CN111625912A - Deep learning oriented Bom structure and creation method thereof - Google Patents
Deep learning oriented Bom structure and creation method thereof Download PDFInfo
- Publication number
- CN111625912A CN111625912A CN202010499178.0A CN202010499178A CN111625912A CN 111625912 A CN111625912 A CN 111625912A CN 202010499178 A CN202010499178 A CN 202010499178A CN 111625912 A CN111625912 A CN 111625912A
- Authority
- CN
- China
- Prior art keywords
- group
- nodes
- created
- components
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013135 deep learning Methods 0.000 title claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 2
- 241000854350 Enicospilus group Species 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Geometry (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Computational Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Mathematical Analysis (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a deep learning-oriented Bom structure and a creating method thereof, which mainly comprise two parts of contents: the first part introduces a deep learning oriented Bom structure (i.e. a deep Bom structure), mainly introduces 7 node types contained in the structure and their roles; in the second section, the creation process of 7 node types in the deep bom structure is explained. The deep learning-oriented Bom structure (namely, a DeepBom structure) created by the method has the characteristics of standardization, configurability and the like, and adopts a stepped hierarchical structure as the Bom structure, wherein the stepped hierarchical structure comprises a complete set of available parts in all configuration states of a product, so that all order requirements of a class of products can be met. And based on the characteristics of the DeepBom structure, the method can be applied to deep learning, and the Bom structure of the product is effectively recommended by utilizing a neural network algorithm, so that the intelligent design efficiency of the product is improved.
Description
Technical Field
The invention relates to a BOM structure creating method, in particular to a deep learning-oriented Bom structure and a creating method thereof.
Background
In the field of manufacturing, the demands of users are in the form of orders. Designers typically use an interactive CAD (computer aided design) system to design a product, and ultimately generate a Bom structure, according to the configuration requirements of the order. The Bom structure is a description of the product structure relationship, which includes information such as the type, quantity, and assembly relationship of the components of the product, and usually one order corresponds to one Bom structure.
At present, with the increasingly greater differentiation of user demands and the increasingly higher customization degree of products, more and more Bom structures of the products are made according to the characteristics of single design, more orders, large configuration change and the like, and the consumption of resources such as manpower, time, space and the like is increased. Therefore, how to quickly and effectively respond to the order requirements of the users and quickly design the Bom structure of the product meeting the requirements of the users is a very important issue facing the manufacturing industry.
Disclosure of Invention
The present invention aims to provide a deep learning oriented Bom structure and a method for creating the same, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
introduction of DeepBom structure:
the DeepBom structure mainly comprises 7 node types, namely a Group node type, a model node type, a part node type, a component node type, a Components node type, a DrivenModels node type and a driving part node type, and has the following functions:
1) the Group node type is mainly used for classifying parts of a class;
2) the Models node type is mainly used for placing parts classified under the Group node type;
3) the part node type is mainly used for placing parts classified under the Group node type;
4) the function of the component node type is mainly used for placing components classified under the Group node type;
5) the functions of the Components node types are mainly used for placing the sub Group node types of the component parts and the driving parts;
6) the role of drivenmodes node type is mainly to place the drive components;
7) the driving component node type is mainly used for placing components consisting of parts and driving components classified under the sub Group node type.
A Bom structure facing deep learning and a creating method thereof mainly comprise the steps of creating Group nodes for all parts forming a product, creating existing part groups, creating model nodes, creating part nodes and part nodes under the model nodes, creating component nodes for the existing part groups, creating component nodes, creating sub-groups for the existing parts, creating model and component nodes again, creating DrivenModels nodes for all the Group nodes, creating all the Group nodes, forming the Bom structure facing deep learning of the product, applying the DeepBom structure of the product to a neural network algorithm and predicting according to given order parameters, and performing steps according to a top-down description sequence.
A deep learning oriented Bom structure and a method for creating the same, the method comprises the following steps:
1) creating Group nodes for all parts forming a product;
2) creating a model node for an existing part Group, and creating a part node and a part node under the model node;
3) creating Components nodes for the existing component Group;
4) creating model and Components nodes again for the existing component sub-Group;
5) creating DrivenMoodels nodes for all Group nodes;
6) all Group nodes form a product deep learning-oriented Bom structure;
7) applying a DeepBom structure of a product to a neural network algorithm;
8) the prediction is made according to the given order parameters.
As a further scheme of the invention: in the step 1), the product is assumed to contain 6 parts in total, namely a part A, a part B1, a part B2, a part C and a part D, wherein the part B is composed of a part B1 and a part B2. Group nodes can be created for all parts constituting the product (parts excluding component parts) A, B, C and D, respectively, from top to bottom in the assembly order, and named Group pa, Group pb, Group pc, and Group pd, as shown in fig. 1.
As a still further scheme of the invention: in the step 2), a model nodes is created, and part nodes are created under the model nodes. Model nodes are created under GroupA, GroupB, GroupC and GroupD, respectively. As is known, the model nodes are mainly used for placing parts classified by Group nodes, and part nodes need to be created under the model nodes, as shown in fig. 2.
As a still further scheme of the invention: in the step 3), Components nodes are respectively created under group pA, group pB, group pC and group pD. It is known that Components nodes are mainly used for placing component sub-groups of component parts and driving parts, so that for the parts Group a, Group pc and Group pd constituting a product, the sub-Group nodes do not need to be created again under the Components nodes as null values, while for the parts Group B, the sub-Group nodes need to be created again under the Components nodes for the parts B1 and B2 constituting the component B and are named as Group pb1 and Group pb2 (the method is the same as that of step 1), as shown in fig. 3.
As a still further scheme of the invention: said step 4), model and Components nodes are created again under group pb1 and group pb2 (same method as steps 2, 3), as shown in fig. 4. Since the component constituting component B includes no component, the Components nodes of GroupB1 and GroupB2 are both null at this time. Assuming component B is composed of component B1 and part B2, component sub-Group of component B1 needs to be created under the Components node of Group pB1, and model and Components nodes need to be created under the sub-Group node until all Components nodes are empty.
As a still further scheme of the invention: in the step 5), a drivenmodes node is created under all the Group nodes (i.e. the Group nodes Group pa, Group pb, Group pc, Group pd, and sub-Group nodes Group pb1, Group pb2) created by the product. As is known, the drivenmodes node is mainly used for placing the driving components classified by the Group node, and the driving components are different from the components, so that the driving component node needs to be created below the drivenmodes node, as shown in fig. 5.
As a still further scheme of the invention: in the step 6), when all the Group nodes (and each Group node must include three nodes of Models, Components and drivenmodes) of the product are created, a deep learning oriented Bom structure, i.e., a deep Bom structure, of the product can be formed.
As a still further scheme of the invention: in the step 7), when the deep bom structure of the product is created, all parts required in the configuration state of the product can be stored in the deep bom structure through the three nodes below the Group node. Therefore, the type information of all product parts can be used as the output of the neural network, the order information of the user is converted into a sample matrix (the number of rows of the sample matrix is the number of orders of different clients and is listed as the number of order parameters) to be used as the input of the neural network, the sample matrix is substituted into the defined neural network, a proper activation function (such as Tanh, Sigmoid, ReLu and the like) is selected, and a corresponding weight matrix is obtained by calculation (BP neural network and the like), so that the network structure which is in line with the expectation is finally obtained.
As a still further scheme of the invention: in the step 8), after vectorization processing is performed on the given order parameters, the order parameters are brought into a trained neural network for prediction, and a Bom structure of a product which meets the expectation of a user is obtained.
Compared with the prior art, the invention has the beneficial effects that:
the deep learning-oriented Bom structure (namely, a DeepBom structure) created by the method has the characteristics of standardization, configurability and the like, and adopts a stepped hierarchical structure as the Bom structure, wherein the stepped hierarchical structure comprises a complete set of available parts in all configuration states, so that the deep learning-oriented Bom structure can meet all order requirements of a class of products. And based on the characteristics of the DeepBom structure, the method can be applied to deep learning, and the Bom structure of the product is effectively recommended by utilizing a neural network algorithm, so that the intelligent design efficiency of the product is improved.
Drawings
Fig. 1 is a schematic diagram of a deep learning-oriented Bom structure and a component Group created in the method for creating the same.
Fig. 2 is a schematic diagram of a deep learning-oriented Bom structure and a relationship between model nodes under Group nodes and part nodes under model nodes in a creating method thereof.
Fig. 3 is a schematic diagram of a deep learning-oriented Bom structure and a principle of Components nodes under a Group node in a creating method thereof.
FIG. 4 is a schematic diagram of Models and Components nodes under sub Group nodes in a deep learning-oriented Bom structure and a creating method thereof.
Fig. 5 is a framework schematic diagram of a deep learning-oriented Bom structure and a drivenmodes node under a Group node in a creation method thereof.
Fig. 6 is a flowchart illustrating an overall method for creating a deep learning oriented Bom structure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus are not to be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "disposed" are to be construed broadly and can, for example, be fixedly connected, disposed, detachably connected, disposed, or integrally connected and disposed. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1 to 5, in an embodiment of the present invention, a deep learning-oriented Bom structure and a creating method thereof mainly include creating a Group node for all Components constituting a product, creating a Models node for an existing component Group, creating a part node and a part node under the Models node, creating a Components node for the existing component Group, creating a Components node for the existing component sub-Group, creating Models and Components nodes again, creating a drivenmodel node for all the Group nodes, forming a deep learning-oriented Bom structure of the product, applying a deep Bom structure of the product to a neural network algorithm, and performing prediction according to a given order parameter, wherein the steps are performed in a top-down order.
A deep learning oriented Bom structure and a method for creating the same, the method comprises the following steps:
1) creating Group nodes for all parts forming a product;
2) creating a model node for an existing part Group, and creating a part node and a part node under the model node;
3) creating Components nodes for the existing component Group;
4) creating model and Components nodes again for the existing component sub-Group;
5) creating DrivenMoodels nodes for all Group nodes;
6) all Group nodes form a product deep learning-oriented Bom structure;
7) applying a DeepBom structure of a product to a neural network algorithm;
8) the prediction is made according to the given order parameters.
In the step 1), the product is assumed to contain 6 parts in total, namely a part A, a part B1, a part B2, a part C and a part D, wherein the part B is composed of a part B1 and a part B2. Group nodes can be created for all parts (parts of which constituent parts are not included) A, B, C and D constituting the product in the assembly order from top to bottom, respectively, and named Group pa, Group pb, Group pc, and Group pd, as shown in fig. 1.
In the step 2), model nodes are respectively created under GroupA, GroupB, GroupC and GroupD. As the model nodes are mainly used for placing parts classified by Group nodes, part nodes and part nodes need to be created below the model nodes, as shown in fig. 2.
In the step 3), Components nodes are respectively created under group pA, group pB, group pC and group pD. It is known that Components nodes are mainly used for placing component sub-groups of component parts and driving parts, so that for the parts Group a, Group pc and Group pd constituting a product, the Components nodes do not need to create sub-Group nodes again as null values, while for the parts Group B, the Components nodes need to create sub-Group nodes again for the part B1 and the part B2 constituting the component part B, and are named as Group pb1 and Group pb2 (the method is the same as step 1), as shown in fig. 3.
Said step 4), model and Components nodes are created again under group pb1 and group pb2 (same method as steps 2, 3), as shown in fig. 4. Since the component parts constituting component B do not include any component parts, the Components nodes of GroupB1 and GroupB2 are both null values at this time. Assuming component B is composed of component B1 and part B2, component sub-groups of component B1 continue to be created under the Components node of Group pB1, and model and Components nodes continue to be created under the sub-groups node until all Components nodes are empty.
In the step 5), a drivenmodes node is created under all the Group nodes (i.e. the Group nodes Group pa, Group pb, Group pc, Group pd, and sub-Group nodes Group pb1, Group pb2) created by the product. As is known, the drivenmodes node is mainly used for placing the driving component classified by the Group node, and the driving component is different from the component, so that the driving component node needs to be created below the drivenmodes node, as shown in fig. 5.
In the step 6), when all the Group nodes (and each Group node must include three nodes of Models, Components and drivenmodes) of the product are created, a deep learning oriented Bom structure, i.e., a deep Bom structure, of the product can be formed.
In the step 7), when the deep bom structure of the product is created, all parts required in the configuration state of the product can be stored in the deep bom structure through the three nodes below the Group node. Therefore, the type information of all product parts can be used as the output of the neural network, the order information of the user is converted into a sample matrix (the number of rows of the sample matrix is the number of orders of different clients and is listed as the number of order parameters) to be used as the input of the neural network, the sample matrix is substituted into the defined neural network, a proper activation function (such as Tanh, Sigmoid, ReLu and the like) is selected, a corresponding weight matrix is obtained through calculation (BP neural network and the like), and finally the network structure which is in line with the expectation is obtained.
In the step 8), after vectorization processing is performed on the given order parameters, the order parameters are brought into a trained neural network for prediction, and a Bom structure of a product which meets the expectation of a user is obtained.
The working principle of the invention is as follows:
the invention relates to a deep learning-oriented Bom structure and a creation method thereof, and therefore, in the invention, a deep learning-oriented Bom structure and a creation method thereof are provided. The deep learning-oriented Bom structure (namely, DeepBom structure) created by the method has the characteristics of standardization, configurability and the like, and adopts a ladder hierarchical structure as the Bom structure, wherein the ladder hierarchical structure comprises a complete set of available parts in all configuration states, so that all order requirements of a class of products can be met. And based on the characteristics of the DeepBom structure, the method can be applied to deep learning, and the Bom structure of the product is effectively recommended by utilizing a neural network algorithm, so that the intelligent design efficiency of the product is improved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. A Bom structure facing deep learning and a creating method thereof are characterized in that for forming all parts of a product, a Group node is created, a Models node is created for the existing part Group, part nodes and part nodes are created under the Models node, the part nodes and the part nodes are created for the existing part Group, a Components node is created, the part sub-Group is created, Models and Components nodes are created again, DrivenModels nodes are created for all the Group nodes, all the Group nodes are created, the Bom structure facing deep learning of the product is formed, the DeepBom structure of the product is applied to a neural network algorithm and prediction is carried out according to given order parameters, and the steps are carried out according to the sequence from top to bottom;
a deep learning oriented Bom structure and a method for creating the same, the method comprises the following steps:
1) creating Group nodes for all parts forming a product;
2) creating a model node for an existing part Group, and creating a part node and a part node under the model node;
3) creating Components nodes for the existing component Group;
4) creating model and Components nodes again for the existing component sub-Group;
5) creating DrivenMoodels nodes for all Group nodes;
6) all Group nodes form a product deep learning-oriented Bom structure;
7) applying a DeepBom structure of a product to a neural network algorithm;
8) the prediction is made according to the given order parameters.
2. The deep learning oriented Bom structure and its creation method as claimed in claim 1, wherein in said step 1), assuming that the product contains 6 parts in total, part a, part B1, part B2, part C and part D, respectively, wherein part B is composed of part B1 and part B2;
group nodes can be created for all the parts A, B, C and D constituting the product (excluding parts of the constituent parts thereof) respectively from top to bottom in the assembly order and named Group pa, Group pb, Group pc and Group pd.
3. The deep learning oriented Bom structure and the creation method thereof as claimed in claim 1, wherein in said step 2), model nodes are created under GroupA, GroupB, GroupC and GroupD, respectively;
as known, the model nodes are mainly used for placing parts classified by Group nodes, and part nodes need to be created under the model nodes.
4. The deep learning oriented Bom structure and the creation method thereof as claimed in claim 1, wherein in said step 3), Components nodes are created under GroupA, GroupB, GroupC and GroupD, respectively;
it is known that Components nodes are mainly used for placing component sub-groups of component parts and driving parts, so that for the parts Group a, Group pc and Group pd constituting a product, the Components nodes do not need to create sub-Group nodes again as null values, while for the parts Group B, the Components nodes need to create sub-Group nodes again for the parts B1 and B2 constituting the component B, and are named as Group pb1 and Group pb 2.
5. The deep learning oriented Bom structure and its creation method as claimed in claim 1, wherein in said step 4), model and Components nodes are created again under group pb1 and group pb 2;
since the component parts of component part B do not include any component parts, the Components nodes of GroupB1 and GroupB2 are both null values at this time;
assuming component B is composed of component B1 and part B2, component sub-groups of component B1 continue to be created under the Components node of Group pB1, and model and Components nodes continue to be created under the sub-groups node until all Components nodes are empty.
6. The deep learning oriented Bom structure and its creation method as claimed in claim 1, wherein in said step 5), under all the Group nodes (i.e. Group nodes Group pa, Group pb, Group pc, Group pd and sub-Group nodes Group pb1, Group pb2) that the product has been created, a drivenmodes node is created;
the driving component nodes are mainly used for placing driving components classified by Group nodes, and the driving components are different from the components, so that the driving component nodes need to be created under the driving component nodes.
7. The deep learning oriented Bom structure and the creating method thereof as claimed in claim 1, wherein in said step 6), when all Group nodes (and each Group node must include three nodes of Models, Components and driver nodes) of the product are created, a deep learning oriented Bom structure, i.e. deep Bom structure, can be formed.
8. The deep learning oriented Bom structure and the creation method thereof according to claim 1, wherein in step 7), when the creation of the deep Bom structure of the product is completed, all the components required in the configuration state of the product can be stored in the deep learning oriented Bom structure through the three nodes below the Group node;
therefore, the type information of all product parts can be used as the output of the neural network, the order information of the user is converted into a sample matrix (the number of rows of the sample matrix is the number of orders of different clients and is listed as the number of order parameters) to be used as the input of the neural network, the sample matrix is substituted into the defined neural network, a proper activation function (such as Tanh, Sigmoid, ReLu and the like) is selected, a corresponding weight matrix is obtained through calculation (BP neural network and the like), and finally a network structure which is in line with the expectation is obtained.
9. The deep learning oriented Bom structure and the creation method thereof as claimed in claim 1, wherein in said step 8), for the given order parameters, after vectorization processing, the order parameters are brought into the trained neural network for prediction, so as to obtain the Bom structure of the product that meets the user's expectations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010499178.0A CN111625912A (en) | 2020-06-04 | 2020-06-04 | Deep learning oriented Bom structure and creation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010499178.0A CN111625912A (en) | 2020-06-04 | 2020-06-04 | Deep learning oriented Bom structure and creation method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111625912A true CN111625912A (en) | 2020-09-04 |
Family
ID=72260194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010499178.0A Pending CN111625912A (en) | 2020-06-04 | 2020-06-04 | Deep learning oriented Bom structure and creation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111625912A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4312165A1 (en) * | 2022-07-27 | 2024-01-31 | Siemens Aktiengesellschaft | Method and system for providing recommendations for bill of materials revision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346143A (en) * | 2013-07-26 | 2015-02-11 | 同济大学 | Data conversion method from EBOM (Engineering Bill of Material) to MBOM (Maintenance Bill of Material) |
| CN105512258A (en) * | 2015-12-02 | 2016-04-20 | 上海大学 | Intelligent configuration method for automobile generalized products |
| CN107067200A (en) * | 2016-12-15 | 2017-08-18 | 武汉开目信息技术股份有限公司 | The operating method and device of a kind of BOM data |
| CN107273131A (en) * | 2017-06-22 | 2017-10-20 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method applied to Configurable BOM |
| CN110688722A (en) * | 2019-10-17 | 2020-01-14 | 深制科技(苏州)有限公司 | Automatic generation method of part attribute matrix based on deep learning |
-
2020
- 2020-06-04 CN CN202010499178.0A patent/CN111625912A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346143A (en) * | 2013-07-26 | 2015-02-11 | 同济大学 | Data conversion method from EBOM (Engineering Bill of Material) to MBOM (Maintenance Bill of Material) |
| CN105512258A (en) * | 2015-12-02 | 2016-04-20 | 上海大学 | Intelligent configuration method for automobile generalized products |
| CN107067200A (en) * | 2016-12-15 | 2017-08-18 | 武汉开目信息技术股份有限公司 | The operating method and device of a kind of BOM data |
| CN107273131A (en) * | 2017-06-22 | 2017-10-20 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method applied to Configurable BOM |
| CN110688722A (en) * | 2019-10-17 | 2020-01-14 | 深制科技(苏州)有限公司 | Automatic generation method of part attribute matrix based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| 李爱平等: "基于Inventor的三维参数化部件库系统的开发方法" * |
| 肖凯等: "大规模定制下的产品配置管理研究" * |
| 邱胜海等: "先进制造环境下BOM的存储结构与表现形式研究与实现" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4312165A1 (en) * | 2022-07-27 | 2024-01-31 | Siemens Aktiengesellschaft | Method and system for providing recommendations for bill of materials revision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033001B (en) | Three-dimensional digital factory modeling method and system for digital twin application | |
| Braha et al. | Topology of large-scale engineering problem-solving networks | |
| Yin et al. | A connector-based hierarchical approach to assembly sequence planning for mechanical assemblies | |
| CN106530405B (en) | Auto production line real time roaming system based on virtual reality technology | |
| CN112231917B (en) | Space digital twin modeling method, device, computer equipment and storage medium | |
| WO2016091038A1 (en) | Fast design method and system for high-speed train | |
| CN101093517A (en) | Design system for product configuration | |
| CN102768703A (en) | Water-turbine generator set virtual assembly modeling method and system based on tree graph model | |
| Li et al. | Product data model for PLM system | |
| CN108717601A (en) | A kind of more innovative approach towards enterprise's problem are integrated and fusion method | |
| Bodner et al. | A structured approach to simulation modeling of manufacturing systems | |
| Ding et al. | Hierarchical structure of a green supply chain | |
| CN111625912A (en) | Deep learning oriented Bom structure and creation method thereof | |
| Astanaliev | Important principles of innovative reforms in the process of electronic document management in railway automation and telemechanics | |
| CN111722599B (en) | CPS modeling and analyzing method based on object-oriented generalized stochastic Petri network | |
| CN111078203B (en) | 4M1T innovation system supporting incubation of creators and small micro-enterprises | |
| Lou et al. | Cooperation emergence of manufacturing services in cloud manufacturing with agent-based modeling and simulating | |
| Li et al. | Mechanical design paradigm based on ACP method in parallel manufacturing | |
| Deng | Digital Twin‐Based Modeling of Complex Systems for Smart Aging | |
| Chen et al. | Research on network management technology of power line carrier communication in low-voltage distribution network based on digital twin | |
| CN107577880A (en) | A kind of process structure modeling method based on multi views | |
| Yin et al. | Modeling and configuring product family based on the polychromatic sets | |
| CN107145631B (en) | A kind of piecemeal linkage design method of customed product non-standard component partial structurtes | |
| Zhongtu et al. | A knowledge-based approach for the task implementation in mechanical product design | |
| Lu et al. | Fast Calibration of Agent-Based Model using Mean-Field Approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |