;

[0037] B2, using a long short-term memory network to perform time series prediction on the temperature data and analyze the temperature change trend;

[0038] B3, predicting the temperature change value in the future period of time;

[0039] B4, outputting the prediction result to the temperature control module to adjust the temperature in advance.

[0040] Using a long short-term memory network (LSTM) to perform time series prediction on historical temperature data, analyze temperature change trend, predict temperature change in the future period of time, and output prediction result to temperature control module to adjust temperature in advance.

[0041] As an advanced recurrent neural network (RNN), LSTM has the ability to process and predict long-term dependent data, and is particularly suitable for complex temperature time series data analysis. By learning and modeling the temperature data at the last nnn time points, LSTM can capture the potential rules and trends of temperature change and provide high-precision future temperature prediction. This prediction capability enables the temperature regulation system to take advance adjustment measures to avoid mold defects or production interruptions caused by rapid temperature changes.

[0042] Firstly, the prediction model based on LSTM has high adaptability and learning ability, which can continuously optimize the prediction accuracy with the change of production environment. Secondly, the advance prediction of temperature change trend enables the temperature control module to realize pre-adjustment, reduces the impact of temperature fluctuations on mold production, and improves the stability of the production process and the consistency of the products. In addition, the LSTM model can handle nonlinear and complex temperature change patterns, adapt to temperature regulation requirements under various working conditions, and further improve the intelligent level and adaptive ability of the system.

[0043] Preferably, the specific formula for temperature prediction in the temperature trend prediction algorithm is:

[0044] ;

[0045] Where T pred (t+Δt) is the predicted temperature value at time t+Δt, T(t) to are the temperature values at the last n time points, and LSTM() represents the long short-term memory network model.

[0046] Predict the temperature value at the future time. The LSTM model, through its unique memory cell structure, can effectively capture the long-term dependencies and complex nonlinear patterns in the temperature data, providing accurate temperature predictions. The design mechanism of this formula lies in fully utilizing the advantages of LSTM model in time series prediction, ensuring that the prediction result not only reflects the current temperature state, but also considers the historical temperature change trend and pattern. By inputting multiple historical temperature data at different times, LSTM can identify and learn the potential rules of temperature change, improving the accuracy and reliability of the prediction.

[0047] First, high-precision temperature prediction enables the temperature control module to adjust in advance, reducing the negative impact of temperature fluctuations on mold production and improving the stability of the production process. Second, the prediction model based on LSTM has high flexibility and adaptability, which can continuously optimize the prediction performance as the production environment changes, ensuring reliable temperature prediction under different working conditions. In addition, the implementation of this formula is simple and clear, making it easy for technicians to understand and apply, reducing the complexity and maintenance cost of the system.

[0048] By introducing the LSTM model for temperature prediction, the temperature trend prediction algorithm significantly improves the intelligence and adaptability of the system, enabling the mold pressure regulation mechanism to maintain efficient and stable temperature control in a dynamically changing production environment, thereby improving overall production efficiency and product quality.

[0049] Preferably, the integrated control module further comprises a multivariate optimization control algorithm, which integrates the output of the pressure data analysis algorithm and the temperature trend prediction algorithm to realize the linkage optimization of the system, specifically including the following steps:

[0050] C1, receiving the output of the pressure data analysis algorithm and the output of the temperature trend prediction algorithm;

[0051] C2, based on the pressure estimate value and the temperature prediction value, establishing a coupling relationship model between pressure and temperature;

[0052] C3, applying genetic algorithm to optimize and solve the coupling model to determine the optimal pressure and temperature regulation strategy;

[0053] C4, outputting the optimized control instructions to the pressure control module and the temperature control module to realize the coordinated regulation of pressure and temperature;

[0054] C5, feeding back the optimized control instructions to the pressure data analysis algorithm and the temperature trend prediction algorithm to form a closed-loop feedback, improving the self-adaptability of the system.

[0055] The algorithm realizes the linkage optimization of the system by integrating the output of the pressure data analysis algorithm and the temperature trend prediction algorithm. The specific process includes receiving the pressure estimation value and the temperature prediction value, establishing a coupling relationship model of pressure and temperature, applying a genetic algorithm (Genetic Algorithm) to optimize and solve the coupling model, determining the optimal pressure and temperature adjustment strategy, outputting the optimized control instructions to the pressure control module and the temperature control module, and feeding back these instructions to the data processing module to form a closed-loop feedback, thereby improving the self-adaptive ability of the system. The core of the multivariable optimization control algorithm lies in its ability to consider the mutual influence between the two key parameters of pressure and temperature, and to find the optimal adjustment strategy through global optimization solving by the genetic algorithm. This optimization method has the characteristics of strong global search ability and high adaptability, and can find an adjustment scheme close to the optimal solution in a complex multivariable environment, avoiding the problem of local optimal solution.

[0056] Firstly, by comprehensively considering the two key parameters of pressure and temperature, the system can realize more coordinated and accurate adjustment, avoiding the discordance and errors that may be caused by single parameter adjustment. Secondly, the application of genetic algorithm makes the optimization process highly flexible and adaptable, which can automatically adjust the adjustment strategy according to different production needs and environmental changes, improving the intelligent level of the system. In addition, the optimized control instructions can be fed back to the data processing module in real time to form a closed-loop control, further improving the response speed and adjustment precision of the system, ensuring that the mold can maintain stable pressure and temperature state under various working conditions.

[0057] By introducing the multivariable optimization control algorithm, the pressure regulation mechanism not only improves the overall adjustment effect and system performance, but also enhances the self-adaptive ability and robustness of the system, effectively solving the problem that the traditional pressure regulation system is difficult to realize efficient and stable regulation in complex production environment, significantly improving the automation level and product quality of the plastic mold production process.

[0058] Preferably, the specific formula for realizing linkage optimization in the multivariable optimization control algorithm includes:

[0059] Coupling relationship model formula:

[0060] ;

[0061] Wherein, F is the coupling relationship function, β1, β2 and β3 are coupling coefficients for balancing the influence of pressure and temperature.

[0062] The formula fuses the pressure estimation value and the temperature prediction value by a combination of linear and nonlinear to form a comprehensive coupling relationship function. Each coupling coefficient respectively measures the weight of each parameter. By introducing the interaction term model, the complex relationship between pressure and temperature can be captured, and a more detailed coupling effect can be provided.

[0063] Optimization objective function formula:

[0064] ;

[0065] Wherein, L is the optimization objective function, ω1, ω2 and ω3 are weight coefficients, P t and T t are the preset pressure target value and temperature target value respectively, R is a regularization term for constraining the complexity of the coupling relationship model;

[0066] The optimization objective function comprehensively considers the deviation of pressure and temperature and the complexity of the coupling relationship model, and weights each error and regularization term by the weight coefficient. The objective function aims to minimize the relative error of pressure and temperature while controlling the complexity of the coupling model to avoid overfitting. By optimizing the objective function through genetic algorithm, the optimal pressure and temperature regulation strategy can be found under the premise of ensuring system performance.

[0067] Control instruction adjustment formula:

[0068] ;

[0069] ;

[0070] Wherein, UP(t) is the pressure control instruction for adjusting the pressure inside the mold;

[0071] UT(t) is the temperature control instruction for adjusting the temperature inside the mold;

[0072] K P is the proportional gain coefficient of pressure control;

[0073] K T is the proportional gain coefficient of temperature control;

[0074] is the optimization adjustment coefficient of pressure control instruction;

[0075] is the optimization adjustment coefficient of temperature control instruction;

[0076] is the partial derivative of the optimization objective function to the pressure estimation value;

[0077] To optimize the target function for the partial derivative of the temperature estimate.

[0078] The formula combines traditional proportional control and the derivative of the optimization target function to dynamically adjust the control command for precise regulation of pressure and temperature. The proportional gain factor ensures a linear relationship between the control command and the deviation, while the optimization adjustment factor dynamically adjusts the control command based on the derivative of the optimization target function, further improving the accuracy and response speed of the regulation. Through the application of these formulas, the multivariable optimization control algorithm can achieve highly coordinated and optimized regulation of pressure and temperature, significantly improving the overall efficiency and control accuracy of the system. This not only ensures that the mold is in the best state of pressure and temperature during production, reducing the product defect rate, but also improves the stability and reliability of the production process. In addition, the introduction of the closed-loop feedback mechanism enables the system to continuously optimize the regulation strategy based on real-time data, with stronger adaptive ability to cope with complex and variable production environments, further enhancing the intelligent level and technical competitiveness of the pressure regulation mechanism.

[0079] Compared with the prior art, the beneficial effects of the present application are:

[0080] By adopting the pressure data analysis algorithm, the present regulation mechanism uses Kalman filtering technology to process real-time pressure signals, effectively eliminating noise interference and accurately predicting future pressure states. The introduction of Kalman filtering makes the pressure estimation highly real-time and accurate, even in complex production environments with high signal noise, the system can still provide reliable pressure estimation values. This high-precision pressure estimation not only improves the regulation accuracy of the pressure control module, but also enhances the stability and response speed of the entire regulation system, reducing pressure fluctuations and overshoot phenomena, ensuring that the mold maintains the best pressure state under different working conditions, thereby significantly improving product quality and production efficiency.

[0081] The temperature trend prediction algorithm uses Long Short-Term Memory (LSTM) to perform deep learning and time series prediction on historical temperature data, achieving accurate prediction of future temperature changes. The specific process includes collecting and inputting temperature data at multiple past times, processing through the LSTM model, and outputting temperature prediction values at future times. The LSTM model captures long-term dependencies and nonlinear change patterns in temperature data, providing high-precision prediction results. Based on the predicted temperature trend, the temperature control module can perform adjustment operations in advance to avoid the adverse effects of temperature fluctuations on mold production, ensuring the continuity of the production process and the consistency of the product. This forward-looking temperature regulation capability not only improves the response speed of the system, but also reduces the production defect rate caused by temperature fluctuations, significantly improving production efficiency and product quality.

[0082] The multivariable optimization control algorithm integrates the outputs of the pressure data analysis algorithm and the temperature trend prediction algorithm, achieving a linkage optimization and closed-loop feedback control of the system. By optimizing the coupling relationship model through genetic algorithm, the system can find the optimal regulation balance point between pressure and temperature, generating optimal control instructions. This linkage optimization mechanism not only improves the coordination and precision of pressure and temperature regulation, but also continuously optimizes the control strategy through closed-loop feedback, enhancing the system's self-adaptability and robustness. As a result, the entire pressure regulation mechanism can maintain efficient and stable operation in the face of dynamic changes in the production environment, significantly improving the overall efficiency of the system and the reliability of the production process, ensuring that the mold maintains the optimal pressure and temperature state under various working conditions, thereby improving product quality and production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0083] Figure 1 A module schematic diagram of the pressure regulation mechanism for a plastic mold. DETAILED DESCRIPTION

[0084] A pressure regulation mechanism for a plastic mold, comprising:

[0085] a pressure detection module, a temperature detection module, a data processing module, a pressure control module, a temperature control module, an execution mechanism, a communication interface module, and an integrated control module;

[0086] The pressure detection module is used to monitor the pressure state inside the mold in real time and send the monitored pressure signal to the data processing module;

[0087] The temperature detection module is used to monitor the temperature state inside the mold in real time and send the monitored temperature signal to the data processing module;

[0088] The data processing module connects the pressure detection module and the temperature detection module, receives the pressure signal from the pressure detection module and the temperature signal from the temperature detection module, processes the data, and sends the processed pressure signal to the pressure control module and the processed temperature signal to the temperature control module;

[0089] The pressure control module connects the data processing module, receives the pressure signal from the data processing module, adjusts the pressure inside the mold according to the received pressure signal, and sends the pressure control instructions to the execution mechanism;

[0090] The temperature control module connects the data processing module, receives the temperature signal from the data processing module, adjusts the temperature inside the mold according to the received temperature signal, and sends the temperature control instructions to the execution mechanism;

[0091] The actuator connects the pressure control module and the temperature control module, and is used to implement actual pressure and temperature adjustment operations according to control instructions from the pressure control module and the temperature control module.

[0092] The communication interface module is used for data exchange and instruction transmission with an external control system, and is interconnected with the data processing module to realize bidirectional data communication.

[0093] The integrated control module is connected with the data processing module, the pressure control module and the temperature control module, and is used to integrate pressure and temperature adjustment, form a closed-loop control, and feed back optimized control instructions to the data processing module to realize adaptive adjustment of the system.

[0094] The pressure detection module and the temperature detection module respectively transmit real-time monitored pressure signals and temperature signals to the data processing module.

[0095] After receiving the signals from the pressure and temperature detection modules, the data processing module processes the signals through a pressure data analysis algorithm and a temperature trend prediction algorithm respectively to generate processed pressure signals and temperature signals.

[0096] The processed pressure signals and temperature signals are respectively transmitted to the pressure control module and the temperature control module, and these control modules generate corresponding control instructions according to the received signals.

[0097] The pressure control module and the temperature control module send the control instructions generated by themselves to the actuator to implement specific pressure and temperature adjustment operations.

[0098] The integrated control module integrates the outputs from the pressure control module and the temperature control module, generates optimized control instructions through a multivariable optimization control algorithm, and feeds back these instructions to the data processing module to form a closed-loop feedback and improve the adaptive ability of the system.

[0099] The communication interface module realizes data exchange and instruction transmission with an external control system, and ensures that the entire pressure adjustment mechanism can seamlessly cooperate with the external system.

[0100] The system monitors the pressure and temperature conditions inside the mold in real-time through the pressure detection module and temperature detection module, transmits the collected data to the data processing module for analysis and processing. The data processing module further transmits the processed pressure and temperature signals to the pressure control module and temperature control module respectively, generating corresponding control instructions. These instructions are implemented through actuators to perform specific pressure and temperature adjustment operations. At the same time, the communication interface module ensures that the system can communicate with external control systems for bidirectional data communication, realizing seamless information transmission. The integrated control module is responsible for integrating the adjustment signals of each module, forming a closed-loop control, and feeding back the optimized control instructions to the data processing module, forming a self-adaptive adjustment mechanism.

[0101] This overall structure design brings many technical advantages. First, the modular design makes the system parts clear in function, easy to maintain and upgrade. Second, the detailed data flow relationship ensures efficient information transmission and processing, improving the system's response speed and adjustment accuracy. In addition, the introduction of the closed-loop feedback mechanism greatly enhances the system's adaptive ability, allowing it to dynamically adjust control strategies based on real-time data, ensuring that the mold maintains the best pressure and temperature state under different working conditions. This design effectively solves the problem of traditional pressure regulation systems in complex production environments, significantly improving the production efficiency and product quality of plastic molds.

[0102] Specifically, the data processing module includes a pressure data analysis algorithm, which includes the following steps:

[0103] A1, receiving real-time pressure signals from the pressure detection module;

[0104] A2, applying Kalman filtering to the received pressure signals to eliminate noise interference and predict future pressure conditions;

[0105] A3, calculating the current pressure estimate based on the filtered pressure signal;

[0106] A4, outputting the calculated pressure estimate to the pressure control module.

[0107] The algorithm processes real-time pressure signals through Kalman Filtering technology. The specific process includes receiving real-time pressure signals transmitted by the pressure detection module, performing Kalman filtering to eliminate noise interference, predicting future pressure states, and finally outputting the current pressure estimate to the pressure control module. As a recursive filtering algorithm, Kalman filtering has the characteristics of strong real-time and high precision, and can effectively extract useful signals and suppress noise in a dynamically changing environment. By applying Kalman filtering, the pressure data analysis algorithm can accurately estimate the actual pressure state inside the mold, even in high noise interference or unstable signal conditions, providing reliable pressure estimation. This high-precision pressure estimation is crucial for subsequent pressure control, ensuring that the pressure regulation module can make precise control decisions based on accurate data. In addition, the introduction of Kalman filtering enables the system to have stronger prediction ability, enabling it to predict pressure trends in advance, thus implementing a more proactive adjustment strategy. This not only improves the response speed of the system, but also optimizes the smoothness of pressure regulation, reducing overshoot and oscillation phenomena, further improving the stability of the mold production process and the consistency of the product.

[0108] Specifically, the specific formula for pressure estimation in the pressure data analysis algorithm is:

[0109] ;

[0110] where P(t) is the pressure estimate at time t, is the predicted value based on the previous state, SP(t) is the actual measurement value of the pressure detection module at time t, K(t) is the Kalman gain, and H is the observation matrix.

[0111] The formula is based on the core principle of Kalman filtering, which dynamically updates the pressure estimate by combining the predicted value and the actual measurement value. The advantage of the formula design is its strong adaptability, which can automatically adjust the weight coefficient according to real-time data changes, thereby maintaining high estimation accuracy under different noise levels and system dynamics. The dynamic adjustment of the Kalman gain ensures that the system relies more on the measurement value when the signal quality is good, and relies more on the predicted value when the signal noise is large, balancing the real-time and stability of the signal.

[0112] In addition, the pressure estimation formula can effectively suppress the influence of noise by coupling prediction and measurement, improving the sensitivity and response speed of the system to pressure changes. This high-precision pressure estimation not only improves the regulation accuracy of the pressure control module, but also further optimizes the performance of the entire pressure regulation system, ensuring that the mold maintains a stable pressure environment during the production process, thereby improving product quality and production efficiency.

[0113] In particular, the data processing module further comprises a temperature trend prediction algorithm, which comprises the following steps:

[0114] B1, receiving historical temperature data from the temperature detection module;

[0115] B2, using a long short-term memory network to perform time series prediction on the temperature data and analyze the temperature change trend;

[0116] B3, predicting the temperature change value in the future period of time;

[0117] B4, outputting the prediction result to the temperature control module to adjust the temperature in advance.

[0118] The long short-term memory network (LSTM) is used to perform time series prediction on historical temperature data, analyze temperature change trend, predict temperature change in the future period of time, and output the prediction result to the temperature control module to adjust the temperature in advance.

[0119] As an advanced recurrent neural network (RNN), LSTM has the ability to process and predict long-time dependent data, and is particularly suitable for complex temperature time series data analysis. By learning and modeling the temperature data at the past nnn time points, LSTM can capture the potential rules and trends of temperature change and provide high-precision future temperature prediction. This prediction capability enables the temperature regulation system to take adjustment measures in advance to avoid mold defects or production interruptions caused by rapid temperature changes.

[0120] Firstly, the prediction model based on LSTM has high adaptability and learning ability, which can continuously optimize the prediction accuracy with the change of production environment. Secondly, the prediction of temperature change trend in advance enables the temperature control module to realize pre-adjustment, reduces the impact of temperature fluctuations on mold production, and improves the stability of the production process and the consistency of the products. In addition, the LSTM model can handle nonlinear and complex temperature change patterns, adapt to temperature regulation requirements under various working conditions, and further improve the intelligent level and adaptive ability of the system.

[0121] In particular, the specific formula for temperature prediction in the temperature trend prediction algorithm is:

[0122] ;

[0123] Where T pred (t+Δt) is the predicted temperature value at time t+Δt, T(t) to are the temperature values at the past n time points, and LSTM() represents the long short-term memory network model.

[0124] Predict the temperature value at the future time. The LSTM model can effectively capture the long-term dependencies and complex nonlinear patterns in the temperature data through its unique memory cell structure, providing accurate temperature predictions. The design mechanism of this formula is to fully utilize the advantages of the LSTM model in time series prediction, ensuring that the prediction results not only reflect the current temperature state, but also consider historical temperature trends and patterns. By inputting multiple historical temperature data at different times, the LSTM can identify and learn the potential rules of temperature changes, improving the accuracy and reliability of the prediction.

[0125] First, high-precision temperature prediction enables the temperature control module to adjust in advance, reducing the negative impact of temperature fluctuations on mold production and improving the stability of the production process. Second, the LSTM-based prediction model has high flexibility and adaptability, allowing it to continuously optimize prediction performance as the production environment changes, ensuring reliable temperature prediction under different working conditions. In addition, the implementation of this formula is simple and clear, making it easy for technicians to understand and apply, reducing system complexity and maintenance costs.

[0126] By introducing the LSTM model for temperature prediction, the temperature trend prediction algorithm significantly improves the system's intelligence and adaptability, enabling the mold pressure regulation mechanism to maintain efficient and stable temperature control in dynamically changing production environments, thereby improving overall production efficiency and product quality.

[0127] Specifically, the integrated control module further includes a multivariate optimization control algorithm, which integrates the output of the pressure data analysis algorithm and the temperature trend prediction algorithm to achieve system linkage optimization, specifically including the following steps:

[0128] C1, receiving the output of the pressure data analysis algorithm and the output of the temperature trend prediction algorithm;

[0129] C2, based on the pressure estimate value and the temperature prediction value, establishing a coupling relationship model between pressure and temperature;

[0130] C3, applying a genetic algorithm to optimize and solve the coupling model to determine the optimal pressure and temperature regulation strategy;

[0131] C4, outputting the optimized control instructions to the pressure control module and the temperature control module to achieve coordinated regulation of pressure and temperature;

[0132] C5, feeding back the optimized control instructions to the pressure data analysis algorithm and the temperature trend prediction algorithm to form a closed-loop feedback, improving the system's adaptability.

[0133] The algorithm realizes the linkage optimization of the system by integrating the output of the pressure data analysis algorithm and the temperature trend prediction algorithm. The specific process includes receiving the pressure estimation value and the temperature prediction value, establishing a coupling relationship model between pressure and temperature, applying a genetic algorithm (Genetic Algorithm) to optimize and solve the coupling model, determining the optimal pressure and temperature adjustment strategy, outputting the optimized control instructions to the pressure control module and the temperature control module, and feeding back these instructions to the data processing module to form a closed-loop feedback, improving the self-adaptive ability of the system. The core of the multivariable optimization control algorithm lies in its ability to consider the mutual influence between the two key parameters of pressure and temperature, and to find the optimal adjustment strategy through global optimization solving by genetic algorithm. This optimization method has the characteristics of strong global search ability and high adaptability, and can find an adjustment scheme close to the optimal solution in a complex multivariable environment, avoiding the problem of local optimal solution.

[0134] Firstly, by comprehensively considering the two key parameters of pressure and temperature, the system can realize more coordinated and accurate adjustment, avoiding the discordance and errors that may be caused by single parameter adjustment. Secondly, the application of genetic algorithm makes the optimization process highly flexible and adaptable, which can automatically adjust the adjustment strategy according to different production needs and environmental changes, improving the intelligent level of the system. In addition, the optimized control instructions can be fed back to the data processing module in real time to form a closed-loop control, further improving the response speed and adjustment precision of the system, ensuring that the mold can maintain stable pressure and temperature state under various working conditions.

[0135] By introducing the multivariable optimization control algorithm, the pressure regulation mechanism not only improves the overall adjustment effect and system performance, but also enhances the self-adaptive ability and robustness of the system, effectively solving the problem that the traditional pressure regulation system is difficult to realize efficient and stable regulation in complex production environment, significantly improving the automation level and product quality of the plastic mold production process.

[0136] Specifically, the specific formula for realizing linkage optimization in the multivariable optimization control algorithm includes:

[0137] Coupling relationship model formula:

[0138] ;

[0139] Where F is the coupling relationship function, β1, β2 and β3 are coupling coefficients for balancing the influence of pressure and temperature.

[0140] The formula fuses the pressure estimation value and the temperature prediction value by a combination of linear and nonlinear to form a comprehensive coupling relationship function. Each coupling coefficient respectively measures the weight of each parameter. By introducing the interaction term model, the complex relationship between pressure and temperature can be captured, and a more refined coupling effect can be provided.

[0141] Optimization objective function formula:

[0142] ;

[0143] Wherein, L is the optimization objective function, ω1, ω2 and ω3 are weight coefficients, P t and T t are the preset pressure target value and temperature target value respectively, R is a regularization term for constraining the complexity of the coupling relationship model;

[0144] The optimization objective function comprehensively considers the deviation of pressure and temperature and the complexity of the coupling relationship model, and weights each error and regularization term by the weight coefficient. The objective function aims to minimize the relative error of pressure and temperature while controlling the complexity of the coupling model to avoid overfitting. By optimizing the objective function through genetic algorithm, the optimal pressure and temperature regulation strategy can be found under the premise of ensuring system performance.

[0145] Control instruction adjustment formula:

[0146] ;

[0147] ;

[0148] Wherein, UP(t) is the pressure control instruction for adjusting the pressure inside the mold;

[0149] UT(t) is the temperature control instruction for adjusting the temperature inside the mold;

[0150] K P is the proportional gain coefficient of pressure control;

[0151] K T is the proportional gain coefficient of temperature control;

[0152] is the optimization adjustment coefficient of pressure control instruction;

[0153] is the optimization adjustment coefficient of temperature control instruction;

[0154] is the partial derivative of the optimization objective function to the pressure estimation value;

[0155] The partial derivative of the optimization objective function with respect to the temperature estimate.

[0156] The UP(t) and UT(t) are output to the pressure control module and the temperature control module, driving the actuator to adjust the pressure and temperature.

[0157] The optimized control instructions are fed back to the data processing module, adjusting the parameters of the pressure data analysis algorithm and the temperature trend prediction algorithm, forming a closed-loop feedback to continuously optimize the system's adjustment strategy.

[0158] The formula combines traditional proportional control and the derivative of the optimization objective function, dynamically adjusting the control instructions to achieve precise regulation of pressure and temperature. The proportional gain coefficient ensures a linear relationship between the control instructions and the deviation, while the optimization adjustment coefficient dynamically adjusts the control instructions according to the derivative of the optimization objective function, further improving the accuracy and response speed of the adjustment. Through the application of these formulas, the multivariable optimization control algorithm can achieve highly coordinated and optimized regulation of pressure and temperature, significantly improving the overall efficiency and control accuracy of the system. This not only ensures that the pressure and temperature of the mold remain in the best state during the production process, reducing the product defect rate, but also improves the stability and reliability of the production process. In addition, the introduction of the closed-loop feedback mechanism enables the system to continuously optimize the adjustment strategy based on real-time data, with stronger adaptive ability to cope with complex and variable production environments, further enhancing the intelligent level and technical competitiveness of the pressure regulation mechanism.

Claims

1. A pressure regulating mechanism for plastic molds, characterized in that, include: Pressure detection module, temperature detection module, data processing module, pressure control module, temperature control module, actuator, communication interface module, and integrated control module; The pressure detection module is used to monitor the pressure state inside the mold in real time and send the monitored pressure signal to the data processing module. The temperature detection module is used to monitor the temperature inside the mold in real time and send the monitored temperature signal to the data processing module. The data processing module is connected to the pressure detection module and the temperature detection module. It is used to receive pressure signals from the pressure detection module and temperature signals from the temperature detection module, process the data, and then send the processed pressure signal to the pressure control module and the processed temperature signal to the temperature control module. The pressure control module is connected to the data processing module and is used to receive pressure signals from the data processing module, adjust the pressure inside the mold according to the received pressure signals, and send pressure control commands to the actuator. The temperature control module is connected to the data processing module and is used to receive temperature signals from the data processing module, adjust the temperature inside the mold according to the received temperature signals, and send temperature control commands to the actuator. The actuator is connected to the pressure control module and the temperature control module, and is used to perform actual pressure and temperature regulation operations according to the control commands from the pressure control module and the temperature control module; The communication interface module is used to exchange data and transmit commands with an external control system. The communication interface module is interconnected with the data processing module to achieve bidirectional data communication. The integrated control module connects the data processing module, pressure control module, and temperature control module. It integrates pressure and temperature regulation to form a closed-loop control and feeds back the optimized control commands to the data processing module to achieve adaptive adjustment of the system. The specific formula used for pressure estimation in pressure data analysis algorithms is as follows: P(t)=P(t∣t 1)+K(t) (SP(t) H P(t∣t 1)); Where P(t) is the pressure estimate at time t, P(t|t) 1) is the predicted value based on the previous state, SP(t) is the actual measurement value of the pressure detection module at time t, K(t) is the Kalman gain, and H is the observation matrix; The specific formula used for temperature prediction in the temperature trend prediction algorithm is as follows: Tpred(t+Δt)=LSTM(T(t),T(t 1),…,T(t n+1)); Where Tpred(t+Δt) is the predicted temperature value at time t+Δt, and T(t) to T(t) n+1) represents the temperature values ​​at the past n times, and LSTM() represents the Long Short-Term Memory network model; The specific formulas for achieving linkage optimization in multivariable optimization control algorithms include: Coupling relationship model formula: F(P(t),Tpred(t+Δt))=β1 P(t)+β2 Tpred(t+Δt)+β3 (P(t) Tpred(t+Δt)); Where F is the coupling function, and β1, β2 and β3 are coupling coefficients used to balance the effects of pressure and temperature.

2. The pressure adjusting mechanism for a plastic mold according to claim 1, characterized in that, The data processing module includes a pressure data analysis algorithm, which includes the following steps: A1. Receive real-time pressure signals from the pressure detection module; A2. Apply Kalman filtering to the received pressure signal to eliminate noise interference and predict future pressure conditions; A3. Calculate the current pressure estimate based on the filtered pressure signal; A4. Output the calculated pressure estimate to the pressure control module.

3. The pressure adjusting mechanism for a plastic mold according to claim 2, characterized in that, The data processing module further includes a temperature trend prediction algorithm, which comprises the following steps: B1. Receive historical temperature data from the temperature detection module; B2. Use long short-term memory networks to perform time series prediction of temperature data and analyze temperature change trends; B3. Predict temperature changes over a future period of time; B4. Output the prediction results to the temperature control module to adjust the temperature in advance.

4. The pressure adjusting mechanism for a plastic mold according to claim 3, characterized in that, The integrated control module also includes a multivariable optimization control algorithm, which integrates the outputs of pressure data analysis algorithm and temperature trend prediction algorithm to achieve system linkage optimization, specifically including the following steps: C1 receives the output of the pressure data analysis algorithm and the output of the temperature trend prediction algorithm; C2. Based on the pressure estimate and temperature prediction, establish a coupling relationship model between pressure and temperature; C3. Apply genetic algorithms to optimize the coupled model and determine the optimal pressure and temperature regulation strategies; C4. Output optimized control commands to the pressure control module and temperature control module to achieve coordinated regulation of pressure and temperature; C5. The optimized control commands are fed back to the pressure data analysis algorithm and the temperature trend prediction algorithm to form a closed-loop feedback and improve the system's adaptability.

Images