High-toughness weather-resistant PVC (polyvinyl chloride) plastic sheet and production process

Abstract

The invention is applicable to the technical field of PVC (polyvinyl chloride) sheet production, and provides a high-toughness weather-resistant PVC plastic sheet and a production process, and the process is applied to a production control system of the high-toughness weather-resistant PVC plastic sheet. The system comprises a data acquisition module, a model construction module, a model training module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center and an intelligent mobile terminal. The data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, the memory and the alarm are respectively connected with the processing center; the intelligent mobile terminal is wirelessly connected with the wireless communication module in the range of a wireless network or the Internet; the invention further discloses a high-toughness weather-resistant PVC plastic sheet. Different PVC sheets can be manufactured according to different user requirements, and automatic production can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of PVC sheet production control technology, and in particular to a high-toughness weather-resistant PVC plastic sheet and a production process in the field of artificial intelligence. Background Art

[0002] With the continuous growth of market demand for plastic sheets and the promotion of technological innovation, high-toughness weather-resistant PVC plastic sheets are widely used in construction, wires and cables, packaging materials, and emerging fields such as automotive manufacturing, 3D printing, and medical industries. There are differences in quality standards in different industries. The specific standards are determined according to the application characteristics and needs of the industry. For example: In the construction industry, PVC sheets are often used for doors and windows, pipes and decorative materials. The sheets are required to have good weather resistance, wear resistance, impact resistance, and stable physical and chemical properties. Therefore, its quality standards include tensile strength, elongation at break, impact strength, heat resistance, cold resistance, weather resistance and other indicators of the material to ensure that the sheet can maintain stable performance and a long service life during use; in the electrical industry, PVC sheets are used for the insulation layer of wires and cables, and the sheets are required to have excellent insulation properties, electrical breakdown resistance, and good mechanical properties. Therefore, its quality standards include the insulation resistance, withstand voltage, breakdown strength, tensile strength, elongation at break and other indicators of the material to ensure the safety and reliability of wires and cables; in addition, the automotive industry, packaging industry and other emerging industries such as new energy, aerospace, etc. also have their own requirements for the quality standards of PVC sheets. For example, the automotive industry may pay more attention to the wear resistance, oil resistance and high temperature resistance of the material, while the packaging industry may pay more attention to the transparency, sealing and environmental protection of the material. At the same time, with the continuous advancement of technology and the development of emerging fields, the performance requirements of PVC plastic sheets are also constantly improving, such as higher toughness, better weather resistance and more environmentally friendly production processes. Therefore, the quality standards of high-toughness weather-resistant PVC plastic sheets in different industries are formulated according to specific application requirements and industry characteristics to ensure that PVC sheets can meet specific performance requirements and safety standards during use.

[0003] The traditional production process is to produce a fixed high-toughness weather-resistant PVC plastic sheet, but cannot meet the different performance requirements of different users for high-toughness weather-resistant PVC sheets to meet their personalized quality needs. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a high-toughness weather-resistant PVC plastic sheet and a production process. By setting various functional modules such as a data acquisition module, a model construction module, a model training module, a parameter determination module, and a production application module, and by introducing advanced sensors, machine vision, artificial intelligence and other technologies, the scientific formulation of PVC plastic sheets is automatically achieved, the entire production process is monitored and automatically tested, the detection efficiency and accuracy are improved, and the labor cost of detection is reduced. The high-toughness weather-resistant PVC sheet can be produced according to the different performance requirements of different users to meet their personalized quality requirements.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A high-toughness weather-resistant PVC plastic sheet production process is applied to a high-toughness weather-resistant PVC plastic sheet production control system, the system comprising a data acquisition module, a model construction module, a model training module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal comprises a smart phone, a tablet computer or a smart remote control, which are respectively connected to the wireless network of the wireless communication module within the range of a wireless network or the Internet;

[0007] The wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically connects to a smart phone, a gateway, or a server within an effective network range;

[0008] The alarm device compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory, and automatically sounds an alarm and notifies to adjust the parameters to continue training if the standard is not met; and compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory, and automatically sounds an alarm and notifies to re-adjust the parameters and rework if the standard is not met; and compares the quality information of the PVC plastic sheet with the production quality standard of the PVC sheet stored in the memory, and automatically sounds an alarm and notifies to rework or scrap if the standard is not met;

[0009] The memory is responsible for storing the information of the data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, and the alarm, as well as the storage of the model comprehensive evaluation sub-standard and the PVC sheet production quality standard;

[0010] The processing center is responsible for the information transmission of the data acquisition module, model construction module, model training module, parameter determination module, production application module, wireless communication module, alarm, and memory, and is the hub center of the system. It compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified that it can be tried out; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters to continue training; and compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to re-debug the parameters for rework; and compares the quality information of the PVC plastic sheet with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is transmitted to the alarm and notified to rework or scrap;

[0011] The data acquisition module includes an information acquisition unit, a cleaning data unit, a data enhancement unit, a normalization processing unit, a filtering and denoising unit, and a grayscale conversion unit. The data acquisition unit acquires the types of various PVC sheets, various auxiliary agent information, and normal and abnormal image data of performance parameters, pre-processes them, and transmits them to the model building module.

[0012] The model building module includes a feature extraction unit, a padding input unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, and an output conversion unit, which is responsible for extracting the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets based on the preprocessed data and building a model, and passing it to the model training module;

[0013] The model training module includes a data marking unit, a training simulation unit, a model evaluation unit, and an abnormality recognition unit, which is responsible for using a convolutional neural network to perform model training based on the image features of the PVC plastic sheet to learn the features of distinguishing normal and abnormal images and continuously adjust the model parameters, and pass them to the parameter determination module;

[0014] The parameter determination module includes a fracture toughness unit, a tensile strength unit, an impact toughness unit, a weathering calculation unit, a parameter presetting unit, and a trial production verification unit, which is responsible for matching the presetting PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model, and conducting experiments to obtain the formal PVC sheet production process parameters, and pass them to the production application module;

[0015] The production application module includes a material preparation unit, an extrusion molding unit, a surface cleaning unit, a quality inspection unit, and a slitting and packaging unit, which is responsible for automatically matching the production process parameters through the PVC sheet production equipment according to the trained model to perform material production and production inspection of the PVC sheet to ensure that the PVC sheet meets customer requirements.

[0016] The present invention provides a high-toughness weather-resistant PVC plastic sheet production process, comprising the following steps:

[0017] S10. Before production, the data acquisition module acquires the types of various PVC sheets, various additive information, normal and abnormal image data of performance parameters and pre-processes them to ensure data accuracy, and passes them to the model building module;

[0018] S20, the model building module extracts the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets according to the preprocessed data and builds the model for subsequent model training, and transmits it to the model training module;

[0019] S30, the model training module uses a convolutional neural network to perform model training according to the PVC sheet image features to learn the features of distinguishing normal and abnormal images and continuously adjusts the model parameters to improve the model accuracy, and transmits the model parameters to the parameter determination module;

[0020] S40, the parameter determination module matches the predetermined PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model and conducts experiments to obtain the formal production process parameters, so as to automatically match and apply them in subsequent production, and pass them to the production application module;

[0021] S50, the production application module automatically matches the production process parameters through the PVC sheet production equipment according to the trained model to carry out material production and production testing of the PVC sheet to ensure that the PVC sheet meets customer requirements.

[0022] Further, the step S10 comprises the following steps:

[0023] S11. The information collection unit obtains various production quality data and images of the formula, performance, and process of various high-toughness weather-resistant PVC plastic sheets in the industry database through networking, so as to facilitate subsequent data cleaning and transmit them to the cleaning data unit;

[0024] S12, the data cleaning unit removes duplicate data, removes outliers, and fills missing values ​​to remove duplicate and missing values ​​in the PVC plastic sheet image data to ensure the accuracy of the data, and passes it to the data enhancement unit;

[0025] S13, the data enhancement unit increases the diversity of the PVC plastic sheet image and improves the stability of the model through the data enhancement method of rotation, scaling, flipping and cutting, so as to improve the generalization ability of the model, and transmits it to the normalization processing unit;

[0026] S14, the normalization processing unit obtains the normalized PVC plastic sheet image data according to the image normalization conversion calculation formula "Xn = (X0-Xmin) / Xmax-Xmin), X2 is the normalized image matrix, X0 is the original image matrix, Xmax and Xmin are the maximum value and minimum value in the original image respectively", so as to facilitate subsequent standardization processing and pass it to the filtering and denoising unit;

[0027] S15, the filtering and denoising unit obtains the denoised PVC sheet image according to the median filtering method calculation formula "g(I,j)=Med{g(x,y),(x,y)∈S}, g is the original image, g(I,j) is the pixel point with coordinates in the original image g, g(x,y) is the pixel point with coordinates in the denoised image, S is the domain space of K pixels obtained by the pixel point" and passes it to the grayscale conversion unit;

[0028] S16. The grayscale conversion unit obtains the grayscaled PVC sheet image according to the grayscale calculation formula "f(I,j) = max(R(I,j), G(I,j), B(I,j)), f(I,j) is the grayscale image, R(I,j), G(i,j), B(I,j) are the original images of three colors respectively" for subsequent feature extraction.

[0029] Further, the step S20 comprises the following steps:

[0030] S21, the feature extraction unit extracts the feature information of the physical properties, weather resistance, and appearance quality of the PVC sheet and its corresponding quality anomalies and preventive measures according to the processed image data, so as to facilitate subsequent machine learning, and transmits the information to the filling input unit;

[0031] S22, fill input unit according to the fill size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W -Wi] / 2,P H , P W are the padding sizes in height / width directions, Hi and Wi are the height / width of the input feature map, and K H , K W are the height / width of the convolution kernel, S H , S W Where Ho and Wo are the values ​​of the step length in the height / width direction, respectively. Ho and Wo are the height and width of the output feature map, respectively. The padding data is obtained and input into the model for subsequent data convolution input and passed to the convolution input unit.

[0032] S23, the convolution input unit obtains the convolution input data according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential of the variable m" for subsequent data pooling conversion and passes it to the pooling conversion unit;

[0033] S24, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values ​​in the input window, X is the input feature map, P S The maximum pixel value after pooling is obtained by setting the window size of the pooling operation to the fully connected layer to retain important feature information and pass it to the fully connected layer unit;

[0034] S25, the fully connected layer unit calculates the formula of the fully connected layer according to "y=f(∑(w n *x n )+b), y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, and b is the bias. The output data of the connection layer is obtained and enters the output layer for subsequent output calculation and is passed to the output conversion unit.

[0035] S26. The output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F + 2C) / S + 1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of 0 layers added around the image, and S is the step size" to facilitate subsequent model analysis and training.

[0036] Further, the step S30 comprises the following steps:

[0037] S31, the data labeling unit divides the quality abnormality categories of the PVC plastic sheet into corresponding data sample categories and labels them for subsequent machine learning of the model, and transmits them to the training simulation unit;

[0038] S32, the training simulation unit trains the machine learning model using the extracted feature information, and identifies whether the PVC sheet inspection data has quality abnormalities and its abnormality category for subsequent model evaluation, and transmits it to the model evaluation unit;

[0039] S33. The model evaluation unit obtains the comprehensive evaluation score after model training according to the model comprehensive evaluation score calculation formula "F = 2*(Pr*Re) / (Pr+Re), F is the model comprehensive evaluation score, Pr is the precision rate, and Re is the recall rate" to ensure the accuracy of model verification and transmit it to the processing center;

[0040] S34, the processing center compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified to be ready for trial use; if it does not meet the standard, the alarm is transmitted to the alarm and the parameters are notified to continue training;

[0041] S35, the abnormality recognition unit inputs the trained image into the trained convolutional neural network model to match it with the real-time acquired PVC sheet monitoring image and confirm its abnormality category.

[0042] Further, the step S40 comprises the following steps:

[0043] S41, fracture toughness unit is calculated according to the fracture toughness formula of PVC sheet "K = M*C / I*sqrt(π*a), K is the fracture toughness of PVC sheet M is the bending moment of the sheet at the stress point (N·m), C is the distance of the sheet cross section (m), and I is the moment of inertia of the sheet cross section (m 4 ), a is the sheet crack length (m)” to obtain the fracture toughness value of the PVC sheet for subsequent sheet quality testing and transfer to the tensile strength unit;

[0044] S42, tensile strength unit is calculated according to the tensile strength formula of PVC sheet "T S =P / (b*d),T S is the sheet tensile strength (Pa), P is the maximum tensile load when the sheet sample breaks (N), b is the sheet sample width (m), and d is the sheet sample thickness (m)” to obtain the PVC sheet tensile strength for subsequent sheet quality testing and transfer to the impact toughness unit;

[0045] S43, impact toughness unit is calculated according to the PVC sheet impact toughness formula "It = W / S, It is the sheet impact toughness (MJ / m 2 ), W is the work consumed when the sheet sample is broken (MJ), S is the cross-sectional area of ​​the notch of the sheet sample (m 2 )” to obtain the impact toughness of the PVC sheet for subsequent sheet quality testing and pass it to the weathering calculation unit;

[0046] S44, the weather resistance calculation unit obtains the weather resistance value of the PVC sheet according to the PVC sheet weather resistance index calculation formula "w = T1 / T2*100, w is the weather resistance index of the PVC sheet, T1 is the exposure time of the sheet sample (h), and T2 is the actual use time of the sheet (h)" for subsequent sheet quality inspection, and transmits it to the material parameter presetting unit;

[0047] S45, the parameter presetting unit obtains the corresponding PVC sheet formula and production process parameters in the model according to the PVC sheet abnormality category and the industry database as the pre-set production process parameters for subsequent trial production verification, and transmits them to the trial production verification unit;

[0048] S46, the trial production verification unit performs material production and production tests according to the predetermined material formula and the corresponding production process parameters to obtain high-toughness weather-resistant PVC plastic sheets and their corresponding quality data, and transmits them to the processing center;

[0049] S47, the processing center compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to re-debug the parameters for rework.

[0050] Further, the step S50 comprises the following steps:

[0051] S51, the material preparation unit fully stirs the prepared PVC resin and various additives according to the PVC sheet material formula through a mixer according to program instructions and predetermined operating parameters to ensure that the various components are evenly mixed, and transfers them to the extrusion molding unit;

[0052] S52, the extrusion molding unit extrude the PVC sheet through a conical twin-screw extruder and a three-roller shaping machine according to program instructions and predetermined operating parameters, cools and solidifies the sheet through a cooling device to ensure that the sheet is uniform and flat, and transfers it to a surface cleaning unit;

[0053] S53, the surface cleaning unit performs surface grinding and cleaning treatment on the cooled and shaped PVC sheet through the grinding and polishing equipment according to the control command to ensure that the surface is smooth and the color is uniform, and then transmits it to the quality inspection unit;

[0054] S54, the quality inspection unit detects the appearance size, high toughness, weather resistance and other quality information of the PVC sheet through a high-definition camera and PVC sheet inspection equipment according to program instructions to meet the needs of different users and transmits it to the processing center;

[0055] S55. The processing center compares the quality information of the PVC plastic sheet with the PVC sheet production quality standard stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is transmitted to the alarm and notified to rework or scrap.

[0056] S56, the slitting and packaging performance testing unit cuts the PVC sheets into required lengths and widths by shearing machines according to program instructions and packages them to protect the sheets from contamination and damage and to facilitate transportation and storage.

[0057] A high-toughness weather-resistant PVC plastic sheet production control system provided by the present invention also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and each functional module implements the steps of any one of the above-mentioned high-toughness weather-resistant PVC plastic sheet production processes when executing the computer program; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, the steps of any one of the above-mentioned high-toughness weather-resistant PVC plastic sheet production processes are implemented; and also includes a PVC sheet production control device, which is implemented by the above-mentioned high-toughness weather-resistant PVC plastic sheet production process.

[0058] The present invention also provides a high-toughness weather-resistant PVC plastic sheet, which is composed of 100 parts of PVC resin, 1-2 parts of toughening agent, 4-6 parts of heat stabilizer, 0.5-1 part of antioxidant, 0.3-0.8 part of ultraviolet absorber, 50-250 parts of filler, 1-3 parts of lubricant, 0.2-2 parts of plasticizer, 0.1-0.8 parts of titanium dioxide, 0.1-0.5 parts of foaming agent, 0.1-0.6 parts of coupling agent, 0.2-1 parts of brightener, 0.3-0.6 parts of foaming regulator and 0.1-0.8 parts of color powder, and is achieved by using the above-mentioned high-toughness weather-resistant PVC plastic sheet production process.

[0059] The beneficial effects of the present invention compared with the prior art are as follows:

[0060] By setting up various functional modules such as data acquisition module, model construction module, model training module, parameter determination module, production application module, etc., and by introducing advanced sensors, machine vision, artificial intelligence and other technologies, it is possible to produce high-toughness weather-resistant PVC sheets according to the different performance requirements of different users to meet their personalized quality requirements, realize automatic screening of the formula of high-toughness weather-resistant PVC plastic sheets, and achieve timely monitoring and automatic detection of the entire production process, thereby improving production efficiency and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or exemplary technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 It is a schematic diagram of the system module of the present invention;

[0063] Figure 2 It is a schematic diagram of a data acquisition module of the present invention;

[0064] Figure 3 It is a schematic diagram of the model construction module of the present invention;

[0065] Figure 4 This is a schematic diagram of a model training module of the present invention;

[0066] Figure 5 It is a schematic diagram of a parameter determination module of the present invention;

[0067] Figure 6 It is a schematic diagram of the production application module of the present invention;

[0068] Figure 7 It is a schematic diagram of the process control program of the present invention;

[0069] Figure 8 This is a schematic diagram of step S10 in the process flow of the present invention;

[0070] Fig. 9 This is a schematic diagram of step S20 in the process flow of the present invention;

[0071] Fig.10 This is a schematic diagram of step S30 in the process flow of the present invention;

[0072] Fig.11 This is a schematic diagram of step S40 in the process flow of the present invention;

[0073] Fig.12 It is a schematic diagram of the process of step S50 in the process flow of the present invention. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0075] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments:

[0076] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0077] It should be noted that when a module is referred to as being "disposed on" another module, it can be directly on the other module or indirectly on the other module. When a module is referred to as being "connected to" another module, it can be directly connected to the other module or indirectly connected to the other module.

[0078] In the description of this application, "multiple" means two or more, unless otherwise clearly defined. "Several" means one or more, unless otherwise clearly defined; "high-toughness weather-resistant PVC plastic sheet" in this application is referred to as "PVC plastic sheet" or "PVC sheet" or "sheet", all of which refer to the same extruded sheet.

[0079] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0080] See also Figure 1 As shown, the present invention provides a high-toughness weather-resistant PVC plastic sheet production process, which is applied to a high-toughness weather-resistant PVC plastic sheet production control system, the system includes a data acquisition module, a model construction module, a model training module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal includes a smart phone, a tablet computer or a smart remote control, which are respectively connected to the wireless communication module wireless network within the range of a wireless network or the Internet.

[0081] The wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals, and is automatically networked with a smart phone, a gateway, or a server within an effective network range, so that various types of production and testing equipment in the production site are effectively connected through a wireless network or a wired network to achieve effective data transmission, thereby realizing the automation of production and testing. The wireless signals include MQTT, CoAP, HTTP, REST API, Zigbee, LoRaWAN, NB-IoT, Bluetooth and other Internet of Things signals; the specific application of the wireless communication module in the Internet of Things system will not be elaborated on in detail here.

[0082] The alarm compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory. If the standard is not met, a sound alarm is automatically issued and a notice is given to adjust the parameters to continue training; and the quality information of the PVC sheet is compared with the production quality standard of the PVC sheet stored in the memory. If the standard is not met, a sound alarm is automatically issued and a notice is given to re-debug the parameters for rework; and the quality information of the PVC plastic sheet is compared with the production quality standard of the PVC sheet stored in the memory. If the standard is not met, a sound alarm is automatically issued and a notice is given to rework or scrap; the PVC sheet production quality standard is only formulated for each industry, and the PVC sheet production quality standards of different industries are different. There are also slight differences in the production quality standards of different PVC sheets in some of the same industries, and they are not exactly the same.

[0083] The memory is responsible for storing information of a data acquisition module, a model construction module, a model training module, a parameter determination module, a production application module, a wireless communication module, and an alarm, as well as storing the model comprehensive evaluation sub-standard and the PVC sheet production quality standard.

[0084] The processing center is responsible for the information transmission of the data acquisition module, model construction module, model training module, parameter determination module, production application module, wireless communication module, alarm, and memory, and is the hub center of the system. The actual comprehensive evaluation score of the model is compared with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified that it can be tried out; if it does not meet the standard, it is passed to the alarm and notified to adjust the parameters to continue training; and the quality information of the PVC sheet is compared with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is passed to the alarm and notified to re-debug the parameters for rework; and the quality information of the PVC plastic sheet is compared with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is passed to the alarm and notified to rework or scrap.

[0085] See also Figure 2As shown, the data acquisition module includes an information acquisition unit, a cleaning data unit, a data enhancement unit, a normalization processing unit, a filtering and denoising unit, and a grayscale conversion unit. The data acquisition device acquires the normal and abnormal image data of various PVC sheet types, various auxiliary agent information, and performance parameters, pre-processes them, and transmits them to the model building module.

[0086] Furthermore, the information acquisition unit obtains various production quality data and images of the formula, performance, and process of various high-toughness weather-resistant PVC plastic sheets in the industry database through networking, and transmits them to the cleaning data unit; the cleaning data unit removes duplicate data, removes outliers, and fills missing values ​​to remove duplicate and missing values ​​in the PVC plastic sheet image data, and transmits them to the data enhancement unit; the data enhancement unit increases the diversity of the PVC plastic sheet image and improves the stability of the model through data enhancement methods such as rotation, scaling, flipping, and cropping, and transmits them to the normalization processing unit; the normalization processing unit performs image processing according to the image. The normalized PVC plastic sheet image data is obtained according to the normalization conversion calculation formula "Xn=(X0-Xmin) / Xmax-Xmin)" and passed to the filtering and denoising unit; the filtering and denoising unit obtains the denoised PVC sheet image according to the median filtering method calculation formula "g(I,j)=Med{g(x,y),(x,y)∈S}" and passes it to the grayscale conversion unit; the grayscale conversion unit obtains the grayscale PVC sheet image according to the grayscale calculation formula "f(I,j)=max(R(I,j),G(I,j),B(I,j))" for subsequent feature information extraction.

[0087] See also Figure 3 As shown, the model building module includes a feature extraction unit, a padding input unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, and an output conversion unit, which is responsible for extracting the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets based on the preprocessed data and building a model, and passing it to the model training module.

[0088] Furthermore, the feature extraction unit extracts the feature information of the physical properties, weather resistance, and appearance quality of the PVC sheet and the corresponding quality abnormalities and preventive measures according to the processed image data, and transmits them to the filling input unit; the filling input unit calculates the filling size according to the filling size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W-Wi] / 2" to obtain the padding data and input it into the model, and pass it to the convolution input unit; the convolution input unit obtains the convolution input data according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm" and passes it to the pooling conversion unit; the pooling conversion unit obtains the convolution input data according to the maximum pooling calculation formula "Z(i, j) = max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ])” obtains the maximum pixel value after pooling and enters the fully connected layer, and passes it to the fully connected layer unit; the fully connected layer unit calculates the value according to the fully connected layer calculation formula “y=f(∑(w n *x n )+b)” obtains the connection layer output data and enters the output layer, and passes it to the output conversion unit; the output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N=(P-F+2C) / S+1" for subsequent model analysis and training.

[0089] See also Figure 4 As shown, the model training module includes a data labeling unit, a training simulation unit, a model evaluation unit, and an abnormality recognition unit, which is responsible for using a convolutional neural network to perform model training based on the image features of PVC plastic sheets to learn the features that distinguish normal and abnormal images and continuously adjust the model parameters, and pass them to the parameter determination module.

[0090] Furthermore, the data labeling unit divides the data samples into corresponding categories according to the quality anomaly categories of the PVC plastic sheets, labels them, and transmits them to the training simulation unit; the training simulation unit trains the machine learning model using the extracted feature information, identifies whether the PVC sheet detection data has quality anomalies and its anomaly categories, and transmits them to the model evaluation unit; the model evaluation unit obtains the comprehensive evaluation score after model training according to the model comprehensive evaluation score calculation formula "F=2*(Pr*Re) / (Pr+Re)", and transmits it to the processing center; the anomaly recognition unit inputs the trained image into the trained convolutional neural network model to match it with the real-time acquired PVC sheet monitoring image and confirm its anomaly category.

[0091] See also Figure 5 As shown, the parameter determination module includes a fracture toughness unit, a tensile strength unit, an impact toughness unit, a weathering calculation unit, a parameter presetting unit, and a trial production verification unit. It is responsible for matching the predetermined PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model, and conducting experiments to obtain the formal PVC sheet production process parameters, and pass them to the production application module.

[0092] Further, the fracture toughness unit obtains the fracture toughness value of the plastic sheet according to the fracture toughness calculation formula of the PVC sheet "K = M*C / I*sqrt(π*a)", and transmits it to the tensile strength unit; the tensile strength unit obtains the fracture toughness value of the plastic sheet according to the tensile strength calculation formula of the PVC sheet "T S =P / (b*d)" ​​to obtain the tensile strength of the PVC sheet and pass it to the impact toughness unit; the impact toughness unit obtains the impact toughness of the PVC sheet according to the PVC sheet impact toughness calculation formula "It=W / S", and passes it to the weather resistance calculation unit; the weather resistance calculation unit obtains the weather resistance value of the PVC sheet according to the PVC sheet weather resistance index calculation formula "w=T1 / T2*100", and passes it to the material parameter presetting unit; the parameter presetting unit obtains the corresponding PVC sheet formula and production process parameters in the model according to the PVC sheet abnormality category and the industry database as the predetermined production process parameters, and passes them to the trial production verification unit; the trial production verification unit performs material production and production tests according to the predetermined material formula and its corresponding production process parameters to obtain high-toughness weather-resistant PVC plastic sheets and their corresponding quality data, and passes them to the processing center.

[0093] See also Figure 6 As shown, the production application module includes a material preparation unit, an extrusion molding unit, a surface cleaning unit, a quality inspection unit, and a slitting and packaging unit, which are responsible for automatically matching the production process parameters through the PVC sheet production equipment according to the trained model to perform material production and production inspection of the PVC sheet to ensure that the PVC sheet meets customer requirements.

[0094] Furthermore, the material preparation unit fully mixes the prepared PVC resin and various additives according to the PVC sheet formula through a mixer according to program instructions and predetermined operating parameters, and passes them to the extrusion molding unit; the extrusion molding unit extrude the PVC sheet through a conical twin-screw extruder and a three-roller shaping machine according to program instructions and predetermined operating parameters, cools and solidifies the PVC sheet through a cooling device, and passes it to the surface cleaning unit; the surface cleaning unit grinds and cleans the surface of the cooled and solidified PVC sheet through a grinding and polishing device according to control commands, and passes it to the quality inspection unit; the quality inspection unit detects the appearance, size, high toughness, and weather resistance of the PVC sheet through a high-definition camera and a PVC sheet inspection device according to program instructions, and transmits it to the processing center; the slitting and packaging unit cuts the PVC sheet into the required length and width through a shearing machine according to program instructions and packages it to protect the sheet from pollution and damage and facilitate transportation and storage.

[0095] System operation working principle:

[0096] Before production, the data acquisition module obtains the types of various PVC sheets, various additive information, normal and abnormal image data of performance parameters and preprocesses them, and passes them to the model building module; the model building module extracts the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets based on the preprocessed data and builds the model, and passes it to the model training module; then the model training module uses a convolutional neural network to train the model based on the image features of PVC plastic sheets to learn to distinguish the features of normal and abnormal images and continuously adjust the model parameters, and pass them to the parameter determination module; the parameter determination module matches the predetermined PVC sheet production process parameters with the trained model according to the PVC sheet abnormality category and conducts experiments to obtain the formal PVC sheet production process parameters, and passes them to the production application module; then the production application module automatically matches the production process parameters through the PVC sheet production equipment according to the trained model to carry out material production and production testing of PVC sheets to ensure that the PVC sheets meet customer requirements.

[0097] When operators or managers are outdoors or away from home, they can use smartphones to automatically connect to the wireless network or the Internet through wireless communication modules, thereby combining with smartphones, the Internet and Internet of Things technologies. Through mobile phone APP, they can remotely monitor the production and inspection of PVC sheets in real time, thereby improving production management efficiency and reducing production management costs. By connecting to sensors and control devices embedded in various key nodes of the industrial system during the production process, industrial application data can be collected, and various parameters such as screw diameter and aspect ratio, screw speed and direction, drive power, heating power, temperature, etc. in the production equipment can be monitored and recorded in real time, providing original information for the Internet of Things system. The collected data is transmitted between different levels of the system through wired or wireless network networks. The data is processed and analyzed on cloud or edge computing devices to provide decision support for managers, optimize production processes, improve production efficiency, reduce manufacturing costs and improve the quality of PVC plastic sheets, so as to realize industrial intelligence and efficiency.

[0098] See also Figure 7 As shown, the present invention provides a high-toughness weather-resistant PVC plastic sheet production process, comprising the following steps:

[0099] S10. Before production, the data acquisition module acquires the types of various PVC sheets, various additive information, normal and abnormal image data of performance parameters and pre-processes them to ensure data accuracy, and passes them to the model building module;

[0100] See also Figure 8 As shown, the step S10 includes the following steps:

[0101] S11. The information collection unit obtains various production quality data and images of the formula, performance, and process of various high-toughness weather-resistant PVC plastic sheets in the industry database through networking, so as to facilitate subsequent data cleaning and transmit them to the cleaning data unit;

[0102] It is further explained that the formula, performance, various production process parameters of various PVC sheets, as well as the quality information of the images or videos of the corresponding sheets and the data of the use effects of users in different industries are collected from the domestic and foreign PVC sheet databases through the data collector and its software for classification and collection; the PVC plastic sheet data includes but is not limited to the historical data of different users' evaluation of the use effects of different such PVC plastic sheets, and also includes the normal and abnormal quality information of similar PVC sheets and the historical data of the use effects of different users obtained from third-party sharing platforms such as the Internet, social media, professional testing institutions, processing trade platforms, or public data sets, so as to obtain high-quality, diverse and rich historical data of similar PVC sheets, specifically including the historical data of the formula, performance parameters, process parameters, test data and image quality information of PVC sheets; the formula includes the proportion, mechanism of action, influence on PVC performance and mutual compatibility of vinyl chloride monomer and additives such as stabilizers, plasticizers, toughening agents and anti-aging agents; the performance parameters include physical, chemical, flammability, environmental protection, wear resistance, weather resistance, high toughness and other performance parameters; the process parameters include production process flow, equipment control parameters and detection parameters.

[0103] S12, the data cleaning unit removes duplicate data, removes outliers, and fills missing values ​​to remove duplicate and missing values ​​in the PVC plastic sheet image data to ensure the accuracy of the data, and passes it to the data enhancement unit;

[0104] It is further explained that a deduplication algorithm is used to delete duplicate records in the data set. Since the acquired images contain noise and outliers due to sensor errors or data transmission errors, filters are used to smooth the data for denoising, and statistical methods are used to detect and repair or delete outliers or replace them with reasonable values. Data is missing due to sensor failure, data loss, etc. Code is written to detect each feature in the data set to determine the missing values ​​and identify the missing value pattern. According to the number and impact of the missing values, code is written to select samples or variables containing missing values ​​to fill or delete. For time series data, forward filling or backward filling is used to fill the missing values. The processing effect is verified by comparing indicators such as data quality before and after processing, accuracy and reliability of the model. If the processing effect is not good, the processing method is reselected or the data is re-cleaned until the best effect is achieved, so as to remove duplicate, erroneous, and invalid data to effectively process missing values ​​for subsequent model construction.

[0105] S13, the data enhancement unit increases the diversity of the PVC plastic sheet image and improves the stability of the model through the data enhancement method of rotation, scaling, flipping and cutting, so as to improve the generalization ability of the model, and transmits it to the normalization processing unit;

[0106] It is further explained that after rotating the cleaned PVC plastic sheet image data by a certain angle through the PVC plastic sheet image rotation, multiple pixels will be generated and correspond to the same pixel after rotation, resulting in pixel loss in the rotated PVC plastic sheet image. Therefore, a mapping is constructed by reverse thinking to map the pixel coordinates after rotation to the pixel coordinates of the original PVC plastic sheet image, so that each pixel after rotation can be guaranteed to have a pixel value; the neighborhood interpolation algorithm is used to copy and map each original pixel in the rotated high-toughness weather-resistant PVC plastic sheet image intactly to the corresponding four pixels after expansion, thereby retaining all information of the original PVC plastic sheet image; the PVC plastic sheet image with abnormal orientation after scaling is flipped 180 degrees around the central axis or symmetry axis of the original image to ensure the orientation consistency of the PVC plastic sheet image; the flipped PVC plastic sheet image is cropped to ensure image integrity and clarity.

[0107] S14, the normalization processing unit obtains the normalized PVC plastic sheet image data according to the image normalization conversion calculation formula "Xn = (X0-Xmin) / Xmax-Xmin), X2 is the normalized image matrix, X0 is the original image matrix, Xmax and Xmin are the maximum value and minimum value in the original image respectively", so as to facilitate subsequent standardization processing and pass it to the filtering and denoising unit;

[0108] To further illustrate, the pixel values ​​of the PVC sheet image are normalized from the range of 0-255 to between 0-1, and a set of parameters are obtained using the invariant moments of the PVC sheet image so that it can eliminate the influence of other transformation functions on the transformation of the PVC sheet image, that is, it is converted into a unique standard form to resist affine transformation, so that the PVC sheet image can resist the attack of geometric transformation, and the invariants in the PVC sheet image can be found, so that these PVC sheet images are the same or the same series, which can reduce the dynamic range of the PVC sheet image and help further processing and analysis; the enhanced PVC sheet image is normalized and converted into standardized PVC sheet image data for model establishment and training.

[0109] S15, the filtering and denoising unit obtains the denoised PVC sheet image according to the median filtering method calculation formula "g(I,j)=Med{g(x,y),(x,y)∈S}, g is the original image, g(I,j) is the pixel point with coordinates in the original image g, g(x,y) is the pixel point with coordinates in the denoised image, S is the domain space of K pixels obtained by the pixel point" and passes it to the grayscale conversion unit;

[0110] Further explanation: the normalized sheet image is converted according to the image standardization calculation formula Obtain standardized PVC sheet image data, where X2 is the standardized image matrix, X1 is the original image matrix, μ is the image feature average, σ1 is the standard deviation of all pixels in the image, and N is the number of pixels in the image. This transforms it into multiple copies of a fixed standard form, so that the image data is converted to a unified interval; scale the image pixel values ​​to the range of [0,1] by dividing all pixel values ​​by 255, so that the pixel values ​​of different images can be comparable, which is convenient for subsequent image data grayscale processing.

[0111] S16. The grayscale conversion unit obtains the grayscaled PVC sheet image according to the grayscale calculation formula "f(I,j) = max(R(I,j), G(I,j), B(I,j)), f(I,j) is the grayscale image, R(I,j), G(i,j), B(I,j) are the original images of three colors respectively" for subsequent feature information extraction.

[0112] It is further explained that the grayscale image is obtained through the grayscale calculation formula, the sampling value in the input signal is checked to determine whether it represents the signal itself, and the values ​​in the window are sorted by using an observation window composed of an odd number of samples, the middle value is taken as the output, the earliest value is discarded, and a new sample is obtained. The above calculation process is repeated to remove noise in the image or other signals, so as to subsequently extract the key features of the PVC sheet image data, including physical performance characteristics such as tensile strength, elongation at break, and impact strength, weather resistance characteristics such as aging resistance, UV resistance, and temperature change resistance, surface quality characteristics such as smoothness, flatness, presence of cracks, bubbles, and spots, color characteristics such as color uniformity and color difference, texture characteristics such as roughness and fineness, and appearance shape characteristics such as size and shape regularity of plastic sheets.

[0113] S20, the model building module extracts the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets according to the preprocessed data and builds the model for subsequent model training, and transmits it to the model training module;

[0114] See also Fig. 9 As shown, the step S20 includes the following steps:

[0115] S21, the feature extraction unit extracts the feature information of the physical properties, weather resistance, and appearance quality of the PVC sheet and its corresponding quality anomalies and preventive measures according to the processed image data, so as to facilitate subsequent machine learning, and transmits the information to the filling input unit;

[0116] Further explanation: various quality abnormalities of PVC sheets are classified as follows: 1) Rough and dull surface: take measures such as "appropriately adjust the amount of material stored between the calendering rollers, improve the mixing and plasticizing effect of the material, appropriately increase the mixing and calendering temperature, adjust the calendering roller speed ratio, increase the amount of lubricant, repair or replace the calendering roller in time, reduce the amount of recycled materials or replace high-quality raw materials" to prevent; 2) There are bubbles on the surface: take measures such as "strengthen the kneading and drying of the raw materials, appropriately reduce the calendering temperature, shorten the plasticizing time" to prevent; 3) There are precipitates on the surface: take measures such as "reduce the amount of lubricant or adjust the lubricant type, appropriately adjust the formula design to improve the compatibility of the additives and resins" to prevent; 4) Color difference: take measures such as "strictly control the quality of raw materials, processing parameters, add appropriate additives to and strict color difference detection" and other measures to prevent; 5) Brittleness: Take measures such as "adding toughening agents, preventing ultraviolet radiation, controlling ambient temperature, using high-quality PVC resins, optimizing processing technology, adding stabilizers" to prevent; 6) Insufficient toughness: Take measures such as "strengthening the mixing and plasticization of materials, appropriately increasing the calendering temperature, replacing new raw materials or reducing the amount of recycled materials, controlling the amount of fillers added, and reasonably selecting and adding impact modifiers" to improve the high toughness of PVC sheets; 7) Insufficient weather resistance: Take measures such as "selecting PVC resins with good weather resistance, optimizing the formula design to improve the material's aging resistance, strengthening quality control in the production process to ensure that the sheets meet weather resistance requirements, adding weather resistance additives, and performing surface treatment" to improve the weather resistance of PVC sheets.

[0117] S22, fill input unit according to the fill size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W -Wi] / 2,P H , P W are the padding sizes in height / width directions, Hi and Wi are the height / width of the input feature map, and K H , K W are the height / width of the convolution kernel, S H , S WWhere Ho and Wo are the values ​​of the step length in the height / width direction, respectively. Ho and Wo are the height and width of the output feature map, respectively. The padding data is obtained and input into the model for subsequent data convolution input and passed to the convolution input unit.

[0118] It is further explained that after the image is standardized, the PVC sheet data is used to construct a convolutional neural network model containing an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer, and then the calculated padding data is input. Since the convolution kernel in the convolution layer contains a weight coefficient, and the pooling layer does not contain a weight coefficient, the pooling layer is not an independent layer. The convolution layer is used to extract local features of the image, the pooling layer is used to reduce the dimension of the feature map, and the fully connected layer is used to integrate features and classify them; the amount of padding is determined by the size of the convolution kernel, the step size, and the padding size. In order to keep the height and width of the input and output images the same, or to reduce the size quickly in continuous convolution operations, the amount is usually set to the convolution kernel size minus 1.

[0119] S23, the convolution input unit obtains the convolution input data according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential of the variable m" for subsequent data pooling conversion and passes it to the pooling conversion unit;

[0120] Further explanation: the integral differential element dm is the "width" or "increment" when integrating each infinitesimal interval of the variable m. By accumulating the function values ​​on these infinitesimal intervals (i.e. x(m)y(tm)), the cumulative effect on the entire definition domain, i.e. z(t), is obtained. dm is the integral differential element of the variable m, i.e. the infinitesimal quantity in the integration process; then the convolution calculation is performed to obtain the convolution value, which enters the convolution layer and is activated as the feature value output by the convolution layer or the fully connected layer; the function activation is calculated by the ReLU function. The formula "f(x)=max(0,x+Y)" is used to obtain the activation function value and enter the pooling layer, where f(x) is the activated function, x is the eigenvalue of the output of the convolutional layer or the fully connected layer, and Y is a random variable. When the input x is greater than 0, the output is x, and when the input x is less than or equal to 0, the output is 0. When x=0, it is not differentiable, that is, when the input is a positive number, the original value is maintained, and when the input is a negative number, the output is 0; but the ReLU activation function is used after the convolutional layer to increase the nonlinearity of the network and promote the model to learn complex patterns.

[0121] S24, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values ​​in the input window, X is the input feature map, P S The maximum pixel value after pooling is obtained by setting the window size of the pooling operation to the fully connected layer to retain important feature information and pass it to the fully connected layer unit;

[0122] Further explanation, before the maximum pooling, the average pooling calculation formula "Z(i,j)=mean(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ])" obtains the average value of all values ​​in each area as the output, which can retain more information in the feature map, help improve the accuracy of the model, retain more detailed information, and be used in the deeper layers of the network to ensure the integrity of the information. In the formula, Z(i,j) is a pixel value in the output feature map after pooling, and mean is the average value of all pixel values ​​in the input window; according to the maximum pooling calculation formula, the maximum value is selected from each area of ​​the input feature map as the output, retaining the most significant features in the feature map, reducing the size of the feature map, and losing some useful information. Since the maximum value of each area is focused on, the grain size characteristics are retained, and features with better classification recognition are selected.

[0123] S25, the fully connected layer unit calculates the formula of the fully connected layer according to "y=f(∑(w n *x n )+b), y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, and b is the bias. The output data of the connection layer is obtained and enters the output layer for subsequent output calculation and is passed to the output conversion unit.

[0124] Further explanation: after pooling, the data is fully connected according to the fully connected layer calculation formula "y = f (∑ (w n *x n )+b)” to obtain the output value after convolution, where y is the output result, f is the activation function, and w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, b is the bias; the “y=f(∑(w n *x n )+b)” is calculated from “y=f(w*x+b)” to “y=f(w1*x1+w2*x2+…+w n *x n+b)” and transformed, where w is the weight, x n The features extracted by the convolution layer and the pooling layer are integrated and classified through the fully connected layer, so that each neuron is connected to all the neurons in the previous layer, and the output is generated through weighted summation and nonlinear activation function.

[0125] S26. The output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F + 2C) / S + 1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of 0 layers added around the image, and S is the step size" to facilitate subsequent model analysis and training.

[0126] Further explanation: the output size N is the size of the feature map after the convolution operation, the input size P is the width or height of the input image or feature map, and the padding size P in the height direction is obtained by calculating the above step S21. H , the padding size P in the width direction W The convolution kernel size F is obtained by calculating the above step S22. The number of layers C of adding 0 around the image is the number of layers of adding 0 around the input image or feature map to control the size of the output feature map, which is also obtained by the above network construction. The step size S is the distance that the convolution kernel slides on the input image or feature map, which is obtained by the above calculation.

[0127] S30, the model training module uses a convolutional neural network to perform model training according to the image features of the PVC plastic sheet to learn the features of distinguishing normal and abnormal images and continuously adjust the model parameters to improve the accuracy of the model, and pass it to the parameter determination module;

[0128] See also Fig.10 As shown, the step S30 includes the following steps:

[0129] S31, the data labeling unit divides the quality abnormality categories of the PVC plastic sheet into corresponding data sample categories and labels them for subsequent machine learning of the model, and transmits them to the training simulation unit;

[0130] To further illustrate, data classification is performed according to various quality anomalies of PVC plastic sheets: "rough / matte surface" is category 1, "bubbles on the surface" is category 2, "precipitates on the surface" is category 3, "color difference" is category 4, "brittle" is category 5, "insufficient toughness" is category 6, and "insufficient weather resistance" is category 7; when category 1 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (1,0,0,0,0,0,0); when category 2 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,1,0,0,0,0,0); when category 3 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,1,0,0,0,0); when category 4 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0, 0,1,0,0,0), when category 5 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,0,0,1,0,0), when category 6 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,0,0,0,1,0), when category 7 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,0,0,0,1); the above 6 abnormal categories are relatively typical abnormal classifications of PVC plastic sheets, including but not limited to the above 7 categories, and one or more of the categories can also be reclassified into more categories, and a more detailed and in-depth division can be performed according to the actual production test results. The above classification is not fixed. The model is retrained after each category change to meet the actual needs of production.

[0131] S32, the training simulation unit trains the machine learning model using the extracted feature information, and identifies whether the PVC sheet inspection data has quality abnormalities and its abnormality category for subsequent model evaluation, and transmits it to the model evaluation unit;

[0132] It is further explained that the processed image data is divided into a training set and a test set. According to the characteristics of the abnormal quality of PVC sheets, a 10-layer deep convolutional neural network structure of "input layer (1st layer) → convolution layer (2nd layer) → activation layer (3rd layer) → convolution layer (4th layer) → pooling layer (5th layer) → convolution layer (6th layer) → activation layer (7th layer) → pooling layer (8th layer) → fully connected layer (9th layer) → output layer (10th layer)" is constructed to train the PVC sheet image dataset that has been labeled with categories to obtain the probability of the corresponding category; and a labeled dataset containing PVC sheet samples is established, including the bounding box coordinates and category labels of the PVC sheet area, and these data are used to train the YOLOv5 model, and the hyperparameters are adjusted to optimize the detection performance; the convolutional neural network is used to train the labeled category PVC sheet image dataset to obtain the probability of the corresponding category, and the data is continuously trained using the back propagation principle until the total loss function of all samples is minimized, so that the predicted sample probability is close to 0 in the remaining categories and close to 1 in this category.

[0133] S33, the model evaluation unit obtains the comprehensive evaluation score after model training according to the model comprehensive evaluation score calculation formula "F = 2*(Pr*Re) / (Pr+Re), F is the model comprehensive evaluation score, Pr is the precision rate, and Re is the recall rate", ensures the accuracy of model verification, and transmits it to the processing center;

[0134] Further explanation: the precision rate Pr and recall rate Re are respectively calculated by the formula “Pr=∑T P / ∑(T P +F P ),Re=∑T P / ∑T P +∑F N "Get, where F is the comprehensive evaluation score of the model, T P is the number of true positive samples, F P is the number of false positive samples, F N is the number of false negative samples; the number of true positive samples T P Also called true positive, that is, the number of samples correctly predicted as positive; the number of false positive samples FP is also called false positive, that is, the number of samples incorrectly predicted as positive; the number of false negative samples F N Also called false negatives, that is, the number of samples that are incorrectly predicted as negative classes, to verify the generalization ability and accuracy of the model; the generalization ability and accuracy of the model are verified by the cross-validation method to obtain the model evaluation score, ensuring that the model accurately predicts the properties of PVC sheets under different conditions; during the training process, the weights and biases in the network are updated through the back propagation algorithm, and the neural network is trained to gradually learn the normal characteristics of the PVC sheet in the image and its corresponding process parameters, abnormal characteristics and its corresponding preventive measures.

[0135] S34, the processing center compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified to be ready for trial use; if it does not meet the standard, the alarm is transmitted to the alarm and the parameters are notified to continue training;

[0136] It is further explained that the model comprehensive evaluation score standard is to obtain the optimal evaluation score based on the comprehensive evaluation score of the company's own historical similar PVC sheet anomaly model after training and combined with the comprehensive evaluation score of the similar PVC sheet anomaly model after training in the industry database; because the model recall rate data size is affected by factors such as data quality, model design, training data volume, and contextual information; when the data in the database is incomplete, inaccurate or redundant, it is difficult for the system to accurately find matching data, resulting in false positives and false negatives; because in deep learning, deeper network structures and more training data can enhance the model's expressive power, enabling it to better distinguish between targets and backgrounds.

[0137] S35, the abnormality recognition unit inputs the trained image into the trained convolutional neural network model to match it with the real-time acquired PVC sheet monitoring image and confirm its abnormality category.

[0138] It is further explained that the image is input into the model and the trained model is used to predict the new monitoring image. The abnormal type of PVC sheet is judged according to the output result. If the model's judgment on the abnormality of PVC sheet reaches a certain threshold, the early warning system is triggered and corresponding solutions are taken in time; the abnormal types of PVC sheet include: rough / matte surface, bubbles on the surface, precipitates on the surface, color difference, brittleness, insufficient toughness, insufficient weather resistance, etc. These trained models are applied to subsequent PVC sheet inspections. By inputting new sample data, the trained model and its corresponding inspection process parameters can quickly obtain inspection results, instead of manually judging the quality status of PVC sheets.

[0139] S40, the parameter determination module matches the predetermined PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model and conducts experiments to obtain the formal PVC sheet production process parameters, so as to automatically match and apply them in subsequent production, and pass them to the production application module;

[0140] See also Fig.11 As shown, the step S40 includes the following steps:

[0141] S41, fracture toughness unit is calculated according to the fracture toughness formula of PVC sheet "K = M*C / I*sqrt(π*a), K is the fracture toughness of PVC sheet M is the bending moment of the sheet at the stress point (N·m), C is the distance of the sheet cross section (m), and I is the moment of inertia of the sheet cross section (m 4 ), a is the sheet crack length (m)” to obtain the fracture toughness value of the PVC sheet for subsequent sheet quality testing and transfer to the tensile strength unit;

[0142] Further explanation, the calculation formula for the fracture toughness of the PVC sheet is derived based on the theory of beams and the theory of linear elastic fracture mechanics, and is obtained by substituting "σ=M*C / I" into "K=σ*sqrt(π*a)", where σ is the bending stress (Pa) of the PVC sheet, which refers to the bending resistance of the plastic material under bending. The unit of K calculated by the calculation formula for the fracture toughness of the plastic material is Since 1Pa=N / m 2 , so the unit of K is The moment of inertia I of the sheet cross section is the ability of the cross section to resist bending; the bending moment M of the sheet stress point and the moment of inertia I of the sheet cross section are obtained through sampling mechanical testing and calculation; the distance C of the sheet cross section and the length a of the sheet crack are obtained through sheet design data combined with test data; the fracture toughness K of the material is the intensity of the stress field at the crack tip, which reflects the ability of the material to absorb energy and resist crack expansion when subjected to external force, and is affected by factors such as the composition, structure, and processing technology of the plastic material.

[0143] S42, tensile strength unit is calculated according to the tensile strength formula of PVC sheet "T S =P / (b*d),T S is the sheet tensile strength (Pa), P is the maximum tensile load when the sheet sample breaks (N), b is the sheet sample width (m), and d is the sheet sample thickness (m)” to obtain the PVC sheet tensile strength for subsequent sheet quality testing and transfer to the impact toughness unit;

[0144] Further description, the sheet tensile strength T S It is the maximum tensile stress that the PVC sheet is subjected to until it breaks during the tensile test. It is calculated by the tensile strength formula of the PVC sheet “T S =P / (b*d)” is calculated to measure the ability of plastic materials to resist fracture during stretching. Its size directly affects the performance and safety of the material. It is proportional to the maximum tensile load P when the sheet sample breaks, and inversely proportional to the width b and thickness d of the sheet sample. The calculated unit is N / m 2 , because 1Pa=1N / m 2 , so T S The unit is Pa; the maximum tensile load P when the sheet sample breaks is obtained through sampling mechanical testing; the sheet sample width b and the sheet sample thickness d are obtained through sheet design data combined with test data.

[0145] S43, impact toughness unit is calculated according to the PVC sheet impact toughness formula "It = W / S, It is the sheet impact toughness (MJ / m 2 ), W is the work consumed when the sheet sample is broken (MJ), S is the cross-sectional area of ​​the notch of the sheet sample (m 2 )” to obtain the impact toughness of the PVC sheet for subsequent sheet quality testing and pass it to the weathering calculation unit;

[0146] It is further explained that the work W consumed when the sheet sample is broken is obtained through sampling mechanical testing; the cross-sectional area S at the notch of the sheet sample is selected according to the specific usage scenario and unit system; the PVC sheet impact toughness calculation formula is used to measure the ability of plastic materials to resist fracture when subjected to impact loads, reflecting the toughness behavior of the material under impact loads, that is, the property that the material can absorb energy and is not easy to break when subjected to impact. When calculating, the work W consumed when the sheet sample is broken and the cross-sectional area S at the notch of the sheet sample must be accurately measured, which is proportional to the work W consumed when the sheet sample is broken and inversely proportional to the cross-sectional area S at the notch of the sheet sample. If the It value is larger, it means that the impact toughness of the sheet is better and the ability to resist impact loads is stronger.

[0147] S44, the weather resistance calculation unit obtains the weather resistance value of the PVC sheet according to the PVC sheet weather resistance index calculation formula "w = T1 / T2*100, w is the weather resistance index of the PVC sheet, T1 is the exposure time of the sheet sample (h), and T2 is the actual use time of the sheet (h)" for subsequent sheet quality inspection, and transmits it to the material parameter presetting unit;

[0148] It is further explained that the PVC sheet weather resistance index calculation formula "w=T1 / T2*100" is used to evaluate the weather resistance index of PVC sheets under different environmental conditions, and can predict the durability of PVC sheets exposed to the natural environment for a long time. It is determined according to the material properties of the specific PVC sheet and the characteristics of the use environment, and is affected by factors such as the material chemical composition, physical properties, processing technology, and environmental conditions of the PVC sheet; the sheet sample exposure time T1 and the actual use time T2 of the sheet are obtained through sampling testing; the weather resistance index w of the PVC sheet is proportional to the sheet sample exposure time T1, and inversely proportional to the actual use time T2 of the sheet. If the sheet sample exposure time T1 is longer, the weather resistance index w of the PVC sheet is larger, and if the actual use time T2 of the sheet is longer, the weather resistance index w of the PVC sheet is smaller.

[0149] S45, the parameter presetting unit obtains the corresponding PVC sheet formula and production process parameters in the model according to the PVC sheet abnormality category and the industry database as the pre-set production process parameters for subsequent trial production verification, and transmits them to the trial production verification unit;

[0150] It is further explained that the data of various PVC sheets obtained according to the different needs of users in different industries for PVC sheets are used to predict and simulate the polymer structure using AI technology. Molecular dynamics simulation based on the physical laws of Newtonian mechanics and statistical mechanics predicts the conformation, dynamics and thermodynamic properties of PVC polymer chains. The interaction energy between atoms and molecules is calculated through potential field methods such as force field or density functional theory to guide molecular dynamics simulation, and the constraints obtained by experiments and theoretical calculations are combined to improve the accuracy of structure prediction, so as to match the production process parameters in the model with the industry database, including material formula, equipment operating parameters, production process, testing process, etc. Among them, the material formula includes: PVC resin, toughening agent, thermal stabilizer and other core ingredients, filler, lubricant, Auxiliary ingredients such as plasticizers and other additives; the equipment operating parameters include: 1) mixer: speed, stirring time, rotation speed, water supply, etc.; 2) conical twin-screw extruder: screw diameter and aspect ratio, screw speed and direction, drive power, heating power, temperature control, etc.; 3) three-roller setting machine: roller temperature, roller gap, traction speed, control pressure, setting time, cooling method, etc.; 4) cooling and traction bracket: cooling temperature, traction speed, control tension, cooling time, air volume, water pressure, etc.; 5) shearing machine: shearing speed, shearing force, shearing length and width, shearing angle, feeding speed, feeding length, shearing times, shearing interval, etc. These can ensure the matching of model and equipment parameters in the subsequent actual PVC sheet production, and ensure the quality level of automatic production of PVC sheets.

[0151] S46, the trial production verification unit performs material production and production tests according to the predetermined material formula and the corresponding production process parameters to obtain high-toughness weather-resistant PVC plastic sheets and their corresponding quality data, and transmits them to the processing center;

[0152] Further explanation: According to the needs of users in different industries and their predetermined PVC sheet raw material formula ratio, PVC resin and various additives such as toughening agent, heat stabilizer, antioxidant, ultraviolet absorber, filler, lubricant, plasticizer, titanium dioxide, foaming agent, coupling agent, brightener, foaming regulator, color powder, etc. are mixed with a mixer to fully stir the mixture; the mixed material is sent to a conical twin-screw extruder to extrude a PVC sheet with uniform thickness and smooth surface through its head and die according to predetermined operating parameters; according to the control command, it is quickly cooled through the cooling roller of the three-roller shaping machine and the cooling traction bracket and the cooling device to solidify and shape it, and according to the predetermined operating parameters, the mixed material is sent to a conical twin-screw extruder to extrude a PVC sheet with uniform thickness and smooth surface through its head and die; according to the control command, it is quickly cooled through the cooling roller of the three-roller shaping machine and the cooling traction bracket and the cooling device to solidify and shape it, and according to the predetermined operating parameters, the mixed material is sent to a conical twin-screw extruder to extrude a PVC sheet with uniform thickness and smooth surface through the conical twin-screw extruder and the die; ... The cooling speed and time are strictly controlled to avoid deformation or internal stress of the PVC sheet caused by uneven cooling; then the surface is polished and cleaned by polishing equipment to ensure that the surface is smooth and the color is uniform; the PVC sheet production inspection equipment obtains the inspection parameters according to steps S41-S44 to sample and inspect the PVC sheet, and obtains quality information such as its appearance, size, and physical properties to ensure that the quality of the PVC sheet meets the standards; then the shearing machine cuts the PVC sheet into the required length and width according to customer needs, so that PVC sheets with high toughness and weather resistance can be produced to meet the needs of different users in various application fields.

[0153] S47, the processing center compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to re-debug the parameters for rework.

[0154] It is further explained that the surface quality of the produced PVC sheet is inspected by a high-definition camera using an image recognition technology based on artificial intelligence to confirm whether the surface is flat, whether there are no bumps, no obvious scratches and wear, whether the color is consistent, whether there are no color differences, whether there are no bubbles, cracks, impurities, whether the edges are straight, and other appearance quality information. The tensile strength, fracture toughness, impact toughness, weather resistance and other test data of the PVC sheet are respectively tested by a tensile testing machine, a toughness tester, an impact testing machine, a UV aging testing machine and other performance testing equipment to see whether they meet the standards, and compared with the test parameters obtained in steps S41-S44. According to the toughness requirements of the PVC sheet, the model is used to assist in the design of the formula of the toughening agent. For example, the influence of different toughening agents on the toughness of PVC is analyzed by a machine learning algorithm to determine the best type and addition ratio of the toughening agent. Taking into account the weather resistance, You can also choose additives such as anti-ultraviolet agents and antioxidants with anti-aging properties to extend the service life of PVC sheets. After trial production, the model can be used to analyze production data in real time to optimize process parameters such as mixing, extrusion, and cooling to ensure that the toughness and weather resistance of PVC plastic sheets reach the best state. The machine learning algorithm can be used to monitor and predict quality data in the production process to promptly detect and correct possible problems, such as uneven mixing and excessive extrusion temperature, so as to improve sheet quality and production efficiency. After testing, the machine learning algorithm can be used to process and analyze the test data to promptly detect problems in the trial production process, and provide feedback and adjustments to continuously optimize the production process and formula. Through continuous iteration and improvement, the toughness and weather resistance of PVC sheets can be improved until they meet the standards. Users of different industries and categories have different quality requirements for PVC sheets.

[0155] S50, the production application module automatically matches the production process parameters through the PVC sheet production equipment according to the trained model to carry out material production and production testing of the PVC sheet to ensure that the PVC sheet meets customer requirements.

[0156] See also Fig.12 As shown, the step S50 includes the following steps:

[0157] S51, the material preparation unit fully stirs the prepared PVC resin and various additives according to the PVC sheet material formula through a mixer according to program instructions and predetermined operating parameters to ensure that the various components are evenly mixed, and transfers them to the extrusion molding unit;

[0158] Further explanation, according to step S40 and the target user's performance requirements for the PVC sheet, the optimal formula range of the PVC sheet raw materials is: 100 parts of PVC resin, 1-2 parts of toughening agent, 4-6 parts of heat stabilizer, 0.5-1 part of antioxidant, 0.3-0.8 parts of ultraviolet absorber, 50-250 parts of filler, 1-3 parts of lubricant, 0.2-2 parts of plasticizer, 0.1-0.8 parts of titanium dioxide, 0.1-0.5 parts of foaming agent, 0.1-0.6 parts of coupling agent, 0.2-1 parts of brightener, 0.3-0.6 parts of foaming regulator, 0.1-0.8 parts of color powder , if specific adjustments are made within these ranges based on application requirements, production costs, processing conditions and other factors as well as the performance requirements of different users for PVC sheets, so as to meet the quality and performance requirements of different users for PVC sheets; according to the control command and the predetermined gear and speed, mixing time, rotation speed, water supply, feed fineness, slurry concentration and other operating parameters, the prepared raw materials are fully mixed through the mixer to ensure that the various components are evenly dispersed to avoid local performance differences, and the mixed materials are sent to the feeding equipment of the conical twin-screw extruder through the conveying equipment to wait for extrusion molding; The core materials of the PVC sheet include: PVC resin: as the main material, providing the basic performance of the PVC sheet, ensuring the toughness and weather resistance of the PVC sheet; toughening agent: CPE (chlorinated polyethylene), etc., to improve the toughness of the PVC sheet, so that it has better resistance to impact and stress; heat stabilizer: composite lead salt stabilizer, etc., to improve the thermal stability and weather resistance of the PVC sheet; antioxidant: to combine the free radicals to form stable compounds, to improve the stability of the PVC sheet; ultraviolet absorber: to improve the anti-ultraviolet ability of the PVC sheet, improve the weather resistance, and ensure that the PVC sheet can be used in outdoor environments for a long time. It can still maintain good performance after being used for a long time; fillers: heavy calcium (calcium carbonate), light calcium, etc., reduce costs and improve processing performance and maintain its physical properties; lubricants: stearic acid, paraffin, etc., improve the processing fluidity of PVC resin and maintain the stability of the material; plasticizers: to improve the toughness of the sheet; titanium dioxide: to improve whiteness and hiding power; foaming agent: to prepare foamed PVC sheet; coupling agent: to improve the interface bonding between filler and PVC resin; other additives: brightener, foaming regulator, color powder, etc.; the formula proportions of various materials implemented for different users are also different to meet the application needs of different users.

[0159] S52, the extrusion molding unit extrude the PVC sheet through a conical twin-screw extruder and a three-roller shaping machine according to program instructions and predetermined operating parameters, cools and solidifies the sheet through a cooling device to ensure that the sheet is uniform and flat, and transfers it to a surface cleaning unit;

[0160] It is further explained that according to the instructions after the installation of the extrusion die is completed, the conical twin-screw extruder is heated for 40-50 minutes, and according to the predetermined operating parameters such as screw diameter and aspect ratio, screw speed and direction, drive power and productivity, heating power and temperature control, the conical twin-screw extruder uses heating and the shearing action of the screw to melt and plasticize the material to form a uniform melt, and the melt is squeezed into the die through the head under the shearing and extrusion action of the screw to extrude into the shape of a sheet, thereby completing the heating, melting and extrusion of the PVC sheet raw material, and the thickness of the sheet can be accurately adjusted to ensure that the thickness of the sheet is uniform, the surface is flat and the internal structure is stable; then according to the predetermined roller temperature, roller gap, traction speed, control pressure, The three-roller setting machine calenders and sets the sheet according to horizontal, vertical or 45-degree inclined rollers according to the operating parameters such as setting time and cooling method, and uses the cooling and traction bracket and cooling equipment to quickly cool and pull the shaped sheet through the cooling rollers according to the predetermined cooling temperature, traction speed, tension control, cooling time, air volume control, water pressure control and other operating parameters, and strictly controls the cooling speed and time to avoid sheet deformation or internal stress caused by uneven cooling, so that it is solidified and set. In the production process, various production process parameters such as temperature, pressure, extrusion speed are monitored and adjusted in real time, and the automatic control system is used to ensure the shape and size stability of the PVC sheet in the production process, thereby improving the toughness and weather resistance of the PVC sheet.

[0161] S53, the surface cleaning unit performs surface grinding and cleaning treatment on the cooled and shaped PVC sheet through the grinding and polishing equipment according to the control command to ensure that the surface is smooth and the color is uniform, and then transmits it to the quality inspection unit;

[0162] To further explain, since the PVC sheet has obtained the required surface finish during the production process, it generally does not need to be polished. However, if polishing is required for some customers and some parts of the PVC sheet, professional automatic polishing equipment equipped with fine-grained sandpaper is used to polish the parts of the PVC sheet that need to be polished to avoid damaging the surface of the sheet. Apply force evenly during polishing to avoid excessive polishing at the same position, which may cause uneven sheet thickness or surface damage. Use professional plastic cleaners or diluted alcohol to remove dust and dirt on the surface of the PVC sheet through professional automatic cleaning equipment. Be careful to avoid using strong acids, strong alkalis or corrosive cleaners to avoid damaging the surface of the sheet. Rinse the surface of the sheet with clean water and wipe it dry with a clean cloth using professional equipment to avoid leaving water stains or detergent residues.

[0163] S54, the quality inspection unit detects the appearance, size, toughness, and weather resistance of the PVC sheet through a high-definition camera and PVC sheet inspection equipment according to program instructions to meet the needs of different users and transmit it to the processing center;

[0164] It is further explained that by using a high-definition camera to shoot at a 360-degree angle, images of various positions of the PVC sheet are taken from multiple different angles, and different positions of the PVC sheet are identified at different angles, so that the positions and shapes of the PVC sheet can be more accurately and comprehensively identified, or based on multiple images of the PVC sheet taken from different angles, the PVC sheet is identified by multi-angle matching, so as to determine whether the surface of the PVC sheet is flat, whether it has no bumps, no obvious scratches and wear, whether the color is consistent, whether there is no color difference, whether there are no bubbles, cracks, impurities, whether the edges are straight, and other appearance quality information; the melt flow rate tester is used to detect the melt flow rate of thermoplastics at a certain temperature and pressure, the density of the PVC sheet is detected by a density tester, and the quality of the PVC sheet is detected by an infrared spectrometer. The content of PVC in the PVC sheet is detected by a vinyl chloride residue detector and an element analyzer. The content of precious metals in the PVC sheet is detected by a thickness tester, a wear-resistant layer thickness tester, and a heating size change rate tester. The thickness of the PVC sheet before and after heating is detected by a thickness tester, a wear-resistant layer thickness tester, and a heating size change rate tester. The length and width of the PVC sheet are detected by a three-coordinate rangefinder. The deformation of the PVC sheet before and after heating is detected by a heating warpage tester. The tensile strength, fracture toughness, impact toughness, and weather resistance of the PVC sheet are respectively detected by a tensile testing machine, a toughness testing machine, an impact testing machine, and an ultraviolet aging testing machine. The detection parameters obtained according to steps S41-S44 are compared, and combined with the quality requirements of different users and the needs of actual application fields, it is judged whether the high toughness and weather resistance functions of the PVC sheet meet the needs of the target users, so as to evaluate whether the various performances of the PVC sheet meet the standards.

[0165] S55. The processing center compares the quality information of the PVC plastic sheet with the PVC sheet production quality standard stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is transmitted to the alarm and notified to rework or scrap.

[0166] Further explanation: the production quality standards of the PVC sheet include: 1) Appearance: The surface should be flat and smooth, with uniform color, without perforations, cracks, bubbles, wrinkles, and no crystal points larger than 13 mm or black and white impurities larger than 0.8 mm are allowed. Crystal points smaller than 13 mm should not exceed 75 in an area of ​​50 cm × 50 cm, and black and white impurities of 0.3 to 0.8 mm should not exceed 1 m 2No more than 30 pieces, uniform thickness and flatness, consistent color difference; 2) Physical properties: tensile strength and elongation at break, bending strength, impact strength, hardness, etc. all meet national standards; 3) Chemical properties: corrosion resistance, migration resistance, thermal stability, etc. all meet national standards; 4) Combustion performance: flame retardancy, smoke density and harmful gas emissions all meet national standards; 5) Environmental protection performance: the content of harmful substances such as heavy metals and volatile organic compounds meets environmental protection requirements; 6) Special properties: oil resistance, acid and alkali resistance, etc. all meet national standards, which ensure the high quality and stability of the sheet; The material formula in the production process parameters of the PVC sheet is based on the collected PVC sheet data, and the PVC raw materials and their stabilizers, plasticizers, toughening agents, anti-aging agents and other additives are screened and optimized according to the model, and the machine The machine learning algorithm predicts the impact of different combinations of raw materials and additives on the toughness and weather resistance of PVC sheets. For example, it can analyze the effect of different toughening agents on the toughness of PVC, or evaluate the degree of improvement of PVC weather resistance by different anti-aging agents. On this basis, the system can screen out a combination of raw materials with excellent performance and reasonable cost; it is adjusted according to factors such as application requirements, production costs, and processing conditions, and the final formula is determined after multiple iterations and optimizations. It not only considers the performance and cost of the raw materials, but also fully considers the feasibility and stability of the production process, ensuring that the selected raw materials can maintain good dispersibility and processability in production links such as mixing and extrusion, ensuring the scientificity and rationality of raw material selection, and providing a strong guarantee for the production of high-performance PVC sheets, thereby ensuring the quality and performance of the final PVC sheets.

[0167] S56, the slitting and packaging performance testing unit cuts the PVC sheets into required lengths and widths by shearing machines according to program instructions and packages them to protect the sheets from contamination and damage and to facilitate transportation and storage.

[0168] It is further explained that the PVC plastic sheet is placed on the workbench of the shearing machine to ensure that the material is flat and firmly fixed. According to the preset cutting size and specifications, the PVC plastic sheet is accurately and automatically cut according to the predetermined shearing speed, shearing force, shearing length and width, shearing angle, feeding speed, feeding length, shearing times, shearing interval and other operating parameters to ensure the accuracy and efficiency of the cutting; then the cut PVC plastic sheet is inspected again before shipment, specifically referring to the standard of the above-mentioned step S54 to avoid missing the inspection of the above-mentioned step S54, to ensure that the quality meets the standard, and plastic film is used for wrapping and packaging, or cartons are used for boxing and packaging, and the packaged PVC plastic sheets are marked with sheet specifications, quantity, production date and other information to facilitate subsequent management and transportation, so as to complete the shearing and packaging work of the PVC plastic sheet, and ensure that the PVC plastic sheet is accurately cut, beautifully packaged and easy to carry and transport.

[0169] It is further explained that the above steps are displayed in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows, unless clearly stated in this document. There is no strict order restriction for the execution of these steps, and these steps can also be executed according to other orders, and some steps can include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed and completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0170] Further explanation, the present invention is described according to the content implemented by the software program of the high-toughness weather-resistant PVC plastic sheet production control system. Each high-toughness weather-resistant PVC plastic sheet production process is divided into several modules or units to implement the software program instructions generated by each step. The software program instructions include the above-mentioned high-toughness weather-resistant PVC plastic sheet production process.

[0171] A high-toughness weather-resistant PVC plastic sheet production control system provided by the present invention also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and each functional module implements the steps of any one of the above-mentioned high-toughness weather-resistant PVC plastic sheet production processes when executing the computer program; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, the steps of any one of the above-mentioned high-toughness weather-resistant PVC plastic sheet production processes are implemented; and also includes a PVC sheet production control device, which is implemented by the above-mentioned high-toughness weather-resistant PVC plastic sheet production process.

[0172] Further explanation, the computer-readable storage medium includes a memory, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program and instructions corresponding to a high-toughness weather-resistant PVC plastic sheet production process in the present invention, including information transmission instructions of each module; the memory executes various functional applications and data processing of each module by running the stored non-volatile software programs and instructions, that is, realizes a high-toughness weather-resistant PVC plastic sheet production process in the above process embodiment; one or more units are stored in the memory, and when executed by the one or more modules, a high-toughness weather-resistant PVC plastic sheet production process in any of the above process embodiments is executed; the computer-readable storage medium stores computer executable instructions, which are executed by one or more modules, and can also be a high-toughness weather-resistant PVC plastic sheet production process in any of the above process embodiments.

[0173] It is further explained that the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two, and may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device, including but not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, wherein the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, carrying a computer-readable program code, and the propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above, and may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate or transmit a program for use by or in combination with an instruction execution system, apparatus or device, and the program code that may be contained may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0174] It is further explained that the computer program is divided into multiple modules / units, and the multiple modules / units are stored in the memory and executed by each module / unit to complete the present invention; the multiple modules / units can be a series of computer program instructions that can complete specific functions, and the instructions can be used to describe the execution process of the computer program in each module / unit.

[0175] It is further explained that the control device is composed of the above-mentioned related equipment or devices, and can be made into a complete set of PVC sheet production and testing equipment together with the PVC sheet production and testing equipment according to the needs of the production enterprise, including various assembly production and testing equipment; it can also be made into a unit device of each functional module belonging to each step or the entire control device, and each control device can be connected to the PVC sheet production and testing equipment through a wireless connection during installation; the existing old PVC sheet production and testing equipment can also be upgraded and modified by adding the control device, thereby saving equipment costs. These equipment structures are not described in detail here; the control device of the present invention can also be applied to professional PVC sheet testing institutions to improve detection efficiency.

[0176] The present invention also provides a high-toughness weather-resistant PVC plastic sheet, which is composed of the formula ratio range of various materials in step S55, and is specifically adjusted within this ratio range according to the needs of different users, and is achieved by using the above-mentioned high-toughness weather-resistant PVC plastic sheet production process.

[0177] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, and therefore it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application can be modified or replaced by equivalents, and all of these should be included in the scope of protection of the present application.

Claims

1. A production process for high-toughness weather-resistant PVC plastic sheets, characterized in that: The process is applied to a high-toughness weather-resistant PVC plastic sheet production control system, the system comprising a data acquisition module, a model construction module, a model training module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal comprises a smart phone, a tablet computer or a smart remote control, which are wirelessly connected to the wireless communication module within the range of a wireless network or the Internet; the process comprises the following steps: S10. Before production, the data acquisition module acquires the types of various PVC sheets, various additive information, normal and abnormal image data of performance parameters and pre-processes them to ensure data accuracy, and passes them to the model building module, including the following steps: S11. The information collection unit obtains various production quality data and images of the formula, performance, and process of various high-toughness weather-resistant PVC plastic sheets in the industry database through networking, so as to facilitate subsequent data cleaning and transmit them to the cleaning data unit; S12, the data cleaning unit removes duplicate data, removes outliers, and fills missing values ​​to remove duplicate and missing values ​​in the PVC plastic sheet image data to ensure the accuracy of the data, and passes it to the data enhancement unit; S13, the data enhancement unit increases the diversity of the PVC plastic sheet image and improves the stability of the model through the data enhancement method of rotation, scaling, flipping and cutting, so as to improve the generalization ability of the model, and transmits it to the normalization processing unit; S14, the normalization processing unit obtains the normalized PVC plastic sheet image data according to the image normalization conversion calculation formula "Xn=(X0-Xmin) / Xmax-Xmin), X2 is the normalized image matrix, X0 is the original image matrix, Xmax and Xmin are the maximum value and minimum value in the original image respectively", so as to facilitate subsequent standardization processing and pass it to the filtering and denoising unit; S15, the filtering and denoising unit obtains the denoised PVC sheet image according to the median filtering method calculation formula "g(I,j)=Med{g(x,y),(x,y)∈S}, g is the original image, g(I,j) is the pixel point with coordinates in the original image g, g(x,y) is the pixel point with coordinates in the denoised image, S is the domain space of K pixels obtained by the pixel point" and passes it to the grayscale conversion unit; S16, the grayscale conversion unit obtains the grayscaled PVC sheet image according to the grayscale calculation formula "f(I,j) = max(R(I,j), G(I,j), B(I,j)), f(I,j) is the grayscaled image, R(I,j), G(i,j), B(I,j) are the original images of three colors respectively", so as to facilitate the subsequent feature extraction; S20, the model building module extracts the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets according to the preprocessed data and builds the model for subsequent model training, and transmits it to the model training module; S30, the model training module uses a convolutional neural network to perform model training according to the PVC sheet image features to learn the features of distinguishing normal and abnormal images and continuously adjusts the model parameters to improve the model accuracy, and transmits the model parameters to the parameter determination module; S40, the parameter determination module matches the predetermined PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model and conducts experiments to obtain the formal production process parameters, so as to automatically match and apply them in subsequent production, and pass them to the production application module; S50, the production application module automatically matches the production process parameters through the PVC sheet production equipment according to the trained model to carry out material production and production testing of the PVC sheet to ensure that the PVC sheet meets customer requirements.

2. A process for producing high-toughness weather-resistant PVC plastic sheets according to claim 1, characterized in that The system also includes: the wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically connects to a smart phone, a gateway, or a server within an effective network range; The alarm compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory, and automatically sounds an alarm if it does not meet the standard and notifies to adjust the parameters to continue training; and compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory, and automatically sounds an alarm if it does not meet the standard and notifies to re-adjust the parameters for rework; The quality information of the PVC plastic sheet is compared with the PVC sheet production quality standard stored in the memory. If it does not meet the standard, an alarm will be automatically sounded and a notice will be given to rework or scrap it. The memory is responsible for storing the information of the data acquisition module, the model construction module, the model training module, the parameter determination module, the production application module, the wireless communication module, and the alarm, as well as the storage of the model comprehensive evaluation sub-standard and the PVC sheet production quality standard; The processing center is responsible for the information transmission of the data acquisition module, model construction module, model training module, parameter determination module, production application module, wireless communication module, alarm, and memory, and is the hub center of the system. It compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified that it can be tried out; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters to continue training; and the quality information of the PVC sheet is compared with the production quality standard of the PVC sheet stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to re-debug the parameters for rework; The quality information of the PVC plastic sheet is compared with the PVC sheet production quality standard stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is transmitted to the alarm and notified to rework or scrap; The data acquisition module includes an information acquisition unit, a cleaning data unit, a data enhancement unit, a normalization processing unit, a filtering and denoising unit, and a grayscale conversion unit. The data acquisition unit acquires the types of various PVC sheets, various auxiliary agent information, and normal and abnormal image data of performance parameters, pre-processes them, and transmits them to the model building module. The model building module includes a feature extraction unit, a padding input unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, and an output conversion unit, which is responsible for extracting the key features of the physical properties, weather resistance, and appearance quality of various PVC sheets based on the preprocessed data and building a model, and passing it to the model training module; The model training module includes a data marking unit, a training simulation unit, a model evaluation unit, and an abnormality recognition unit, which is responsible for using a convolutional neural network to perform model training based on the image features of the PVC plastic sheet to learn the features of distinguishing normal and abnormal images and continuously adjust the model parameters, and pass them to the parameter determination module; The parameter determination module includes a fracture toughness unit, a tensile strength unit, an impact toughness unit, a weathering calculation unit, a parameter presetting unit, and a trial production verification unit, which is responsible for matching the presetting PVC sheet production process parameters according to the PVC sheet abnormality category and the trained model, and conducting experiments to obtain the formal PVC sheet production process parameters, and pass them to the production application module; The production application module includes a material preparation unit, an extrusion molding unit, a surface cleaning unit, a quality inspection unit, and a slitting and packaging unit, which is responsible for automatically matching the production process parameters through the PVC sheet production equipment according to the trained model to perform material production and production inspection of the PVC sheet to ensure that the PVC sheet meets customer requirements.

3. The high-toughness weather-resistant PVC plastic sheet production process according to claim 1 is characterized in that: The step S20 comprises the following steps: S21, the feature extraction unit extracts the feature information of the physical properties, weather resistance, and appearance quality of the PVC sheet and its corresponding quality anomalies and preventive measures according to the processed image data, so as to facilitate subsequent machine learning, and transmits the information to the filling input unit; S22, fill input unit according to fill size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W -Wi] / 2,P H , P W are the padding sizes in height / width directions, Hi and Wi are the height / width of the input feature map, and K H , K W are the height / width of the convolution kernel, S H , S W Where Ho and Wo are the values ​​of the step length in the height / width direction, respectively. Ho and Wo are the height and width of the output feature map, respectively. The padding data is obtained and input into the model for subsequent data convolution input and passed to the convolution input unit. S23, the convolution input unit obtains the convolution input data according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential of the variable m" for subsequent data pooling conversion and passes it to the pooling conversion unit; S24, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values ​​in the input window, X is the input feature map, P S The maximum pixel value after pooling is obtained by setting the window size of the pooling operation to the fully connected layer to retain important feature information and pass it to the fully connected layer unit; S25, the fully connected layer unit is calculated according to the fully connected layer formula "y=f(∑(w n *x n )+b), y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, and b is the bias. The output data of the connection layer is obtained and enters the output layer for subsequent output calculation and is passed to the output conversion unit. S26, the output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F + 2C) / S + 1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of 0 layers added around the image, and S is the step size" for subsequent model analysis and training; The step S30 comprises the following steps: S31, the data labeling unit divides the quality abnormality categories of the PVC plastic sheet into corresponding data sample categories and labels them for subsequent machine learning of the model, and transmits them to the training simulation unit; S32, the training simulation unit trains the machine learning model using the extracted feature information, and identifies whether the PVC sheet inspection data has quality abnormalities and its abnormality category for subsequent model evaluation, and transmits it to the model evaluation unit; S33. The model evaluation unit obtains the comprehensive evaluation score after model training according to the model comprehensive evaluation score calculation formula "F = 2*(Pr*Re) / (Pr+Re), F is the model comprehensive evaluation score, Pr is the precision rate, and Re is the recall rate" to ensure the accuracy of model verification and transmit it to the processing center; S34, the processing center compares the actual comprehensive evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, the model is notified to be ready for trial use; if it does not meet the standard, the alarm is transmitted to the alarm and the parameters are notified to continue training; S35, the abnormality recognition unit inputs the trained image into the trained convolutional neural network model to match it with the real-time acquired PVC sheet monitoring image and confirm its abnormality category.

4. The high-toughness weather-resistant PVC plastic sheet production process according to claim 1 is characterized in that: The step S40 comprises the following steps: S41, fracture toughness unit is calculated according to the fracture toughness formula of PVC sheet "K = M*C / I*sqrt(π*a), K is the fracture toughness of PVC sheet M is the bending moment of the sheet at the stress point (N·m), C is the distance of the sheet cross section (m), and I is the moment of inertia of the sheet cross section (m 4 ), a is the sheet crack length (m)” to obtain the fracture toughness value of the PVC sheet for subsequent sheet quality testing and transfer to the tensile strength unit; S42, tensile strength unit is calculated according to the tensile strength formula of PVC sheet "T S =P / (b*d),T S is the sheet tensile strength (Pa), P is the maximum tensile load when the sheet sample breaks (N), b is the sheet sample width (m), and d is the sheet sample thickness (m)” to obtain the PVC sheet tensile strength for subsequent sheet quality testing and transfer to the impact toughness unit; S43, impact toughness unit is calculated according to the PVC sheet impact toughness formula "It = W / S, It is the sheet impact toughness (MJ / m 2 ), W is the work consumed when the sheet sample is broken (MJ), S is the cross-sectional area of ​​the notch of the sheet sample (m 2 )” to obtain the impact toughness of the PVC sheet for subsequent sheet quality testing and pass it to the weathering calculation unit; S44, the weather resistance calculation unit obtains the weather resistance value of the PVC sheet according to the PVC sheet weather resistance index calculation formula "w = T1 / T2*100, w is the weather resistance index of the PVC sheet, T1 is the exposure time of the sheet sample (h), and T2 is the actual use time of the sheet (h)" for subsequent sheet quality inspection, and transmits it to the material parameter presetting unit; S45, the parameter presetting unit obtains the corresponding PVC sheet formula and production process parameters in the model according to the PVC sheet abnormality category and the industry database as the pre-set production process parameters for subsequent trial production verification, and transmits them to the trial production verification unit; S46, the trial production verification unit performs material production and production tests according to the predetermined material formula and the corresponding production process parameters to obtain high-toughness weather-resistant PVC plastic sheets and their corresponding quality data, and transmits them to the processing center; S47, the processing center compares the quality information of the PVC sheet with the production quality standard of the PVC sheet stored in the memory: if the standard is met, it is set as the official production process parameter; if the standard is not met, it is transmitted to the alarm and notified to re-debug the parameters for rework; The step S50 comprises the following steps: S51, the material preparation unit fully stirs the prepared PVC resin and various additives according to the PVC sheet material formula through a mixer according to program instructions and predetermined operating parameters to ensure that the various components are evenly mixed, and transfers them to the extrusion molding unit; S52, the extrusion molding unit extrude the PVC sheet through a conical twin-screw extruder and a three-roller shaping machine according to program instructions and predetermined operating parameters, cools and solidifies the sheet through a cooling device to ensure that the sheet is uniform and flat, and transfers it to a surface cleaning unit; S53, the surface cleaning unit performs surface grinding and cleaning treatment on the cooled and shaped PVC sheet through the grinding and polishing equipment according to the control command to ensure that the surface is smooth and the color is uniform, and then transmits it to the quality inspection unit; S54, the quality inspection unit detects the appearance size, high toughness, weather resistance and other quality information of the PVC sheet through a high-definition camera and PVC sheet inspection equipment according to program instructions to meet the needs of different users and transmits it to the processing center; S55. The processing center compares the quality information of the PVC plastic sheet with the PVC sheet production quality standard stored in the memory: if it meets the standard, it is cut and packaged; if it does not meet the standard, it is transmitted to the alarm and notified to rework or scrap. S56, the slitting and packaging performance testing unit cuts the PVC sheets into required lengths and widths by shearing machines according to program instructions and packages them to protect the sheets from contamination and damage and to facilitate transportation and storage.

5. A process for producing high-toughness weather-resistant PVC plastic sheets according to claims 1-4, characterized in that: The system also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the above functional modules execute the computer program, the steps of a high-toughness weather-resistant PVC plastic sheet production process described in any one of claims 1 to 4 are implemented; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, the steps of a high-toughness weather-resistant PVC plastic sheet production process described in any one of claims 1 to 4 are implemented; and also includes a PVC sheet production control device, which is implemented by the high-toughness weather-resistant PVC plastic sheet production process described in any one of claims 1 to 4.

6. A high-toughness weather-resistant PVC plastic sheet, consisting of 100 parts of PVC resin, 1-2 parts of toughening agent, 4-6 parts of heat stabilizer, 0.5-1 parts of antioxidant, 0.3-0.8 parts of ultraviolet absorber, 50-250 parts of filler, 1-3 parts of lubricant, 0.2-2 parts of plasticizer, 0.1-0.8 parts of titanium dioxide, 0.1-0.5 parts of foaming agent, 0.1-0.6 parts of coupling agent, 0.2-1 parts of brightener, 0.3-0.6 parts of foaming regulator, and 0.1-0.8 parts of color powder, characterized in that: The method is achieved by using a high-toughness weather-resistant PVC plastic sheet production process as described in any one of claims 1 to 4 above.

Images