Product process standard generation method and device based on industrial Internet of Things, terminal and medium

Abstract

The invention discloses a product process standard generation method and device based on industrial Internet of Things, a terminal and a medium. The method comprises the steps of obtaining design parameters, production process parameters, production line static parameters, raw material parameters, raw material storage process parameters, raw material storage equipment static parameters and product quality standards of preset pilot production products; obtaining a product production process standard through a preset first model; obtaining a raw material storage standard through a preset second model; a workshop environment standard is obtained through a preset third model; and obtaining a target product process standard based on the raw material storage standard, the product production process standard and the workshop environment standard. The invention aims to improve the accuracy of product process standard formulation by combining the Internet of Things technology and the neural network model.

Description

Technical Field

[0001] This application relates to the technical field of product process technology, and particularly to a method, device, terminal, and medium for generating product process standards based on the industrial Internet of Things. Background Art

[0002] Product process standards are a series of regulations designed to ensure that products meet the expected requirements for quality, performance, safety, reliability, etc. during the manufacturing process. These standards cover multiple aspects from the selection of raw materials to the inspection of finished products. Currently, most enterprises still rely on technicians to manually formulate product process standards, and the formulation process usually includes the following: Technicians analyze the production requirements and quality standards of products based on product design requirements, customer feedback, and market trends; collect historical production data, raw material data, equipment performance data, etc. to provide a basis for standard formulation; technicians draft preliminary process standards based on the collected data and analysis results; submit the drafted standards to an expert team for review to ensure the rationality and feasibility of the standards; implement the formulated standards on a small-scale test line to verify their effectiveness; after verification and adjustment, officially release the product process standards and strictly implement them during the production process; regularly revise and optimize the standards based on production practice and market feedback.

[0003] However, the standards formulated by different technicians may vary greatly, lacking unified standards and specifications, which affects production consistency and quality; the formulation of standards depends to a large extent on the personal experience and judgment of technicians, and it is prone to deviations and inconsistencies; although a large amount of data is collected during the process of manually formulating standards, these data are often not fully utilized for in-depth analysis and optimization, resulting in limited scientificity and rationality of the standards, and thus insufficient accuracy of product process standards, leading to the inability to guarantee product quality. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, terminal, and medium for generating product process standards based on the industrial Internet of Things, aiming to improve the accuracy of formulating product process standards by combining Internet of Things technology and neural network models, and thereby improve the production quality of products.

[0005] To achieve the above objective, this application provides a method for generating product process standards based on the industrial Internet of Things, which is applied to a product process system. The product process system includes a management platform, an object platform, and a sensing network platform. The object platform includes workshop environment monitoring equipment, a production line, and raw material storage equipment. The workshop environment monitoring equipment is used to monitor the environmental conditions of the production workshop. The management platform is communicatively connected to the object platform through the sensing network platform;

[0006] The method includes:

[0007] Obtain the design parameters of the preset pilot production product, the production process parameters of the pilot production product, the production line static parameters corresponding to the production line, the raw material parameters corresponding to the pilot production product, the storage process parameters of the raw materials corresponding to the pilot production product, the raw material storage equipment static parameters corresponding to the raw material storage equipment, and the product quality standard corresponding to the pilot production product. Among them, the production process parameters are used to characterize the situation of the process of producing the pilot production product, the production line static parameters are used to characterize the situation of the production line in a static state, the raw material parameters are used to characterize the situation of the raw materials of the pilot production product, the storage process parameters are used to characterize the storage process situation of the raw materials of the pilot production product, and the raw material storage equipment static parameters are used to characterize the situation of the raw material storage equipment in a static state;

[0008] Through a preset first model, according to the design parameters of the preset pilot production product, the production process parameters, the production line static parameters, and the product quality standard, obtain a product production process standard, where the product production process standard is used to characterize the regulations in the process of producing a product;

[0009] Through a preset second model, according to the raw material parameters, the storage process parameters, the raw material storage equipment static parameters, and the product quality standard, obtain a raw material storage standard, where the raw material storage standard is used to characterize the regulations in the process of storing raw materials;

[0010] Through a preset third model, according to the product production process standard, the production process parameters, and the product quality standard, obtain a workshop environment standard, where the workshop environment standard is used to characterize the regulations regarding the internal environment of the workshop in the process of producing a product;

[0011] Based on the raw material storage standard, the product production process standard, and the workshop environment standard, obtain a target product process standard.

[0012] Specifically, the preset first model includes a first input layer, a first hidden layer, and a first output layer, and the first output layer includes three first nodes;

[0013] The obtaining of the product production process standard through the preset first model according to the design parameters of the preset pilot production product, the production process parameters, the production line static parameters, and the product quality standard includes:

[0014] Through the first input layer, according to the design parameters of the preset pilot production product, the production process parameters, the production line static parameters, and the product quality standard, obtain a first input vector;

[0015] Through the first hidden layer, a first feature vector is obtained according to the first input vector;

[0016] Through the first output layer, a product production process standard is obtained according to the first feature vector, where the product production process standard includes process operation steps, process time control ranges, and process quality inspection points, and the process operation steps, process time control ranges, and process quality inspection points respectively correspond to the three first nodes.

[0017] Specifically, the first hidden layer includes a first fully connected layer, a second fully connected layer, and a third fully connected layer. The ratio of the number of nodes in the first fully connected layer, the number of nodes in the second fully connected layer, and the number of nodes in the third fully connected layer is 4:2:1. The activation functions of the first fully connected layer, the second fully connected layer, and the third fully connected layer are all ReLU functions;

[0018] The obtaining of the first feature vector according to the first input vector through the first hidden layer includes:

[0019] Through the first fully connected layer, a first intermediate vector is obtained according to the first input vector;

[0020] Through the second fully connected layer, a second intermediate vector is obtained according to the first intermediate vector;

[0021] Through the third fully connected layer, the first feature vector is obtained according to the second intermediate vector.

[0022] Specifically, the preset second model includes a second input layer, a second hidden layer, and a second output layer, and the second output layer includes three second nodes;

[0023] The obtaining of the raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment, and the product quality standard through the preset second model includes:

[0024] Through the second input layer, a second input vector is obtained according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment, and the product quality standard;

[0025] Through the second hidden layer, a second feature vector is obtained according to the second input vector;

[0026] Through the second output layer, according to the second feature vector, obtain the raw material storage standard, where the raw material storage standard includes a storage temperature range, a humidity control range, and a pressure control range, and the storage temperature range, the humidity control range, and the pressure control range respectively correspond to the three second nodes.

[0027] Specifically, the second hidden layer includes a fourth fully connected layer, a fifth fully connected layer, and a sixth fully connected layer. The ratio of the number of nodes in the fourth fully connected layer, the number of nodes in the fifth fully connected layer, and the number of nodes in the sixth fully connected layer is 4:2:1. The activation functions of the fourth fully connected layer, the fifth fully connected layer, and the sixth fully connected layer are all ReLU functions;

[0028] The obtaining of the second feature vector through the second hidden layer according to the second input vector includes:

[0029] Through the fourth fully connected layer, according to the second input vector, obtain a third intermediate vector;

[0030] Through the fifth fully connected layer, according to the third intermediate vector, obtain a fourth intermediate vector;

[0031] Through the sixth fully connected layer, according to the fourth intermediate vector, obtain the second feature vector.

[0032] Specifically, the preset third model includes a third input layer, a third hidden layer, and a third output layer. The third output layer includes three third nodes;

[0033] The obtaining of the workshop environment standard through the preset third model according to the product production process standard, the production process parameters, and the product quality standard includes:

[0034] Through the third input layer, according to the product production process standard, the production process parameters, and the product quality standard, obtain a third input vector;

[0035] Through the third hidden layer, according to the third input vector, obtain a third feature vector;

[0036] Through the third output layer, according to the third feature vector, obtain the workshop environment standard, where the workshop environment standard includes a workshop temperature range, a workshop humidity range, and a workshop lighting intensity range, and the workshop temperature range, the workshop humidity range, and the workshop lighting intensity range respectively correspond to the three third nodes.

[0037] Specifically, the third hidden layer includes the seventh fully connected layer, the eighth fully connected layer, and the ninth fully connected layer. The ratio of the number of nodes in the seventh fully connected layer, the number of nodes in the eighth fully connected layer, and the number of nodes in the ninth fully connected layer is 4:2:1. The activation functions of the seventh fully connected layer, the eighth fully connected layer, and the ninth fully connected layer are all ReLU functions;

[0038] Obtaining the third feature vector through the third hidden layer according to the third input vector includes:

[0039] Obtaining the fifth intermediate vector through the seventh fully connected layer according to the third input vector;

[0040] Obtaining the sixth intermediate vector through the eighth fully connected layer according to the fifth intermediate vector;

[0041] Obtaining the third feature vector through the ninth fully connected layer according to the sixth intermediate vector.

[0042] To achieve the above object, the present application further provides a product process standard generation device based on the industrial Internet of Things, which is applied to a product process system. The product process system includes a management platform, an object platform, and a sensing network platform. The object platform includes workshop environment monitoring equipment, a production line, and raw material storage equipment. The workshop environment monitoring equipment is used to monitor the environmental conditions of the production workshop. The management platform and the object platform are communicatively connected through the sensing network platform;

[0043] The device includes:

[0044] A first unit, configured to obtain the design parameters of a preset trial production product, the production process parameters of the trial production product, the production line static parameters corresponding to the production line, the raw material parameters corresponding to the trial production product, the storage process parameters of the raw materials corresponding to the trial production product, the raw material storage device static parameters corresponding to the raw material storage device, and the product quality standards corresponding to the trial production product. Among them, the production process parameters are used to characterize the status of the process of producing the trial production product, the production line static parameters are used to characterize the status of the production line in a static state, the raw material parameters are used to characterize the status of the raw materials of the trial production product, the storage process parameters are used to characterize the storage process status of the raw materials of the trial production product, and the raw material storage device static parameters are used to characterize the status of the raw material storage device in a static state;

[0045] A second unit, configured to obtain a product production process standard according to the design parameters of the preset pilot production product, the production process parameters, the static parameters of the production line, and the product quality standard through a preset first model, where the product production process standard is used to characterize the regulations in the process of producing the product;

[0046] A third unit, configured to obtain a raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment, and the product quality standard through a preset second model, where the raw material storage standard is used to characterize the regulations in the process of storing the raw materials;

[0047] A fourth unit, configured to obtain a workshop environment standard according to the product production process standard, the production process parameters, and the product quality standard through a preset third model, where the workshop environment standard is used to characterize the regulations regarding the internal environment of the workshop in the process of producing the product;

[0048] A fifth unit, configured to obtain a target product process standard based on the raw material storage standard, the product production process standard, and the workshop environment standard.

[0049] To achieve the above object, the present application further provides a terminal, including a memory storing multiple instructions; the processor loads the instructions from the memory to execute the steps in any one of the methods provided by the present application.

[0050] To achieve the above object, the present application further provides a medium, the medium storing multiple instructions, the instructions being adapted to be loaded by a processor to execute the steps in any one of the methods provided by the present application.

[0051] A method, device, terminal, and medium for generating a product process standard based on an industrial Internet of Things provided by the present application can first obtain the design parameters of a preset pilot production product, production process parameters, static parameters of a production line, raw material parameters, storage process parameters of raw materials, static parameters of raw material storage equipment, and product quality standards; then, obtain a product production process standard through a preset first model; thereafter, obtain a raw material storage standard through a preset second model; then, obtain a workshop environment standard through a preset third model; and finally, accurately obtain a target product process standard based on the raw material storage standard, the product production process standard, and the workshop environment standard, improving the ex-factory quality of the product.

[0052] The present application can improve the accuracy of formulating a product process standard by combining Internet of Things technology and a neural network model, thereby improving the production quality of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 Schematic flowchart of the method provided by the embodiment of the present application;

[0054] Figure 2 Schematic diagram of the product process system provided by the embodiment of the present application;

[0055] Figure 3 Schematic structural diagram of the device provided by the embodiment of the present application;

[0056] Figure 4 Schematic structural diagram of the terminal provided by the embodiment of the present application. Detailed implementation manners

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0058] Since the standards formulated by different technicians may vary greatly, lacking unified standards and specifications, which affects the consistency and quality of production; the formulation of standards depends to a large extent on the personal experience and judgment of technicians, and it is easy to have deviations and inconsistencies; although a large amount of data is collected in the process of manually formulating standards, these data are often not fully utilized for in-depth analysis and optimization, resulting in limited scientificity and rationality of the standards, and then resulting in insufficient accuracy of the product process standards, thus resulting in the inability to guarantee the product quality.

[0059] Therefore, the embodiments of the present application provide a product process standard generation method, device, terminal and medium based on the industrial Internet of Things to solve actual technical problems.

[0060] In some embodiments, the device may be specifically integrated in an electronic device, and the electronic device may be a device such as a terminal or a server.

[0061] In some embodiments, the server may also be implemented in the form of a terminal.

[0062] Among them, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0063] Among them, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, and this application does not make any restrictions here.

[0064] The following will be described in detail respectively. It should be noted that the serial numbers of the following embodiments do not limit the preferred order of the embodiments.

[0065] An embodiment of the present application provides a method for generating product process standards based on the industrial Internet of Things. The method can improve the accuracy of formulating product process standards by combining Internet of Things technology and neural network models, thereby improving the production quality of products.

[0066] As Figure 1 and Figure 2 shown, the method is applied to a product process system. The product process system includes a management platform, an object platform, and a sensing network platform. The object platform includes workshop environment monitoring equipment, a production line, and raw material storage equipment. The workshop environment monitoring equipment is used to monitor the environmental conditions of the production workshop. The management platform is communicatively connected to the object platform through the sensing network platform.

[0067] In some embodiments, the management platform is responsible for the management and control of the entire system, including task scheduling, data processing, etc.

[0068] The object platform can refer to an object-oriented design architecture for managing and processing various data objects within the system. The object platform provides a structured way to organize, store, and operate data, making the system more flexible and scalable. Specifically, the object platform in the product process system includes workshop environment monitoring equipment, a production line, and raw material storage equipment. The workshop environment monitoring equipment is used to monitor the environmental conditions of the production workshop. The production line is used to produce trial production products and subsequent products. The raw material storage equipment is used to store the raw materials corresponding to the trial production products or the raw materials corresponding to the products.

[0069] The sensing network platform can serve as the middle layer of the product process system, used to collect data information from the object platform, and responsible for transmitting the input instructions of the operator from the management platform to the object platform.

[0070] Industrial Internet of Things (IIoT) refers to a technology system that realizes the real-time collection, transmission, analysis, and application of data through the interconnection of Internet technology and physical devices such as sensors and smart devices in the industrial production and manufacturing process. The core goal of the industrial Internet of Things is to improve production efficiency, optimize resource allocation, enhance product quality and safety, thereby promoting the intelligent and digital transformation of industrial production.

[0071] In some embodiments, based on the product process system, the workshop environment monitoring equipment, production line, and raw material storage equipment are controlled through a management platform.

[0072] Such as Figure 1 , the specific process of the method can be as follows:

[0073] S110. Obtain the design parameters of the preset trial-produced product, the production process parameters of the trial-produced product, the production line static parameters corresponding to the production line, the raw material parameters corresponding to the trial-produced product, the storage process parameters of the raw materials corresponding to the trial-produced product, the raw material storage equipment static parameters corresponding to the raw material storage equipment, and the product quality standards corresponding to the trial-produced product. Among them, the production process parameters are used to characterize the status of the process of producing the trial-produced product, the production line static parameters are used to characterize the status of the production line in a static state, the raw material parameters are used to characterize the status of the raw materials of the trial-produced product, the storage process parameters are used to characterize the storage process status of the raw materials of the trial-produced product, and the raw material storage equipment static parameters are used to characterize the status of the raw material storage equipment in a static state.

[0074] In some embodiments, the design parameters may be various specifications and requirements determined during the design stage of the product, which are used to guide the production process. The design parameters may include:

[0075] Dimensions and shape: The specific dimensions, shape, and structure of the product;

[0076] Material: The material type, composition, and performance requirements of the product;

[0077] Function requirements: The function and performance requirements of the product, such as strength, durability, electrical conductivity, etc.;

[0078] Appearance requirements: The appearance requirements of the product, such as color, surface treatment, etc.

[0079] The production process parameters may be various parameters that need to be monitored and controlled during the production process to ensure the stability of the production process and product quality. The production process parameters may include:

[0080] Temperature: The temperature control range of each process during the production process;

[0081] Pressure: The pressure control range of each process during the production process;

[0082] Speed: The operating speed of the production equipment;

[0083] Time: The time control of each process;

[0084] Power: The power consumption of the production equipment;

[0085] Flow rate: The flow rate of the material.

[0086] The static parameters of the production line can be the basic characteristics of the production line under static conditions, which are used to evaluate the capacity and applicability of the production line. The static parameters of the production line can include:

[0087] Equipment model: The main equipment models and specifications on the production line;

[0088] Maximum production capacity: The maximum production capacity of the production line;

[0089] Precision: The precision and stability of the production equipment;

[0090] Control system: The type and function of the control system of the production line;

[0091] Maintenance frequency: The maintenance frequency and cycle of the equipment;

[0092] Service life: The service life and lifespan of the equipment;

[0093] Energy consumption: The energy consumption level of the production line;

[0094] Safety level: The safety protection level of the production line.

[0095] The raw material parameters can be the various characteristics of the raw materials used to produce products, which are used to ensure the quality and applicability of the raw materials. The raw material parameters can include:

[0096] Composition: The chemical composition and ratio of the raw materials;

[0097] Purity: The purity and impurity content of the raw materials;

[0098] Density: The density of the raw materials;

[0099] Particle size: The particle size distribution of the raw materials;

[0100] Moisture content: The moisture content of the raw materials;

[0101] Physical properties: Such as hardness, elastic modulus, etc.;

[0102] Chemical properties: Such as corrosion resistance, chemical stability, etc.

[0103] The storage process parameters can be the various parameters that need to be monitored and controlled during the storage process of the raw materials, which are used to ensure the quality of the raw materials during storage. The storage process parameters can include:

[0104] Temperature: The temperature control range of the storage environment;

[0105] Humidity: The humidity control range of the storage environment;

[0106] Light: The lighting conditions of the storage environment;

[0107] Ventilation: The ventilation situation of the storage environment;

[0108] Oxygen concentration: The oxygen concentration of the storage environment;

[0109] Air pressure: The air pressure of the storage environment.

[0110] The static parameters of the raw material storage device can be the basic characteristics of the storage device under static conditions, which are used to evaluate the performance and applicability of the storage device. The static parameters of the raw material storage device can include:

[0111] Capacity: The storage capacity of the storage device;

[0112] Sealing performance: The sealing performance of the storage device;

[0113] Material: The material type and performance of the storage device;

[0114] Cleanliness: The cleanliness and hygiene conditions of the storage device;

[0115] Temperature control ability: The temperature control ability of the storage device;

[0116] Humidity control ability: The humidity control ability of the storage device;

[0117] Ventilation ability: The ventilation ability of the storage device;

[0118] Safety performance: The safety protection measures of the storage device.

[0119] The product quality standard can be the quality requirements that the product needs to meet after production, which are used to evaluate the performance and quality of the product. The product quality standard can include:

[0120] Strength: The mechanical strength of the product;

[0121] Durability: The service life and durability of the product;

[0122] Appearance: The appearance quality and surface treatment of the product;

[0123] Dimensional tolerance: The dimensional accuracy and tolerance range of the product;

[0124] Surface roughness: The surface roughness of the product;

[0125] Chemical stability: The chemical stability and corrosion resistance of the product.

[0126] S120. Using a preset first model, based on the design parameters of the preset trial production product, the production process parameters, the static parameters of the production line, and the product quality standards, obtain the product production process standards, where the product production process standards are used to characterize the regulations in the process of producing products, and the preset first model is used to optimize the production process of products and the quality of subsequent products.

[0127] In some embodiments, the preset first model includes a first input layer, a first hidden layer, and a first output layer, and the first output layer includes three first nodes.

[0128] Specifically, the step of obtaining the product production process standards by using the preset first model based on the design parameters of the preset trial production product, the production process parameters, the static parameters of the production line, and the product quality standards includes the step contents of S121 to S123 as shown below:

[0129] S121. Through the first input layer, based on the design parameters of the preset trial production product, the production process parameters, the static parameters of the production line, and the product quality standards, obtain a first input vector.

[0130] In some embodiments, if the design parameters of the preset trial production product, the production process parameters, the static parameters of the production line, and the product quality standards are n design parameters, m production process parameters, p static parameters of the production line, and q product quality standards respectively, the first input vector obtained through the first input layer can be a vector with a dimension of (n + m + p + q).

[0131] S122. Through the first hidden layer, based on the first input vector, obtain a first feature vector.

[0132] In some embodiments, the first hidden layer includes a first fully connected layer, a second fully connected layer, and a third fully connected layer, and the ratio of the number of nodes in the first fully connected layer, the number of nodes in the second fully connected layer, and the number of nodes in the third fully connected layer is 4:2:1, and the activation functions of the first fully connected layer, the second fully connected layer, and the third fully connected layer are all ReLU functions.

[0133] Specifically, the step of obtaining the first feature vector through the first hidden layer based on the first input vector includes the following:

[0134] S1221. Through the first fully connected layer, based on the first input vector, obtain a first intermediate vector.

[0135] In some embodiments, the input dimension corresponding to the first fully connected layer may be (n + m + p + q), the output dimension of the first fully connected layer is 128, the activation function of the first fully connected layer is the ReLU function, and the weight matrix corresponding to the first fully connected layer may be (128, n + m + p + q). Input the first input vector into the first fully connected layer, and output the first intermediate vector.

[0136] S1222. Through the second fully connected layer, obtain a second intermediate vector according to the first intermediate vector.

[0137] In some embodiments, the input dimension corresponding to the second fully connected layer may be 128, the output dimension of the second fully connected layer is 64, the activation function of the second fully connected layer is the ReLU function, and the weight matrix corresponding to the second fully connected layer may be (64, 128). Input the first intermediate vector into the second fully connected layer, and output the second intermediate vector.

[0138] S1223. Through the third fully connected layer, obtain the first feature vector according to the second intermediate vector.

[0139] In some embodiments, the input dimension corresponding to the third fully connected layer may be 64, the output dimension of the first fully connected layer is 32, the activation function of the second fully connected layer is the ReLU function, and the weight matrix corresponding to the second fully connected layer may be (32, 64). Input the second intermediate vector into the third fully connected layer, and output the first feature vector.

[0140] S123. Through the first output layer, obtain the product production process standard according to the first feature vector, where the product production process standard includes process operation steps, process time control range, and process quality inspection points, and the process operation steps, process time control range, and process quality inspection points respectively correspond to the three first nodes.

[0141] In some embodiments, the output dimension of the first output layer may be 3, the activation function of the first output layer may be a linear activation function, the weight matrix corresponding to the first output layer may be (3, 32), and the product production process standard may be a vector with a dimension of 3, that is, it can be expressed as (process operation steps, process time control range, process quality inspection points).

[0142] S130. Through a preset second model, obtain a raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage device, and the product quality standard, where the raw material storage standard is used to characterize the regulations in the process of storing raw materials, and the preset second model is used to ensure the quality of raw materials.

[0143] In some embodiments, the preset second model includes a second input layer, a second hidden layer, and a second output layer, and the second output layer includes three second nodes.

[0144] Specifically, obtaining the raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage device, and the product quality standard through the preset second model includes the step contents of S131 to S133 as shown below:

[0145] S131: Through the second input layer, obtain a second input vector according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage device, and the product quality standard.

[0146] In some embodiments, if the raw material parameters, the storage process parameters, the static parameters of the raw material storage device, and the product quality standard are a raw material parameters, b storage process parameters, c static parameters of the raw material storage device, and d product quality standards respectively, the second input vector obtained through the second input layer may be a vector with a dimension of (a + b + c + d).

[0147] S132: Through the second hidden layer, obtain a second feature vector according to the second input vector.

[0148] In some embodiments, the second hidden layer includes a fourth fully connected layer, a fifth fully connected layer, and a sixth fully connected layer. The ratio of the number of nodes in the fourth fully connected layer, the number of nodes in the fifth fully connected layer, and the number of nodes in the sixth fully connected layer is 4:2:1. The activation functions of the fourth fully connected layer, the fifth fully connected layer, and the sixth fully connected layer are all ReLU functions.

[0149] Specifically, obtaining the second feature vector according to the second input vector through the second hidden layer includes the step contents of S1321 to S1323 as shown below:

[0150] S1321: Through the fourth fully connected layer, obtain a third intermediate vector according to the second input vector.

[0151] In some embodiments, the input dimension corresponding to the fourth fully connected layer may be (a + b + c + d), the output dimension of the fourth fully connected layer is 128, the activation function of the fourth fully connected layer is a ReLU function, and the weight matrix corresponding to the fourth fully connected layer may be (128, a + b + c + d). Input the second input vector into the fourth fully connected layer, and output to obtain the third intermediate vector.

[0152] S1322. Through the fifth fully-connected layer, obtain a fourth intermediate vector according to the third intermediate vector.

[0153] In some embodiments, the input dimension corresponding to the fifth fully-connected layer may be 128, the output dimension of the fifth fully-connected layer is 64, the activation function of the fifth fully-connected layer is the ReLU function, and the weight matrix corresponding to the fifth fully-connected layer may be (64, 128). Input the third intermediate vector into the fifth fully-connected layer, and output to obtain the fourth intermediate vector.

[0154] S1323. Through the sixth fully-connected layer, obtain the second feature vector according to the fourth intermediate vector.

[0155] In some embodiments, the input dimension corresponding to the sixth fully-connected layer may be 64, the output dimension of the sixth fully-connected layer is 32, the activation function of the sixth fully-connected layer is the ReLU function, and the weight matrix corresponding to the sixth fully-connected layer may be (32, 64). Input the fourth intermediate vector into the sixth fully-connected layer, and output to obtain the second feature vector.

[0156] S133. Through the second output layer, obtain the raw material storage standard according to the second feature vector, where the raw material storage standard includes a storage temperature range, a humidity control range, and a pressure control range, and the storage temperature range, the humidity control range, and the pressure control range respectively correspond to the three second nodes.

[0157] In some embodiments, the output dimension of the second output layer may be 3, the activation function of the second output layer may be a linear activation function, the weight matrix corresponding to the second output layer may be (3, 32), and the raw material storage standard may be a vector with a dimension of 3, that is, it can be expressed as (storage temperature range, humidity control range, pressure control range).

[0158] S140. Through a preset third model, obtain a workshop environment standard according to the product production process standard, the production process parameters, and the product quality standard, where the workshop environment standard is used to characterize the regulations on the internal environment of the workshop during the product production process, and the preset third model is used to standardize the management of the workshop environment and ensure that the workshop environment will not have a negative impact on the product production process and product quality.

[0159] In some embodiments, the preset third model includes a third input layer, a third hidden layer, and a third output layer, and the third output layer includes three third nodes.

[0160] Specifically, through a preset third model, according to the product production process standard, the production process parameters, and the product quality standard, a workshop environment standard is obtained, including the step contents of S141 to S143 shown below:

[0161] S141. Through the third input layer, according to the product production process standard, the production process parameters, and the product quality standard, a third input vector is obtained.

[0162] In some embodiments, if the product production process standard, the production process parameters, and the product quality standard are x product production process standards, y production process parameters, and z product quality standards respectively, the third input vector obtained through the third input layer can be a vector of (x + y + z).

[0163] S142. Through the third hidden layer, according to the third input vector, a third feature vector is obtained.

[0164] In some embodiments, the third hidden layer includes a seventh fully connected layer, an eighth fully connected layer, and a ninth fully connected layer. The ratio of the number of nodes in the seventh fully connected layer, the number of nodes in the eighth fully connected layer, and the number of nodes in the ninth fully connected layer is 4:2:1. The activation functions of the seventh fully connected layer, the eighth fully connected layer, and the ninth fully connected layer are all ReLU functions.

[0165] Specifically, the step of obtaining the third feature vector through the third hidden layer according to the third input vector includes the step contents of S1421 to S1423 shown below:

[0166] S1421. Through the seventh fully connected layer, according to the third input vector, a fifth intermediate vector is obtained.

[0167] In some embodiments, the input dimension corresponding to the seventh fully connected layer can be (x + y + z), the output dimension of the seventh fully connected layer is 128, the activation function of the seventh fully connected layer is a ReLU function, and the weight matrix corresponding to the seventh fully connected layer can be (128, x + y + z). The third input vector is input into the seventh fully connected layer, and the fifth intermediate vector is output.

[0168] S1422. Through the eighth fully connected layer, according to the fifth intermediate vector, a sixth intermediate vector is obtained.

[0169] In some embodiments, the input dimension corresponding to the eighth fully-connected layer may be 128, the output dimension of the eighth fully-connected layer is 64, the activation function of the eighth fully-connected layer is the ReLU function, and the weight matrix corresponding to the eighth fully-connected layer may be (64, 128). The fifth intermediate vector is input into the eighth fully-connected layer, and the sixth intermediate vector is output.

[0170] S1423. Through the ninth fully-connected layer, the third feature vector is obtained according to the sixth intermediate vector.

[0171] In some embodiments, the input dimension corresponding to the ninth fully-connected layer may be 64, the output dimension of the ninth fully-connected layer is 32, the activation function of the ninth fully-connected layer is the ReLU function, and the weight matrix corresponding to the ninth fully-connected layer may be (32, 64). The sixth intermediate vector is input into the ninth fully-connected layer, and the third feature vector is output.

[0172] S143. Through the third output layer, the workshop environment standard is obtained according to the third feature vector, where the workshop environment standard includes a workshop temperature range, a workshop humidity range, and a workshop lighting intensity range, and the workshop temperature range, the workshop humidity range, and the workshop lighting intensity range respectively correspond to the three third nodes.

[0173] In some embodiments, the output dimension of the third output layer may be 3, the activation function of the third output layer may be a linear activation function, the weight matrix corresponding to the third output layer may be (3, 32), and the workshop environment standard may be a vector with a dimension of 3, that is, it can be expressed as (workshop temperature range, workshop humidity range, workshop lighting intensity range).

[0174] S150. Based on the raw material storage standard, the product production process standard, and the workshop environment standard, the target product process standard is obtained.

[0175] In some embodiments, the raw material storage standard, the product production process standard, and the workshop environment standard are independently integrated respectively, and then, the raw material storage standard, the product production process standard, and the workshop environment standard can be directly combined to form the target product process standard. The target product process standard may include the following contents:

[0176] (1) Raw material management standard:

[0177] Storage temperature range: 15°C - 25°C;

[0178] Storage humidity range: 40% - 60%;

[0179] Light control: Avoid direct sunlight;

[0180] Ventilation frequency: Ventilate at least once per hour;

[0181] Regular inspection period: Inspect once a week;

[0182] Safety operation procedures: Prohibit smoking and fire, wear anti-static clothing;

[0183] Waste treatment: Store separately by category and dispose of regularly;

[0184] (2) Production process management standards:

[0185] Process sequence: Raw material preparation → Cutting → Welding → Assembly → Inspection → Packaging; Operating steps: Record the operating steps of each process in detail;

[0186] Time control: Time requirements for each process;

[0187] Temperature control: The welding temperature is set at 300 °C;

[0188] Pressure control: The assembly pressure is set at 10 N;

[0189] Speed control: The production line speed is set at 10 pieces per minute;

[0190] Quality inspection points: Inspect the quality of welding points after welding and the overall performance after assembly;

[0191] Inspection frequency: Randomly inspect 10% of each batch of products;

[0192] Equipment maintenance: Conduct a comprehensive maintenance once a month;

[0193] Safety operation procedures: Wear protective equipment and prohibit unauthorized disassembly of equipment;

[0194] Waste treatment: Store separately by category and dispose of regularly;

[0195] Environmental protection measures: Install waste gas treatment devices and regularly clean the wastewater treatment pool;

[0196] (3) Workshop environmental management standards:

[0197] Temperature range: 20 °C - 25 °C;

[0198] Humidity range: 40% - 60%;

[0199] Cleanliness class: ISO Class 7;

[0200] Noise level: Not exceeding 70 dB;

[0201] Illumination intensity: Not less than 300 lux;

[0202] Ventilation frequency: Ventilate at least twice per hour;

[0203] Safety operating procedures: Conduct safety training regularly and set up emergency evacuation routes;

[0204] Exhaust gas emission standards: Meet national emission standards;

[0205] Wastewater treatment standards: Meet national emission standards;

[0206] Solid waste treatment standards: Store classified and treat regularly.

[0207] In summary, this application provides a method for generating product process standards based on the industrial Internet of Things. By combining Internet of Things technology and neural network models, the accuracy of formulating product process standards is improved, thereby improving the production quality of products.

[0208] To better implement the above method, an embodiment of this application also provides a device for generating product process standards based on the industrial Internet of Things. This device can be specifically integrated in an electronic device, which can be a terminal, a server, or other devices. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, or other devices; the server can be a single server or a server cluster composed of multiple servers.

[0209] For example, in this embodiment, taking the device for generating product process standards based on the industrial Internet of Things specifically integrated in a terminal as an example, the method of the embodiment of this application will be described in detail.

[0210] For example, as Figure 3 shown, the device 300 for generating product process standards based on the industrial Internet of Things may include a first unit 301, a second unit 302, a third unit 303, a fourth unit 304, and a fifth unit 305, and is applied to a product process system. The product process system includes a management platform, an object platform, and a sensing network platform. The object platform includes workshop environment monitoring equipment, a production line, and raw material storage equipment. The workshop environment monitoring equipment is used to monitor the environmental conditions of the production workshop. The management platform is communicatively connected to the object platform through the sensing network platform;

[0211] The device includes:

[0212] The first unit 301 is configured to obtain the design parameters of a preset pre-production product, the production process parameters of the pre-production product, the production line static parameters corresponding to the production line, the raw material parameters corresponding to the pre-production product, the storage process parameters of the raw materials corresponding to the pre-production product, the raw material storage device static parameters corresponding to the raw material storage device, and the product quality standards corresponding to the pre-production product. Among them, the production process parameters are used to characterize the status of the process of producing the pre-production product, the production line static parameters are used to characterize the status of the production line in a static state, the raw material parameters are used to characterize the status of the raw materials of the pre-production product, the storage process parameters are used to characterize the storage process status of the raw materials of the pre-production product, and the raw material storage device static parameters are used to characterize the status of the raw material storage device in a static state;

[0213] The second unit 302 is configured to obtain a product production process standard according to the design parameters of the preset pre-production product, the production process parameters, the production line static parameters, and the product quality standards through a preset first model. Among them, the product production process standard is used to characterize the regulations in the process of producing a product;

[0214] The third unit 303 is configured to obtain a raw material storage standard according to the raw material parameters, the storage process parameters, the raw material storage device static parameters, and the product quality standards through a preset second model. Among them, the raw material storage standard is used to characterize the regulations in the process of storing raw materials;

[0215] The fourth unit 304 is configured to obtain a workshop environment standard according to the product production process standard, the production process parameters, and the product quality standards through a preset third model. Among them, the workshop environment standard is used to characterize the regulations regarding the internal environment of the workshop in the process of producing a product;

[0216] The fifth unit 305 is configured to obtain a target product process standard based on the raw material storage standard, the product production process standard, and the workshop environment standard.

[0217] In specific implementation, the above-mentioned units can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. For the specific implementation of the above-mentioned units, reference can be made to the foregoing method embodiments, which will not be elaborated herein.

[0218] As can be seen from the above, the embodiments of the present application can improve the accuracy of formulating product process standards by combining Internet of Things technology and neural network models, thereby improving the production quality of products.

[0219] The embodiments of the present application further provide an electronic device, which can be a device such as a terminal, a server, etc. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, and so on; the server can be a single server or a server cluster composed of multiple servers, and so on.

[0220] In some embodiments, the product processing device can also be integrated in multiple electronic devices. For example, the product processing device can be integrated in multiple servers, and the method for generating product process standards based on the industrial Internet of Things of the present application can be implemented by multiple servers.

[0221] In this embodiment, the electronic device in this embodiment will be described in detail taking the example that the electronic device is a terminal. For example, as Figure 4 shown, it shows a schematic structural diagram of the terminal 400 involved in the embodiments of the present application. Specifically:

[0222] The terminal 400 may include components such as a processor 401 with one or more processing cores, a memory 402 of one or more media, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art can understand that Figure 4 the structure of the terminal 400 shown in does not constitute a limitation on the terminal 400, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0223] The processor 401 is the control center of the terminal 400, connecting various parts of the entire terminal 400 through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402, it executes various functions of the terminal 400 and processes data, thereby monitoring the terminal 400 as a whole. In some embodiments, the processor 401 may include one or more processing cores; in some embodiments, the processor 401 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 401 either.

[0224] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the terminal 400. In addition, the memory 402 can include high-speed random access memory and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. Correspondingly, the memory 402 can also include a memory controller to provide the processor 401 with access to the memory 402.

[0225] The terminal 400 further includes a power supply 403 for powering each component. In some embodiments, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0226] The terminal 400 may further include an input module 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0227] The terminal 400 may further include a communication module 405. In some embodiments, the communication module 405 can include a wireless module. The terminal 400 can perform short-distance wireless transmission through the wireless module of the communication module 405, thereby providing users with wireless broadband Internet access. For example, the communication module 405 can be used to help users send and receive emails, browse web pages, and access streaming media, etc.

[0228] Although not shown, the terminal 400 may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 401 in the terminal 400 will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402 to implement various functions as follows:

[0229] Obtain the design parameters of the preset pilot production product, the production process parameters of the pilot production product, the production line static parameters corresponding to the production line, the raw material parameters corresponding to the pilot production product, the storage process parameters of the raw materials corresponding to the pilot production product, the raw material storage equipment static parameters corresponding to the raw material storage equipment, and the product quality standard corresponding to the pilot production product. Among them, the production process parameters are used to characterize the situation of the process of producing the pilot production product, the production line static parameters are used to characterize the situation of the production line in a static state, the raw material parameters are used to characterize the situation of the raw materials of the pilot production product, the storage process parameters are used to characterize the storage process situation of the raw materials of the pilot production product, and the raw material storage equipment static parameters are used to characterize the situation of the raw material storage equipment in a static state;

[0230] Through a preset first model, according to the design parameters of the preset pilot production product, the production process parameters, the production line static parameters, and the product quality standard, obtain the product production process standard. Among them, the product production process standard is used to characterize the regulations in the process of producing products;

[0231] Through a preset second model, according to the raw material parameters, the storage process parameters, the raw material storage equipment static parameters, and the product quality standard, obtain the raw material storage standard. Among them, the raw material storage standard is used to characterize the regulations in the process of storing raw materials;

[0232] Through a preset third model, according to the product production process standard, the production process parameters, and the product quality standard, obtain the workshop environment standard. Among them, the workshop environment standard is used to characterize the regulations regarding the internal environment of the workshop in the process of producing products;

[0233] Based on the raw material storage standard, the product production process standard, and the workshop environment standard, obtain the target product process standard.

[0234] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, which will not be elaborated here.

[0235] As can be seen from the above, the embodiments of the present application can improve the accuracy of formulating the product process standard by combining the Internet of Things technology and the neural network model, and thus improve the production quality of the product.

[0236] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions. The instructions can be stored in a medium and loaded and executed by a processor.

[0237] To this end, an embodiment of the present application provides a medium in which multiple instructions are stored, and these instructions can be loaded by a processor to execute the steps in any one of the product process standard generation methods based on the industrial Internet of Things provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0238] Obtain the design parameters of the pre-production product, the production process parameters of the pre-production product, the static production line parameters corresponding to the production line, the raw material parameters corresponding to the pre-production product, the storage process parameters of the raw materials corresponding to the pre-production product, the static raw material storage device parameters corresponding to the raw material storage device, and the product quality standard corresponding to the pre-production product. Among them, the production process parameters are used to characterize the situation of the process of producing the pre-production product, the static production line parameters are used to characterize the situation of the production line in a static state, the raw material parameters are used to characterize the situation of the raw materials of the pre-production product, the storage process parameters are used to characterize the storage process situation of the raw materials of the pre-production product, and the static raw material storage device parameters are used to characterize the situation of the raw material storage device in a static state;

[0239] Through a preset first model, according to the design parameters of the preset pre-production product, the production process parameters, the static production line parameters, and the product quality standard, obtain the product production process standard, where the product production process standard is used to characterize the regulations in the process of producing a product;

[0240] Through a preset second model, according to the raw material parameters, the storage process parameters, the static raw material storage device parameters, and the product quality standard, obtain the raw material storage standard, where the raw material storage standard is used to characterize the regulations in the process of storing raw materials;

[0241] Through a preset third model, according to the product production process standard, the production process parameters, and the product quality standard, obtain the workshop environment standard, where the workshop environment standard is used to characterize the regulations regarding the internal environment of the workshop in the process of producing a product;

[0242] Based on the raw material storage standard, the product production process standard, and the workshop environment standard, obtain the target product process standard.

[0243] Among them, the medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0244] According to one aspect of the present application, there is provided a computer program product or a computer program, which includes computer instructions stored in a medium. The processor of the computer device reads the computer instructions from the medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the various alternative implementations provided in the above embodiments.

[0245] Due to the instructions stored in this medium, the steps in any one of the product process standard generation methods based on the industrial Internet of Things provided in the embodiments of the present application can be executed. Therefore, the beneficial effects that can be achieved by any one of the product process standard generation methods based on the industrial Internet of Things provided in the embodiments of the present application can be realized. For details, please refer to the previous embodiments and will not be elaborated here.

[0246] The above has introduced in detail a product process standard generation method, device, terminal, and medium based on the industrial Internet of Things provided in the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for generating product process standards based on industrial Internet of Things, characterized in that: Applied to a product process system, the product process system includes a management platform, a sensor network platform and an object platform, the object platform includes a workshop environment monitoring device, a production line and a raw material storage device, the workshop environment monitoring device is used to monitor the environmental conditions of the production workshop, and the management platform is connected to the object platform through the sensor network platform; The method comprises: Obtaining preset design parameters of the trial production product, production process parameters of the trial production product, static parameters of the production line corresponding to the production line, raw material parameters corresponding to the trial production product, storage process parameters of the raw materials corresponding to the trial production product, static parameters of raw material storage equipment corresponding to the raw material storage equipment, and product quality standards corresponding to the trial production product, wherein the production process parameters are used to characterize the status of the process of producing the trial production product, the static parameters of the production line are used to characterize the status of the production line in a static state, the raw material parameters are used to characterize the status of the raw materials of the trial production product, the storage process parameters are used to characterize the storage process status of the raw materials of the trial production product, and the static parameters of the raw material storage equipment are used to characterize the status of the raw material storage equipment in a static state; Obtaining a product production process standard through a preset first model according to the preset design parameters of the trial production product, the production process parameters, the production line static parameters and the product quality standard, wherein the product production process standard is used to characterize the regulations in the process of producing the product; Obtaining a raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment and the product quality standard through a preset second model, wherein the raw material storage standard is used to characterize the regulations in the process of storing raw materials; By using a preset third model, according to the product production process standard, the production process parameter and the product quality standard, a workshop environment standard is obtained, wherein the workshop environment standard is used to characterize the provisions on the internal environment of the workshop during the production process of the product; Based on the raw material storage standard, the product production process standard and the workshop environment standard, the target product process standard is obtained.

2. The method according to claim 1, characterized in that The preset first model includes a first input layer, a first hidden layer and a first output layer, and the first output layer includes three first nodes; The method of obtaining the product production process standard by using the preset first model according to the preset design parameters of the trial production product, the production process parameters, the production line static parameters and the product quality standard includes: Obtaining a first input vector through the first input layer according to the preset design parameters of the trial production product, the production process parameters, the production line static parameters and the product quality standard; Obtaining a first feature vector according to the first input vector through the first hidden layer; Through the first output layer, the product production process standard is obtained according to the first feature vector, wherein the product production process standard includes process operation steps, process time control range and process quality inspection points, and the process operation steps, process time control range and process quality inspection points correspond to the three first nodes respectively.

3. The method according to claim 2, characterized in that The first hidden layer includes a first fully connected layer, a second fully connected layer, and a third fully connected layer, the ratio of the number of nodes in the first fully connected layer, the number of nodes in the second fully connected layer, and the number of nodes in the third fully connected layer is 4:2:1, and the activation function of the first fully connected layer, the activation function of the second fully connected layer, and the activation function of the third fully connected layer are all ReLU functions; The step of obtaining a first feature vector according to the first input vector through the first hidden layer includes: Obtaining a first intermediate vector according to the first input vector through the first fully connected layer; Obtaining a second intermediate vector according to the first intermediate vector through the second fully connected layer; The first feature vector is obtained according to the second intermediate vector through the third fully connected layer.

4. The method according to claim 1, characterized in that The preset second model includes a second input layer, a second hidden layer and a second output layer, and the second output layer includes three second nodes; The method of obtaining the raw material storage standard by using the preset second model according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment and the product quality standard includes: Obtaining a second input vector through the second input layer according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage device and the product quality standard; Obtaining a second feature vector according to the second input vector through the second hidden layer; Through the second output layer, the raw material storage standard is obtained according to the second eigenvector, wherein the raw material storage standard includes a storage temperature range, a humidity control range and an air pressure control range, and the storage temperature range, the humidity control range and the air pressure control range correspond to the three second nodes respectively.

5. The method according to claim 4, characterized in that The second hidden layer includes a fourth fully connected layer, a fifth fully connected layer and a sixth fully connected layer, the ratio of the number of nodes in the fourth fully connected layer, the number of nodes in the fifth fully connected layer and the number of nodes in the sixth fully connected layer is 4:2:1, and the activation function of the fourth fully connected layer, the activation function of the fifth fully connected layer and the activation function of the sixth fully connected layer are all ReLU functions; The step of obtaining a second feature vector according to the second input vector through the second hidden layer includes: Obtaining a third intermediate vector according to the second input vector through the fourth fully connected layer; Obtaining a fourth intermediate vector according to the third intermediate vector through the fifth fully connected layer; The second feature vector is obtained according to the fourth intermediate vector through the sixth fully connected layer.

6. The method according to claim 1, characterized in that The preset third model includes a third input layer, a third hidden layer and a third output layer, and the third output layer includes three third nodes; The workshop environment standard is obtained by using the preset third model according to the product production process standard, the production process parameter and the product quality standard, including: Obtaining a third input vector through the third input layer according to the product production process standard, the production process parameter and the product quality standard; Obtaining a third eigenvector according to the third input vector through the third hidden layer; Through the third output layer, the workshop environment standard is obtained according to the third eigenvector, wherein the workshop environment standard includes a workshop temperature range, a workshop humidity range and a workshop lighting intensity range, and the workshop temperature range, the workshop humidity range and the workshop lighting intensity range correspond to the three third nodes respectively.

7. The method according to claim 6, characterized in that The third hidden layer is a seventh fully connected layer, an eighth fully connected layer and a ninth fully connected layer, the ratio of the number of nodes in the seventh fully connected layer, the number of nodes in the eighth fully connected layer and the number of nodes in the ninth fully connected layer is 4:2:1, and the activation function of the seventh fully connected layer, the activation function of the eighth fully connected layer and the activation function of the ninth fully connected layer are all ReLU functions; The step of obtaining a third feature vector according to the third input vector through the third hidden layer includes: Obtaining a fifth intermediate vector according to the third input vector through the seventh fully connected layer; Obtaining a sixth intermediate vector according to the fifth intermediate vector through the eighth fully connected layer; The third eigenvector is obtained through the ninth fully connected layer according to the sixth intermediate vector.

8. A product process standard generation device based on industrial Internet of Things, characterized in that: Applied to a product process system, the product process system includes a management platform, an object platform and a sensor network platform, the object platform includes a workshop environment monitoring device, a production line and a raw material storage device, the workshop environment monitoring device is used to monitor the environmental conditions of the production workshop, and the management platform is connected to the object platform through the sensor network platform; The device comprises: The first unit is used to obtain preset design parameters of the trial production product, production process parameters of the trial production product, static parameters of the production line corresponding to the production line, raw material parameters corresponding to the trial production product, storage process parameters of the raw materials corresponding to the trial production product, static parameters of raw material storage equipment corresponding to the raw material storage equipment, and product quality standards corresponding to the trial production product, wherein the production process parameters are used to characterize the status of the process of producing the trial production product, the production line static parameters are used to characterize the status of the production line in a static state, the raw material parameters are used to characterize the status of the raw materials of the trial production product, the storage process parameters are used to characterize the storage process status of the raw materials of the trial production product, and the raw material storage equipment static parameters are used to characterize the status of the raw material storage equipment in a static state; The second unit is used to obtain a product production process standard through a preset first model according to the preset design parameters of the trial production product, the production process parameters, the production line static parameters and the product quality standard, wherein the product production process standard is used to characterize the regulations in the process of producing the product; A third unit is used to obtain a raw material storage standard according to the raw material parameters, the storage process parameters, the static parameters of the raw material storage equipment and the product quality standard through a preset second model, wherein the raw material storage standard is used to characterize the regulations in the process of storing the raw materials; A fourth unit is used to obtain a workshop environment standard according to the product production process standard, the production process parameter and the product quality standard through a preset third model, wherein the workshop environment standard is used to characterize the provisions on the internal environment of the workshop during the production process of the product; The fifth unit is used to obtain the target product process standard based on the raw material storage standard, the product production process standard and the workshop environment standard.

9. A terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps in the method according to any one of claims 1 to 7.

10. A medium, characterized in that The medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method according to any one of claims 1 to 7.

Images