Process scheme generation method and device based on industrial Internet of Things, terminal and medium

Abstract

The invention discloses a process scheme generation method and device based on an industrial internet of things, a terminal and a medium. The method comprises the steps of obtaining design data of a product, design requirements of the product, standby raw material information of a production workshop, environmental data in the production workshop and production equipment parameters of production equipment; through a raw material scheme generation model, obtaining a target raw material scheme corresponding to the product according to the design data, the design demand and the standby raw material information; and through a process scheme generation model, obtaining a target process scheme corresponding to the product according to the target raw material scheme, the environmental data and the production equipment parameters. According to the technical scheme, through the neural network model, changing design requirements, raw material information and changes of production environment conditions are better adapted, so that errors caused by human judgment errors are reduced, and then the reliability of the obtained process scheme is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, terminal and medium for generating a process plan based on the industrial Internet of Things. Background Art

[0002] The process plan for producing a product refers to a series of steps and technical specifications formulated during the manufacturing process to ensure that the product meets the design requirements. It usually includes all the technical details required in the manufacturing process, from the selection of raw materials to the assembly and testing of the final product. The process plan usually includes the following aspects: Raw material selection: Select the type of material and its specifications suitable for manufacturing a specific product. These materials need to meet the performance requirements and cost control of the product; Processing technology: including cutting, forming, welding, casting, forging and other processing methods. Each method has its scope of application and advantages and disadvantages. Choosing the right processing technology is crucial to ensuring product quality; Equipment configuration: Determine the required type of production equipment and its configuration based on the processing technology adopted. Different equipment is suitable for different processing tasks; Environmental conditions: Specific environmental conditions may be required during the manufacturing process, such as temperature, humidity, etc., which will affect the processing effect.

[0003] However, the formulation of process plans is often highly dependent on the experience and technical level of engineers. The reliability of the process plan may not be guaranteed due to human misjudgment. Moreover, when production conditions or production needs change, adjustments are difficult. Human-made process plans cannot quickly adapt to changes in design requirements, raw material information and production environment conditions. Summary of the invention

[0004] The main purpose of this application is to provide a process plan generation method, device, terminal and medium based on the industrial Internet of Things, aiming to better adapt to changing design requirements, raw material information and production environment conditions through a neural network model, thereby reducing errors caused by human misjudgment and improving the reliability of the obtained process plan.

[0005] To achieve the above-mentioned purpose, the present application provides a process plan generation method based on industrial Internet of Things, which is applied to a process plan system, wherein the process plan system includes a management platform, a sensor network platform and an object platform, wherein the object platform includes an environmental detection device in a production workshop corresponding to a product and a data acquisition device corresponding to the production equipment in the production workshop, and the management platform is communicatively connected with the object platform via the sensor network platform;

[0006] The method comprises:

[0007] Acquire product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment;

[0008] By using a raw material solution generation model, a target raw material solution corresponding to the product is obtained according to the design data, the design requirements and the spare raw material information, wherein the target raw material solution includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product;

[0009] Through the process plan generation model, the target process plan corresponding to the product is obtained according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes each process for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

[0010] Specifically, the raw material solution generation model includes a first input layer, a second input layer, a third input layer, a hidden layer, a first output layer and a second output layer;

[0011] The raw material solution generation model is used to obtain a target raw material solution corresponding to the product according to the design data, the design requirements and the spare raw material information, including:

[0012] Generate a first input vector according to the design data through the first input layer;

[0013] Generate a second input vector according to the design requirements through the second input layer;

[0014] Generate a first input matrix according to the spare raw material information through the third input layer;

[0015] Generate a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix;

[0016] Generate a first output vector through the first output layer according to the first fused feature vector, wherein the first output vector is used to represent the type of raw materials required to produce the product;

[0017] Generate a second output vector through the second output layer according to the first fused feature vector, wherein the second output vector is used to represent the recommended usage of various raw materials required to produce the product;

[0018] The target raw material solution is determined based on the first output vector and the second output vector.

[0019] Specifically, the hidden layer includes a feature extraction layer and a fusion layer;

[0020] The step of generating a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix includes:

[0021] Generate a first feature extraction vector, a second feature extraction vector and a third feature extraction vector through the feature extraction layer according to the first input vector, the second input vector and the first input matrix, wherein the first input vector corresponds to the first feature extraction vector in one-to-one correspondence, the second input vector corresponds to the second feature extraction vector in one-to-one correspondence, and the first input matrix corresponds to the third feature extraction vector in one-to-one correspondence;

[0022] The first fused feature vector is generated through the fusion layer according to the first feature extraction vector, the second feature extraction vector and the third feature extraction vector.

[0023] Specifically, the feature extraction layer includes a first dense layer, a second dense layer and a third dense layer, and the activation function of the first dense layer, the activation function of the second dense layer and the activation function of the third dense layer are all ReLU functions;

[0024] The step of generating a first feature extraction vector, a second feature extraction vector, and a third feature extraction vector according to the first input vector, the second input vector, and the first input matrix through the feature extraction layer includes:

[0025] Generate the first feature extraction vector according to the first input vector through the first dense layer;

[0026] Generate the second feature extraction vector according to the second input vector through the second dense layer;

[0027] The third feature extraction vector is generated according to the first input matrix through the third dense layer.

[0028] Specifically, the process scheme generation model includes a first input processing module, a second processing module, a third processing module, an integration module and an output module;

[0029] The process scheme generation model is used to obtain a target process scheme corresponding to the product according to the target raw material scheme, the environmental data and the production equipment parameters, including:

[0030] Generate a third input vector according to the target raw material solution through the first input processing module;

[0031] generating, by the second input processing module, a fourth input vector according to the environmental data;

[0032] Producing a fifth input vector according to the production equipment parameters by the third input processing module;

[0033] Generate a second fused feature vector according to the third input vector, the fourth input vector and the fifth input vector by the integration module;

[0034] Generate a third output vector according to the second fused feature vector by the output module, wherein the third output vector is used to characterize each process of producing the product, the type of production equipment required for each process, and the operation mode of the production equipment in each process;

[0035] Based on the third output vector, the target process plan is confirmed.

[0036] Specifically, the first input processing module includes an embedding layer, a combination layer, and a fourth dense layer;

[0037] The step of generating a third input vector according to the target raw material solution through the first input processing module includes:

[0038] Generate a raw material type embedding vector through the embedding layer according to the raw material types required to produce the product in the target raw material solution;

[0039] Normalizing the recommended usage amounts of various raw materials required for producing the product in the target raw material solution to obtain normalized recommended usage amount values;

[0040] Generate a fourth eigenvector through the combination layer according to the raw material type embedding vector and the normalized recommended usage value;

[0041] The third input vector is generated according to the fourth eigenvector through the fourth dense layer.

[0042] Specifically, the integration module includes a concatenation layer, a first fully connected layer, and a second fully connected layer, and the number of neurons in the first fully connected layer is twice the number of neurons in the second fully connected layer;

[0043] The step of generating a second fused feature vector according to the third input vector, the fourth input vector and the fifth input vector by the integration module includes:

[0044] Generate a concatenated feature vector according to the third input vector, the fourth input vector and the fifth input vector through the concatenation layer;

[0045] Generate a first intermediate vector according to the concatenated feature vectors through the first fully connected layer;

[0046] The second fused feature vector is generated according to the first intermediate vector through the second fully connected layer.

[0047] To achieve the above-mentioned purpose, the present application also provides a process plan generation device based on industrial Internet of Things, which is applied to a process plan system, wherein the process plan system includes a management platform, a sensor network platform and an object platform, wherein the object platform includes an environmental detection device in a production workshop corresponding to a product and a data acquisition device corresponding to the production equipment in the production workshop, and the management platform is communicatively connected with the object platform via the sensor network platform;

[0048] The device comprises:

[0049] The first unit is used to obtain product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment;

[0050] The second unit is used to generate a model through a raw material scheme, and obtain a target raw material scheme corresponding to the product according to the design data, the design requirements and the spare raw material information, wherein the target raw material scheme includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product;

[0051] The third unit is used to generate a model through a process plan, and obtain a target process plan corresponding to the product according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes various processes for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

[0052] To achieve the above-mentioned purpose, the present application also provides a terminal, including a memory storing multiple instructions; the processor loads instructions from the memory to execute the steps in any one of the methods provided in the present application.

[0053] To achieve the above objectives, the present application also provides a medium, wherein the medium stores a plurality of instructions, wherein the instructions are suitable for a processor to load to execute the steps in any one of the methods provided in the present application.

[0054] The present application provides a process plan generation method, device, terminal and medium based on industrial Internet of Things, which can first obtain product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop and production equipment parameters of the production equipment; then, through the raw material plan generation model, according to the design data, the design requirements and the spare raw material information, a target raw material plan corresponding to the product is obtained, wherein the target raw material plan includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product; finally, through the process plan generation model, according to the target raw material plan, the environmental data and the production equipment parameters, a reliable target process plan corresponding to the product is obtained, and the obtained target process plan can better adapt to changes in design requirements, raw material information and production environment conditions, thereby reducing errors caused by human misjudgment, so that the production workshop can adopt a more reliable process plan to produce products.

[0055] The present application can better adapt to changing design requirements, raw material information and production environment conditions through a neural network model, thereby reducing errors caused by human misjudgment and improving the reliability of the resulting process solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of a process flow provided for an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a process scheme system provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of the structure of a process solution generation device based on the industrial Internet of Things provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0061] Since the formulation of process plans is often highly dependent on the experience and technical level of engineers, the reliability of the process plans may not be guaranteed due to human misjudgment; and when production conditions or production needs change, adjustments are difficult, and human-made process plans cannot quickly adapt to changes in design requirements, raw material information and production environment conditions.

[0062] Therefore, the embodiments of the present application provide a process solution generation method, device, terminal and medium based on the industrial Internet of Things to solve practical technical problems.

[0063] In some embodiments, the device may be specifically integrated into an electronic device, which may be a terminal, a server or other device.

[0064] In some embodiments, the server may also be implemented in the form of a terminal.

[0065] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides 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), as well as big data and artificial intelligence platforms.

[0066] The terminal may 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 may be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0067] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0068] An embodiment of the present application provides a method for generating a process plan based on the industrial Internet of Things. The method can better adapt to changing design requirements, raw material information, and changes in production environment conditions through a neural network model, thereby reducing errors caused by human misjudgment and further improving the reliability of the obtained process plan.

[0069] like Figure 1 and Figure 2 As shown, it is applied to a process plan system, which includes a management platform, a sensor network platform and an object platform. The object platform includes environmental detection equipment in a production workshop corresponding to the product and data acquisition equipment corresponding to the production equipment in the production workshop. The management platform and the object platform are communicatively connected via the sensor network platform.

[0070] In some embodiments, the management platform is responsible for the management and control of the entire system, including task scheduling, data processing, etc.

[0071] The object platform may refer to an object-oriented design framework for managing and processing various data objects in the system, and the object platform provides a structured way to organize, store and manipulate data, making the system more flexible and scalable. Specifically, the object platform in the process scheme system includes environmental detection equipment and data acquisition equipment.

[0072] For example, the environmental detection equipment in the production workshop corresponding to the product is a key facility used to monitor and control the production environment. The environmental detection equipment is used to detect whether the environmental conditions in the workshop (such as temperature, humidity, cleanliness, etc.) meet the requirements of the production process; the data acquisition equipment used to collect equipment parameters of the production equipment in the production workshop is an important part of realizing intelligent manufacturing and industrial automation. The data acquisition equipment can monitor and record various parameters in the production process in real time to help factory managers and engineers understand the equipment status. The following are several common data acquisition equipment:

[0073] Sensors: including temperature sensors, humidity sensors, pressure sensors, vibration sensors and other types, used to monitor the physical characteristics of the equipment during operation;

[0074] PLC (Programmable Logic Controller): PLC is one of the core components of industrial control systems. It can collect data from various sensors and control the actions of production equipment according to preset logic;

[0075] SCADA system (Supervisory Control and Data Acquisition System): SCADA system is used to centrally monitor and control industrial processes. It acquires data by communicating with various field devices and displays it on the user interface, enabling operators to monitor and adjust the production process.

[0076] The sensor network platform can be used as the middle layer of the process scheme system to collect data information from the object platform and is responsible for transmitting the input instructions of the operator from the management platform to the object platform.

[0077] The Industrial Internet of Things (IIoT) plays a vital role in modern manufacturing, especially in the operation and management of production lines. The Industrial Internet of Things involves connecting various types of sensors, devices, machines and other objects through a network, enabling them to collect and exchange data. The goal of the Industrial Internet of Things is to improve the efficiency, productivity and reliability of industrial production processes through intelligence, automation and data analysis.

[0078] In some embodiments, the process plan generation system based on the industrial Internet of Things controls the environmental detection equipment and the data acquisition equipment through a management platform.

[0079] The specific process of the method can be as follows:

[0080] S110, obtaining the design data of the product, the design requirements of the product, the spare raw material information of the production workshop, the environmental data in the production workshop, and the production equipment parameters of the production equipment, wherein the design data is used to characterize the product-related information generated during the design stage of the product, the design requirements are used to characterize the customer or market expectations for the function and appearance of the product, the spare raw material information is used to characterize the inventory status of the available raw materials in the production workshop and the related attributes of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment.

[0081] In some embodiments, the user can input the design data and design requirements of the product into the process plan system through an input device. The process plan system may include a storage device, and the spare raw material information may be data information pre-stored in the storage device.

[0082] In some embodiments, the environmental detection device can be used to detect environmental conditions in a production workshop to obtain environmental data in the production workshop, and the data acquisition device can be used to acquire production equipment parameters of the production equipment.

[0083] S120. Generate a model through a raw material scheme, and obtain a target raw material scheme corresponding to the product according to the design data, the design requirements and the spare raw material information, wherein the target raw material scheme includes the types of raw materials required to produce the product and the recommended usage amounts of various raw materials required to produce the product.

[0084] In some embodiments, the raw material solution generation model includes a first input layer, a second input layer, a third input layer, a hidden layer, a first output layer, and a second output layer.

[0085] In some embodiments, the raw material solution generation model is used to obtain a target raw material solution corresponding to the product according to the design data, the design requirements and the spare raw material information, including the steps S121 to S127 as shown below:

[0086] S121. Generate a first input vector according to the design data through the first input layer.

[0087] In some embodiments, for example, the design data of a product is [length 200mm, width 150mm, height 50mm, weight 500g, shape square, color blue], where the length, width, height and weight are actual measurement values ​​in millimeters and grams; the shape code and color code are numerical values ​​represented by a certain encoding method (for example, shape code 0 represents square, color code 1 represents blue), then the first input vector can be a vector containing product design attributes, that is, (length, width, height, weight, shape code, color code).

[0088] S122. Generate a second input vector through the second input layer according to the design requirements.

[0089] In some embodiments, the design requirements may represent market research, customer demand analysis, or environmental protection grade standards; for example, if the design requirements are expressed as [100 yuan, 8, 3], it means that the upper limit of the cost of the product is 100 yuan, the durability index is 8 (out of 10), and the environmental protection grade is 3 (out of 5), then the second input vector may be expressed as (upper limit cost, durability index, environmental protection grade).

[0090] S123. Generate a first input matrix through the third input layer according to the spare raw material information.

[0091] In some embodiments, the backup raw material information is expressed as [material A attributes], [material B attributes], [material C attributes], [material D attributes], [material E attributes], and the attributes of each material may include cost, density, strength, etc. Then the first input matrix may include the following characteristics: each row corresponds to a raw material, and each column represents a different attribute of the raw material (such as density, cost, strength, etc.).

[0092] For example, if there are 5 raw materials and each raw material has 4 attributes, then the first input matrix is ​​[5x4].

[0093] S124. Generate a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix.

[0094] In some embodiments, the hidden layer includes a feature extraction layer and a fusion layer.

[0095] In some embodiments, generating a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix includes the steps S1241 to S1242 as shown below:

[0096] S1241. Generate a first feature extraction vector, a second feature extraction vector and a third feature extraction vector through the feature extraction layer according to the first input vector, the second input vector and the first input matrix, wherein the first input vector corresponds one-to-one to the first feature extraction vector, the second input vector corresponds one-to-one to the second feature extraction vector, and the first input matrix corresponds one-to-one to the third feature extraction vector.

[0097] In some embodiments, the feature extraction layer includes a first dense layer, a second dense layer, and a third dense layer, and the activation function of the first dense layer, the activation function of the second dense layer, and the activation function of the third dense layer are all ReLU functions.

[0098] In some embodiments, the generating of the first feature extraction vector, the second feature extraction vector and the third feature extraction vector according to the first input vector, the second input vector and the first input matrix through the feature extraction layer includes the following steps S12411 to S12413:

[0099] S12411. Generate the first feature extraction vector according to the first input vector through the first dense layer.

[0100] In some embodiments, the first input vector is input into the first dense layer to obtain the first feature extraction vector.

[0101] S12412. Generate the second feature extraction vector according to the second input vector through the second dense layer.

[0102] In some embodiments, the second input vector is input into the second dense layer to obtain the second feature extraction vector.

[0103] S12413. Generate the third feature extraction vector according to the first input matrix through the third dense layer.

[0104] In some embodiments, the first input matrix is ​​input into the third dense layer to obtain the third feature extraction vector.

[0105] S1242. Generate the first fused feature vector according to the first feature extraction vector, the second feature extraction vector and the third feature extraction vector through the fusion layer.

[0106] The fusion layer is a mechanism or layer in the network architecture that is specifically used to integrate information from different sources or different types. The main purpose of the fusion layer is to merge data from different sub-networks, sensors or other information sources into a unified representation so that subsequent processing layers (such as fully connected layers, classification layers, etc.) can effectively use this information for higher-level reasoning or decision-making.

[0107] In some embodiments, the first feature extraction vector, the second feature extraction vector and the third feature extraction vector are subjected to feature-level fusion, that is, feature vectors from different sources are directly concatenated or averaged to obtain the first fused feature vector.

[0108] S125. Generate a first output vector through the first output layer according to the first fused feature vector, wherein the first output vector is used to characterize the type of raw materials required to produce the product.

[0109] In some embodiments, the first output vector may be a probability distribution vector, which indicates the probability of each raw material being selected, which can be understood as the probability of the model suggesting the use of each raw material.

[0110] For example, the output probability distribution vector is [0.1, 0.3, 0.5, 0.05, 0.05], which means that material C has the highest probability of being selected, followed by material B, and the probabilities of materials A, D and E are lower. If three raw materials are required to produce a product, materials A, B and C are selected as the required types of raw materials.

[0111] S126. Generate a second output vector through the second output layer according to the first fused feature vector, wherein the second output vector is used to represent the recommended usage of various raw materials required to produce the product.

[0112] In some embodiments, the second output vector may be a specific numerical vector, indicating the recommended usage of each selected raw material, which can be understood as the quantity of each raw material recommended by the model.

[0113] For example, the second output vector is [0kg, 5kg, 20kg, 0kg, 0kg], and the types of raw materials required are material B and material C, then the second output vector indicates that it is recommended to use 5 kg of material B and 20 kg of material C.

[0114] S127. Determine the target raw material solution based on the first output vector and the second output vector.

[0115] S130. Generate a model through a process plan, and obtain a target process plan corresponding to the product according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes various processes for producing the product, the type of production equipment required for each process and the operation mode of the production equipment in each process.

[0116] In some embodiments, the process plan generation model includes a first input processing module, a second processing module, a third processing module, an integration module, and an output module.

[0117] In some embodiments, the process scheme generation model is used to obtain a target process scheme corresponding to the product according to the target raw material scheme, the environmental data and the production equipment parameters, including the steps S131 to S136 as shown below:

[0118] S131. Generate a third input vector according to the target raw material solution through the first input processing module.

[0119] In some embodiments, the first input processing module includes an embedding layer, a combination layer, and a fourth dense layer.

[0120] The embedding layer maps discrete symbols (such as words, characters, or other categorical data) into a continuous vector space, which is usually called an embedding space or word vector space. Such a mapping helps capture the semantic relationship between symbols and can be used in subsequent neural network layers for efficient calculations.

[0121] In some embodiments, the generating of the third input vector according to the target raw material solution by the first input processing module includes the following steps S1311 to S1314:

[0122] S1311. Generate a raw material type embedding vector through the embedding layer according to the raw material types required to produce the product in the target raw material solution.

[0123] In some embodiments, the input corresponding to the embedding layer may be the raw material type (as an integer index), and the output corresponding to the embedding layer may be an embedding vector. The embedding layer converts each raw material type into a vector in a high-dimensional space.

[0124] For example, if there are K different raw materials, the embedding layer will have a weight matrix of shape [K, D], where D is the embedding dimension. When a raw material type index is input, the embedding layer will return the vector of the corresponding row as output, that is, output the embedding vector of the raw material type.

[0125] S1312. Normalize the recommended usage amounts of various raw materials required for producing the product in the target raw material solution to obtain normalized recommended usage amount values.

[0126] In some embodiments, the recommended usage amounts of various raw materials required to produce products in the target raw material scheme can be normalized to a specific range, such as [0,1], using methods such as minimum and maximum scaling (MinMaxScaler) and standardization (StandardScaler) to obtain the normalized recommended usage amount value.

[0127] S1313. Generate a fourth feature vector through the combination layer according to the raw material type embedding vector and the normalized recommended usage value.

[0128] In some embodiments, the raw material type embedding vector and the normalized recommended usage value may be concatenated together to form a new vector, namely, the fourth eigenvector.

[0129] S1314. Generate the third input vector according to the fourth eigenvector through the fourth dense layer.

[0130] S132. Generate a fourth input vector according to the environmental data through the second input processing module.

[0131] S133. Produce a fifth input vector according to the production equipment parameters through the third input processing module.

[0132] S134. Generate a second fused feature vector according to the third input vector, the fourth input vector and the fifth input vector through the integration module.

[0133] In some embodiments, the integration module includes a concatenation layer, a first fully connected layer, and a second fully connected layer, and the number of neurons in the first fully connected layer is twice the number of neurons in the second fully connected layer.

[0134] The fully connected layer (FC layer) is one of the most basic and commonly used layers in a neural network. In the neural network architecture, the function of the fully connected layer is to connect all neurons in the previous layer with every neuron in the current layer to form a fully interconnected layer.

[0135] In some embodiments, the generating of the second fused feature vector by the integration module according to the third input vector, the fourth input vector and the fifth input vector includes the following steps S1341 to S1343:

[0136] S1341. Generate a concatenated feature vector through the concatenation layer according to the third input vector, the fourth input vector, and the fifth input vector.

[0137] In some embodiments, the third input vector, the fourth input vector and the fifth input vector are concatenated to generate a concatenated feature vector.

[0138] S1342. Generate a first intermediate vector according to the concatenated feature vectors through the first fully connected layer.

[0139] S1343. Generate the second fused feature vector according to the first intermediate vector through the second fully connected layer.

[0140] S135. Generate a third output vector through the output module according to the second fused feature vector, wherein the third output vector is used to characterize each process of producing a product, the type of production equipment required for each process, and the operation mode of the production equipment in each process.

[0141] S136. Confirm the target process plan based on the third output vector.

[0142] For example, the target process scheme may include the following:

[0143] Process 1: Mixing;

[0144] Equipment used: Mixer A;

[0145] Operation mode: continuous stirring, speed 50rpm.

[0146] Step 2: Heating;

[0147] Equipment used: Heater;

[0148] Mode of operation: Continuously heat to 70°C.

[0149] The embodiment of the present application first obtains the design data of the product, the design requirements of the product, the spare raw material information of the production workshop, the environmental data in the production workshop, and the production equipment parameters of the production equipment; then, through the raw material scheme generation model, according to the design data, the design requirements and the spare raw material information, a target raw material scheme corresponding to the product is obtained, wherein the target raw material scheme includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product; finally, through the process scheme generation model, according to the target raw material scheme, the environmental data and the production equipment parameters, a reliable target process scheme corresponding to the product is obtained, and the obtained target process scheme can better adapt to the changes in design requirements, raw material information and production environment conditions, thereby reducing errors caused by human misjudgment, so that the production workshop can adopt a more reliable process scheme to produce products.

[0150] In summary, this application provides a process plan generation method based on industrial Internet of Things, which, through a neural network model, can better adapt to changing design requirements, raw material information and changes in production environment conditions, thereby reducing errors caused by human misjudgment and improving the reliability of the obtained process plan.

[0151] In order to better implement the above method, the embodiment of the present application also provides a process plan generation device based on the industrial Internet of Things, which can be integrated in an electronic device, and the electronic device can be a terminal, a server, etc. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers.

[0152] For example, in this embodiment, the method of the embodiment of the present application will be described in detail by taking the specific integration of a process plan generation device based on the industrial Internet of Things in a terminal as an example.

[0153] For example, Figure 3 As shown, the process plan generating device 300 based on the industrial Internet of Things may include a first unit 301, a second unit 302 and a third unit 303, which are applied to a process plan system, wherein the process plan system includes a management platform, a sensor network platform and an object platform, wherein the object platform includes an environmental detection device in a production workshop corresponding to a product and a data acquisition device corresponding to the production equipment in the production workshop, and the management platform is communicatively connected with the object platform via the sensor network platform;

[0154] The device comprises:

[0155] The first unit 301 is used to obtain product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment;

[0156] The second unit 302 is used to generate a model through a raw material scheme, and obtain a target raw material scheme corresponding to the product according to the design data, the design requirements and the spare raw material information, wherein the target raw material scheme includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product;

[0157] The third unit 303 is used to generate a model through a process plan, and obtain a target process plan corresponding to the product according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes each process for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

[0158] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0159] From the above, it can be seen that the embodiments of the present application can better adapt to changing design requirements, raw material information and production environment conditions through a neural network model, thereby reducing errors caused by human misjudgment and improving the reliability of the resulting process solution.

[0160] The embodiment of the present application also provides an electronic device, which can be a terminal, a server, etc. The terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc. The server can be a single server or a server cluster composed of multiple servers, etc.

[0161] In some embodiments, the product processing device can also be integrated into multiple electronic devices. For example, the product processing device can be integrated into multiple servers, and the process plan generation method based on industrial Internet of Things of this application is implemented by multiple servers.

[0162] In this embodiment, the electronic device of this embodiment is a terminal as an example for detailed description, for example, Figure 4 As shown, it shows a schematic diagram of the structure of the terminal 400 involved in the embodiment of the present application, specifically:

[0163] The terminal 400 may include one or more processing core processors 401, one or more medium storages 402, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art will appreciate that Figure 4 The structure of the terminal 400 shown in the figure does not constitute a limitation on the terminal 400, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0164] The processor 401 is the control center of the terminal 400. It uses various interfaces and lines to connect various parts of the entire terminal 400. It executes various functions of the terminal 400 and processes data by running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402, so as to monitor 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, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0165] 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 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal 400, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0166] The terminal 400 also includes a power supply 403 for supplying power to various components. In some embodiments, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0167] The terminal 400 may further include an input module 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0168] The terminal 400 may also include a communication module 405. In some embodiments, the communication module 405 may include a wireless module. The terminal 400 may perform short-range wireless transmission through the wireless module of the communication module 405, thereby providing the user with wireless broadband Internet access. For example, the communication module 405 may be used to help the user send and receive emails, browse web pages, and access streaming media.

[0169] Although not shown, the terminal 400 may also include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the terminal 400 will load the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 will run the applications stored in the memory 402, thereby realizing various functions, as follows:

[0170] Acquire product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment;

[0171] By using a raw material solution generation model, a target raw material solution corresponding to the product is obtained according to the design data, the design requirements and the spare raw material information, wherein the target raw material solution includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product;

[0172] Through the process plan generation model, the target process plan corresponding to the product is obtained according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes each process for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

[0173] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0174] From the above, it can be seen that the embodiments of the present application can better adapt to changing design requirements, raw material information and production environment conditions through a neural network model, thereby reducing errors caused by human misjudgment and improving the reliability of the resulting process solution.

[0175] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a medium and loaded and executed by a processor.

[0176] To this end, an embodiment of the present application provides a medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the process plan generation methods based on the industrial Internet of Things provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0177] Acquire product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment;

[0178] By using a raw material solution generation model, a target raw material solution corresponding to the product is obtained according to the design data, the design requirements and the spare raw material information, wherein the target raw material solution includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product;

[0179] Through the process plan generation model, the target process plan corresponding to the product is obtained according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes each process for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

[0180] The medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0181] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes a computer instruction, the computer instruction is stored in a medium. A processor of a computer device reads the computer instruction from the medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional implementations provided in the above embodiments.

[0182] Since the instructions stored in the medium can execute the steps in any one of the process plan generation methods based on the industrial Internet of Things provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the process plan generation methods based on the industrial Internet of Things provided in the embodiments of the present application can be achieved. For details, please refer to the previous embodiments and will not be repeated here.

[0183] The above is a detailed introduction to a process solution generation method, device, terminal and medium based on industrial Internet of Things provided in the embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A process plan generation method based on industrial Internet of Things, characterized in that: Applied to a process scheme system, the process scheme system includes a management platform, a sensor network platform and an object platform, the object platform includes an environmental detection device in a production workshop corresponding to a product and a data acquisition device corresponding to the production equipment in the production workshop, and the management platform is communicatively connected with the object platform via the sensor network platform; The method comprises: Acquire product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment; By using a raw material solution generation model, a target raw material solution corresponding to the product is obtained according to the design data, the design requirements and the spare raw material information, wherein the target raw material solution includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product; Through the process plan generation model, the target process plan corresponding to the product is obtained according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes each process for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

2. The method according to claim 1, characterized in that The raw material solution generation model includes a first input layer, a second input layer, a third input layer, a hidden layer, a first output layer and a second output layer; The raw material solution generation model is used to obtain a target raw material solution corresponding to the product according to the design data, the design requirements and the spare raw material information, including: Generate a first input vector according to the design data through the first input layer; Generate a second input vector according to the design requirements through the second input layer; Generate a first input matrix according to the spare raw material information through the third input layer; Generate a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix; Generate a first output vector through the first output layer according to the first fused feature vector, wherein the first output vector is used to represent the type of raw materials required to produce the product; Generate a second output vector through the second output layer according to the first fused feature vector, wherein the second output vector is used to represent the recommended usage of various raw materials required to produce the product; The target raw material solution is determined based on the first output vector and the second output vector.

3. The method according to claim 2, characterized in that The hidden layer includes a feature extraction layer and a fusion layer; The step of generating a first fused feature vector through the hidden layer according to the first input vector, the second input vector and the first input matrix includes: Generate a first feature extraction vector, a second feature extraction vector and a third feature extraction vector through the feature extraction layer according to the first input vector, the second input vector and the first input matrix, wherein the first input vector corresponds to the first feature extraction vector in one-to-one correspondence, the second input vector corresponds to the second feature extraction vector in one-to-one correspondence, and the first input matrix corresponds to the third feature extraction vector in one-to-one correspondence; The first fused feature vector is generated through the fusion layer according to the first feature extraction vector, the second feature extraction vector and the third feature extraction vector.

4. The method according to claim 3, characterized in that The feature extraction layer includes a first dense layer, a second dense layer and a third dense layer, and the activation function of the first dense layer, the activation function of the second dense layer and the activation function of the third dense layer are all ReLU functions; The step of generating a first feature extraction vector, a second feature extraction vector, and a third feature extraction vector according to the first input vector, the second input vector, and the first input matrix through the feature extraction layer includes: Generate the first feature extraction vector according to the first input vector through the first dense layer; Generate the second feature extraction vector according to the second input vector through the second dense layer; The third feature extraction vector is generated according to the first input matrix through the third dense layer.

5. The method according to claim 1, characterized in that The process scheme generation model includes a first input processing module, a second processing module, a third processing module, an integration module and an output module; The process scheme generation model is used to obtain a target process scheme corresponding to the product according to the target raw material scheme, the environmental data and the production equipment parameters, including: Generate a third input vector according to the target raw material solution through the first input processing module; generating, by the second input processing module, a fourth input vector according to the environmental data; Producing a fifth input vector according to the production equipment parameters by the third input processing module; Generate a second fused feature vector according to the third input vector, the fourth input vector and the fifth input vector by the integration module; Generate a third output vector according to the second fused feature vector by the output module, wherein the third output vector is used to characterize each process of producing the product, the type of production equipment required for each process, and the operation mode of the production equipment in each process; Based on the third output vector, the target process plan is confirmed.

6. The method according to claim 5, characterized in that The first input processing module includes an embedding layer, a combination layer and a fourth dense layer; The step of generating a third input vector according to the target raw material solution through the first input processing module includes: Generate a raw material type embedding vector through the embedding layer according to the raw material types required to produce the product in the target raw material solution; Normalizing the recommended usage amounts of various raw materials required for producing the product in the target raw material solution to obtain normalized recommended usage amount values; Generate a fourth eigenvector through the combination layer according to the raw material type embedding vector and the normalized recommended usage value; The third input vector is generated according to the fourth eigenvector through the fourth dense layer.

7. The method according to claim 5, characterized in that The integration module includes a concatenation layer, a first fully connected layer, and a second fully connected layer, wherein the number of neurons in the first fully connected layer is twice the number of neurons in the second fully connected layer; The step of generating a second fused feature vector according to the third input vector, the fourth input vector and the fifth input vector by the integration module includes: Generate a concatenated feature vector according to the third input vector, the fourth input vector and the fifth input vector through the concatenation layer; Generate a first intermediate vector according to the concatenated feature vectors through the first fully connected layer; The second fused feature vector is generated according to the first intermediate vector through the second fully connected layer.

8. A process plan generation device based on industrial Internet of Things, characterized in that: Applied to a process scheme system, the process scheme system includes a management platform, a sensor network platform and an object platform, the object platform includes an environmental detection device in a production workshop corresponding to a product and a data acquisition device corresponding to the production equipment in the production workshop, and the management platform is communicatively connected with the object platform via the sensor network platform; The device comprises: The first unit is used to obtain product design data, product design requirements, spare raw material information of a production workshop, environmental data in the production workshop, and production equipment parameters of the production equipment, wherein the design data is used to characterize product-related information generated during the design phase of the product, the design requirements are used to characterize customer or market expectations of product functions and appearance, the spare raw material information is used to characterize the inventory status of available raw materials in the production workshop and related properties of the available raw materials, the environmental data is used to characterize the environmental conditions in the production workshop, and the production equipment parameters are used to characterize the equipment conditions of the production equipment; The second unit is used to generate a model through a raw material scheme, and obtain a target raw material scheme corresponding to the product according to the design data, the design requirements and the spare raw material information, wherein the target raw material scheme includes the types of raw materials required for producing the product and the recommended usage amounts of various raw materials required for producing the product; The third unit is used to generate a model through a process plan, and obtain a target process plan corresponding to the product according to the target raw material plan, the environmental data and the production equipment parameters, wherein the target process plan includes various processes for producing the product, the type of production equipment required for each process and the operation method of the production equipment in each process.

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