CN116595230A - Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base - Google Patents
Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base Download PDFInfo
- Publication number
- CN116595230A CN116595230A CN202310761781.5A CN202310761781A CN116595230A CN 116595230 A CN116595230 A CN 116595230A CN 202310761781 A CN202310761781 A CN 202310761781A CN 116595230 A CN116595230 A CN 116595230A
- Authority
- CN
- China
- Prior art keywords
- database
- parameters
- stamping
- polishing
- library
- 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 202
- 238000003860 storage Methods 0.000 title claims abstract description 41
- 238000007517 polishing process Methods 0.000 title claims abstract description 29
- 239000000463 material Substances 0.000 claims abstract description 111
- 238000005498 polishing Methods 0.000 claims abstract description 85
- 238000013461 design Methods 0.000 claims abstract description 34
- 230000015654 memory Effects 0.000 claims description 30
- 238000013527 convolutional neural network Methods 0.000 claims description 28
- 238000004519 manufacturing process Methods 0.000 claims description 23
- 238000013507 mapping Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000009411 base construction Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000005299 abrasion Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims 4
- 238000000465 moulding Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 7
- 238000013499 data model Methods 0.000 description 7
- 238000007493 shaping process Methods 0.000 description 7
- 239000004973 liquid crystal related substance Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000010206 sensitivity analysis Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 229910000851 Alloy steel Inorganic materials 0.000 description 1
- 229910000975 Carbon steel Inorganic materials 0.000 description 1
- 229910001018 Cast iron Inorganic materials 0.000 description 1
- 229910001208 Crucible steel Inorganic materials 0.000 description 1
- 229910000746 Structural steel Inorganic materials 0.000 description 1
- 229910001315 Tool steel Inorganic materials 0.000 description 1
- 239000010962 carbon steel Substances 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method, a device, equipment and a storage medium for constructing a process knowledge base for stamping and polishing, and relates to the technical field of stamping and polishing; comprising the following steps: constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base; dividing a first database into a material database, a mold database, an equipment database, a process parameter database and a user database, and respectively storing product information corresponding to a stamping process into a storage library divided by the first database; dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer, and respectively storing all parameters required by the polishing process into all data layers divided by the second database. The method can extract the molding process characteristics of various stamping parts by establishing a stamping process database and a polishing process database, and realize the intelligent design of the die.
Description
Technical Field
The invention relates to the technical field of stamping and polishing, in particular to a method, a device, equipment and a storage medium for constructing a stamping and polishing process knowledge base.
Background
The stamping process is a core technology for developing stamping dies, and basically depends on experience specific design due to factors such as variety of stamping parts, different shapes, material changes, different stamping equipment conditions and the like, so the technical bottleneck is a technical bottleneck for restricting intelligent die manufacturing. The sanding process is one of the processes of stamping and is therefore also limited to manual experience design.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method, a device, equipment and a storage medium for constructing a stamping and polishing process knowledge base, which can extract the molding process characteristics of various stamping parts by establishing a stamping process database and a polishing process database, realize the intelligent design of a die and break through the technical bottleneck of intelligent manufacturing of the die.
In order to solve at least one of the above technical problems, an embodiment of the present invention provides a method for constructing a process knowledge base for stamping and polishing, where the method includes:
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 mold 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 a stamping die and data information of materials and parameters of the stamping die into the die library, storing various stamped parameter information into the equipment library, storing data, formulas and rule information in a 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 data into the user database;
dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;
and taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model into the reasoning layer.
Preferably, the storing the material data information in the material library includes:
and storing one or more material data information in the brand, mechanical property, thickness, part shape, hardness, chemical composition and metallographic structure of each material into the material library.
Preferably, the storing the punched various parameter information to the equipment library includes:
one or more of stamping equipment parameters, category parameters and technical parameters of stamping are stored in the equipment library.
Preferably, the storing the process parameters obtained by the stamping process in the process parameter library includes:
one or more process parameters of the stamping process, material dimensions, material pattern, mold, and equipment are stored to the process parameter library.
Preferably, the method further comprises:
receiving product information of an input new product, the product information of the new product including a size, a material, a production lot, a tolerance, and a shape of the new product;
calculating the forming similarity of the new product and any old product in the first database according to the size, the material, the production batch and the tolerance of the new product and the size, the material, the production batch and the tolerance of any old product in the first database;
calculating the shape similarity of the new product and any old product according to the shape of the new product and the shape of any old product;
calculating the overall similarity of the new product and any old product according to the forming similarity and the shape similarity;
if it is determined from the overall similarity that the new product is dissimilar to the any old product, the new product is stored in the library of materials for size, material, production lot, tolerance, and shape.
Preferably, the condition parameters include one or more of initial surface quality, body material, curvature of the polished local area;
the technological parameters of the polishing robot for polishing the mold surface comprise one or more of polishing head parameters, polishing head moving speed, polishing head moving path and polishing force.
Preferably, the training step of the convolutional neural network model includes:
acquiring sampling data, wherein the sampling data comprise initial surface quality of polishing, moving speed of a polishing head, gaussian curvature of a polishing area, polishing force, machine body materials, polishing head parameters, polishing direction and abrasion;
and adopting a convolutional neural network back propagation algorithm, and carrying out model training on the convolutional neural network model based on the established cost function and the sampling data.
A process knowledge base construction apparatus for stamping and polishing, the apparatus comprising:
the construction module is used for constructing a first database of the stamping process knowledge base and a second database of the polishing process knowledge base;
the first dividing module is used for dividing the first database into a material library, a mould library, an equipment library, a process database, a process parameter library and a user database;
the first storage module is used for storing material data information into the material library, storing the type of a stamping die and data information of materials and parameters of the stamping die into the die library, storing various stamped parameter information into the equipment library, storing data, formulas and rule information in a 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 data into the user database;
the second division module is used for dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;
the second storage module is used for taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing the convolutional neural network model and the parameters of the convolutional neural network model into the reasoning layer.
In addition, the embodiment of the invention also provides computer equipment, which comprises: the system comprises a memory, a processor and an application program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the method of any embodiment when executing the application program.
In addition, the embodiment of the invention also provides a computer readable storage medium, on which an application program is stored, and when the application program is executed by a processor, the steps of the method of any embodiment are realized.
The first database of the stamping process knowledge base is divided into a material base, a mold base, an equipment base, a process database, a process parameter base and a user database, material data information is stored in the material base, the type of a stamping mold and the data information of materials and parameters of the stamping mold are stored in the mold base, various stamped parameter information is stored in the equipment base, data, formulas and rule information in the design flow of the stamping process are stored in the process database, process parameters obtained by the stamping process are stored in the process parameter base, and user data is stored in the user database. Dividing a second database of the polishing process knowledge base into an input layer, a knowledge storage layer, an reasoning layer and an output layer; and taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model into the reasoning layer.
Therefore, the forming process characteristics of various stamping parts can be extracted by establishing a stamping process database and a polishing process database, the intelligent design of the die is realized, and the technical bottleneck of intelligent die manufacturing is broken through.
Drawings
FIG. 1 is a schematic flow chart of a method for constructing a process knowledge base for stamping and polishing in an embodiment of the invention;
FIG. 2 is a schematic diagram of a stamping process knowledge base in an embodiment of the invention;
FIG. 3 is a schematic diagram of the basic architecture of a process knowledge base constructed in an embodiment of the invention;
FIG. 4 is a schematic diagram of a tree property structure of a model body in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a tree property structure of a tool body according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a neural network model constructed in an embodiment of the present invention;
FIG. 7 is a flow chart of the use of a polishing process knowledge base in an embodiment of the invention;
FIG. 8 is a block diagram of a process knowledge base construction apparatus for stamping and polishing in accordance with an embodiment of the present invention;
fig. 9 is a schematic diagram showing the structural composition of a computer device in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a construction method of a stamping and polishing process knowledge base, as shown in fig. 1, which comprises the following steps:
s101, constructing a first database of a stamping process knowledge base and a second database of a polishing process knowledge base.
Specifically, a database of a stamping process knowledge base is established, forming process characteristics of various stamping parts are extracted, a stamping process analysis system based on knowledge engineering is developed, and a first database of the stamping process knowledge base is constructed. Similarly, a database of a polishing process knowledge base is established, polishing process parameters are analyzed based on the polishing process flow, and a second database of the polishing process knowledge base is constructed.
S102, dividing the first database into a material library, a mold library, an equipment library, a process database, a process parameter library and a user database.
Specifically, the first database is divided into a materials library, a mold library, an equipment library, a process database, a process parameter library and a user database. Wherein each divided database is built through a conceptual data model.
The conceptual data model is formed by abstracting, generalizing and integrating these real world demand data features after the database designer gets the user's demand. The conceptual data model is a high-level data model, which is an accurate representation of the needs of users, and can be said to be a tie connecting the computer world and the real world. A common conceptual model is an Entity-relationship model (E-R model for short) which can intuitively represent entities, relationships, and their relationships in a graph. Therefore, a material library, a mold library, an equipment library, a process database, a process parameter library and a user database are constructed based on the conceptual data model by analyzing the stamping process.
The stamping knowledge base is the basis of a process analysis design system, and takes a stamping process type as an example by referring to the stamping process design process, the stamping knowledge base can be classified into a plurality of parts including determination of stamping materials, stamping process analysis, stamping layout, selection of dies and selection of stamping equipment, so that the database of the stamping process knowledge base is also built according to the plurality of parts. The database is designed to separate data information from application programs, so that data consistency and sharing are realized, and the running efficiency of the network is greatly improved. The comprehensive and complete analysis result can greatly improve the speed and accuracy of database design. Therefore, analysis and summary of database structures is necessary for database design. The conceptual design of the database is performed from the aspects of a material library, a die library, an equipment library, a process database, a process parameter library and a user database according to the demand analysis of the stamping process system database. The structure of the stamping process knowledge base is shown in fig. 2.
S103, storing material data information into the material library, storing the type of a stamping die and data information of materials and parameters of the stamping die into the die library, storing various stamped parameter information into the equipment library, storing data, formulas and rule information in a 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 data into the user database.
Preferably, the storing the material data information in the material library includes: and storing one or more material data information in the brand, mechanical property, thickness, part shape, hardness, chemical composition and metallographic structure of each material into the material library.
Preferably, the storing the punched various parameter information to the equipment library includes: one or more of stamping equipment parameters, category parameters and technical parameters of stamping are stored in the equipment library.
Preferably, the storing the process parameters obtained by the stamping process in the process parameter library includes: one or more process parameters of the stamping process, material dimensions, material pattern, mold, and equipment are stored to the process parameter library.
Specifically, the respective concepts of the first database are designed as follows:
(1) Concept structural design of material library
Before designing the stamping process, the chemical composition and mechanical properties of the material are determined. Hardness, part shape, etc. In the design of stamping process, the materials are classified by common carbon steel, high-quality carbon structural steel, carbon tool steel, alloy steel, cast iron, cast steel and the like, and the application range of process data is distinguished.
Specifically, whether a specific material is suitable for a stamping process is judged, and whether the material is suitable for stamping can be comprehensively judged only by knowing various information such as specific brands, mechanical properties, thickness, part shape, hardness, chemical components, metallographic structures and the like of the material. The chemical properties of the material comprise upper limit of component content, lower limit of content and elements; hardness includes Brinell hardness, rockwell hardness, vickers hardness, shore hardness; the part shape includes information such as size and shape of the part. The mechanical properties of the material comprise shear property, tensile property, elongation and yield strength, wherein the yield strength comprises material marks, a heat treatment system, a sampling direction, temperature, an upper limit of the yield strength, a lower limit of the yield strength and remarks. The materials can be abstracted into entities through the information, and various mechanical properties, chemical components, part shapes, brand information and the like of the materials can be abstracted into one entity, and the information entities and the material entities have corresponding relations, because different material properties are different.
(2) Concept design structure of mould library
The mold library contains data information such as the type of the mold, the mold material and the like. The quality and the service life of the stamping die directly influence the quality and the cost of the determined stamping part, and the stamping production efficiency and the production safety.
Specifically, the stamping die is necessary technological equipment in the stamping production process, and the quality and the service life of the stamping die have important influences on the stamping cost and the stamping part quality, so that the stamping die plays an important role in the production efficiency and the economic benefit of enterprises. The mold library is abstracted into one entity, and materials, mold parameters and types are abstracted into different entities. The die material comprises a male die material, a female die material and others; the category includes category information of the mold; the mold parameters include information such as closing height, dimensional parameters, allowable stress, etc.
(3) Concept design structure of equipment library
The equipment library contains various parameters of stamping equipment, and mainly contains the maximum stamping force which can be generated by the equipment, namely nominal pressure, the stroke number of sliding blocks, the stroke length of the sliding blocks, the maximum die height, the die height adjustment quantity, the size of a working table surface, the size of the bottom of the sliding blocks and the like.
Specifically, the main technical parameters of the equipment include stamping equipment, types and technical parameters. The stamping equipment comprises equipment numbers, names, models and equipment types; the categories include device usage, device characteristics, device category. Taking a hydraulic machine as an example, the technical parameters comprise information such as nominal force, maximum ejection stroke, maximum stroke of a main piston, maximum distance from a piston beam to a workbench, workbench size and the like. By means of which the device is abstracted to an entity.
(4) Concept design structure of process database
The process database contains data, formulas, rules and the like required by the whole stamping process design flow, and is an important point of database design. The essence of the method is to provide data support for each step of the stamping process and reduce the workload of process designers.
Specifically, the process database is the core of the system, and the data, rules and experience required in the stamping process design process are summarized according to the stamping process flow design. The process database can provide data support for each step of stamping process design, and the working efficiency of process designers is greatly improved.
(5) Concept design structure of process parameter library
The process parameter library comprises all data obtained by system design, and is divided into a temporary process parameter library and a formal process parameter library.
Specifically, the process parameter library is the final objective of the stamping process design, and includes stamping processes, materials, material dimensions, material layout, dies, equipment, and the like.
(6) Concept design structure of user database
The user database comprises user accounts, passwords, rights, identity information, operation records and the like, and aims to identify users and manage the use rights of the users, so that the safety of system data is effectively ensured.
Specifically, the user database includes information for identifying the user, checking the authority and distributing the authority, and specifically includes information such as account number, password, login information and operation authority of the user. The password file in the user database is stored by adopting an encryption algorithm carried in the database; the login information comprises login time and exit time; the operation right is represented by an operation level, which illustrates an operation range that can be used by the user.
For the first database of the stamping process knowledge base, the logical structure design of the database is as follows:
the main task of the design of a logical structure of a database is to transform the global conceptual structure into a logical structure of a database supported by a database management system. The data model most suitable for describing its conceptual structure is selected, and then the most suitable one is selected from a plurality of database management systems supporting such data model. According to the model conversion principle, the relation mode of the ER model conversion part of the stamping process knowledge base is as follows:
in one implementation, after the step S103, the method further includes: receiving product information of an input new product, the product information of the new product including a size, a material, a production lot, a tolerance, and a shape of the new product; calculating the forming similarity of the new product and any old product in the first database according to the size, the material, the production batch and the tolerance of the new product and the size, the material, the production batch and the tolerance of any old product in the first database; calculating the shape similarity of the new product and any old product according to the shape of the new product and the shape of any old product; calculating the overall similarity of the new product and any old product according to the forming similarity and the shape similarity; if it is determined from the overall similarity that the new product is dissimilar to the any old product, the new product is stored in the library of materials for size, material, production lot, tolerance, and shape.
After S103 is performed, product information of a plurality of old products is stored in the first database. At this time, when a new product is received, product information of the new product needs to be put in storage. Specifically, in order to facilitate product retrieval and maintenance of a product library, classification, identification and extraction of an input new product and related knowledge are required, and classification mainly depends on two parts of shape similarity and shaping similarity. The shape similarity comprises the similarity degree of the geometric shape and the topological relation of the product, and is mainly used for judging whether a product model with similar shape exists in a case library of a new product or not; the forming similarity comprises the similarity degree of contents such as critical dimension, material parameter, production batch and the like related to the forming difficulty of the product, and is mainly used for judging the formability of the new product. The similarity calculation formula is as follows:
wherein Sim represents the degree of similarity of the two stampings; s is S Shape and shape And S is Shaping Respectively representing shape similarity and shaping similarity; omega Shape and shape And omega Shaping Weight factors representing shape similarity and shaping similarity, respectively.
One of the main efforts in applying CBR is to use the forming parameters, process schemes and die structures of similar cases in the case library to assist in the design of new stamping part stamping schemes and die structures. When the new product and the existing product are different in characteristic type, the forming parameters and the process scheme are not comparable, so that the types are used for large classification in calculation of product characteristics and the similarity of the types. S is S Type(s) The values of (2) are defined as:
wherein, the liquid crystal display device comprises a liquid crystal display device,and->Representing all the characteristics and types of the new and old products respectively.
The feature details have been described in coded form as different numbers and combinations of numbers at the time of product description, the similarity of which can be directly calculated by the euler formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,and->Respectively representing the ith detail characteristic of the new and old products; omega Details, i Weights representing the ith detail feature; />Similar distance for calculating the ith forming parameter, in generalDividing byThe value of the similar distance can be made between 0 and 1.
The product codes according to the shaping similarity are coded, in order to distinguish the similarity of the codes after substitution and the true products corresponding to the codes, a calculation formula of the similarity after substitution is as follows:
P details, i ＝P True, i -(P True, i -P Instead, i )×ω Instead, i ；
Wherein P is True, i True encodings representing the ith detail feature; p (P) Instead, i Representing the coding after the ith detail feature is replaced according to the shaping similarity; omega Instead, i The similarity of the forming features of the ith detail feature, namely the degree to which the ith detail feature can be replaced, is expressed, and if the ith detail feature is not replaced, 0 is obtained.
From the above formula, it can be seen that: d (D) Details of the ∈[0.0,1.0]S is therefore Details of the ∈[0.0,1.0]. When the similarity is 0.0, the similarity degree of the two products is the lowest; when the similarity is 1.0, it means that the two products are the highest in similarity.
The forming similarity calculation is to calculate the similarity degree of the main size combination, production batch, tolerance and materials of the products related to the forming property in the forming parameter information description. The calculation formula is as follows:
wherein D is Size of the device Representing the similar distance between the forming size combination of the new product and the old product;and->Respectively representing the production batches of new and old products; />And->Respectively representing the tolerance values of new and old products; d (D) Material Representing the similar distance between new and old product materials; ω represents the respective weights.
In the method, in the process of the invention,and->The i-th size parameter values respectively representing new and old products; omega Specific dimensions, i The weight of the i-th size parameter is represented. According to the stamping forming theory, the product size combination influencing the stamping forming mainly comprises the stamping relative height +.>Relative thickness of blank->Radius of relative rotation>Relative limit heightWherein D is the blank length, d=d 0 +(L-B)。
D 0 ＝1.13×[B 2 +4B(H-0.43r)-1.72r(H+0.5r)-4r 1 (0.11r 1 -0.18r)] 1/2 。
In the method, in the process of the invention,and->The i-th material parameter values respectively representing new and old products; omega Material parameters, i Representing the weight of the ith material parameter.
When the new and old product feature types are different, the forming parameters and the process scheme are not comparable, so that the type similarity S is firstly judged when the similarity is calculated Type(s) When S Type(s) When the value is=0, stopping calculation of the similarity between the new product and the current instance in the instance library, and transferring to calculation of the similarity between the new product and the next instance in the instance library; when S is Type(s) When the method is in the range of (1), the detail feature similarity is calculated again, the product shape similarity and the product forming similarity are calculated respectively, and finally the total similarity of the products is calculated, so that a good foundation is laid for classifying the products and the process data, and the subsequent related research is facilitated.
S104, dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer.
S105, taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing the convolutional neural network model and the parameters of the convolutional neural network model into the reasoning layer.
Preferably, the condition parameters include one or more of initial surface quality, body material, curvature of the polished local area; the technological parameters of the polishing robot for polishing the mold surface comprise one or more of polishing head parameters, polishing head moving speed, polishing head moving path and polishing force.
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. Wherein the condition parameter is an input layer comprising: initial surface quality, body material, curvature of the ground localized area, etc. The output layer includes the technological parameter of the mould profile of polishing robot, includes: polishing head parameters (type, shape, size, polishing mode, etc.), polishing head moving speed, polishing head moving path, polishing force, etc. The knowledge storage layer comprises data formed by input layer parameters, output layer parameters and polished surface quality and a basic mapping relation of the data. The data acquisition comes from two paths: and the second is from the data which is actually generated and is verified and corrected. The test data are subjected to special test equipment, the experimental sample distribution is designed by adopting a uniform Latin method by setting the threshold value of each input parameter, the optimized output parameters obtained by test are subjected to test, a limited sample mapping relation is established, and meanwhile, the weight coefficient is designed for each input parameter through sensitivity analysis. And then establishing a knowledge inference machine through deep learning and training of an inference layer, and inferring based on data in a process database to obtain optimized polishing process parameters of different mold profiles. The basic architecture of the process knowledge base to be built for the project is shown in fig. 3.
It should be noted that, in the process knowledge base shown in fig. 3, each parameter is an attribute of each body. The body in the knowledge base mainly comprises a die body and a tool body. The tree property diagram of the mold body and the tool body to be constructed in an object-oriented manner is shown in fig. 4 and 5.
Preferably, the training step of the convolutional neural network model includes: acquiring sampling data, wherein the sampling data comprise initial surface quality of polishing, moving speed of a polishing head, gaussian curvature of a polishing area, polishing force, machine body materials, polishing head parameters, polishing direction and abrasion; and adopting a convolutional neural network back propagation algorithm, and carrying out model training on the convolutional neural network model based on the established cost function and the sampling data.
Specifically, the data of the polishing process knowledge base output layer is formed based on knowledge reasoning, and a convolutional neural network widely used at present is adoptedAnd carrying out reasoning and learning of knowledge. The convolutional neural network needs to accumulate and train a large amount of data, the data mainly originate from experiments and simulation analysis before the deep learning system corrects and improves, factors influencing polishing quality are obtained, sensitivity analysis is carried out, mapping relations of the polishing quality and the polishing head moving speed, gaussian curvature of a polishing area, polishing force, machine body materials, polishing head (shape: circular, arc, bar and the like; type: oilstone, sponge sand and the like) parameters, polishing direction, abrasion and the like parameters are obtained, and a corresponding neural network model is constructed as shown in fig. 6. As shown in figure 6 of the drawings,representing initial surface quality, gaussian curvature, body material, sanding head parameters … …, +.>The polishing force, polishing direction, and polishing speed … … are shown.
Specifically, training and learning are carried out through the constructed neural network model to establish a knowledge reasoning machine, a convolutional neural network back propagation algorithm is adopted in the learning process, and a cost function of each training sample of N is establishedThe cost function for the ith training sample is +.>Then reversely adjusting the weight coefficient +/in each layer based on the output error of each sample>For non-output layers, the layer I sensitivity can be expressed as delta l ＝(W l+I ) T δ l+I ·f′(u l ) The sensitivity to the output layer L can be expressed as delta L ＝f′(u L )·(y n -t n ). For layer I, the partial derivative of the error for each weight is +.>The weighting value of the neurons of the current layer can be obtained according to the calculation and updated to +.>And then, by combining with optimization calculation, intelligently reasoning out proper process data, and reasonably selecting a polishing head, a polishing mode and a polishing head replacement period. Meanwhile, the method can receive the guidance of a deep learning system and optimize an intelligent reasoning strategy. The technical route is shown in the following figure 7.
The first database of the stamping process knowledge base is divided into a material base, a mold base, an equipment base, a process database, a process parameter base and a user database, material data information is stored in the material base, data information of types of stamping molds, materials and parameters of the stamping molds is stored in the mold base, various parameter information of stamping is stored in the equipment base, data, formulas and rule information in a design flow of the stamping process are stored in the process database, process parameters obtained by the stamping process are stored in the process parameter base, and user data is stored in the user database. Dividing a second database of the polishing process knowledge base into an input layer, a knowledge storage layer, an reasoning layer and an output layer; and taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model into the reasoning layer. Therefore, the forming process characteristics of various stamping parts can be extracted by establishing a stamping process database and a polishing process database, the intelligent design of the die is realized, and the technical bottleneck of intelligent die manufacturing is broken through.
The invention also provides a device for constructing the process knowledge base for stamping and polishing. As shown in fig. 8, a process knowledge base construction apparatus for stamping and polishing 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. A construction module 801, configured to construct a first database of a stamping process knowledge base and a second database of a polishing process knowledge base; a first partitioning module 802, configured to partition the first database into a materials library, a mold library, an equipment library, a process database, a process parameter library, and a user database; a first storage module 803, configured to store material data information into the material library, store data information of types of stamping dies and materials and parameters of the stamping dies into the die library, store various parameter information of stamping into the equipment library, store data, formulas and rule information in a design flow of the stamping process into the process database, store process parameters obtained by the stamping process into the process parameter library, and store user data into the user database; a second partitioning module 804, configured to partition 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 use a condition parameter as an input layer parameter of the input layer, use a process parameter of a polishing mold surface of the polishing robot as an output layer parameter of the output layer, store a mapping relationship between the input layer parameter, the output layer parameter, and data formed by polished surface quality in the knowledge storage layer, and store a convolutional neural network model and parameters of the convolutional neural network model in the inference layer.
For a specific definition of a press-polished process knowledge base construction device, reference may be made to the definition of a press-polished process knowledge base construction method hereinabove, and the description thereof will not be repeated. The above-mentioned various modules in the stamping and polishing process knowledge base construction device can be implemented in whole or in part by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
The embodiment of the invention provides a computer readable storage medium, wherein an application program is stored on the computer readable storage medium, and the program is executed by a processor to realize the method for constructing the stamping and polishing process knowledge base in any one of the 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, ROMs (Read-Only memories), RAMs (Random AcceSS Memory, random access memories), EPROMs (EraSable Programmable Read-Only memories), EEPROMs (Electrically EraSable ProgrammableRead-Only memories), flash memories, magnetic cards, or optical cards. That is, a storage device includes any medium that stores or transmits information in a form readable by a device (e.g., computer, cell phone), and may be read-only memory, magnetic or optical disk, etc.
The embodiment of the invention also provides a computer application program which runs on a computer and is used for executing the process knowledge base construction method for stamping and polishing in any one of the embodiments.
Further, fig. 9 is a schematic structural composition diagram of a computer device in the embodiment of the present invention.
The embodiment of the invention also provides computer equipment, as shown in fig. 9. The computer device includes a processor 902, a memory 903, an input unit 904, a display unit 905, and the like. It will be appreciated by those skilled in the art that the device architecture shown in fig. 9 does not constitute a limitation of all devices, and may include more or fewer components than shown, or may combine certain components. The memory 903 may be used to store an application 901 and various functional modules, and the processor 902 runs the application 901 stored in the memory 903, thereby executing various functional applications of the device and data processing. The memory may be internal memory or external memory, or include both internal memory and external memory. The 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. The external memory may include a hard disk, floppy disk, ZIP disk, U-disk, tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The memory disclosed herein is by way of example only and not by way of limitation.
The input unit 904 is for receiving input of a signal, and receiving keywords input by a user. The input unit 904 may include a touch panel and other input devices. The touch panel may collect touch operations on or near the user (e.g., the user's operation on or near the touch panel using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, mouse, joystick, etc. The display unit 905 may be used to display information input by a user or information provided to the user and various menus of the terminal device. The display unit 905 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 902 is a control center of the terminal device, connects various parts of the entire device using various interfaces and lines, performs various functions and processes data by running or executing software programs and/or modules stored in the memory 903, and invoking data stored in the memory.
As one embodiment, the computer device includes: the system comprises one or more processors 902, a memory 903, 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 a process knowledge base construction method of stamping and polishing in any one of the above embodiments.
In addition, the foregoing describes in detail the method, apparatus, computer device and storage medium for constructing a process knowledge base for stamping and polishing provided in the embodiments of the present invention, and specific examples should be adopted herein to illustrate the principles and embodiments of the present invention, where the foregoing examples are only for helping to understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The method for constructing the process knowledge base of stamping and polishing is characterized by comprising the following steps of:
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 mold 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 a stamping die and data information of materials and parameters of the stamping die into the die library, storing various stamped parameter information into the equipment library, storing data, formulas and rule information in a 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 data into the user database;
dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;
and taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing a convolutional neural network model and parameters of the convolutional neural network model into the reasoning layer.
2. The method of claim 1, wherein storing material data information to the material library comprises:
and storing one or more material data information in the brand, mechanical property, thickness, part shape, hardness, chemical composition and metallographic structure of each material into the material library.
3. The method of claim 1, wherein storing the stamped various parameter information to the equipment library comprises:
one or more of stamping equipment parameters, category parameters and technical parameters of stamping are stored in the equipment library.
4. The method of claim 1, wherein storing the process parameters obtained from the stamping process in the process parameter library comprises:
one or more process parameters of the stamping process, material dimensions, material pattern, mold, and equipment are stored to the process parameter library.
5. The method according to claim 1, wherein the method further comprises:
receiving product information of an input new product, the product information of the new product including a size, a material, a production lot, a tolerance, and a shape of the new product;
calculating the forming similarity of the new product and any old product in the first database according to the size, the material, the production batch and the tolerance of the new product and the size, the material, the production batch and the tolerance of any old product in the first database;
calculating the shape similarity of the new product and any old product according to the shape of the new product and the shape of any old product;
calculating the overall similarity of the new product and any old product according to the forming similarity and the shape similarity;
if it is determined from the overall similarity that the new product is dissimilar to the any old product, the new product is stored in the library of materials for size, material, production lot, tolerance, and shape.
6. The method of claim 1, wherein the condition parameters include one or more of initial surface quality, body material, curvature of the ground localized area;
the technological parameters of the polishing robot for polishing the mold surface comprise one or more of polishing head parameters, polishing head moving speed, polishing head moving path and polishing force.
7. The method of claim 1, wherein the training step of the convolutional neural network model comprises:
acquiring sampling data, wherein the sampling data comprise initial surface quality of polishing, moving speed of a polishing head, gaussian curvature of a polishing area, polishing force, machine body materials, polishing head parameters, polishing direction and abrasion;
and adopting a convolutional neural network back propagation algorithm, and carrying out model training on the convolutional neural network model based on the established cost function and the sampling data.
8. A process knowledge base construction apparatus for stamping and polishing, the apparatus comprising:
the construction module is used for constructing a first database of the stamping process knowledge base and a second database of the polishing process knowledge base;
the first dividing module is used for dividing the first database into a material library, a mould library, an equipment library, a process database, a process parameter library and a user database;
the first storage module is used for storing material data information into the material library, storing the type of a stamping die and data information of materials and parameters of the stamping die into the die library, storing various stamped parameter information into the equipment library, storing data, formulas and rule information in a 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 data into the user database;
the second division module is used for dividing the second database into an input layer, a knowledge storage layer, an inference layer and an output layer;
the second storage module is used for taking the condition parameters as input layer parameters of the input layer, taking the technological parameters of the polishing mould surface of the polishing robot as output layer parameters of the output layer, storing the mapping relation between the input layer parameters, the output layer parameters and data formed by polished surface quality into the knowledge storage layer, and storing the convolutional neural network model and the parameters of the convolutional neural network model into the reasoning 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 implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761781.5A CN116595230A (en) | 2023-06-27 | 2023-06-27 | Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761781.5A CN116595230A (en) | 2023-06-27 | 2023-06-27 | Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595230A true CN116595230A (en) | 2023-08-15 |
Family
ID=87601016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310761781.5A Pending CN116595230A (en) | 2023-06-27 | 2023-06-27 | Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595230A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117932971A (en) * | 2024-03-14 | 2024-04-26 | 季华实验室 | Stamping process design method and device, electronic equipment and storage medium |
-
2023
- 2023-06-27 CN CN202310761781.5A patent/CN116595230A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117932971A (en) * | 2024-03-14 | 2024-04-26 | 季华实验室 | Stamping process design method and device, electronic equipment and storage medium |
| CN117932971B (en) * | 2024-03-14 | 2024-05-28 | 季华实验室 | Stamping process design method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gupta et al. | Evolutionary multitasking in bi-level optimization | |
| Fu et al. | Using genetic algorithm-back propagation neural network prediction and finite-element model simulation to optimize the process of multiple-step incremental air-bending forming of sheet metal | |
| CN116595230A (en) | Method, device, equipment and storage medium for constructing stamping and polishing process knowledge base | |
| CN113554063B (en) | Industrial digital twin virtual-real data fusion method, system, equipment and terminal | |
| CN104951590B (en) | Knowledge service system and method for die designing | |
| Li et al. | Multi‐objective optimization of injection molding parameters, based on the Gkriging‐NSGA‐vague method | |
| CN109447698A (en) | A kind of proposed algorithm neural network based | |
| CN110197307B (en) | Regional sea surface temperature prediction method combined with attention mechanism | |
| Zhao et al. | Optimization of Injection‐Molding Process Parameters for Weight Control: Converting Optimization Problem to Classification Problem | |
| Teimouri et al. | Modeling and optimization of spring-back in bending process using multiple regression analysis and neural computation | |
| CN110222838B (en) | Document sorting method and device, electronic equipment and storage medium | |
| Wang et al. | Feature weighting fuzzy clustering integrating rough sets and shadowed sets | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| CN111785326B (en) | Gene expression profile prediction method after drug action based on generation of antagonism network | |
| EP4207432A3 (en) | Method and system for predicting thermal runaway of battery based on machine learning | |
| CN111931307A (en) | Part quality prediction and evaluation optimization method and system | |
| Cheng et al. | Optimization of injection mold based on fuzzy moldability evaluation | |
| CN114580847A (en) | Energy efficiency assessment service resource supply and demand matching system and method considering similarity and credibility | |
| CN101404073B (en) | Complex product fuzz hierarchy collocation method | |
| CN111652444B (en) | K-means and LSTM-based daily guest volume prediction method | |
| CN104460594A (en) | Dispatching optimization method based on two-layer nest structure | |
| CN110502779A (en) | A kind of Intelligentized design method of the injection forming mold based on fuzzy reasoning | |
| Park et al. | Establishment of an IoT-based smart factory and data analysis model for the quality management of SMEs die-casting companies in Korea | |
| Siller et al. | Advanced CPS service oriented architecture for smart injection molding and molds 4.0 | |
| CN110866317A (en) | Design tool kit reconstruction method based on product historical information and design behavior analysis |
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 |