Multi-layer composite material preparation process control optimization method and system based on big data

Abstract

The invention discloses a multi-layer composite material preparation process control optimization method and system based on big data, and belongs to the field of process optimizing.The method comprises the steps that a sensor cluster composed of various sensors is installed, data generated when a multi-layer co-extrusion laminating machine works are collected, and the data are uploaded and processed; preprocessing the collected data, aligning timestamps, mapping the data to a uniform coordinate system grid, and constructing a sensor historical database; analyzing the data, and constructing a key index dynamic model and an optimization control algorithm; and according to the real-time data transmitted back by the sensor cluster, a predicted value is calculated in combination with the optimization control algorithm, and the predicted value is compared with the real-time data of the sensor to obtain an optimization operation combination. The production efficiency is greatly improved through automatic optimization operation.

Description

Technical Field

[0001] The present invention relates to the field of process optimization, and in particular to a method and system for controlling and optimizing a multi-layer composite material preparation process based on big data. Background Art

[0002] Multilayer composite materials are widely used in packaging, construction and other fields. The traditional production process of multilayer composite materials is mainly carried out by laminating machines, but there are some problems. First of all, the mechanical structure of the laminating machine is relatively fixed, and it is difficult to improve the production efficiency of composite materials by improving the laminating machine. It can only be adjusted by skilled workers according to the finished products. The laminating machine has temperature changes, pressure distribution, and film thickness evolution, which leads to poor product quality and uneven film thickness. The traditional process lacks effective optimization control means, and it is impossible to dynamically adjust production parameters according to real-time data, and the energy consumption is high. In order to solve the above problems, a method is needed to realize automatic process control optimization based on the real-time production data of the laminating machine. Summary of the invention

[0003] One of the purposes of the present invention is to provide a method for controlling and optimizing the preparation process of multi-layer composite materials based on big data, so as to solve the problems of uneven film thickness and high energy consumption in the production process of multi-layer composite materials in the prior art.

[0004] The present invention is implemented through the following technical scheme, a method for optimizing the control of a multilayer composite material preparation process, comprising the following steps: S1, installing a sensor cluster consisting of multiple sensors on a multilayer co-extrusion laminating machine, collecting data generated during operation, and uploading the collected data to a back-end processing device for processing; S2, the back-end processing device pre-processes the data collected by the sensor cluster, aligns the timestamps of the pre-processed data, maps them to a unified coordinate system grid, integrates and constructs a sensor history database; S3, analyzes the data in the sensor history database, constructs a key indicator dynamic model, and obtains an optimization control algorithm based on the key indicator dynamic model; S4, calculates a predicted value based on the real-time data transmitted back by the sensor cluster in combination with the optimization control algorithm, compares the predicted value with the real-time data of the sensor, dynamically adjusts the parameters of the key indicator dynamic model based on the comparison results, and dynamically adjusts the production parameters based on the comparison results to obtain an operation combination, and adjusts the production parameters in the process flow based on the operation combination.

[0005] Furthermore, the sensor cluster is constructed through the following sub-steps: S11. According to the main factors affecting the molding of multi-layer composite materials, different types of sensors are selected to collect data, and the data include: temperature, pressure, material conveying speed and extrusion speed, thickness and uniformity of composite materials, sealing tightness and blistering at the edge of composite materials, and tension of materials during conveying; S12. Temperature sensors are used to collect roller temperature, mold temperature, and temperature data before the material enters the roller. Pressure sensors collect data on pressure distribution and pressure change trend of the roller. Speed ​​sensors collect material conveying speed and extrusion speed. Thickness measurement sensors monitor the thickness of composite materials to ensure the uniformity of extruded materials. Infrared sensors monitor the sealing tightness and blistering at the edge. Tension sensors monitor the tension of materials during conveying; S13. Different types of sensors are installed at corresponding positions of the multi-layer co-extrusion laminating machine. Different types of sensors transmit the collected data to the network end in real time through the Internet of Things port. Data of different types of sensors are integrated at the network end to synchronize sensor data, and the synchronized data are sent to the back-end processing equipment.

[0006] Furthermore, preprocessing includes: denoising, completing and standardizing the data, wherein the window sliding average method is used to perform sliding average filtering on the time series data, the instantaneous jitter signal of the tension sensor is decomposed by wavelet to remove high-frequency noise and retain low-frequency signals, and data outside the range of ±3 times the standard deviation of the mean is regarded as an outlier and eliminated through outlier detection; after denoising, the data is repaired and completed, and linear interpolation is used to repair data missing caused by temporary sensor failure or transmission loss; finally, Z-Score standardization is used to standardize the data.

[0007] Further,

[0008] The key indicator dynamic model is composed of three composite material influencing factor equations with coupling relationships, including: the temperature indicator equation used to describe the impact of temperature changes on materials, as shown in the following formula:

[0009] ,in, is the material density, kg / m 3 ; is the specific heat capacity, J / (kg·K); k is the thermal conductivity, W / (m·K); Q ext is the external heat source, W / m 3 ; v is the flow velocity field of the composite material, m / s; is the gradient of the temperature field; the pressure index equation used to describe the effect of pressure change on the material is shown in the following formula:

[0010] , where γ' is the shear rate, a scalar measure used to describe the rate of fluid during shear; is the shear rate-dependent viscosity function, which is used to indicate that the viscosity changes according to the shear rate. is the velocity gradient tensor, is the pressure gradient; the index equation used to describe the thickness change of the finished composite material is as shown below:

[0011] , where h is the thickness of the material, is the Laplace operator, It is the product of the material thickness and the flow velocity of the composite material, indicating the amount of material passing through a certain cross-sectional area per unit time. Q is the expansion rate of material thickness with flow, indicating the expansion or contraction of material thickness during flow. extrusion is the extruder flow rate, m³ / s; A is the cross-sectional area of ​​the composite material, m 2 ; In the above three equations, t represents time, It indicates the rate of change of temperature T relative to time t, that is, how the temperature changes at different time points; is the rate of change of velocity field with time; is the rate at which the material thickness changes with time; in the above formula, is the partial derivative.

[0012] Furthermore, the viscosity function is represented by a power law model, and the power law model is shown in the following formula:

[0013] , where K is the consistency coefficient, Pa·s; n is the flow index, dimensionless.

[0014] Furthermore, the optimization control algorithm includes an objective function and constraints, wherein the objective function is:

[0015] , where H is the prediction time domain; is a spatial point (x, y) and time The thickness function at is the integral variable, which varies in the range [t, t+H]; h target is the target thickness of the composite material, mm; w is the weight coefficient; is a time-varying control variable; It is a control variable; the constraints are set based on the production situation, including physical constraints, which are used to characterize the constraints directly determined by material properties or process requirements; control variable constraints, which are used to characterize the physical limits of various control parameters of the multi-layer co-extrusion laminating machine; process constraints, which are used to characterize the constraints related to the performance of the finished composite material.

[0016] Furthermore, step S4 also includes a closed-loop control step, in which the sensor cluster continuously collects new data. The sensor cluster collects data every Δt time, inputs the latest data into the error function, obtains updated parameters through the gradient descent method, and dynamically calibrates the key indicator dynamic model through the updated parameters.

[0017] Furthermore, the error function is shown as follows:

[0018] , where θ is a model parameter and is dimensionless; is the initial value of the model parameter, N is the total number of samples; is the model prediction value, which means at point (x i ,y i ) and the temperature at time t depends on the model parameter θ, is the actual measured value, indicating that at point (x i ,y i ) and the actual data of the sensor at time t; λ is the weight of the regularization term, which is used to control the influence of the regularization term on the total error. By iteratively adjusting the parameter θ, the error is gradually reduced. The parameter update mechanism of J(θ) is expressed as:

[0019] , where θ k+1 is the parameter value after the k+1th iteration; θ k is the parameter value of the current k-th iteration; α is the control parameter used to control the step size of each adjustment; is the gradient of the error function at the current parameter.

[0020] On the other hand, the present invention provides a multi-layer composite material preparation process control optimization system based on big data, including a multi-layer co-extrusion laminating machine and a back-end processing device, a sensor cluster module is installed on the multi-layer co-extrusion laminating machine; the back-end processing device is used to process the data collected by the sensor cluster, and adjust the production parameters of the multi-layer co-extrusion laminating machine according to the results of the data processing. The process control optimization system also includes a data preprocessing module, a data analysis module and an optimization control module, wherein the data preprocessing module is configured to preprocess the data collected by the sensor cluster, align the timestamp of the preprocessed data, map it to a unified coordinate system grid, integrate and construct a sensor history database; the data analysis module is connected to the data preprocessing module, configured to analyze the data in the sensor history database, construct a key indicator dynamic model, and design an optimization control algorithm based on the key indicator dynamic model; the optimization control module is connected to the data analysis module and the sensor cluster module, configured to calculate the predicted value according to the real-time data transmitted back by the sensor cluster and the optimization control algorithm, compare the predicted value with the real-time data of the sensor, and dynamically adjust the parameters of the key indicator dynamic model according to the comparison result.

[0021] Furthermore, the sensor cluster module is configured to install the different types of sensors at corresponding positions of the multi-layer co-extrusion laminating machine, and the different types of sensors transmit the collected data to the network end in real time through the Internet of Things port, integrate the data of different types of sensors at the network end, synchronize the sensor data, and send the synchronized data to the back-end processing equipment; use temperature sensors to collect roller temperature, mold temperature, and temperature data before the material enters the roller, pressure sensors to collect roller pressure distribution and pressure change trend data, speed sensors to collect material conveying speed and extrusion speed, thickness measurement sensors to monitor the thickness of the composite material to ensure the uniformity of the extruded material, infrared sensors to monitor the sealing tightness and bubbling at the edge, and tension sensors to monitor the tension of the material during the conveying process.

[0022] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0023] 1. The present invention collects the operating data of the multi-layer co-extrusion laminating machine in real time by constructing a sensor cluster, can monitor the key parameters in the production process in real time, and construct a dynamic model of key indicators by analyzing historical data. An optimization control algorithm is designed based on the model, and production parameters are dynamically adjusted according to real-time data, thereby effectively reducing energy consumption and solving the problem that the prior art cannot dynamically optimize production parameters.

[0024] 2. The present invention greatly improves production efficiency through automated optimization operations. At the same time, the present invention can not only optimize the production process of the multi-layer co-extrusion laminating machine, but also further optimize other equipment such as the cooling mechanism, preheating mechanism, traction mechanism and winding mechanism, and can comprehensively improve the production quality and efficiency of multi-layer composite materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0026] Figure 1 This is a flow chart of the method provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0028] Example 1

[0029] In this embodiment, a multilayer composite material preparation process control optimization method based on big data is provided. In this embodiment, the multilayer composite material has a three-layer structure, which is a surface composite material. The surface film is obtained by combining the BOPP film and the aluminized film using solvent-free composite A and B glue (the surface film can also be a single BOPP film). Then the surface film (composite film) is compounded with the white non-woven fabric by PP cast film to obtain a surface composite material. The middle layer uses PP as the main material and then adds a connector. It is combined with non-woven fabric, paper or plastic sheet by hot pressing with a flat roller or various texture rollers to obtain the middle layer. The inner film can be of various types, which can be a printed BOPP film or a PP aluminized film. At the same time, the inner film is not necessarily required, and it can be present or absent. After the surface composite material, the middle layer and the inner film are prepared, a multi-layer laminating composite process is used to form a multi-layer composite material for product outer packaging in one time.

[0030] In this embodiment, by considering the characteristics of the multi-layer co-extrusion laminating machine used in the multi-layer laminating composite process, the key parameters that need to be monitored are determined, and by installing corresponding sensors on the multi-layer co-extrusion laminating machine, sensor data is collected, and an optimization control algorithm is constructed based on the data collected during production. Then, in the subsequent production process, the production process of the multi-layer co-extrusion laminating machine is regulated according to the real-time data collected by the sensor combined with the constructed optimization control algorithm, thereby realizing process optimization of multi-layer composite materials. Figure 1 The flow chart of the control optimization method in this embodiment is shown. It can be seen from the figure that this embodiment includes the following steps:

[0031] Step 1: First, build a sensor cluster consisting of multiple sensors, install the sensor cluster on the multi-layer co-extrusion laminating machine, collect data when the multi-layer co-extrusion laminating machine is working, and upload the collected data to the back-end processing system.

[0032] Specifically, building a sensor cluster includes:

[0033] 1) After analyzing the key data in the multi-layer lamination process, the key parameters that need to be monitored are determined. The parameters that affect material molding mainly include: temperature, pressure, material conveying speed and extrusion speed, thickness and uniformity of the composite material, sealing tightness and blistering at the edge of the composite material, and tension of the material during conveying.

[0034] 2) According to the above-mentioned main parameters that affect material forming, select appropriate sensors. The temperature sensor collects the roller temperature, mold temperature, and material temperature data before entering the roller; the pressure sensor collects the pressure distribution and pressure change trend data of the roller; the speed sensor collects the material conveying speed and extrusion speed; the thickness measurement sensor monitors the thickness of the composite material to ensure the uniformity of the extruded material; the infrared sensor monitors the sealing tightness and blistering at the edge; the tension sensor monitors the tension of the material during the conveying process.

[0035] 3) After selecting the sensor, install it at key locations of the laminating machine, such as the pressure roller, mold, material inlet, outlet, etc.

[0036] 4) The data collected by the sensor is transmitted to the network end in real time through the Internet of Things (IoT) interface. The network end integrates data from multiple sources (temperature sensors, pressure sensors, speed sensors, etc.) to achieve accurate data synchronization and send the synchronized data to the back-end processing system.

[0037] Step 2: After receiving the data from the sensor cluster, the backend processing system first performs denoising, completion, and standardization on the data to ensure data quality. The processed data is then aligned with the timestamp, mapped to a unified coordinate grid, and integrated and constructed into a sensor history database.

[0038] Specifically, data denoising, completion, and standardization can include:

[0039] First, use the window sliding average to smooth short-term fluctuations and perform sliding average filtering on the time series data. Use wavelet decomposition to remove high-frequency noise from the instantaneous jitter signal of the tension sensor and retain the low-frequency useful signal. If a data point exceeds the mean ±3 times the standard deviation range, it is considered an outlier and removed.

[0040] The denoised data is then repaired and supplemented using linear interpolation to repair missing data caused by temporary sensor failure or transmission loss.

[0041] Finally, Z-Score standardization is used to standardize the data, so that the sensor data after denoising, completion and standardization can be directly used for model training and optimization control.

[0042] Step 3: Analyze the data in the sensor history database. By analyzing the data in the history database, the three key indicators that have the greatest impact on the composite material are obtained, namely: temperature change, pressure distribution, and membrane thickness evolution. A dynamic model is established based on the coupling relationship between these three key indicators, and an optimized control algorithm is designed based on the constructed key indicator dynamic model.

[0043] Specifically, in order to accurately describe the production process of the multi-layer co-extrusion laminating machine, the dynamic change laws of the three key physical quantities of temperature, pressure and film thickness need to be expressed by mathematical equations. The core of the key indicator dynamic model is to construct a coupled equation group that can reflect the actual production process by combining the data collected during the production process with the material properties. The coupled equation group can specifically include the following contents:

[0044] 1) When the composite material passes through the heating roller, extruder and other components, the temperature will change. At the same time, the temperature distribution will directly affect the fluidity, bonding effect and final product performance of the material. The heat transfer of the material at different positions and at different times after entering the multi-layer co-extrusion laminating machine can be described by equations. It can be described by the partial differential equation shown below:

[0045] ,

[0046] in, is the material density, kg / m 3 ; is the specific heat capacity, J / (kg·K); k is the thermal conductivity, W / (m·K); Q ext is the external heat source, W / m 3 ; v is the flow velocity field of the composite material, m / s; It is the gradient of the temperature field, that is, the rate of change of temperature in space. It is a vector indicating the change of temperature in all directions.

[0047] It should be noted that in this equation, is the energy storage term, which is used to represent the rate of change of thermal energy per unit volume of the composite material over time; is the heat conduction term, which is used to represent the heat transferred by heat conduction; The external heat source term is used to represent the heat input from external equipment such as heating rollers and extruders; The convection term is used to represent the heat migration caused by the extrusion and transmission of materials in the multi-layer co-extrusion laminating machine.

[0048] 2) Composite materials will flow during the lamination process using a multi-layer co-extrusion laminating machine, and the viscoelastic properties of the material will directly affect the pressure distribution and interlayer bonding strength. The pressure distribution of the material during the lamination process of the multi-layer co-extrusion laminating machine can be described by an equation. It can be described by the partial differential equation shown below:

[0049] ,

[0050] in, is the shear rate, , a scalar measure used to describe the rate of a fluid during shear; is a viscosity function related to shear rate, which is used to indicate that viscosity changes according to shear rate. The viscosity function can be represented by a power law model. The specific power law function can be , K is the consistency coefficient, Pa·s; n is the flow index. is the flow velocity field of the composite material, which is a vector function used to describe the flow velocity of the material at each point in space over time. For example, in three-dimensional space, it can be expressed as , Represent the flow velocity along the x, y, and z directions respectively. It is the velocity gradient tensor, which is used to represent the rate of change of velocity in each direction of space and describes how the velocity of the material changes in each direction.

[0051] It should be noted that in this formula The inertia term is used to represent the momentum change caused by the acceleration of the composite material in the multi-layer co-extrusion laminating machine; The pressure gradient term is used to represent the lateral spreading of the composite material caused by the compression of the roller in the multi-layer co-extrusion laminating machine. It has a negative sign in front of it because the negative sign represents the direction of the pressure on the fluid flow, that is, the fluid always flows from the high pressure area to the low pressure area. Therefore, the pressure gradient will push the fluid from the high pressure area to the low pressure area. The purpose of the negative sign is to ensure that the direction of fluid movement is opposite to the direction of the pressure difference. The viscous force term is used to indicate that when the viscosity of the material is high (such as insufficiently heated PP), it flows slowly and requires greater pressure to drive.

[0052] 3) When composite materials are laminated using a multi-layer co-extrusion laminating machine, the thickness of the final product material is determined by the extrusion volume, material flow rate and lamination process, which directly affects the appearance and mechanical properties of the final product. The thickness of the material can be predicted by using equations to predict how the thickness of the material changes with the extrusion speed and pressure. It can be described by the partial differential equation shown below:

[0053] ,

[0054] Where h is the thickness of the material; It is the rate of change of material thickness over time, which is used to reflect how the material changes due to factors such as flow, extrusion and compression during the lamination process. is the Laplace operator, It is the product of material thickness and flow velocity, indicating the amount of material passing through a certain cross-sectional area per unit time. It is the expansion rate of material thickness with flow, indicating the expansion or contraction of material thickness during flow, reflecting how flow velocity and material thickness jointly affect the flow and distribution of materials. The thickness of the material may vary in space due to factors such as pressing and flow. Q extrusion is the extruder flow rate, m³ / s; A is the cross-sectional area of ​​the composite material, m 2 . It is the contribution of material volume to thickness provided by the multi-layer co-extrusion laminating machine per unit time.

[0055] It should be noted that in the above three equations t Indicates time, Represents temperature T relative to time t The rate of change, that is, how the temperature changes at different points in time; is the rate of change of velocity field with time; is the rate at which the material thickness changes with time; in the above formula, The meaning of partial derivative reflects the rate of change of the function along the positive direction of the coordinate axis, which is read as partial. The coupling relationship between the above three equations is temperature-viscosity-flow. The increase in temperature will reduce the viscosity of the material and thus affect the pressure distribution and flow rate. For example, when the heating is insufficient, the viscosity of the material increases, causing the roller to require greater pressure to spread evenly. The change in flow rate will directly change the change in film thickness, and the distribution of pressure will affect the contact tightness of the materials between different layers, thereby affecting the composite strength.

[0056] The three partial differential equations are coupled to form a dynamic model of key indicators, which can quantify the interaction between temperature, pressure and thickness. By combining real-time sensor data, these equations can be solved in real time. Through the optimization algorithm, the results of the real-time solution of the dynamic model of key indicators can predict the future state and find the best control parameters (such as heating power and extrusion speed), ultimately achieving high-quality and low-energy production.

[0057] In this embodiment, the purpose of the optimization control algorithm is to achieve optimal product quality (such as uniform thickness) and minimum energy consumption while meeting production constraints by dynamically adjusting control parameters (such as heating power, extrusion speed, and roller pressure).

[0058] The implementation process of the optimization control algorithm is highly dependent on the predictive ability of the dynamic model of key indicators, because the optimization control algorithm needs to dynamically predict the future state based on the results of the real-time solution of the model, and then make the best decision in advance.

[0059] Specifically, the construction of the optimization control algorithm includes: 1) From the perspective of improving product quality and controlling production costs, in order to achieve the purpose of minimizing film thickness deviation and minimizing energy consumption, an objective function is constructed. In this embodiment, the objective function can be expressed by the following formula:

[0060] ,

[0061] Among them, H is the prediction time domain, that is, the length of the time window for the objective function to predict the future; is a spatial point (x, y) and time The thickness function at is the integral variable, which varies in the range [t, t+H]; h target is the target thickness of the composite material, mm; It is a time-varying control variable, that is, the process parameters that need to be adjusted, which can include the heating power (W), extrusion speed (rpm), roller pressure (N / m²) of the multi-layer co-extrusion laminating machine, etc. is the control variable.

[0062] w is a weight coefficient, which is used to control the trade-off between energy consumption and quality deviation. It can be adjusted according to the actual production situation. The adjustment strategy is that when it is necessary to give priority to reducing energy consumption during production and allow a certain thickness deviation, w is set to a larger value; when it is necessary to give priority to ensuring thickness uniformity during production and allow higher energy consumption, w is set to a smaller value.

[0063] It should be noted that and are all control variable functions, among which, It usually represents the control input or operating parameter at a specific time t, usually for control at a certain moment or stage. Represents a time The changing control variable, which usually appears in the integral form of the objective function, represents the control input over the entire time interval and is used to indicate that the control process is considered within a time interval.

[0064] 2) Set constraints for the objective function based on the actual production situation. In this implementation, the constraints include: physical constraints, which are used to characterize the constraints directly determined by material properties or process requirements; control variable constraints, which are used to characterize the physical limits of various control parameters of the multi-layer co-extrusion laminating machine; and process constraints, which are used to characterize the constraints related to the performance of the finished composite material.

[0065] For example, in this embodiment, the physical constraint conditions include temperature constraint and pressure constraint, wherein the temperature constraint is: T min ≤T(x,y,t)≤T max , the pressure constraint is: P min ≤P(x,y,t)≤P max , the control variable constraint is: min ≤u(t)≤u max , the process constraints are: h min ≤h(t)≤h max .

[0066] Among them, T(x,y,t) is the temperature field, which represents the temperature distribution of the material during the production process; T min It is the minimum temperature constraint, which means the temperature cannot be lower than this value. Temperature lower than this value may result in material properties not meeting the requirements or instability during processing. max The maximum temperature constraint means that the temperature cannot exceed this value. Exceeding this temperature may cause the material to be overheated, damaged, or produce unqualified products. The temperature constraint is to ensure that the temperature of the material during heating or cooling is maintained within a reasonable range during the production process to ensure material performance and processing stability.

[0067] P(x,y,t) is the pressure field, which represents the pressure distribution of the material during the production process. min It is the minimum pressure constraint, which means that the pressure of the material cannot be lower than this value during the production process. Too low pressure may cause uneven material flow or poor pressing effect. max The maximum pressure constraint means that the pressure cannot exceed this value. Excessive pressure may cause equipment damage or excessive material deformation. The pressure constraint is to ensure that the material pressure is maintained within an appropriate range throughout the production process to ensure production stability and product quality.

[0068] u(t) is the control variable, which represents a parameter controlled in the production process. min It is the minimum value constraint of the control variable, indicating that the control parameter cannot be lower than this value. It is usually used to prevent the equipment from operating in an inefficient or unsafe state. max It is the maximum value constraint of the control variable, indicating that the control parameter cannot be higher than this value. It is usually to prevent equipment overload or unstable control process. The control variable constraint is to ensure that all control parameters (such as extrusion speed, pressure control, etc.) are within their physical limits during the production process to avoid equipment damage or improper operation.

[0069] h(t) is the material thickness, which indicates the thickness of the composite material during the production process. min It is the minimum thickness constraint, which means the material thickness cannot be lower than this value. If the thickness is too small, the product strength may be insufficient or fail to meet the use requirements. max The maximum thickness constraint indicates that the thickness of the material cannot exceed this value. If the thickness is too large, it may lead to low production efficiency or substandard products. Process constraints are used to ensure that during the production process, the thickness of the final product remains within an acceptable range to meet the product performance requirements and production capacity.

[0070] Step 4: Based on the real-time data transmitted back by the sensor cluster when the multi-layer co-extrusion laminating machine is working, the predicted value is calculated through the optimization control algorithm, and the predicted value is compared with the real-time data of the sensor. The back-end processing system dynamically adjusts the model parameters according to the comparison results.

[0071] At the same time, according to the comparison results, the heating power, roller pressure and other parameters of the multi-layer co-extrusion laminating machine are dynamically adjusted to find an operation combination that can ensure uniform film thickness and save energy. Based on this operation combination, the production parameters in the process flow are adjusted.

[0072] At the same time, the sensor continues to collect new data. If it is found that the actual thickness still does not meet the standard, a new round of optimization will be started immediately.

[0073] The sensor cluster collects data every Δt, inputs the latest data into the error function, and obtains updated parameters through the gradient descent method. new Substitute key indicators into the dynamic model to generate more accurate predictions. Based on the updated predictions, the optimization algorithm calculates the control instructions to complete the closed-loop control.

[0074] Since the key indicator dynamic model is an idealized model, there are many uncertainties in the actual production process. For example, material parameters may fluctuate due to batch or environmental changes; factors such as the actual temperature distribution of the heating roller and environmental heat dissipation are difficult to measure accurately; and factors such as equipment aging and changes in environmental temperature and humidity are not modeled. Therefore, through real-time sensor data, the model parameters are dynamically calibrated to make the key indicator dynamic model more in line with the actual production status.

[0075] In this embodiment, an error function is constructed to dynamically calibrate the model parameters according to real-time sensor data. The error function sets a set of model parameters θ so that the predicted values ​​of the key indicator dynamic model are as close as possible to the sensor measured values.

[0076] In this embodiment, the error function is shown as follows:

[0077] ,

[0078] Among them, θ is the model parameter, which can include k, η, Q ext etc., dimensionless; is the initial value of the model parameter, N is the total number of samples; is the model prediction value, which means at point (x i ,y i ) and the temperature at time t depend on the model parameters, is the actual measured value, indicating that at point (x i ,y i ) and the actual data of the sensor at time t; λ is the weight of the regularization term, which is used to control the influence of the regularization term on the total error. The above error function is used to dynamically calibrate the model parameters so that the prediction results are as close to the actual measured values ​​as possible. At the same time, the regularization term is used to prevent the model from overfitting, making the final result more accurate.

[0079] The parameter update implemented by the above error function specifically includes: gradually reducing the error by iteratively adjusting the model parameter θ. The parameter update mechanism of J(θ) can be expressed as follows:

[0080] , where θ k+1 is the parameter value after the k+1th iteration; θ kis the parameter value of the current k-th iteration; α is the control parameter used to control the step size of each adjustment; is the gradient of the error function at the current parameter.

[0081] Example 2 In this embodiment, a multi-layer composite material preparation process control optimization system based on big data is disclosed. The system includes a multi-layer co-extrusion laminating machine and a back-end processing device, wherein the multi-layer co-extrusion laminating machine is equipped with a sensor cluster module, and the back-end processing device is used to process the data collected by the sensor cluster and adjust the production parameters of the multi-layer co-extrusion laminating machine according to the results of data processing.

[0082] The control optimization system also includes a data preprocessing module, a data analysis module and an optimization control module.

[0083] Among them, the data preprocessing module is configured to preprocess the data collected by the sensor cluster, align the timestamps of the preprocessed data, map them to a unified coordinate system grid, and integrate and construct a sensor history database.

[0084] Specifically, the data preprocessing module includes: denoising, completion and standardization of the data, in which the window sliding average method is used to perform sliding average filtering on the time series data, and the instantaneous jitter signal of the tension sensor is decomposed by wavelet to remove high-frequency noise and retain low-frequency signals. Through outlier detection, data that exceeds the range of ±3 times the standard deviation of the mean is regarded as an outlier and eliminated; after denoising, the data is repaired and completed, and the linear interpolation method is used to repair the data missing caused by short-term sensor failure or transmission loss; finally, the data is standardized using Z-Score standardization.

[0085] The data analysis module is connected to the data preprocessing module, and is configured to analyze the data in the sensor history database, construct a key indicator dynamic model, and design an optimization control algorithm based on the key indicator dynamic model.

[0086] Specifically, the key indicator dynamic model consists of three composite material influencing factor equations with coupling relationships, including:

[0087] The temperature index equation used to describe the effect of temperature changes on materials is shown below:

[0088] ,

[0089] in, is the material density, kg / m 3 ; is the specific heat capacity, J / (kg·K); k is the thermal conductivity, W / (m·K); Q extis the external heat source, W / m 3 ; v is the flow velocity field of the composite material, m / s; It is the gradient of the temperature field, that is, the rate of change of temperature in space. It is a vector indicating the change of temperature in all directions.

[0090] The pressure index equation used to describe the effect of pressure changes on materials is shown below:

[0091] ,

[0092] in, is the shear rate, , a scalar measure used to describe the rate of a fluid during shear; is a viscosity function related to shear rate, which is used to indicate that viscosity changes according to shear rate. The viscosity function can be represented by a power law model. The specific power law function can be , K is the consistency coefficient, Pa·s; n is the flow index. is the velocity field, which is a vector function that describes the flow velocity of the material at each point in space over time. For example, in three-dimensional space it can be expressed as , Represent the flow velocity along the x, y, and z directions respectively. It is the velocity gradient tensor, which is used to represent the rate of change of velocity in each direction of space and describes how the velocity of the material changes in each direction.

[0093] The equation used to describe the thickness variation of the finished composite material is as follows:

[0094] ,

[0095] Where h is the thickness of the material; It is the rate of change of material thickness over time, which is used to reflect how the material changes due to factors such as flow, extrusion and compression during the lamination process. is the Laplace operator, It is the product of material thickness and flow velocity, indicating the amount of material passing through a certain cross-sectional area per unit time. Q is the expansion rate of material thickness with flow, indicating the expansion or contraction of material thickness during flow, reflecting how flow velocity and material thickness jointly affect material flow and distribution. The thickness of the material may change in space due to factors such as pressing and flow. extrusion is the extruder flow rate, m³ / s; A is the cross-sectional area of ​​the composite material, m 2 . It is the contribution of the material volume provided by the multi-layer co-extrusion laminating machine to the thickness per unit time. In the above three equations, t represents time, It indicates the rate of change of temperature T relative to time t, that is, how the temperature changes at different time points; is the rate of change of velocity field with time; is the rate at which the material thickness changes with time; in the above formula, is the partial derivative.

[0096] The optimization control algorithm includes objective function and constraints, where the objective function is:

[0097] ,

[0098] Among them, H is the prediction time domain, that is, the length of the time window for the objective function to predict the future; is a spatial point (x, y) and time The thickness function at is the integral variable, which varies in the range [t, t+H]; h target is the target thickness of the material, mm; It is a time-varying control variable, that is, the process parameters that need to be adjusted, which can include the heating power (W), extrusion speed (rpm), roller pressure (N / m²) of the multi-layer co-extrusion laminating machine, etc. is the control variable.

[0099] Constraints are set based on production conditions, including physical constraints, which are used to characterize constraints directly determined by material properties or process requirements; control variable constraints, which are used to characterize the physical limits of various control parameters of the multi-layer co-extrusion laminating machine; and process constraints, which are used to characterize constraints related to the performance of finished composite materials.

[0100] The optimization control module is connected to the data analysis module and the sensor cluster module, and is configured to calculate a predicted value based on the real-time data transmitted back by the sensor cluster in combination with the optimization control algorithm, compare the predicted value with the real-time data of the sensor, and dynamically adjust the parameters of the key indicator dynamic model according to the comparison results.

[0101] Specifically, the optimization control module also includes closed-loop control. According to the new data continuously collected by the sensor cluster, the latest data is input into the error function, and the updated parameters are obtained by the gradient descent method. The dynamic model of key indicators is dynamically calibrated by the updated parameters.

[0102] The error function is shown below:

[0103] ,

[0104] Among them, θ is the model parameter, which can include k, η, Q ext etc., dimensionless; is the initial value of the model parameter, N is the total number of samples; is the model prediction value, which means at point (x i ,y i ) and the temperature at time t depend on the model parameters, is the actual measured value, indicating that at point (x i ,y i ) and the actual data of the sensor at time t; λ is the weight of the regularization term, which is used to control the influence of the regularization term on the total error. The above error function is used to dynamically calibrate the model parameters so that the prediction results are as close to the actual measured values ​​as possible. At the same time, the regularization term is used to prevent the model from overfitting, making the final result more accurate.

[0105] By iteratively adjusting the parameter θ, the error is gradually reduced. The parameter update mechanism of J(θ) is expressed as:

[0106] ,

[0107] Among them, θ k+1 is the parameter value after the k+1th iteration; θ k is the parameter value of the current k-th iteration; α is the control parameter used to control the step size of each adjustment; is the gradient of the error function at the current parameter.

[0108] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling and optimizing the preparation process of multilayer composite materials based on big data, characterized in that: The process control optimization method comprises: S1. Install a sensor cluster consisting of multiple sensors on the multi-layer co-extrusion laminating machine to collect data generated during operation, and upload the collected data to the back-end processing equipment for processing; S2, the back-end processing equipment pre-processes the data collected by the sensor cluster, aligns the timestamps of the pre-processed data, maps them to a unified coordinate system grid, and integrates and builds a sensor history database; S3. Analyze the data in the sensor history database, construct a key indicator dynamic model, and obtain an optimization control algorithm based on the key indicator dynamic model; S4, according to the real-time data transmitted back by the sensor cluster, combined with the optimization control algorithm, calculate the predicted value, Compare the predicted value with the real-time sensor data, dynamically adjust the parameters of the key indicator dynamic model according to the comparison results, dynamically adjust the production parameters according to the comparison results, obtain the operation combination, and adjust the production parameters in the process flow based on the operation combination.

2. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 1, characterized in that: The sensor cluster is constructed by the following sub-steps: S11. According to the main factors affecting the molding of multi-layer composite materials, different types of sensors are selected to collect data. The data include: temperature, pressure, material conveying speed and extrusion speed, thickness and uniformity of the composite material, sealing tightness and blistering at the edge of the composite material, and tension of the material during conveying; S12, using a temperature sensor to collect data on the temperature of the pressure roller, the temperature of the mold, and the temperature of the material before it enters the pressure roller, a pressure sensor to collect data on the pressure distribution and pressure change trend of the pressure roller, a speed sensor to collect data on the conveying speed and extrusion speed of the material, a thickness measurement sensor to monitor the thickness of the composite material to ensure the uniformity of the extruded material, an infrared sensor to monitor the sealing tightness and blistering at the edge, and a tension sensor to monitor the tension of the material during the conveying process; S13, installing the different types of sensors at corresponding positions of the multi-layer co-extrusion laminating machine, and the different types of sensors transmit the collected data to the network end in real time through the Internet of Things port, Integrate data from different types of sensors at the network end, synchronize sensor data, and send the synchronized data to the back-end processing device.

3. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 1, characterized in that: The preprocessing includes: denoising, completing and standardizing the data, wherein: The window sliding average method is used to perform sliding average filtering on the time series data. The instantaneous jitter signal of the tension sensor is decomposed by wavelet to remove high-frequency noise and retain low-frequency signals. Through outlier detection, data that exceeds the mean ±3 times the standard deviation is considered as an outlier and removed. After denoising, the data is repaired and supplemented, and linear interpolation is used to repair data missing due to temporary sensor failure or transmission loss; Finally, the data were standardized using Z-Score standardization.

4. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 1, characterized in that: The key indicator dynamic model is composed of three composite material influencing factor equations with coupling relationships, including: The temperature index equation used to describe the effect of temperature changes on materials is shown below: ， in, is the material density, kg / m 3 ; is the specific heat capacity, J / (kg·K); k is the thermal conductivity, W / (m·K); Q ext is the external heat source, W / m 3 ; v is the flow velocity field of the composite material, m / s; is the gradient of the temperature field; The pressure index equation used to describe the effect of pressure changes on materials is shown below: ， Among them, γ' is the shear rate, which is a scalar measure used to describe the rate of fluid during shear process; is the shear rate-dependent viscosity function, which is used to indicate that the viscosity changes according to the shear rate. is the velocity gradient tensor, is the pressure gradient; The equation used to describe the thickness variation of the finished composite material is as follows: ， Where h is the thickness of the material, is the Laplace operator, It is the product of the material thickness and the flow velocity of the composite material, indicating the amount of material passing through a certain cross-sectional area per unit time. Q is the expansion rate of material thickness with flow, indicating the expansion or contraction of material thickness during flow. extrusion is the extruder flow rate, m³ / s; A is the cross-sectional area of ​​the composite material, m 2 ; In the above three equations, t represents time, It indicates the rate of change of temperature T relative to time t, that is, how the temperature changes at different time points; is the rate of change of velocity field with time; is the rate at which the material thickness changes with time; in the above formula, ∂ is the partial derivative.

5. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 4, characterized in that: The viscosity function is represented by a power law model, and the power law model is shown in the following formula: ， Where K is the consistency coefficient, Pa·s; n is the flow index, dimensionless.

6. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 1, characterized in that: The optimization control algorithm includes an objective function and constraints, wherein: The objective function is: ， Among them, H is the prediction time domain; is a spatial point (x, y) and a time The thickness function at is the integral variable, which varies in the range [t, t+H]; h target is the target thickness of the composite material, mm; w is the weight coefficient; is a time-varying control variable; is the control variable; Constraints are set based on production conditions, including physical constraints, which are used to characterize constraints directly determined by material properties or process requirements; control variable constraints, which are used to characterize the physical limits of various control parameters of the multi-layer co-extrusion laminating machine; and process constraints, which are used to characterize constraints related to the performance of finished composite materials.

7. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 1, characterized in that: The step S4 also includes a closed-loop control step, in which the sensor cluster continuously collects new data. The sensor cluster collects data every Δt time, inputs the latest data into the error function, obtains updated parameters through the gradient descent method, and dynamically calibrates the key indicator dynamic model through the updated parameters.

8. The method for controlling and optimizing the preparation process of multi-layer composite materials based on big data according to claim 7, characterized in that: The error function is shown below: ， Among them, θ is a model parameter and is dimensionless; is the initial value of the model parameter, N is the total number of samples; is the model prediction value, which means at point (x i ,y i ) and the temperature at time t depends on the model parameter θ, is the actual measured value, indicating that at point (x i ,y i ) and the actual data of the sensor at time t; λ is the weight of the regularization term, which is used to control the influence of the regularization term on the total error. By iteratively adjusting the parameter θ, the error is gradually reduced. The parameter update mechanism of J(θ) is expressed as: ， Among them, θ k+1 is the parameter value after the k+1th iteration; θ k is the parameter value of the current k-th iteration; α is the control parameter used to control the step size of each adjustment; is the gradient of the error function at the current parameter.

9. A multi-layer composite material preparation process control optimization system based on big data, including a multi-layer co-extrusion laminating machine and back-end processing equipment, characterized in that: The multi-layer co-extrusion laminating machine is equipped with a sensor cluster module, and the back-end processing device is used to process the data collected by the sensor cluster and adjust the production parameters of the multi-layer co-extrusion laminating machine according to the results of the data processing. The control optimization system includes a data preprocessing module, a data analysis module and an optimization control module, wherein: The data preprocessing module is configured to preprocess the data collected by the sensor cluster, align the timestamps of the preprocessed data, map them into a unified coordinate system grid, and integrate and construct a sensor history database; The data analysis module is connected to the data preprocessing module and is configured to analyze the data in the sensor history database, construct a key indicator dynamic model, and design an optimization control algorithm based on the key indicator dynamic model; The optimization control module is connected to the data analysis module and the sensor cluster module, and is configured to calculate a predicted value based on the real-time data transmitted back by the sensor cluster in combination with the optimization control algorithm, compare the predicted value with the real-time data of the sensor, and dynamically adjust the parameters of the key indicator dynamic model according to the comparison results.

10. The multi-layer composite material preparation process control optimization system based on big data according to claim 9, characterized in that: The sensor cluster module is configured to install the different types of sensors at corresponding positions of the multi-layer co-extrusion laminating machine, and the different types of sensors transmit the collected data to the network end in real time through the Internet of Things port, integrate the data of different types of sensors at the network end, synchronize the sensor data, and send the synchronized data to the back-end processing equipment; use temperature sensors to collect roller temperature, mold temperature, and temperature data before the material enters the roller, use pressure sensors to collect roller pressure distribution and pressure change trend data, speed sensors to collect material conveying speed and extrusion speed, thickness measurement sensors to monitor the thickness of the composite material to ensure the uniformity of the extruded material, infrared sensors to monitor the sealing tightness and bubbling at the edge, and tension sensors to monitor the tension of the material during the conveying process.

Images