Method, device and equipment for building process knowledge base of stamping and grinding and storage medium

Abstract

The application relates to a stamping and polishing process knowledge base construction method, device and equipment and a storage medium, and relates to the stamping and polishing technical field; the method comprises the following steps: constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base; dividing the first database into a material library, a die library, an equipment library, a process database, a process parameter library and a user database, and storing product information corresponding to the stamping process into the storage libraries divided from the first database; dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer, and storing various parameters required by the polishing process into various data layers divided from the second database. The method can realize intelligent design of a die by establishing the database of the stamping process and the database of the polishing process and extracting forming process features of various stamping parts.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of stamping and grinding, and in particular to a stamping and grinding process knowledge base construction method, device, equipment and storage medium. BACKGROUND

[0002] The stamping process is the core technology of stamping die development. For a long time, due to the diversity of stamping parts, different shapes, changes in materials, and differences in stamping equipment conditions, the stamping process basically relies on experience-specific design. This technical status is a technical bottleneck restricting the intelligent manufacturing of dies. The grinding process is one of the processes of the stamping process, and is therefore limited by manual experience design. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art and provide a stamping and grinding process knowledge base construction method, device, equipment and storage medium, which can extract the forming process characteristics of various stamping parts by establishing a stamping process database and a grinding process database, realize intelligent design of the die, and break through this technical bottleneck of intelligent manufacturing of the die.

[0004] To solve at least one of the above technical problems, the present application provides a stamping and grinding process knowledge base construction method, which comprises:

[0005] Constructing a first database of a stamping process knowledge base and a second database of a grinding process knowledge base;

[0006] Dividing the first database into a material library, a die library, an equipment library, a process database, a process parameter library and a user database;

[0007] Storing material data information into the material library, storing the type of stamping die and the material and parameter data of the stamping die into the die library, storing various parameter information of stamping into the equipment library, storing data, formulas and rule information in the design process of the stamping process into the process database, storing process parameters obtained by the stamping process into the process parameter library, and storing user information into the user database;

[0008] Dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;

[0009] Taking the conditional parameters as the input layer parameters of the input layer, taking the process parameters of the grinding robot grinding die surface as the output layer parameters of the output layer, storing the data formed by the input layer parameters, the output layer parameters and the surface quality after grinding and the mapping relationship of the data into the knowledge storage layer, and storing the convolutional neural network model and the parameters of the convolutional neural network model into the inference layer.

[0010] Preferably, the storing of the material data information into the material library comprises:

[0011] storing one or more of the material data information of the material grade, mechanical property, thickness, part shape, hardness, chemical composition and microstructure into the material library.

[0012] Preferably, the storing of the various parameters of the stamping into the equipment library comprises:

[0013] storing one or more of the stamping equipment parameters, type parameters and technical parameters of the stamping into the equipment library.

[0014] Preferably, the storing of the process parameters of the stamping process into the process parameter library comprises:

[0015] storing one or more of the process parameters of the stamping process, material, material size, material layout, die and equipment into the process parameter library.

[0016] Preferably, the method further comprises:

[0017] receiving inputted product information of a new product, the product information of the new product comprising the size, material, production batch, tolerance and shape of the new product;

[0018] calculating the forming similarity between the new product and any old product in the first database according to the size, material, production batch and tolerance of the new product and the size, material, production batch and tolerance of the old product;

[0019] calculating the shape similarity between the new product and the old product according to the shape of the new product and the shape of the old product;

[0020] calculating the overall similarity between the new product and the old product according to the forming similarity and the shape similarity;

[0021] if it is determined that the new product is not similar to the old product according to the overall similarity, storing the size, material, production batch, tolerance and shape of the new product into the material library.

[0022] Preferably, the condition parameters comprise one or more of the initial surface quality, body material, curvature of the local area to be polished.

[0023] The process parameters of the polishing robot polishing the die surface profile comprise one or more of the polishing head parameters, polishing head moving speed, polishing head moving path and polishing force.

[0024] Preferably, the training step of the convolutional neural network model comprises:

[0025] Obtaining sampling data, the sampling data comprising initial surface quality after polishing, polishing head moving speed, Gaussian curvature of polishing area, polishing force, material of machine body, polishing head parameter, polishing direction and wear;

[0026] Using a convolutional neural network back propagation algorithm, and based on the cost function and the sampling data, the convolutional neural network model is trained.

[0027] A stamping and polishing process knowledge base construction device, the device comprising:

[0028] A construction module for constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base;

[0029] A first division module for dividing the first database into a material library, a die library, an equipment library, a process database, a process parameter library and a user profile library;

[0030] A first storage module for storing material data information to the material library, storing data information of types of stamping dies, materials of stamping dies and parameters to the die library, storing various parameter information of stamping to the equipment library, storing data, formulas and rule information in the design process of the stamping process to the process database, storing process parameters obtained by the stamping process to the process parameter library, and storing user profiles to the user profile library;

[0031] A second division module for dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;

[0032] A second storage module for storing conditional parameters as input layer parameters of the input layer, storing process parameters of polishing robot polishing die surface as output layer parameters of the output layer, storing data and mapping relationship of the data formed by the input layer parameters, the output layer parameters and surface quality after polishing to the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model to the inference layer.

[0033] In addition, the embodiment of the present application further provides a computer device, comprising a memory, a processor and an application stored on the memory and executable on the processor, and the processor executes the application to realize the steps of the method of any one of the above-mentioned embodiments.

[0034] In addition, the embodiment of the present application further provides a computer readable storage medium, which stores an application, and the application is executed by a processor to realize the steps of the method of any one of the above-mentioned embodiments.

[0035] The embodiment of the application discloses a stamping and polishing process knowledge base construction method, device, equipment and storage medium. A first database of a stamping process knowledge base is divided into a material library, a die library, a device library, a process database, a process parameter library and a user database. Material data information is stored in the material library, data information of types of stamping dies and materials and parameters of the stamping dies is stored in the die library, various parameter information of stamping is stored in the device library, data, formulas and rule information in a design process of the stamping process are stored in the process database, process parameters obtained by the stamping process are stored in the process parameter library, and user information is stored in the user database. A second database of a polishing process knowledge base is divided into an input layer, a knowledge storage layer, an inference layer and an output layer. Conditional parameters are used as input layer parameters of the input layer, process parameters of polishing robot polishing die surfaces are used as output layer parameters of the output layer, data formed by the input layer parameters, the output layer parameters and polished surface quality and a mapping relationship of the data are stored in the knowledge storage layer, and a convolutional neural network model and parameters of the convolutional neural network model are stored in the inference layer.

[0036] Therefore, by establishing a database of a stamping process and a database of a polishing process, forming process features of various stamping parts can be extracted, intelligent design of a die can be realized, and a technical bottleneck of intelligent manufacturing of the die is broken through. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 FIG. 1 is a flowchart of a stamping and polishing process knowledge base construction method according to an embodiment of the application;

[0038] Figure 2 FIG. 2 is a structural diagram of a stamping process knowledge base according to an embodiment of the application;

[0039] Figure 3 FIG. 3 is a basic architecture diagram of a constructed process knowledge base according to an embodiment of the application;

[0040] Figure 4 FIG. 4 is a tree attribute structure diagram of a die body according to an embodiment of the application;

[0041] Figure 5 FIG. 5 is a tree attribute structure diagram of a tool body according to an embodiment of the application;

[0042] Figure 6 FIG. 6 is a neural network model diagram constructed according to an embodiment of the application;

[0043] Figure 7 FIG. 7 is a use flowchart of a polishing process knowledge base according to an embodiment of the application;

[0044] Figure 8 is a structural block diagram of a stamping and grinding process knowledge base construction device in an embodiment of the present application;

[0045] Figure 9 is a structural composition schematic diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the 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 of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0047] The present application provides a stamping and grinding process knowledge base construction method, as shown in Figure 1 The stamping and grinding process knowledge base construction method comprises the following steps:

[0048] S101, a first database of a stamping process knowledge base and a second database of a grinding process knowledge base are constructed.

[0049] Specifically, the database of the stamping process knowledge base is established, the forming process features of various stamping parts are extracted, the stamping process analysis system based on knowledge engineering is developed, and the first database of the stamping process knowledge base is constructed. Similarly, the database of the grinding process knowledge base is established, the grinding process parameters are analyzed based on the grinding process flow, and the second database of the grinding process knowledge base is constructed.

[0050] S102, the first database is divided into a material library, a die library, an equipment library, a process database, a process parameter library and a user profile library.

[0051] Specifically, the first database is divided into a material library, a die library, an equipment library, a process database, a process parameter library and a user profile library. Each database divided is constructed through a conceptual data model.

[0052] The conceptual data model is formed by abstracting, generalizing and synthesizing the data features of the real world after the database designer gets the user's requirements. The conceptual data model is a high-level data model and an accurate expression of the user's requirements. It can be said that it is the link between the computer world and the real world. The common conceptual model is the entity-relationship model (E-R model), which can visually represent entities, relationships and their relationships through graphics. Therefore, by analyzing the stamping process, based on the conceptual data model, the material library, die library, equipment library, process database, process parameter library and user database are constructed.

[0053] The stamping knowledge base is the basis of the process analysis and design system. Referring to the stamping process design process, taking the blanking process type as an example, it can be summarized as the determination of stamping materials, the analysis of blanking process, the layout of blanking, the selection of dies, and the selection of stamping equipment. Therefore, the database of the stamping process knowledge base is also built according to these parts. The design of the database is to separate the data information from the application program, realize the consistency and sharing of the data, and greatly improve the running efficiency of the network. Comprehensive and complete analysis results can greatly improve the speed and accuracy of database design. Therefore, it is necessary to analyze and summarize the database structure for database design. According to the demand analysis of the stamping process system database, the conceptual design of the database will be from the material library, die library, equipment library, process database, process parameter library and user database. The structure of the stamping process knowledge base is shown in Figure 2

[0054] S103, store the material data information into the material library, store the type of stamping die, the material of stamping die and the data information of parameters into the die library, store various parameter information of stamping into the equipment library, store the data, formula and rule information in the design process of the stamping process into the process database, store the process parameters obtained by the stamping process into the process parameter library, and store the user information into the user database.

[0055] Preferably, the material data information is stored into the material library, including: storing one or more material data information of the grade, mechanical properties, thickness, part shape, hardness, chemical composition and metallographic structure of each material into the material library.

[0056] Preferably, the various parameter information of stamping is stored into the equipment library, including: storing one or more of the stamping equipment parameters, type parameters and technical parameters into the equipment library.

[0057] ​Preferably, the storing the process parameters obtained by the stamping process into the process parameter library comprises: storing one or more process parameters of stamping process, material, material size, material layout, die and equipment into the process parameter library.

[0058] Specifically, the concept of the first database is designed as follows:

[0059] (1) Conceptual structure design of material library

[0060] Before designing the stamping process procedure, the chemical composition, mechanical properties, hardness, part shape and the like of the material are determined first. In the stamping process design, the material is classified into ordinary carbon steel, high-quality carbon structural steel, carbon tool steel, alloy steel, cast iron, cast steel and the like, so as to distinguish the application scope of the process data.

[0061] Specifically, to determine whether a specific material is suitable for stamping process, the specific grade, mechanical properties, thickness, part shape, hardness, chemical composition, metallographic structure and the like of the material are comprehensively judged to determine whether the material is suitable for stamping. The chemical properties of the material include upper limit of component content, lower limit of component content and elements; the hardness includes Brinell hardness, Rockwell hardness, Vickers hardness and Shore hardness; the part shape includes size, part shape and the like. The mechanical properties of the material include shear performance, tensile performance, elongation and yield strength, and the yield strength includes material grade, heat treatment system, sampling direction, temperature, upper limit of yield strength and lower limit of yield strength. Through these information, the material can be abstracted into an entity, and various mechanical properties, chemical composition, part shape, grade information and the like of the material can also be abstracted into an entity, and these information entities and the material entity have corresponding relationship because different materials have different properties.

[0062] (2) Conceptual design structure of die library

[0063] The die library contains data information of the type of die and die material. The quality and service life of the stamping die directly affect the quality and cost of the stamping part, and the production efficiency and safety of the stamping production.

[0064] Specifically, the stamping die is a necessary process equipment in the stamping production process, and the quality and service life of the stamping die have important influence on the cost of stamping and the quality of the stamping part, thereby playing an important role in the production efficiency and economic benefit of the enterprise. The die library is abstracted into an entity, and the material, die parameter and type are also abstracted into different entities. The die material includes punch material, die material and other materials; the type includes category information of the die; and the die parameter includes closing height, size parameter, allowable stress and the like.

[0065] (3) Conceptual design structure of equipment library

[0066] The equipment library contains various parameters of the stamping equipment, mainly including the maximum stamping force that the equipment can produce, i.e. the nominal pressure, the number of slide strokes, the length of slide strokes, the maximum die height and the die height adjustment amount, the workbench size and the slide bottom size, etc.

[0067] Specifically, the main technical parameters of the equipment include the stamping equipment, the type, and the technical parameters. The stamping equipment includes the equipment number, the name, the model, and the equipment type; the type includes the equipment purpose, the equipment characteristics, and the equipment type. Taking the hydraulic machine as an example, the technical parameters include the nominal force, the maximum ejection force, the maximum ejection stroke, the maximum stroke of the main piston, the maximum distance from the piston beam to the workbench, the workbench size, and other information. Through these information, the equipment is abstracted as an entity.

[0068] (4) Conceptual design structure of process database

[0069] The process database contains the data, formulas, rules, etc. required for the entire stamping process design process, which is the key of database design. Its essence is to provide data support for each step of the stamping process and reduce the workload of process designers.

[0070] Specifically, the process database is the core of the system, and according to the stamping process design, the data, rules and experience required in the stamping process design process are summarized. The process database can provide data support for each step of the stamping process design, greatly improving the work efficiency of process designers.

[0071] (5) Conceptual design structure of process parameter library

[0072] The process parameter library contains all the data obtained by the system design, which is divided into two parts: temporary process parameter library and formal process parameter library.

[0073] Specifically, the process parameter library is the final purpose of the stamping process design, and the process parameter library includes stamping process, material, material size, material layout, mold, and equipment, etc.

[0074] (6) Conceptual design structure of user database

[0075] The user database contains user accounts, passwords, permissions, identity information, operation records, etc. Its purpose is to identify users and manage user usage permissions, effectively ensuring the security of system data.

[0076] Specifically, the user database includes information for identifying, auditing and assigning the rights of the user, and specifically includes the user's account, password, login information, operation rights and the like. The password file in the user database is saved using an encryption algorithm provided by the database; the login information includes login time and exit time; the operation rights are indicated by an operation level, which indicates the operation range available to the user.

[0077] The first database of the stamping process knowledge base has the following logical structure design:

[0078] The main task of the logical structure design of the database is to convert the global conceptual structure into a database logical structure supported by a certain database management system. A data model that best describes the conceptual structure is selected, and then the most suitable database management system supporting this data model is selected. According to the model conversion principle, the ER model conversion of the stamping process knowledge base is converted into a relational mode as follows:

[0079]

[0080]

[0081] In one implementation, after the step S103, the method further includes: receiving product information of a new product, the product information of the new product including size, material, production batch, tolerance and shape of the new product; calculating a forming similarity between the new product and any old product in the first database according to the size, material, production batch and tolerance of the new product and the size, material, production batch and tolerance of the any old product; calculating a shape similarity between the new product and the any old product according to the shape of the new product and the shape of the any old product; calculating an overall similarity between the new product and the any old product according to the forming similarity and the shape similarity; and storing the size, material, production batch, tolerance and shape of the new product into the material library if it is determined that the new product is not similar to the any old product according to the overall similarity.

[0082] When S103 is executed, the product information of a plurality of old products is stored in the first database. At this time, when a new product is received, the product information of the new product needs to be stored. Specifically, in order to facilitate product retrieval and product library maintenance, the input new product and related knowledge need to be classified and extracted, and the classification mainly depends on shape similarity and forming similarity. The shape similarity includes the similarity of the geometric shape and topological relationship of the product, and is mainly used to determine whether there is a similar product model in the case library. The forming similarity includes the similarity of the key dimensions, material parameters, and production batch related to the forming difficulty of the product, and is mainly used to determine the formability of the new product. The similarity calculation formula is:

[0083]

[0084] wherein Sim represents the similarity of two stampings; S 形状 and S 成形 respectively represent the shape similarity and the forming similarity; ω 形状 and ω 成形 respectively represent the weight factors of the shape similarity and the forming similarity.

[0085] One of the main works of applying CBR is to use the forming parameters, process scheme and mold structure of similar cases in the case library to assist the design of the stamping scheme and mold structure of the new stamping. When the feature types of the new product and the existing product are different, the forming parameters and the process scheme have no comparability, so in the similarity calculation of the product features and their types, the types are used for large classification. 类型 The value is defined as:

[0086]

[0087] wherein, and respectively represent all the features and their types of the new product and the old product.

[0088] The feature details have been described in the form of different numbers and number combinations in the coded form in the product description, and the similarity can be directly calculated by using the Euler formula:

[0089]

[0090] wherein, and respectively represent the i-th detail feature of the new product and the old product; ω 细节，i represents the weight of the i-th detail feature; is used to calculate the similarity distance of the i-th forming parameter, and in the formula, by dividing by the value of the similarity distance can be between 0 and 1.

[0091] According to the product coding according to the forming similarity, in order to distinguish the similarity of the coded product after replacement and the real product corresponding to the coding, the similarity calculation formula after replacement is:

[0092] P 细节,i = P 真实,i -(P 真实,i -P 代替,i )×ω 代替,i ;

[0093] Wherein, P 真实,i represents the real coding of the i-th detail feature; P 代替,i represents the coding after replacement of the i-th detail feature according to the forming similarity; ω 代替,i represents the forming feature similarity of the i-th detail feature, that is, the degree of replacement of the i-th detail feature, and 0 if there is no replacement.

[0094] From the above formula, D 细节 ∈[0.0,1.0], so S 细节 ∈[0.0,1.0]. When the similarity is 0.0, it means that the similarity of the two products is the lowest; when the similarity is 1.0, it means that the similarity of the two products is the highest.

[0095] The forming similarity calculation is to calculate the similarity of the product main size combination, production batch, tolerance and material related to the forming in the forming parameter information description. The calculation formula is:

[0096]

[0097] In the formula, D 尺寸 represents the similarity distance of the forming size combination of the new and old products; and respectively represent the production batch of the new and old products; and respectively represent the tolerance value of the new and old products; D 材料 represents the similarity distance of the material of the new and old products; ω represents the respective weight.

[0098]

[0099] In the formula, and respectively represent the i-th size parameter value of the new and old products; ω 具体尺寸，i represents the weight of the i-th size parameter. According to the stamping forming theory, the product size combination affecting the stamping forming mainly includes the relative height of stamping relative thickness of blank relative corner radius relative limit height Wherein, D is the length of the blank, D=D0+(L-B).

[0100] D0=1.13×[B 2 +4B(H-0.43r)-1.72r(H+0.5r)-4r1(0.11r1-0.18r)] 1 / 2 .

[0101]

[0102] In the formula, and respectively represent the i-th material parameter value of the new and old products; ω 材料参数，i represents the weight of the i-th material parameter.

[0103] When the feature types of the new and old products are different, the forming parameters and process schemes are not comparable, so when calculating the similarity, first judge the type similarity S 类型 , when S 类型 =0, stop the similarity calculation of the new product and the current case in the case library, and turn to the similarity calculation of the next case in the case library; when S 类型 =1, calculate the detailed feature similarity, and calculate the product shape similarity and the forming similarity respectively, and finally calculate the total product similarity, which lays a good foundation for the classification of product and process data, and facilitates subsequent related research.

[0104] S104, divide the second database into an input layer, a knowledge storage layer, an inference layer, and an output layer.

[0105] S105, take the condition parameters as input layer parameters of the input layer, take the process parameters of the polishing robot polishing the mold surface as output layer parameters of the output layer, store the data formed by the input layer parameters, the output layer parameters, and the polished surface quality and the mapping relationship of the data to the knowledge storage layer, and store the convolutional neural network model and the parameters of the convolutional neural network model to the inference layer.

[0106] Preferably, the condition parameters include one or more of the initial surface quality, the body material, and the curvature of the local polishing area; and the process parameters of the polishing robot polishing the mold surface include one or more of the polishing head parameters, the polishing head movement speed, the polishing head movement path, and the polishing force.

[0107] Specifically, the second database of the polishing process knowledge base is divided into an input layer, a knowledge storage layer, an inference layer, and an output layer. The condition parameters are the input layer, including: initial surface quality, body material, curvature of the local polishing area, etc. The output layer includes the process parameters of the polishing robot polishing the mold surface, including: polishing head parameters (type, shape, size, polishing method, etc.), polishing head moving speed, polishing head moving path, polishing force, etc. The knowledge storage layer contains the input layer parameters and the output layer parameters and the data formed by the polished surface quality and its basic mapping relationship. The data is obtained from two sources: one is through experiments, and the other is from actual generated and verified data. The experimental data is obtained through a dedicated test equipment, by setting the threshold of each input parameter, adopting the uniform Latin square method to design the experimental sample distribution, and testing the optimized output parameters to establish a limited sample mapping relationship. At the same time, through sensitivity analysis, a weight coefficient is designed for each input parameter. Then, the knowledge inference machine is established through the deep learning and training of the inference layer, and the optimized polishing process parameters of different mold surfaces are obtained through reasoning based on the data in the process database. The basic architecture of the process knowledge base to be constructed by the project is shown in Figure 3 .

[0108] It should be noted that in the process knowledge base shown in Figure 3 , each parameter is an attribute of its own ontology. The ontology in the knowledge base mainly includes two parts: mold ontology and tool ontology. The project plans to construct the tree attribute graph of the mold ontology and the tool ontology in an object-oriented manner as shown in Figure 4 and Figure 5 .

[0109] Preferably, the training step of the convolutional neural network model comprises: obtaining sampling data, the sampling data comprising initial surface quality of polishing, polishing head moving speed, Gaussian curvature of polishing area, polishing force, body material, polishing head parameter, polishing direction and wear; adopting a convolutional neural network back propagation algorithm, and based on the established cost function and the sampling data, the convolutional neural network model is trained.

[0110] Specifically, the data of the output layer of the polishing process knowledge base is based on knowledge reasoning, and the currently widely used convolutional neural network is used for knowledge reasoning and learning. The convolutional neural network needs to be accumulated and trained through a large amount of data. Before the deep learning system is corrected and improved, these data are mainly obtained from experiments and simulation analysis, the factors affecting the polishing quality are obtained and the sensitivity analysis is performed, the mapping relationship between the polishing quality and the polishing head moving speed, the Gaussian curvature of the polishing area, the polishing force, the body material, the polishing head (shape: circular, arc, strip, etc.; type: oil stone, sponge sand, etc.) parameter, the polishing direction and the wear, and the corresponding neural network model is constructed as shown in Figure 6 .Figure 6 indicates the initial surface quality, Gaussian curvature, body material, polishing head parameters, etc. indicates the polishing force, polishing direction, polishing speed, etc. indicates the polishing force, polishing direction, polishing speed, etc.

[0111] Specifically, a knowledge reasoning machine is established by training and learning of the constructed neural network model, the learning process adopts a convolutional neural network back propagation algorithm, and a cost function of N training samples is established The cost function of the ith training sample is Then, the weight coefficients in each layer are adjusted in reverse according to the output error of each sample For the non-output layer, the sensitivity of the ith layer can be expressed as δ l = (W l+I ) T δ l+I ·f′(u l ), and the sensitivity of the output layer L can be expressed as δ L = f′(u L )·(y n -t n ). For the ith layer, the partial derivative of the error with respect to each weight is According to the above calculation, the weight update of the current layer neuron is Then, combined with the optimization calculation, the appropriate process data is intelligently inferred, the polishing head, the polishing method and the polishing head replacement period are reasonably selected. At the same time, it can accept the guidance of the deep learning system and optimize the intelligent inference strategy. The technical route is as follows Figure 7 indicated.

[0112] The stamping and polishing process knowledge base construction method divides the first database of the stamping process knowledge base into a material library, a die library, an equipment library, a process database, a process parameter library and a user database, stores material data information into the material library, stores the type of stamping die, the material of stamping die and the data information of parameters into the die library, stores various parameter information of stamping into the equipment library, stores data, formulas and rule information in the design flow of the stamping process into the process database, stores process parameters obtained by the stamping process into the process parameter library, and stores user information into the user database. The second database of the polishing process knowledge base is divided into an input layer, a knowledge storage layer, an inference layer and an output layer; the conditional parameters are used as the input layer parameters of the input layer, the process parameters of the polishing robot polishing die surface are used as the output layer parameters of the output layer, the input layer parameters, the output layer parameters and the data formed by the surface quality after polishing and the mapping relationship of the data are stored into the knowledge storage layer, and the convolutional neural network model and the parameters of the convolutional neural network model are stored into the inference layer. Therefore, by establishing the database of the stamping process and the database of the polishing process, the forming process characteristics of various stamping parts can be extracted, the intelligent design of the die can be realized, and this technical bottleneck of die intelligent manufacturing is broken through.

[0113] The application further provides a stamping and polishing process knowledge base construction device. Figure 8As shown, a stamping and polishing process knowledge base construction device includes a construction module 801, a first division module 802, a first storage module 803, a second division module 804, and a second storage module 805. The construction module 801 is configured to construct a first database of a stamping process knowledge base and a second database of a polishing process knowledge base. The first division module 802 is configured to divide the first database into a material library, a die library, an equipment library, a process database, a process parameter library, and a user profile library. The first storage module 803 is configured to store material data information to the material library, store data information of types of stamping dies and materials and parameters of stamping dies to the die library, store various parameter information of stamping to the equipment library, store data, formulas, and rule information in a design flow of the stamping process to the process database, store process parameters obtained by the stamping process to the process parameter library, and store user profiles to the user profile library. The second division module 804 is configured to divide the second database into an input layer, a knowledge storage layer, an inference layer, and an output layer. The second storage module 805 is configured to store condition parameters as input layer parameters of the input layer, store process parameters of a polishing robot polishing a die surface as output layer parameters of the output layer, store data and mapping relationships of the input layer parameters, the output layer parameters, and a polished surface quality to the knowledge storage layer, and store a convolutional neural network model and parameters of the convolutional neural network model to the inference layer.

[0114] For specific limitations of the stamping and polishing process knowledge base construction device, refer to the limitations of the stamping and polishing process knowledge base construction method described above, which will not be repeated here. Each module in the stamping and polishing process knowledge base construction device described above can be realized by software, hardware, and combinations thereof, in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0115] This invention provides a computer-readable storage medium storing an application program. When executed by a processor, the program implements a method for constructing a stamping and grinding process knowledge base according to any one of the above embodiments. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, the storage device includes any medium that stores or transmits information in a readable form by a device (e.g., a computer, a mobile phone), and can be a read-only memory, a disk, or an optical disk, etc.

[0116] This invention also provides a computer application running on a computer, which is used to execute a method for constructing a stamping and grinding process knowledge base according to any of the above embodiments.

[0117] also, Figure 9 This is a schematic diagram of the structural composition of a computer device in an embodiment of the present invention.

[0118] This invention also provides a computer device, such as... Figure 9 As shown. The computer device includes a processor 902, a memory 903, an input unit 904, and a display unit 905, among other components. Those skilled in the art will understand that... Figure 9 The illustrated device structure is not intended to limit all devices and may include more or fewer components than shown, or combine certain components. Memory 903 can be used to store application program 901 and various functional modules. Processor 902 runs application program 901 stored in memory 903, thereby performing various functional applications and data processing of the device. Memory can be internal memory or external memory, or both. Internal memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. External memory may include hard disks, floppy disks, ZIP disks, USB flash drives, magnetic tapes, etc. The memory disclosed in this invention includes, but is not limited to, these types of memory. The memory disclosed in this invention is only an example and not a limitation.

[0119] The input unit 904 is configured to receive input of signals and receive a keyword input by a user. The input unit 904 can include a touch panel and other input devices. The touch panel can collect a touch operation (such as an operation of a user using a finger, a stylus, or any suitable object or accessory on or near the touch panel) of the user on or near the touch panel and drive a corresponding connection device according to a pre-set program; the other input devices can include, but are not limited to, one or more of a physical keyboard, function keys (such as play control buttons, switch buttons, etc.), a trackball, a mouse, a joystick, etc. The display unit 905 can be configured to display information input by the user or information provided to the user and various menus of the terminal device. The display unit 905 can take the form of a liquid crystal display, an organic light-emitting diode, etc. The processor 902 is a control center of the terminal device, connects all parts of the entire device through various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 903 and calling data stored in the memory.

[0120] As an embodiment, the computer device includes: one or more processors 902, a memory 903, and one or more application programs 901, wherein the one or more application programs 901 are stored in the memory 903 and configured to be executed by the one or more processors 902, and the one or more application programs 901 are configured to perform the process knowledge base construction method of the stamping and grinding process according to any one of the above embodiments.

[0121] In addition, the stamping and grinding process knowledge base construction method, device, computer device, and storage medium provided by the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by using specific examples in this paper. The above embodiment descriptions are only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed; in summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for building a process knowledge base for a press polishing, characterized by, The method comprises: constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base; dividing the first database into a material library, a die library, an equipment library, a process database, a process parameter library, and a user database; storing material data information into the material library, storing the type of stamping die, the material of stamping die, and the data information of parameters into the die library, storing various parameter information of stamping into the equipment library, storing data, formulas, and rule information in the design flow of the stamping process into the process database, storing process parameters obtained by the stamping process into the process parameter library, and storing user information into the user database; dividing the second database into an input layer, a knowledge storage layer, an inference layer, and an output layer; storing condition parameters as input layer parameters of the input layer, storing process parameters of polishing die surfaces by a polishing robot as output layer parameters of the output layer, storing data and mapping relationships of the input layer parameters, the output layer parameters, and the surface quality after polishing into the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model into the inference layer.

2. The method of claim 1, wherein, The method further comprises: receiving input product information of a new product, wherein the product information of the new product comprises the size, material, production batch, tolerance, and shape of the new product; 3. The method of claim 1, wherein, calculating the forming similarity between the new product and any old product in the first database according to the size, material, production batch, and tolerance of the new product and the size, material, production batch, and tolerance of the old product; calculating the shape similarity between the new product and the old product according to the shape of the new product and the shape of the old product; 4. The method of claim 1, wherein, calculating the overall similarity between the new product and the old product according to the forming similarity and the shape similarity; storing the size, material, production batch, tolerance, and shape of the new product into the material library if it is determined that the new product is not similar to the old product according to the overall similarity.

5. The method of claim 1, wherein, The condition parameters comprise one or more of the initial surface quality, the body material, and the curvature of the local polishing area. The process parameters of polishing die surfaces by the polishing robot comprise one or more of the polishing head parameters, the polishing head movement speed, the polishing head movement path, and the polishing force. The training steps of the convolutional neural network model comprise: ​ ​ ​ 6. The method of claim 1, wherein, ​ ​ 7. The method of claim 1, wherein, ​ Obtaining sampling data, the sampling data including a polished initial surface quality, a polishing head moving speed, a polishing area Gaussian curvature, a polishing force, a body material, a polishing head parameter, a polishing direction and wear; A convolutional neural network back propagation algorithm is adopted, and a cost function and the sampling data are used to train the convolutional neural network model.

8. A process knowledge base construction apparatus for a press polishing, characterized by, The device comprises: A construction module for constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base; A first division module for dividing the first database into a material library, a die library, an equipment library, a process database, a process parameter library and a user database; A first storage module for storing material data information to the material library, storing data information of a type of stamping die, a material of stamping die and parameters to the die library, storing various parameter information of stamping to the equipment library, storing data, formulas and rule information in a design flow of the stamping process to the process database, storing process parameters obtained by the stamping process to the process parameter library, and storing user information to the user database; A second division module for dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer; A second storage module for storing a condition parameter as an input layer parameter of the input layer, storing a process parameter of a polishing robot polishing die surface as an output layer parameter of the output layer, storing data and a mapping relationship of the data formed by the input layer parameter, the output layer parameter and a polished surface quality to the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model to the inference layer.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 7.

Images