Parts manufacturing method, device, equipment and medium based on industrial neural network

Through the method based on industrial neural networks, the correlation map and industrial neural network are constructed, and the problems of multiple processes and complex data relationships in composite material parts manufacturing are solved, efficient automated manufacturing is achieved, and production efficiency and resource utilization are improved.

CN113850454BActive Publication Date: 2024-11-26SHANG FEI ZHI NENG JI SHU YOU XIAN GONG SI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011164284.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-10-27
Publication Date
2024-11-26
Estimated Expiration
2040-10-27

AI Technical Summary

Technical Problem

There are many steps in the manufacturing process of composite parts, long manufacturing cycles, and manual participation is required for process parameter adjustment and verification, resulting in low production efficiency and waste of resources. It is difficult for existing databases to effectively analyze complex industrial data relationships, affecting manufacturing efficiency.

Method used

Using an industrial neural network-based method, we can construct an association map by sorting out the target entities, constraints and manufacturing processes, and associate them with the algorithm library to establish an industrial neural network to achieve efficient integration and management of data and relationships, and automate the manufacturing process.

Benefits of technology

It improves the efficiency and automation of composite parts manufacturing, reduces human intervention, reduces resource waste, simplifies the analysis and calculation of complex relationships, and improves production efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113850454B_ABST
    Figure CN113850454B_ABST
Patent Text Reader

Abstract

The embodiments of the present application disclose a method, device, equipment and medium for manufacturing parts based on industrial neural networks. The embodiments of the present application include: sorting out the target entities, constraints, manufacturing processes and application types corresponding to the manufacturing of composite parts; constructing an association graph in a graph database according to the target entities, constraints, manufacturing processes and application types; selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with the algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes; constructing an industrial neural network according to the association graph and the associated algorithm library; and manufacturing composite parts based on the industrial neural network. The above scheme manufactures composite parts based on industrial neural network technology, efficiently integrates and manages fragmented data and relationships, thereby improving the efficiency of relationship analysis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of composite parts manufacturing, and in particular to a parts manufacturing method, device, equipment and medium based on industrial neural networks. Background Art

[0002] Composite materials are among the most promising materials currently, widely used due to their low specific gravity, excellent rigidity, and high strength. Over the past 40 years, composite materials have steadily expanded within the manufacturing industry, now comprising over 50% of the structural weight of helicopters and fighter jets, and reaching 70% in some advanced civilian aircraft.

[0003] The manufacturing process of composite parts involves many steps and a long manufacturing cycle. Most process parameter adjustments and process verification require human participation, resulting in low production efficiency and waste of production resources, which seriously restricts the large-scale production and popularization of composite parts.

[0004] The manufacturing process of composite parts involves a vast amount of industrial mechanisms and industrial data. These industrial mechanisms and industrial data have close and complex data relationships, and the relationships between industrial data grow exponentially with the data volume. However, the architecture of relational databases is not designed for the analysis of complex relational networks. To understand and analyze relationships across entities, relational databases require table joins. Queries with complex joins can take hours or even days, and the computational cost increases as the data volume grows. NoSQL databases store all data in a single table. Relational analysis requires scanning huge tables with millions or billions of rows, making it difficult to conduct deeper analysis of relationships beyond two or three levels. Summary of the Invention

[0005] Embodiments of the present invention provide a parts manufacturing method, device, equipment and medium based on industrial neural networks to efficiently integrate and manage fragmented data and relationships, making the manufacturing of composite parts intelligent and automated, and improving the efficiency of composite parts manufacturing.

[0006] In one embodiment, the present application provides a parts manufacturing method based on an industrial neural network, the method comprising:

[0007] Sort out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing;

[0008] Build a correlation graph based on target entities, constraints, manufacturing processes, and application types;

[0009] Selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with an algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its neighbors;

[0010] Constructing an industrial neural network based on the association graph and the associated algorithm library;

[0011] Manufacturing of composite parts based on industrial neural networks.

[0012] In another embodiment, the present application also provides a composite material part manufacturing device, the device comprising:

[0013] A data combing module is used to sort out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing;

[0014] The association graph construction module is used to construct an association graph based on target entities, constraints, manufacturing processes, and application types;

[0015] An algorithm library association module is used to select at least one node in the association graph as an algorithm node, and associate the algorithm node with the algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes;

[0016] An industrial neural network construction module, configured to construct an industrial neural network based on the association graph and the associated algorithm library;

[0017] Manufacturing module for manufacturing composite parts based on industrial neural networks.

[0018] In yet another embodiment, an embodiment of the present application further provides a composite part manufacturing apparatus, comprising: one or more processors;

[0019] a memory for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the parts manufacturing method based on industrial neural network as described in any one of the embodiments of the present application.

[0021] In yet another embodiment, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the part manufacturing method based on an industrial neural network as described in any one of the embodiments of the present application.

[0022] In an embodiment of the present application, by sorting out target entities, constraints, manufacturing processes, and application types and constructing an association map, fragmented data and relationships are efficiently integrated and managed to improve the efficiency of relationship analysis. By constructing an industrial neural network based on the association map and the associated algorithm library, composite parts are manufactured based on the industrial neural network, making the composite parts manufacturing process more intelligent and automated, and improving the efficiency of composite parts manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of a parts manufacturing method based on an industrial neural network provided by one embodiment of the present invention;

[0024] Figure 2 A flowchart of a parts manufacturing method based on an industrial neural network provided in another embodiment of the present invention;

[0025] Figure 3 A schematic diagram of an association map provided by another embodiment of the present invention;

[0026] Figure 4 A schematic structural diagram of a composite material parts manufacturing device provided by an embodiment of the present invention;

[0027] Figure 5 A schematic structural diagram of a composite material parts manufacturing device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0029] Figure 1 This is a flow chart of a method for manufacturing parts based on an industrial neural network according to one embodiment of the present invention. The method for manufacturing parts based on an industrial neural network provided in this embodiment is applicable to the manufacturing of composite parts. Typically, this method is applicable to the manufacturing of composite parts for civil aircraft based on an industrial neural network. This method can be specifically performed by a composite part manufacturing device, which can be implemented in software and / or hardware, and can be integrated into a composite part manufacturing device. Figure 1 , the method of the embodiment of the present application specifically includes:

[0030] S110. Sort out the target entities, constraints, manufacturing processes, and application types corresponding to composite parts manufacturing.

[0031] The target file is a document recording the composite part manufacturing process, which can be data retrieved from the internet or databases. The target entity can include personnel information, equipment information, material information, and supplier information related to the composite part manufacturing process. For example, personnel information can include employee identification, work hours, job title, and certifications held. Equipment information can include equipment identification, operating status, and lifespan. Material information can include material composition, proportions, and hardness. Supplier information can include the name, address, and contact information of equipment and material suppliers for traceability. The target entity can also be a processing step in composite part manufacturing. Constraints can be conditions that must be met during composite part manufacturing, such as whether personnel possess manufacturing qualifications or whether equipment status meets start-up requirements. A manufacturing process can be a fixed process derived from the permutation and combination of multiple processing steps. Application types can include detailed application scenarios implemented within the composite part manufacturing application scenario, such as calculating equipment utilization and personnel allocation.

[0032] S120. Construct an association graph based on the target entity, constraint conditions, manufacturing process, and application type.

[0033] The manufacturing process of composite parts involves many steps and is discrete. In the embodiments of this application, in order to establish connections between entities and processes in the composite part manufacturing process, more effectively integrate the data and relationships in the composite part manufacturing process, and perform structured intelligent analysis on the manufacturing data, a correlation map is constructed based on the target entity, constraints, manufacturing process, and application type, so that the data, relationships, industrial experience, and mechanisms involved in the manufacturing process are digitized and structured.

[0034] Specifically, there may be certain relationships between target entities, constraints, manufacturing processes, and application types. For example, process 1 requires the use of three personnel and one device, and needs to satisfy constraint 1 and mechanism 1. Therefore, the process, personnel, constraint 1, and mechanism 1 can be connected to represent the association relationship. For all acquired target entities, constraints, manufacturing processes, and application types, they are associated according to the association relationships between them to form an association graph. Compared to storing large amounts of data and data relationships in tables, forming an association graph can more effectively integrate data and data relationships, quickly meet access requirements for complex relationships, improve data access efficiency, and thus improve the efficiency of composite parts manufacturing.

[0035] S130. Select at least one node in the association graph as an algorithm node, and associate the algorithm node with an algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes.

[0036] By associating the algorithm nodes with the algorithm library, the necessary connection is established between the association map and the algorithm library, thereby accurately and comprehensively describing the various complex relationships involved in the industrial manufacturing field, and using the algorithm to implement related reasoning and prediction functions. It is understandable that the algorithms or algorithm libraries referred to herein may already exist or have been established. In addition, the algorithms stored in the algorithm library may include neural network algorithms, wherein the neural network algorithms may include convolutional neural network algorithms and deep neural network algorithms, and at least part of these algorithms may be generated based on the industrial mechanisms, industrial models or industrial rules of thumb involved in the operating business in the target industrial manufacturing process.

[0037] In an embodiment of the present application, at least one node in the association graph is selected as an algorithm node, and the algorithm node is associated with an algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes, including: selecting a first preset number of nodes as algorithm nodes, configuring an algorithm interface associated with the algorithm library for the algorithm node, and the algorithm interface enables the algorithm node to call the algorithm stored in the algorithm library through the algorithm interface to calculate the data in the algorithm node and its adjacent nodes. The first preset number can be set according to actual conditions. The algorithm interface is configured to be able to obtain the data in the algorithm node and its adjacent nodes, provide the data to be calculated to the algorithm library, and the algorithm library calls the algorithm stored therein and associated with the algorithm node to perform calculations, and obtains the calculation results returned from the algorithm library. For example, the data can be part of the node attributes of the algorithm node, and the algorithm associated with a certain algorithm node can be preset.

[0038] In an embodiment of the present application, the algorithm interface can also be configured to obtain the pending data of the algorithm node to which it belongs, temporarily call the algorithm stored in the algorithm library and associated with the algorithm node to which it belongs to perform calculations, and obtain the calculation results.

[0039] The beneficial effect of the above scheme is that relatively complex algorithms are placed outside the graph database and are called through an interface to perform calculations. This is particularly suitable for the distributed configuration of the entire industrial neural network (system) and can make the computing resources required at each location in the entire system relatively small.

[0040] S140: Construct an industrial neural network based on the association graph and the associated algorithm library.

[0041] Among them, industrial neural network technology is a new data architecture technology based on a graph database, which involves calling relational database data and algorithm library algorithms. For example, after obtaining the product assembly association graph, by configuring some nodes so that they have interfaces that can call the algorithms stored in the algorithm library, the assembly association graph and the algorithm library establish the necessary connection, thereby accurately and comprehensively describing the various complex relationships involved in the industrial manufacturing field, and using algorithms to implement related reasoning and prediction functions. It is understandable that the algorithms or algorithm libraries referred to herein may already exist or have been established. In addition, the algorithms stored in the algorithm library may include neural network algorithms, wherein neural network algorithms may include convolutional neural network algorithms and deep neural network algorithms, etc., and at least some of these algorithms may be generated based on the industrial mechanisms, industrial models or industrial rules of thumb involved in the operational business in the target industrial manufacturing process.

[0042] S150. Manufacturing of composite parts based on industrial neural networks.

[0043] Exemplarily, based on the algorithm library in the industrial neural network, the algorithms stored therein are called to calculate the data and constraint relationships of the nodes in the associated spectrum to determine the optimal manufacturing parameter solution.

[0044] In an embodiment of the present application, by sorting out target entities, constraints, manufacturing processes, and application types and constructing an association map, fragmented data and relationships are efficiently integrated and managed to improve the efficiency of relationship analysis. By constructing an industrial neural network based on the association map and the associated algorithm library, composite parts are manufactured based on the industrial neural network, making the composite parts manufacturing process more intelligent and automated, and improving the efficiency of composite parts manufacturing.

[0045] Figure 2 This is a flowchart of a parts manufacturing method based on an industrial neural network provided by another embodiment of the present invention. This embodiment of the present application is a further optimization of the technical solution based on the above embodiment. Figure 2 The parts manufacturing method based on industrial neural network provided in this embodiment may include:

[0046] S210. Based on natural language processing technology, extract the target entities, constraints, manufacturing processes and application types of composite parts manufacturing from the target file; wherein the target entities include employee information, employee certificate information, composite parts manufacturing equipment information, tooling information, material information and supplier information.

[0047] Natural language processing technology is a discipline that studies language issues in human-computer interaction. Through natural language processing technology, key information can be extracted from natural language target text.

[0048] S220: Take the target entity, constraint conditions, manufacturing process, and application type as nodes.

[0049] For example, Figure 3 As shown, the target entity can be Figure 3 The equipment, personnel, tooling, processes, and materials in the process can be represented by constraints, such as the number of equipment, personnel, and tooling required by the process, and mechanisms, such as the process's requirements for processes and materials. Each process, equipment, personnel, tooling, process, material, constraint, and mechanism is represented as a node using a fixed-shaped icon.

[0050] S230: Connect the nodes with associated relationships with edges to form an associated graph.

[0051] For example, Figure 3 As shown in the figure, if there is an association between two nodes, they are connected to form an edge, indicating the association. For example, if process 1 is connected to equipment, it means that process 1 requires the equipment to proceed. However, if process 1 is not connected to tooling, it means that process 1 does not require tooling.

[0052] S240: Construct an industrial neural network based on the association graph and the associated algorithm library.

[0053] Constructing an industrial neural network based on the association graph and the associated algorithm library includes: selecting a second preset number of nodes as data association nodes, configuring a data interface associated with a relational database for the data association nodes, so that the data association nodes can call data in the relational database through the data interface.

[0054] For example, the second preset number can be set according to actual conditions. Nodes in the association graph that meet the second preset number are selected as data association nodes, and the data association nodes are configured to have a data interface associated with a relational database, wherein the second type of interface is configured to be able to retrieve data stored in the relational database.

[0055] It should be understood that algorithm nodes and data-related nodes are not identical. The data interface may simply provide an access path to retrieve information stored in the relational database. In other words, the information to be retrieved will only be temporarily accessed and stored in the graph database, thereby reducing overall resource usage and overhead.

[0056] S250. Calculate the data in the association graph based on the algorithm library in the industrial neural network to determine candidate combinations of target entities, constraints, manufacturing processes, and application types.

[0057] In an embodiment of the present application, the data in the association graph is calculated based on the algorithm library in the industrial neural network to determine the candidate combinations of target entities, constraints, manufacturing processes and application types, including: traversing the nodes and edges of the association graph to determine the candidate combinations of target entities, constraints, manufacturing processes and application types that can realize the manufacturing of composite parts.

[0058] For example, traversing any node in the association graph yields multiple solutions, i.e., multiple candidate combinations for fabricating composite parts. Each combination may require different time and cost to fabricate the composite part.

[0059] S260: Determine a target combination from the candidate combinations based on the manufacturing time and / or manufacturing cost corresponding to manufacturing the composite material part.

[0060] The target combination is the combination ultimately selected for composite part manufacturing from a set of target entities, constraints, manufacturing processes, and application types that enable composite part manufacturing. The combination of target entities, constraints, manufacturing processes, and application types that enable composite part manufacturing is the solution obtained by traversing the association graph, and the target combination is the optimal solution.

[0061] For example, process 1 can be completed with three people and one piece of equipment, while process 2 can be completed with two people and two pieces of equipment. Process 1 can also be completed with two people and two pieces of equipment, while process 2 can be completed with four people and one piece of equipment. However, the time and / or cost required to complete the verification material part manufacturing process will vary. Therefore, a trade-off is made between time and / or cost to determine the final target combination for actual composite part manufacturing.

[0062] In an embodiment of the present application, based on the manufacturing time and / or manufacturing cost corresponding to the manufacturing of composite parts by the candidate combinations, a target combination is determined from the candidate combinations, including: determining the candidate combination with the shortest manufacturing time and / or the lowest manufacturing cost as the target combination.

[0063] For example, to shorten the manufacturing time of a composite part and improve manufacturing efficiency, the candidate combination with the shortest manufacturing time can be selected as the target combination and then used for composite part manufacturing. Alternatively, the candidate combination with the lowest cost can be selected as the target combination and then used for composite part manufacturing to reduce manufacturing costs. Alternatively, both time and cost can be considered simultaneously, and a comprehensive trade-off can be made to determine the target combination and then use it for composite part manufacturing.

[0064] S270: Manufacturing composite material parts according to the target combination.

[0065] In an embodiment of the present application, the method also includes: determining the utilization information of composite parts manufacturing equipment based on the target entity, constraints, manufacturing process and application type; and / or determining personnel situation analysis information based on the target entity, constraints, manufacturing process and application type; and / or determining tool life prediction information based on the target entity, constraints, manufacturing process and application type.

[0066] For example, in the application scenario of composite parts manufacturing, other applications can also be realized, such as analyzing equipment utilization, analyzing personnel conditions, predicting tool life, etc., which are not listed here one by one, and corresponding applications can be implemented according to actual needs.

[0067] The technical solution of the embodiment of the present application uses natural language processing technology to extract the target file to obtain the target entity, constraint conditions, manufacturing process and application type for the manufacturing of composite parts, and uses the target entity, constraint conditions, manufacturing process and application type as nodes; the nodes with associated relationships are connected with edges to form an associated graph, so as to quickly and clearly integrate and sort out the data and data relationships, and by traversing the nodes and edges of the associated graph, the candidate combination of target entities, constraints, manufacturing processes and application types that can realize the manufacturing of composite parts is determined, and the target combination with the shortest manufacturing time and / or the lowest manufacturing cost is selected from the candidate combinations to manufacture composite parts, thereby realizing the automation and intelligence of composite parts manufacturing and improving the efficiency of composite parts manufacturing.

[0068] Figure 4 This is a schematic diagram of the structure of a composite part manufacturing device provided by an embodiment of the present invention. The device is applicable to the case of object storage of target files. Typically, the method is applicable to the case of manufacturing composite parts. Typically, the method is applicable to the case of manufacturing composite parts based on a constructed association graph. The device can be implemented by software and / or hardware, and the device can be integrated into a composite part manufacturing device. See Figure 4 , the device specifically includes:

[0069] The data combing module 310 is used to comb the target entities, constraints, manufacturing processes and application types corresponding to the manufacturing of composite parts;

[0070] The association graph construction module 320 is used to construct an association graph based on target entities, constraints, manufacturing processes, and application types;

[0071] An algorithm library association module 330 is configured to select at least one node in the association graph as an algorithm node and associate the algorithm node with an algorithm library so that the algorithm node and its adjacent nodes can use the algorithm stored in the algorithm library to calculate the data in the algorithm node;

[0072] An industrial neural network construction module 340 is used to construct an industrial neural network based on the association graph and the associated algorithm library;

[0073] The manufacturing module 350 is used to manufacture composite parts based on industrial neural networks.

[0074] In the embodiment of the present application, the data combing module 310 is specifically configured to:

[0075] Based on natural language processing technology, the target entities, constraints, manufacturing processes and application types for composite parts manufacturing are extracted from the target file; the target entities include employee information, employee certificate information, composite parts manufacturing equipment information, tooling information, material information and supplier information.

[0076] In the embodiment of the present application, the association graph construction module 320 includes:

[0077] A node determination unit, used to take target entities, constraints, manufacturing processes, and application types as nodes;

[0078] The connection unit is used to connect nodes with associated relationships with edges to form an associated graph.

[0079] In the embodiment of the present application, the algorithm library association module 330 is specifically used to:

[0080] A first preset number of nodes are selected as algorithm nodes, and an algorithm interface associated with the algorithm library is configured for the algorithm node, so that the algorithm node calls the algorithm stored in the algorithm library through the algorithm interface to calculate the data in the algorithm node.

[0081] The industrial neural network building block 340 is specifically configured to:

[0082] A second preset number of nodes are selected as data association nodes, and data interfaces associated with the relational database are configured for the data association nodes, so that the data association nodes can call data in the relational database through the data interface.

[0083] In the embodiment of the present application, the manufacturing module 350 includes:

[0084] a candidate combination determination unit, configured to calculate the data in the association graph based on an algorithm library in an industrial neural network to determine candidate combinations of target entities, constraints, manufacturing processes, and application types;

[0085] The target combination selection unit is used to determine the target combination from the candidate combinations based on the manufacturing time and / or manufacturing cost corresponding to the manufacturing of the composite material part by the candidate combinations.

[0086] In the embodiment of the present application, the candidate combination determination unit is specifically configured to:

[0087] The nodes and edges of the association graph are traversed to determine candidate combinations of target entities, constraints, manufacturing processes, and application types that can enable composite part manufacturing.

[0088] In the embodiment of the present application, the target combination selection unit is specifically configured to:

[0089] The candidate combination with the shortest manufacturing time and / or the lowest manufacturing cost is determined as the target combination.

[0090] In an embodiment of the present application, the device further includes:

[0091] A utilization information determination module, configured to determine personnel situation analysis information based on target entities, constraints, manufacturing processes, and application types; and / or,

[0092] An analysis information determination module, configured to determine personnel situation analysis information based on target entities, constraints, manufacturing processes, and application types; and / or,

[0093] The prediction information determination module is used to determine the tool life prediction information according to the target entity, constraint conditions, manufacturing process and application type.

[0094] The composite parts manufacturing device provided in the embodiments of the present application can execute the parts manufacturing method based on industrial neural networks provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0095] Figure 5 A schematic structural diagram of a composite material parts manufacturing device provided by one embodiment of the present invention. Figure 5 A block diagram of an exemplary composite part manufacturing apparatus 412 suitable for implementing embodiments of the present application is shown. Figure 5 The composite part manufacturing device 412 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0096] like Figure 5As shown, the composite part manufacturing device 412 may include: one or more processors 416; a memory 428 for storing one or more programs. When the one or more programs are executed by the one or more processors 416, the one or more processors 416 implement the part manufacturing method based on the industrial neural network provided in the embodiment of the present application, including:

[0097] Sort out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing;

[0098] Build a correlation graph based on target entities, constraints, manufacturing processes, and application types;

[0099] Selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with an algorithm library so that the algorithm node can call an algorithm stored in the algorithm library to calculate data in the algorithm node and its adjacent nodes;

[0100] Constructing an industrial neural network based on the association graph and the associated algorithm library;

[0101] Manufacturing of composite parts based on industrial neural networks.

[0102] Components of the composite part manufacturing device 412 may include, but are not limited to, one or more processors or processor 416 , memory 428 , and a bus 418 that connects various device components, including the memory 428 and the processor 416 .

[0103] Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0104] The composite part manufacturing device 412 typically includes a variety of computer-readable storage media, which can be any available storage media that can be accessed by the composite part manufacturing device 412, including volatile and non-volatile storage media, removable and non-removable storage media.

[0105] The memory 428 may include computer-readable storage media in the form of volatile memory, such as random access memory (RAM) 430 and / or cache memory 432. The composite part manufacturing device 412 may further include other removable / non-removable, volatile / non-volatile computer storage media. By way of example only, the storage system 434 may be configured to read and write to non-removable, non-volatile magnetic storage media ( Figure 5 Not shown, often called a "hard drive"). Although Figure 5 Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical storage medium) may be provided. In these cases, each drive may be connected to bus 418 via one or more data storage medium interfaces. Memory 428 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0106] A program / utility 440 having a set (at least one) of program modules 442 may be stored, for example, in memory 428. Such program modules 442 include, but are not limited to, operating devices, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 442 generally implement the functions and / or methods of the embodiments described herein.

[0107] The composite part manufacturing device 412 may also communicate with one or more external devices 414 (e.g., a keyboard, a pointing device, a display 424, etc.), one or more devices that enable a user to interact with the composite part manufacturing device 412, and / or any device that enables the composite part manufacturing device 412 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 422. Furthermore, the composite part manufacturing device 412 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 420. Figure 5 As shown, the network adapter 420 communicates with other modules of the composite part manufacturing equipment 412 via the bus 418. Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the composite part manufacturing apparatus 412, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, and data backup storage devices.

[0108] The processor 416 executes various functional applications and data processing by running at least one of the other programs among the multiple programs stored in the memory 428, such as implementing a part manufacturing method based on an industrial neural network provided in an embodiment of the present application.

[0109] One embodiment of the present invention provides a storage medium containing computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to perform a part manufacturing method based on an industrial neural network, including:

[0110] Sort out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing;

[0111] Build a correlation graph based on target entities, constraints, manufacturing processes, and application types;

[0112] Selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with an algorithm library so that the algorithm node can call an algorithm stored in the algorithm library to calculate data in the algorithm node and its adjacent nodes;

[0113] Constructing an industrial neural network based on the association graph and the associated algorithm library;

[0114] Manufacturing of composite parts based on industrial neural networks.

[0115] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable storage media. The computer-readable storage medium can be a computer-readable signal storage medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In an embodiment of the present application, a computer-readable storage medium can be any tangible storage medium containing or storing a program, which can be used by an instruction execution device, device or device or used in combination with it.

[0116] A computer-readable signal storage medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal storage medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution device, apparatus, or component.

[0117] The program code embodied on the computer-readable storage medium may be transmitted using any appropriate storage medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0118] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or device. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0119] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A parts manufacturing method based on industrial neural network, characterized in that: The method comprises: Sort out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing; The target entities are the personnel information, equipment information, material information, supplier information and the processing procedures of composite parts manufacturing in the composite parts manufacturing process; the constraints are the conditions that need to be met in the composite parts manufacturing process; the manufacturing process is a fixed process obtained by arranging and combining multiple processing procedures; the application type is the detailed application scenario realized in the application scenario of composite parts manufacturing; Build a correlation graph based on target entities, constraints, manufacturing processes, and application types; Selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with an algorithm library, so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes; Constructing an industrial neural network based on the association graph and the associated algorithm library; Manufacturing of composite parts based on industrial neural networks.

2. The method according to claim 1, characterized in that Sorting out the target entities, constraints, manufacturing processes and application types corresponding to composite parts manufacturing, including: Based on natural language processing technology, target entities, constraints, manufacturing processes and application types for composite parts manufacturing are extracted from target files; wherein the target entities include employee information, employee certificate information, composite parts manufacturing equipment information, tooling information, material information and supplier information.

3. The method according to claim 1, characterized in that Build a correlation graph based on target entities, constraints, manufacturing processes, and application types, including: The target entity, constraints, manufacturing process, and application type are taken as nodes; The nodes with associated relationships are connected with edges to form an associated graph.

4. The method according to claim 1, characterized in that: Selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with an algorithm library so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes, including: A first preset number of nodes are selected as algorithm nodes, and an algorithm interface associated with the algorithm library is configured for the algorithm nodes, so that the algorithm nodes call the algorithms stored in the algorithm library through the algorithm interface to calculate the data in the algorithm nodes.

5. The method according to claim 1, characterized in that According to the association graph and the associated algorithm library, an industrial neural network is constructed, including: A second preset number of nodes are selected as data-associated nodes, and a data interface associated with a relational database is configured for the data-associated nodes, so that the data-associated nodes can call data in the relational database through the data interface.

6. The method according to claim 1, characterized in that Manufacturing of composite parts based on industrial neural networks, including: Calculating the data in the association graph based on an algorithm library in the industrial neural network to determine candidate combinations of target entities, constraints, manufacturing processes, and application types; Based on the manufacturing time and / or manufacturing cost corresponding to manufacturing the composite material part by the candidate combinations, a target combination is determined from the candidate combinations.

7. The method according to claim 6, characterized in that The data in the association graph is calculated based on the algorithm library in the industrial neural network to determine candidate combinations of target entities, constraints, manufacturing processes, and application types, including: The nodes and edges of the association graph are traversed to determine candidate combinations of target entities, constraints, manufacturing processes, and application types that can achieve composite part manufacturing.

8. The method according to claim 6, characterized in that Based on the manufacturing time and / or manufacturing cost corresponding to the candidate combinations for manufacturing the composite parts, a target combination is determined from the candidate combinations, including: The candidate combination with the shortest manufacturing time and / or the lowest manufacturing cost is determined as the target combination.

9. The method according to claim 1, characterized in that: The method further comprises: Determine composite part manufacturing equipment utilization information based on target entities, constraints, manufacturing processes, and application types; and / or, Determine personnel situation analysis information based on target entities, constraints, manufacturing processes, and application types; and / or, Determine tool life prediction information based on target entities, constraints, manufacturing processes, and application types.

10. A composite material parts manufacturing device, characterized in that: The device comprises: The data combing module is used to comb the target entities, constraints, manufacturing processes and application types corresponding to the manufacturing of composite parts; the target entities are the personnel information, equipment information, material information, supplier information and the processing procedures of composite parts manufacturing in the manufacturing process of composite parts; the constraints are the conditions that need to be met in the manufacturing process of composite parts; the manufacturing process is a fixed process obtained by arranging and combining multiple processing procedures; the application type is the detailed application scenario realized in the application scenario of composite parts manufacturing; The association graph construction module is used to construct the association graph according to the target entity, constraint conditions, manufacturing process and application type; An algorithm library association module, used for selecting at least one node in the association graph as an algorithm node, and associating the algorithm node with the algorithm library, so that the algorithm node can call the algorithm stored in the algorithm library to calculate the data in the algorithm node and its adjacent nodes; An industrial neural network building module, used to build an industrial neural network based on the association graph and the associated algorithm library; Manufacturing module for the manufacturing of composite parts based on industrial neural networks.

11. A composite material parts manufacturing equipment, characterized in that: The composite material parts manufacturing equipment comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the parts manufacturing method based on industrial neural network as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the parts manufacturing method based on industrial neural network as described in any one of claims 1 to 9 is implemented.