A pressure control system for precision injection molding CNC equipment

Abstract

The present invention relates to a pressure control system for precision injection molding numerical control equipment, which uses time series pressure data, takes time as an independent variable and pressure as a dependent variable to draw a pressure smooth curve; obtains the pressure smooth curves of products of different sizes and shapes, and constructs a deep learning model between the pressure smooth curve and the size and shape of the product; and uses the deep learning model to obtain the corresponding pressure smooth curve according to the size and shape of two or more products that need to cooperate with each other to control the pressure of the injection molding process. The present invention uses a generalized additive model to quantify the complex nonlinear relationship between time and injection molding pressure, improves the pressure control accuracy, and uses a convolutional neural network model to determine that different pressure smooth curves can obtain products of different sizes and shapes, achieves the coordination of different products, and improves the processing quality of injection molding products.

Description

Technical Field

[0001] The invention belongs to the technical field of intelligent manufacturing and relates to a pressure control system for precision injection molding numerical control equipment. Background Art

[0002] Precision injection molding CNC equipment is a high-end equipment in the modern plastic processing industry, integrating advanced CNC technology, precision mechanical design and plastic injection molding process. It mainly uses the CNC system to accurately control various parameters in the injection molding process, such as temperature, pressure, speed, etc., to achieve accurate molding of plastic raw materials.

[0003] In the production process of plastic injection molding toys, the quality of the injection molding process directly affects the quality of the product. Traditional injection molding equipment has major defects in pressure control, such as large pressure fluctuations and difficulty in achieving precise pressure regulation. Pressure regulation during injection molding is the key to ensuring that the pressure of the plastic melt is stable and uniform during the injection molding process, thereby avoiding molding defects.

[0004] Since it is difficult to achieve precise pressure control, the plastic products produced have poor dimensional accuracy and a large tolerance range, which makes it difficult to meet the requirements of high-precision products. Injection defects such as flash, shrinkage marks, and material shortages are prone to occur on the product surface, greatly affecting product quality and yield rate. At the same time, due to the differences in size and shape between different products, the matching accuracy between products is low. During the player's assembly process, problems such as loose splicing and unstable structure are prone to occur, seriously affecting the user experience. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a pressure control system for precision injection molding CNC equipment, which aims to solve the problem of unstable injection pressure by collecting pressure data samples of multiple injection molding processes and establishing pressure smooth curves at different times. At the same time, the relationship between the pressure smooth curves and the sizes and shapes of different products is established to improve the matching accuracy between products.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The present application provides a pressure control system for precision injection molding CNC equipment, including a data acquisition module, a pressure curve module, a curve application module and a pressure control module; The data acquisition module is used to collect pressure data of multiple complete injection molding cycles, and the pressure data is divided into specific time steps to obtain time series pressure data; The pressure curve module is used to draw a pressure smooth curve using time series pressure data, with time as the independent variable and pressure as the dependent variable; The curve application module is used to obtain the pressure smoothing curves of products of different sizes and shapes, and to construct a deep learning model between the pressure smoothing curve and the size and shape of the product; The pressure control module is used to control the pressure of the injection molding process by using a deep learning model to obtain a corresponding pressure smooth curve according to the sizes and shapes of two or more products that need to cooperate with each other.

[0007] Furthermore, the data acquisition module is composed of a plurality of high-precision pressure sensors, and the sensors are respectively installed at the barrel feed port, the front end of the screw and the mold cavity of the injection molding machine.

[0008] Furthermore, the pressure smoothing curve is fitted by a generalized additive model and then drawn by R language software.

[0009] Furthermore, the generalized additive model includes the following construction steps: S1. Determine the model structure: The model uses pressure as the response variable and the corresponding explanatory variable is time; S2. Select smoothing function: select cubic spline function as the smoothing function of the model, and divide the time into multiple small segments. In each small segment, use cubic polynomial to describe the pressure change; S3. Parameter estimation: By continuously adjusting the model parameters, the gap between the predicted value and the actual value of the pressure is minimized, thereby determining the final parameters; S4, model verification and evaluation: use the model with adjusted parameters to predict the pressure value, and use the determination coefficient to verify the accuracy of the predicted value; S5. Draw a smooth pressure curve: Calculate the predicted pressure values ​​at different time points based on the adjusted model and parameters; and draw a smooth pressure curve with the help of drawing tools, with time as the horizontal axis and the predicted pressure value as the vertical axis.

[0010] Furthermore, the generalized additive model is expressed as: , In the formula, g Indicates injection pressure; x Indicates time; s represents a smooth function; k The number of nodes representing the smoothing function; μ represents the intercept term.

[0011] Furthermore, the deep learning model is configured as a convolutional neural network model with the pressure smooth curve as the input feature and the size and shape of the product as the output target.

[0012] Furthermore, the convolutional neural network model includes the following construction steps: T1. Data preprocessing: convert the pressure smoothing curve data into a standardized form with zero mean and unit variance, and encode the size and shape information of the product; T2. Model architecture design: Determine the number of input layer nodes by referring to the dimension of the pressure smooth curve data; construct a convolution layer to capture the characteristics of the pressure smooth curve, and determine the number, size, and step size of the convolution kernels; add a pooling layer to reduce the dimension of the data; set up a fully connected layer to achieve feature integration and mapping from the output of the pooling layer to the final output layer; determine the number of output layer nodes based on the characteristic dimensions of the product size and shape; T3, model training: select the loss function and optimizer according to the output target, and adjust the hyperparameters; divide the data into training set, validation set and test set, input the training set data into the model, obtain the output and calculate the error with the help of forward propagation, and then update the model parameters through back propagation, and continuously iterate the training process; T4. Model evaluation and adjustment: Use the test set to evaluate the trained model and determine the model performance by calculating evaluation indicators.

[0013] Furthermore, the pressure control module calculates the pressure deviation according to the preset pressure smoothing curve and the pressure data collected in real time, and performs data processing through the PID control algorithm to generate accurate control instructions.

[0014] Furthermore, the pressure control module also includes a human-computer interaction module, which is equipped with a pressure display screen, and the operator monitors the injection pressure in real time according to the pressure display screen.

[0015] Beneficial effects of the present invention: (1) Using time series pressure data, with time as the independent variable and pressure as the dependent variable, a pressure smooth curve is drawn; the pressure smooth curves of products of different sizes and shapes are obtained, and a deep learning model between the pressure smooth curve and the size and shape of the product is constructed; according to the size and shape of two or more products that need to cooperate with each other, the corresponding pressure smooth curve is obtained using the deep learning model to control the pressure of the injection molding process. This solves the problem of large injection molding pressure fluctuations and poor matching accuracy of products of different sizes and shapes in the prior art.

[0016] (2) The generalized additive model was used to fit the pressure smoothing curve and quantify the complex nonlinear relationship between time and injection pressure in an injection molding cycle, thereby improving the pressure control accuracy and the processing quality of the injection molded products.

[0017] (3) The convolutional neural network model was used to determine that different pressure smoothing curves can produce products of different sizes and shapes, achieve the matching of different products, and improve the processing quality of injection molded products. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0019] Figure 1 The structure diagram of a pressure control system of a precision injection molding CNC equipment in the present invention.

[0020] Figure 2 This is a step of constructing a generalized additive model according to an embodiment of the present invention.

[0021] Figure 3 This is a step for constructing a convolutional neural model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0023] See also Figure 1-Figure 3 , the present application provides a pressure control system for precision injection molding CNC equipment, including a data acquisition module, a pressure curve module, a curve application module and a pressure control module; The data acquisition module is used to collect pressure data of multiple complete injection molding cycles, and the pressure data is divided into specific time steps to obtain time series pressure data; In this embodiment, the main task of the data acquisition module is to collect pressure data for multiple complete injection molding cycles. The reason for focusing on multiple cycles is that the injection molding production process is not static, and each injection molding may be affected by many factors, such as the subtle property differences of different batches of plastic raw materials, the performance changes caused by slight wear of the equipment during continuous operation, etc., all of which will cause the injection molding pressure to fluctuate. Only by collecting data from multiple complete injection molding cycles can the actual law of pressure changes in the injection molding process be fully and truly reflected, thereby providing rich and reliable data support for the precise analysis of each module of the subsequent system.

[0024] After collecting the pressure data, the data acquisition module will divide the data in detail according to a specific time step, and finally obtain the time series pressure data. The setting of this specific time step is not fixed, but needs to be flexibly determined according to the specific characteristics of the injection molding process and the actual production needs. If the pressure changes rapidly during the injection molding process, the pressure value will change greatly in a short period of time, then it is necessary to set a smaller time step, such as 0.01 seconds, to ensure that every instantaneous change in pressure can be accurately captured; on the contrary, if the pressure changes relatively smoothly and the fluctuation amplitude is small, the time step can be appropriately increased. After the time step division, the originally chaotic pressure data will be arranged in chronological order to form an orderly time series pressure data. This data form provides convenient conditions for the subsequent drawing of pressure smooth curves and in-depth exploration of the law of pressure changes, enabling the system to conduct in-depth analysis of the dynamic changes of pressure over time.

[0025] Furthermore, the data acquisition module is composed of a plurality of high-precision pressure sensors, and the sensors are respectively installed at the barrel feed port, the front end of the screw and the mold cavity of the injection molding machine.

[0026] In this embodiment, the core component of the data acquisition module is a plurality of high-precision pressure sensors, which accurately detect the pressure changes during the injection molding process. The reason for selecting high-precision pressure sensors is that the injection molding process has extremely high requirements for the accuracy of pressure data, and even extremely slight pressure fluctuations may have a significant impact on product quality.

[0027] In the specific implementation process, you can choose Kistler 6183A / 6185A series diaphragm pressure sensor, which is specially designed for injection mold pressure monitoring, with a range of 0-2000bar; the accuracy can reach ±0.5%FS, and the dynamic response frequency can reach 5kHz. It can monitor the changes in cavity pressure in real time and optimize the process parameters in the pressure holding stage. Or TEConnectivity M5200 series piezoresistive sensor, which has a small size and high sensitivity, is suitable for injection molding pressure monitoring of small injection molding machines such as space-constrained scenarios. These types of sensors are placed in key positions of injection molding machines. At the barrel feed port, the sensor can monitor the initial pressure of the plastic raw material when it enters the barrel in real time. Due to the entry speed, flow rate and differences in the characteristics of the plastic raw material, the pressure here will change, and these changes will directly affect the subsequent injection molding process, so accurate monitoring of the feed port pressure is crucial.

[0028] The sensor at the front end of the screw is responsible for monitoring the pressure changes when the screw pushes the plastic melt. The screw plays a key role in the injection molding process. It pushes the plastic melt into the mold cavity, and the magnitude of its propulsion force is directly reflected in the pressure value. By collecting the pressure at the front end of the screw in real time, the system can timely grasp the working status of the screw and then accurately control the injection pressure.

[0029] The mold cavity is where the plastic particles are finally formed. The sensor installed here can keenly sense the pressure of the plastic when it is filled in the cavity. The pressure distribution in the mold cavity directly determines the molding quality of the product. For example, whether there are problems such as uneven filling, bubbles or shrinkage marks are closely related to the pressure in the cavity. Through accurate monitoring of the mold cavity pressure, the system can adjust the injection molding parameters in time according to the feedback information to ensure that the plastic products produced are accurate in size and smooth in surface, meeting the high-quality production requirements.

[0030] The pressure curve module is used to draw a pressure smooth curve using time series pressure data, with time as the independent variable and pressure as the dependent variable; Furthermore, the pressure smoothing curve is fitted by a generalized additive model and then drawn by R language software.

[0031] In the pressure control system of precision injection molding CNC equipment, the generation and drawing of pressure smooth curves have a rigorous process. First, the generalized additive model is used to fit the time series pressure data obtained from the data acquisition module. The generalized additive model can effectively handle the complex nonlinear relationship between pressure and time. It breaks through the limitations of traditional linear models and can flexibly capture the pressure change trend.

[0032] In the fitting process, time is used as the independent variable and pressure is used as the dependent variable. The model analyzes the data and uses smoothing techniques, such as spline functions, to estimate the impact of the independent variable on the dependent variable, thereby constructing a relationship model that can accurately reflect the change of pressure over time.

[0033] After completing the fitting, the pressure smoothing curve is drawn with the help of R language software. R language is a powerful data analysis and visualization tool with rich drawing functions and extension packages. When drawing the pressure smoothing curve, you can use drawing packages such as ggplot2 to input the data obtained by generalized additive model fitting into the corresponding function, set the horizontal axis to time, the vertical axis to pressure, and adjust the appearance attributes of the curve such as color and line type to generate an intuitive, clear and beautiful pressure smoothing curve. This method of combining generalized additive model fitting with R language drawing provides a reliable and accurate reference for the pressure change trend for the subsequent curve application module to build a deep learning model and the pressure control module to achieve precise pressure regulation.

[0034] In this embodiment, the pressure curve module is responsible for drawing the pressure smooth curve, and the use of a generalized additive model (GAM) for fitting and drawing has unique advantages and principles.

[0035] The generalized additive model is a semi-parametric regression model that relaxes the strict assumption of a linear relationship between independent variables and dependent variables in traditional linear models, allowing for a more flexible and complex nonlinear relationship between independent variables and dependent variables. In the processing of injection molding pressure data, the actual pressure change cannot always be described by a simple linear equation. It is affected by a variety of complex factors such as raw material characteristics, mechanical properties of the injection molding machine, and mold heat transfer, and presents complex nonlinear characteristics.

[0036] When using the generalized additive model to fit and draw a smooth pressure curve, first take time as the independent variable and pressure as the dependent variable, and input the time series pressure data obtained by the data acquisition module into the model. GAM automatically estimates the nonlinear effect of each independent variable (time) on the dependent variable (pressure) by analyzing these data. It will fit the data points according to the actual distribution of the data, using smoothing techniques such as spline functions, so as to construct a smooth curve that can accurately reflect the trend of pressure changes over time.

[0037] Compared with other simple fitting methods, the pressure smoothing curve drawn by the generalized additive model can better capture the subtle features and complex trends of pressure changes. This allows us to more accurately grasp the dynamic changes of pressure when analyzing the injection molding process, and provides a more reliable and accurate reference for the pressure change trend for the subsequent curve application module to build a deep learning model and the pressure control module to achieve precise pressure regulation, which helps to further improve the quality and precision of injection molding products.

[0038] Furthermore, the generalized additive model includes the following construction steps: S1. Determine the model structure: The generalized additive model is used to explore the complex relationship between pressure and time, not a simple linear relationship. The model contains a base value, a part that changes over time, and some random errors. Since the main focus is on the change of pressure over time, the key is to clarify this special relationship.

[0039] S2. Select smoothing function: The function of smoothing function is to make the pressure change curve smoother. The commonly used one is spline function, such as cubic spline function. It divides time into multiple small segments, and in each small segment, a cubic polynomial is used to describe the pressure change. In order to make the description accurate, it is necessary to reasonably select the segmentation position, and find the appropriate parameters through trial and verification, so that the function can fit the data without being too complicated.

[0040] S3. Parameter estimation: Finding the parameters that allow the model to accurately reflect the relationship between pressure and time is like adjusting the knobs of a machine to make it run accurately. Some methods can be used, such as determining a set of parameters that minimize the difference between the pressure value predicted by the model and the actual measured value. By continuously adjusting the parameters to minimize the difference, the required parameters can be determined.

[0041] S4. Model verification and evaluation: Use the model with adjusted parameters to predict the pressure value and verify the accuracy of the prediction. Use some indicators to measure the prediction effect of the model, such as checking the average error between the predicted value and the actual value, or evaluating the overall explanation of the model for the data. If the model prediction is not good, return to the previous step and adjust the model structure, smoothing function or parameters until the prediction effect is good.

[0042] S5. Draw a smooth pressure curve: Calculate the predicted pressure values ​​at different time points based on the adjusted model and parameters. Use the time as the horizontal axis and the predicted pressure value as the vertical axis to draw a curve with the help of drawing tools. This curve is the pressure smooth curve, which can clearly show the change of pressure over time during the injection molding process.

[0043] The curve application module is used to obtain the pressure smoothing curves of products of different sizes and shapes, and to construct a deep learning model between the pressure smoothing curve and the size and shape of the product; Furthermore, the deep learning model is configured as a convolutional neural network model with the pressure smooth curve as the input feature and the size and shape of the product as the output target.

[0044] In this embodiment, the deep learning model uses a convolutional neural network (CNN) architecture, which is closely related to the data characteristics of the pressure smoothing curve. CNN performs well in processing data with grid structures or sequence characteristics, and the pressure smoothing curve can be regarded as a time-varying sequence data, which is exactly adapted to the processing advantages of CNN.

[0045] Taking the pressure smooth curve as the input feature means that the information about the pressure change over time contained in the curve is input into the model in a specific format. This information includes the pressure values ​​at different time points, the rate of pressure change, the amplitude of fluctuation, etc. They are organized in a sequence to form the initial input of the model. The model sets the size and shape of the product as the output target. The size of the product, such as length, width, height, etc., as well as shape features, such as whether it is regular, whether there are special concave and convex structures, etc., are all encoded into an output format that the model can recognize.

[0046] In the CNN model, the convolution layer is one of the core components. The convolution layer slides the convolution kernel on the input pressure smooth curve data to perform convolution operations and extract local features in the data. For example, the convolution kernel can capture the characteristic pattern of the pressure curve rising or falling rapidly within a certain period of time. The stacking of multiple convolution layers can gradually extract features from simple to complex.

[0047] The pooling layer follows the convolution layer and is used to reduce the dimension of the data, reducing the amount of data while retaining key features. For example, the maximum pooling or average pooling method is used to select the maximum value or average value in a local area to represent the characteristics of the area, reduce the computational complexity, and prevent the model from overfitting.

[0048] After multiple processing by the convolutional layer and the pooling layer, the data is flattened and input into the fully connected layer. The fully connected layer synthesizes the previously extracted features and maps them to the output space corresponding to the product size and shape through the operation of the weight matrix, and finally outputs the prediction results of the product size and shape.

[0049] During the model training process, a large amount of pressure smoothing curve data with annotations (i.e. known size and shape) is used to continuously adjust the internal parameters of the model (such as the weight of the convolution kernel, the weight of the fully connected layer, etc.) so that the error between the model's prediction results and the actual annotations gradually decreases until the model achieves a higher prediction accuracy, thereby accurately establishing the mapping relationship between the pressure smoothing curve and the product size and shape.

[0050] Furthermore, the convolutional neural network model includes the following construction steps: T1. Data preprocessing: After obtaining the existing product injection pressure smooth curve and corresponding size and shape data, comprehensively screen the missing values ​​and abnormal values, fill in the missing parts reasonably, and correct or eliminate the abnormal data. Subsequently, the pressure smooth curve data is converted into a standardized form with zero mean and unit variance, and the size and shape information of the product is encoded into digital features that are easy for the model to recognize, laying a solid foundation for subsequent model training.

[0051] T2. Model architecture design: Refer to the dimension of the pressure smoothing curve data to accurately determine the number of input layer nodes and build an entry for data input. Construct the convolution layer in an orderly manner, and carefully select the number, size and step size of the convolution kernels so that it can effectively capture the characteristics of different levels of the pressure curve. After the convolution layer, add a pooling layer reasonably, and scientifically set the pooling window size and step size to perform just the right dimensionality reduction on the data to reduce the computational burden. According to the complexity of the task and actual needs, set the fully connected layer as appropriate to achieve feature integration and mapping from the pooling layer output to the final output layer. Finally, determine the number of output layer nodes based on the feature dimensions of the product size and shape to ensure that the model can accurately output the prediction results.

[0052] T3. Model training: Select the loss function according to the specific properties of the output target, such as the mean square error loss function for regression tasks and the cross entropy loss function for classification tasks. Select a suitable optimizer from stochastic gradient descent and its derived optimizers, and fine-tune hyperparameters such as the learning rate. Divide the data into training set, validation set, and test set, input the training set data into the model, obtain the output and calculate the error with the help of forward propagation, and then rely on back propagation to update the model parameters, and continuously iterate the training process. At the same time, use the validation set to dynamically adjust the hyperparameters to effectively prevent the model from overfitting.

[0053] T4. Model evaluation and adjustment: According to the task type, select evaluation indicators reasonably. For example, regression tasks focus on mean square error and mean absolute error, while classification tasks focus on accuracy, recall and other indicators. Use the test set to conduct a comprehensive evaluation of the trained model, and objectively judge the model performance by calculating the values ​​of various evaluation indicators. If the model performance fails to meet the expected standards, analyze the reasons behind it in depth, adjust the model architecture, hyperparameter settings or data preprocessing methods in a targeted manner, and then restart the training and evaluation process until the model performance meets the requirements.

[0054] T5. Model deployment and application: The trained and qualified models are properly saved for easy access at any time. Subsequently, the models are successfully deployed in the actual injection molding production environment and deeply integrated with the production system. In this way, the model can quickly and accurately predict the size and shape of the product based on the real-time input pressure smoothing curve, providing strong support for injection molding production.

[0055] The pressure control module is used to control the pressure of the injection molding process by using a deep learning model to obtain a corresponding pressure smooth curve according to the sizes and shapes of two or more products that need to cooperate with each other.

[0056] Furthermore, the pressure control module calculates the pressure deviation according to the preset pressure smoothing curve and the pressure data collected in real time, and performs data processing through the PID control algorithm to generate accurate control instructions.

[0057] In this embodiment, the pressure control module is a key part of the pressure control system of precision injection molding CNC equipment to achieve precise pressure regulation, and its operation process is closely centered around the preset pressure smooth curve and real-time pressure data. The module first compares the pressure data collected by the injection molding machine in real time with the pressure value of the preset pressure smooth curve corresponding to the time point obtained by the deep learning model analysis based on the size and shape of different products. The real-time pressure value is subtracted from the pressure value of the preset curve at the corresponding time point to calculate the pressure deviation, which intuitively reflects the gap between the current injection pressure and the expected pressure.

[0058] Next, the pressure control module inputs the calculated pressure deviation into the PID control algorithm for processing. The PID control algorithm consists of three key links: proportional (P), integral (I), and differential (D). The proportional link outputs the control effect according to the established proportion based on the size of the pressure deviation. The larger the deviation, the stronger the control effect; the integral link integrates the pressure deviation and accumulates the deviation over a period of time to eliminate the steady-state error of the system; the differential link outputs the control effect in advance according to the speed of change of the pressure deviation to effectively suppress the overshoot of the system. These three links work together to process the pressure deviation data comprehensively and meticulously.

[0059] After being processed by the PID control algorithm, the pressure control module finally generates precise control instructions. These instructions will be transmitted to the relevant actuators of the injection molding machine, such as adjusting the screw advancement speed of the injection molding machine, controlling the amount of plastic melt pushed by changing the screw speed; or adjusting the hydraulic system pressure to change the clamping force and injection pressure of the injection molding machine. Through the adjustment of these parameters, the actual injection pressure can quickly and accurately follow the preset pressure smooth curve changes, ensuring that the injection molding process is always in an ideal state, effectively guaranteeing the production quality and precision of the product, and meeting the needs of high-quality injection molding production.

[0060] Furthermore, the pressure control module also includes a human-computer interaction module, which is equipped with a pressure display screen, and the operator monitors the injection pressure in real time according to the pressure display screen.

[0061] In this embodiment, the human-computer interaction module in the pressure control module greatly improves the convenience and real-time monitoring of the injection pressure by the operator by configuring a pressure display screen. The pressure display screen presents the pressure data of the injection process in real time in an intuitive graphical or digital form. The operator can know the current injection pressure value, pressure change trend and other key information by directly observing the screen without the need for complex data analysis tools.

[0062] For example, when the pressure value approaches or exceeds the preset reasonable range, the display screen can issue a warning by changing color, flashing, etc. Based on this, the operator can quickly determine whether the injection molding process is normal, and take corresponding measures in time if the pressure is abnormal. If the pressure is too high, the parameters of the PID control algorithm can be adjusted through the human-computer interaction module to reduce the pressure; if the pressure is too low, the reverse operation can be performed to increase the pressure.

[0063] In addition, the human-machine interaction module can also design an operation interface, allowing operators to flexibly adjust the preset pressure smoothing curve according to the production requirements of different products, thereby optimizing the injection pressure control. This function enables operators to more accurately control the injection pressure when facing a variety of production tasks, ensuring that the products produced meet quality standards and improving production efficiency and product quality.

[0064] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A pressure control system for precision injection molding CNC equipment, characterized in that: It includes data acquisition module, pressure curve module, curve application module and pressure control module; The data acquisition module is used to collect pressure data of multiple complete injection molding cycles, and the pressure data is divided into specific time steps to obtain time series pressure data; The pressure curve module is used to draw a pressure smooth curve using time series pressure data, with time as the independent variable and pressure as the dependent variable; The curve application module is used to obtain the pressure smoothing curves of products of different sizes and shapes, and to construct a deep learning model between the pressure smoothing curve and the size and shape of the product; The pressure control module is used to control the pressure of the injection molding process by using a deep learning model to obtain a corresponding pressure smooth curve according to the sizes and shapes of two or more products that need to cooperate with each other.

2. A pressure control system for precision injection molding CNC equipment according to claim 1, characterized in that: The data acquisition module is composed of a plurality of high-precision pressure sensors, and the sensors are respectively installed at the barrel feed port, the front end of the screw and the mold cavity of the injection molding machine.

3. A pressure control system for precision injection molding CNC equipment according to claim 1, characterized in that: The pressure smoothing curve is fitted by a generalized additive model and then drawn by R language software.

4. A pressure control system for precision injection molding CNC equipment according to claim 3, characterized in that: The generalized additive model includes the following construction steps: S1. Determine the model structure: The model uses pressure as the response variable and the corresponding explanatory variable is time; S2. Select smoothing function: select cubic spline function as the smoothing function of the model, and divide the time into multiple small segments. In each small segment, use cubic polynomial to describe the pressure change; S3. Parameter estimation: By continuously adjusting the model parameters, the gap between the predicted value and the actual value of the pressure is minimized, thereby determining the final parameters; S4, model verification and evaluation: use the model with adjusted parameters to predict the pressure value, and use the determination coefficient to verify the accuracy of the predicted value; S5. Draw a smooth pressure curve: Calculate the predicted pressure values ​​at different time points based on the adjusted model and parameters; and draw a smooth pressure curve with the help of drawing tools, with time as the horizontal axis and the predicted pressure value as the vertical axis.

5. The pressure control system of a precision injection molding CNC equipment according to claim 3 is characterized in that: The generalized additive model is expressed as: ， In the formula, g Indicates injection pressure; x Indicates time; s represents a smooth function; k The number of nodes representing the smoothing function; μ represents the intercept term.

6. The pressure control system of a precision injection molding CNC equipment according to claim 1, characterized in that: The deep learning model is configured as a convolutional neural network model with a pressure smooth curve as an input feature and the size and shape of the product as an output target.

7. A pressure control system for precision injection molding CNC equipment according to claim 6, characterized in that: The convolutional neural network model includes the following construction steps: T1. Data preprocessing: convert the pressure smoothing curve data into a standardized form with zero mean and unit variance, and encode the size and shape information of the product; T2. Model architecture design: Determine the number of input layer nodes based on the dimension of the pressure smooth curve data; construct a convolution layer to capture the characteristics of the pressure smooth curve, and determine the number, size, and step size of the convolution kernels; add a pooling layer to reduce the dimensionality of the data; set up a fully connected layer to achieve feature integration and mapping from the output of the pooling layer to the final output layer; Determine the number of output layer nodes based on the characteristic dimensions of product size and shape; T3, model training: select the loss function and optimizer according to the output target, and adjust the hyperparameters; divide the data into training set, validation set and test set, input the training set data into the model, obtain the output and calculate the error with the help of forward propagation, and then update the model parameters through back propagation, and continuously iterate the training process; T4. Model evaluation and adjustment: Use the test set to evaluate the trained model and determine the model performance by calculating evaluation indicators.

8. The pressure control system of precision injection molding CNC equipment according to claim 1, characterized in that: The pressure control module calculates the pressure deviation according to the preset pressure smoothing curve and the pressure data collected in real time, and performs data processing through the PID control algorithm to generate accurate control instructions.

9. The pressure control system of precision injection molding CNC equipment according to claim 1, characterized in that: The pressure control module also includes a human-computer interaction module, which is equipped with a pressure display screen, and the operator monitors the injection pressure in real time according to the pressure display screen.

Images