CN113901647A - Part process rule compiling method and device, storage medium and electronic equipment - Google Patents
Part process rule compiling method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113901647A CN113901647A CN202111119200.5A CN202111119200A CN113901647A CN 113901647 A CN113901647 A CN 113901647A CN 202111119200 A CN202111119200 A CN 202111119200A CN 113901647 A CN113901647 A CN 113901647A
- Authority
- CN
- China
- Prior art keywords
- views
- feature
- target
- target part
- data set
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 186
- 230000008569 process Effects 0.000 title claims abstract description 119
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 239000013598 vector Substances 0.000 claims abstract description 53
- 239000011159 matrix material Substances 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 239000000463 material Substances 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 abstract description 12
- 238000012545 processing Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000007477 logistic regression Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 239000000956 alloy Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 229910001069 Ti alloy Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013106 supervised machine learning method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a part process procedure compiling method, a device, a storage medium and electronic equipment, which relate to the technical field of part manufacturing and comprise the following steps: acquiring a feature vector of a part image of a target part; inputting the feature vector into a trained classifier to obtain the structural features of the target part; acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the preset knowledge base comprises a plurality of parts and process procedures corresponding to the parts; through the method and the device, the process rules of the target part can be compiled quickly and efficiently, the compiled process rules can guarantee high quality, and the method and the device are more accurate and have smaller errors.
Description
Technical Field
The application relates to the technical field of part manufacturing, in particular to a part process rule compiling method and device, a storage medium and electronic equipment.
Background
With the development of aviation manufacturing technology, the whole development period of modern airplanes is greatly shortened, the control requirement on the development efficiency of each link of airplane manufacturing is higher and higher, especially the matching link of part manufacturing, because the types and the number of related parts are more, the process content and the specific requirement of the manufacturing process rules cannot be unified, for example, frame parts have the characteristics of large structure size, high precision requirement, long processing period and the like, the setting influence of material difference, blank state and the selection of processing equipment on the processing process is larger, and the process rule difference is larger.
In order to ensure the transmission and uniqueness of design requirements and manufacturing information, a manufacturing process rule is compiled for each part before processing, for newly-researched projects, a large number of process rules are compiled in the initial stage of the project, the number of single machines is generally more than 500, the newly-compiled workload is large, the process is easy to be omitted or the content is wrong, and the problems of large workload and low efficiency in process rule compiling exist.
Disclosure of Invention
The application mainly aims to provide a part process rule compiling method, a part process rule compiling device, a storage medium and electronic equipment, and aims to solve the problem that the component process rule compiling method in the prior art is low in efficiency.
In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:
a part process procedure compiling method is applied to electronic equipment and comprises the following steps:
acquiring a feature vector of a part image of a target part;
inputting the feature vector into a trained classifier to obtain the structural features of the target part;
acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the preset knowledge base comprises a plurality of parts and process procedures corresponding to the parts.
Optionally, before the step of obtaining the feature vector of the part image of the target part, the method further includes:
acquiring images of a plurality of existing parts, classifying the images of the existing parts based on the structural features of the existing parts, and forming a plurality of data sets corresponding to a plurality of structural features; wherein each data set comprises an image of an existing part corresponding to a structural feature, each existing part image comprising a plurality of views from different perspectives;
extracting features of a plurality of views at different visual angles in each data set to obtain feature vectors of the views in each data set;
splicing and standardizing the feature vectors of the multiple views to obtain a feature matrix of multiple existing parts;
defining labels of structural features of a plurality of existing parts, and obtaining label matrixes of the existing parts based on the feature matrixes;
and (4) taking the feature matrix as input and the label matrix as output, and performing classifier training to form a trained classifier.
Optionally, the classifier is a naive bayes classifier.
Optionally, the plurality of views at different viewing angles includes an axonometric view and a top view.
Optionally, the step of performing feature extraction on a plurality of views of different viewing angles in each data set to obtain feature vectors of the plurality of views in each data set includes:
and performing feature extraction on the multiple views at different view angles in each data set by adopting a principal component analysis method, and acquiring feature vectors of the multiple views in each data set.
Optionally, the structural features include: the process information comprises at least one of material, property and special inspection information.
In addition, to achieve the above object, the present application further provides a classifier training method applied to an electronic device, including the following steps:
acquiring images of a plurality of existing parts, classifying the images of the existing parts based on the structural features of the existing parts, and forming a plurality of data sets corresponding to a plurality of structural features; wherein each data set comprises an image of an existing part corresponding to a structural feature, each existing part image comprising a plurality of views from different perspectives;
extracting features of a plurality of views at different visual angles in each data set to obtain feature vectors of the views in each data set;
splicing and standardizing the feature vectors of the multiple views to obtain a feature matrix of multiple existing parts;
defining labels of structural features of a plurality of existing parts, and obtaining label matrixes of the existing parts based on the feature matrixes;
and (4) taking the feature matrix as input and the label matrix as output, and performing classifier training to form a trained classifier.
In addition, in order to achieve the above object, the present application further provides a part process rule compiling device, applied to an electronic device, the device including:
the acquisition module is used for acquiring part information of the target part, wherein the part information comprises an image, a characteristic vector, a structural characteristic and process information;
the query module is used for acquiring a target process rule matched with the target part from a preset knowledge base according to the part information;
and the output module is used for outputting the process rules of the target part.
In addition, to achieve the above object, the present application further provides a computer readable storage medium storing a computer program, and when the computer program is loaded and executed by a processor, the computer program implements the method for creating the part process rule provided in the present application.
In addition, to achieve the above object, the present application also provides an electronic device, comprising a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is used for loading and executing the computer program so as to enable the electronic equipment to execute the part process rule programming method provided by the application.
Compared with the prior art, the beneficial effects of this application are:
according to the part process procedure compiling method, the part process procedure compiling device, the storage medium and the electronic equipment, the feature vector of the part image of the target part is obtained; inputting the feature vector into a trained classifier to obtain the structural features of the target part; acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the preset knowledge base comprises a plurality of parts and process procedures corresponding to the parts. According to the method, the preset knowledge base information is matched respectively based on the structural characteristics and the process information of the target part, the process rules corresponding to the corresponding structural characteristics and the corresponding process information can be obtained, under the conditions that the number of the target parts is large and the structure of the target parts is complex, a large number of independent target parts do not need to be compiled, the process rules with high matching degree with the target parts can be obtained quickly after classification and identification of the classifier, the compiling efficiency is greatly improved, and the error rate is reduced.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a method for compiling a part process rule according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a classifier training method according to an embodiment of the present application;
fig. 4 is a functional block diagram of a part process specification compiling apparatus according to an embodiment of the present disclosure.
The labels in the figure are: 101-processor, 102-communication bus, 103-network interface, 104-user interface, 105-memory.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the application is as follows: a method, a device, a storage medium and an electronic device for compiling part process rules are provided, wherein a feature vector of a part image of a target part is obtained; inputting the feature vector into a trained classifier, and obtaining and outputting structural features of the target component through the classifier; acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the classifier is obtained based on part image training of a plurality of existing parts; the preset knowledge base comprises a plurality of existing parts and process rules corresponding to the existing parts.
In the prior art, in the process of manufacturing an airplane, as the whole development period of the airplane is greatly shortened, the control requirement on the development efficiency of each link is higher and higher, in the link matched with part manufacturing, as the types and the number of related parts are more, the process content and the specific requirement of a manufacturing process rule cannot be unified, particularly, frame parts have the characteristics of large structural size, high precision requirement, long processing period and the like, the setting of the processing process is greatly influenced by material difference, blank state and selection of processing equipment, particularly, in a newly-developed project, a large amount of process rule compilation is faced at the initial stage of the project, the process is compiled one by one manually, the efficiency is low, and in the presence of larger workload, the compilation is difficult to avoid missing or mistake, so that the project progress is slowly promoted.
Therefore, the method provides a solution, based on the image information and the process information of the target part, after classification and identification are carried out according to the classifier established through machine learning, matching is carried out in a preset knowledge base, and finally the process rule of the target part is determined. Compared with the existing compiling method, the technical problem of low process procedure compiling efficiency of parts is solved, and the technical effects of high quality, small error and high compiling efficiency are achieved.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application, where the electronic device may include: a processor 101, such as a Central Processing Unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Wherein the communication bus 102 is used for enabling connection communication between these components. The user interface 104 may comprise a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 104 may also comprise a standard wired interface, a wireless interface. The network interface 103 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 105 may optionally be a storage device independent of the processor 101, and the Memory 105 may be a Random Access Memory (RAM) Memory, or a Non-Volatile Memory (NVM), such as at least one disk Memory; the processor 101 may be a general-purpose processor including a central processing unit, a network processor, etc., and may also be a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 105, which is a storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and an electronic program.
In the electronic device shown in fig. 1, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the electronic device of the present invention may be disposed in the electronic device, and the electronic device calls the part process rule compiling device stored in the memory 105 through the processor 101 and executes the part process rule compiling method provided in the embodiment of the present application.
Referring to fig. 2, based on the hardware device of the foregoing embodiment, the embodiment of the present application provides a part process rule compiling method applied to an electronic device, including the following steps:
s20: acquiring a feature vector of a part image of a target part;
in a specific implementation, the target part refers to a part of a process recipe to be determined. The part images refer to images acquired from different directions of a target part, and the image acquisition means includes multiple types: can shoot through artifical fixed point and acquire, it obtains the angle adjustable, but it is slower to obtain speed, can also catch the view through intelligent camera, and it can be used for obtaining the image of eigenvector to discern and use, in this application, obtain the image fast through CATIA's "mechanical design-engineering drawing" function, the front view image of each different directions of target part can accurately be obtained to this means, it is more accurate to compare in the acquisition of other means, and through the direct output image of machine, the time of obtaining the image has been reduced, the image can be the view of a plurality of directions such as main view, side view, top view, axonometric drawing, can discern the image relevant with the establishment technology rule.
In order to perform classification and identification by using a classifier, it is necessary to extract features of an image, extract a feature vector of the image, normalize the size of the image to 256 × 256, and connect pixel points of the image in columns to form a vector t of 65536 × 1(65536 ═ 256 × 256).
S30: inputting the feature vector into a trained classifier to obtain the structural features of the target part; the classifier is obtained based on part image training of a plurality of existing parts;
in a specific implementation process, the classifier is obtained by adopting a supervised machine learning method, the feature matrix is used as input, the label matrix is used as output, the target part information is quickly and intuitively obtained through the label matrix, namely the structural features of the target part, and the subsequent matching with the preset knowledge base is simpler, more convenient and quicker.
S40: acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the preset knowledge base comprises a plurality of parts and process procedures corresponding to the parts; the process information is other relevant parameters of part processing, such as materials, attributes and the like, and after the preset knowledge base is established, the target part information input each time can be stored to enrich the preset knowledge base.
In this embodiment, by matching the target part with information in the established preset knowledge base, the more existing part information is stored in the preset knowledge base, the more accurate the process procedure of the target part is obtained during the comparison and matching, by obtaining the feature vector of the image of the target part, inputting the feature vector into the trained classifier, quickly outputting the structural feature information of the target part, and respectively matching the structural feature information and the process information with corresponding information in the preset knowledge base, quickly calling the process procedures corresponding to each part, and finally combining and compiling the process procedures and outputting the complete standard process procedure of the target part, and because the comparison and matching of the compiled process procedures are more detailed, the compiled quality is higher, and the situations of matching and excessive output errors are not easy to occur.
Referring to fig. 3, the present embodiment further provides a classifier training method, which is performed before the feature vectors of the part image of the target part are obtained in step S20 of the foregoing embodiment, for training to obtain a classifier;
the method comprises the following steps:
s101: acquiring images of a plurality of existing parts, classifying the images of the existing parts based on the structural features of the existing parts, and forming a plurality of data sets corresponding to a plurality of structural features; wherein each data set comprises an image of an existing part corresponding to a structural feature, each existing part image comprising a plurality of views from different perspectives;
in the specific implementation process, firstly, images of a plurality of existing parts are obtained, and the extraction method comprises the following steps: principal component analysis, reverse feature elimination, combined decision tree and the like, and classifying the images of the existing parts based on the structural features of the existing parts; then, forming a plurality of data sets corresponding to the plurality of structural features; the part image refers to images obtained from different directions of a target part and can be obtained by the mechanical design-engineering drawing (CATIA)The method can quickly acquire images, wherein the images can be views in multiple directions such as a front view, a side view, a top view, an axonometric view and the like, and 200 different existing parts are taken as an example to form a data set, and the data set is expressed as SM { SM ═ SM }1,SM2,…,SMi,…SM200In which SMiDenotes the ith part therein, SMiRepresented as a quadruplet SMi＝(FOi,ZCTi,FSTi,JGi)，FOiIndicating the process specification of the part, ZCTiAxonometric view, FST, representing a partiTop view of the component, JGiRepresenting structural features.
S102: extracting features of a plurality of views at different visual angles in each data set to obtain feature vectors of the views in each data set;
in a specific implementation, the size of an axonometric image in a dataset is normalized to 256 × 256, each pixel point of the image is connected in columns to form a vector t of 65536 × 1(65536 × 256), then all the axonometric images in the dataset form a matrix X of 65536 × 200 dimensions, a covariance matrix S of X is calculated, and the first 300 maximum eigenvalues λ corresponding to the covariance matrix S are calculatediThe eigenvectors of (i ═ 1,2, …, k) form the projection matrix W ∈ R65536*300Projecting the high-dimensional image feature vector t to the feature vector y in the low-dimensional space by the projection matrix WTt, converting y to obtain a feature vector of the image; then for the ith part, ZCTiExpressed as a 1 x 300 dimensional vector; similarly, the other selected views can also be expressed in a vector form of 1 x 300 dimensions, such as FST in top viewiSide view is CSTi。
S103: splicing and standardizing the feature vectors of the multiple views to obtain a feature matrix of multiple existing parts;
in the specific implementation process, 150 parts are selected as an example for illustration, and the feature vectors of each part are spliced, that is, the u-th part can be represented as a 1 x 600 vector; the training set has a total of 150 parts, all of which form a 150 x 600 dimensional matrix Train, each row representing one part, and each column of the matrix is normalized based on the form (x- μ)/σ, where x represents the vector value, μ represents the mean value of the column vector value, and σ represents the standard deviation of the column vector value.
S104: defining labels of structural features of a plurality of existing parts, and obtaining label matrixes of the existing parts based on the feature matrixes;
in a specific implementation process, labels of structural features of a plurality of existing parts are defined, and based on a feature matrix, label matrices of the plurality of existing parts are obtained, wherein the structural features are expressed as follows: taking the above six structural features as examples, the structural feature corresponding to the u-th part in the training set can be expressed as a 6-tuple JGu＝(DSMu,GYTu,GBu,CEu,MFTu,KXu) Wherein DSMuE {0,1}, i.e., DSM when the part is single-sideduIs 0, DSM when the part is double-sideduIs 1; in the same way, GYTuE {0,1}, represents the high margin feature, and GYT is not the high margin featureu0, when there is a high margin feature, GYTuIs 1; GBuE is {0,1}, and represents the bulge characteristic; CEuE is {0,1}, and represents a fork ear characteristic; MFC (micro-fluid Fuel cell)uE is {0,1}, and the characteristics of the sealing groove are represented; KXuAnd e {0,1}, representing the hole-series characteristics, and associating the obtained training set matrix Train with the part label to form a 150 × 606 matrix, namely combining the label corresponding to each part in the Train with the part vector, wherein the Train' is (Train, DSM, GYT, GB, CE, MFC, KX) based on the corresponding relation of the parts.
S105: taking the feature matrix as input and the label matrix as output, and carrying out classifier training to form a trained classifier;
in the specific implementation process, the feature matrix is used as input and the label matrix is used as output for each label matrix, a naive Bayes classifier is constructed, training is completed, and a classifier model for identifying the target part can be obtained; taking single and double faces as an example, taking Train (vector matrix of 150 × 300) as input, taking DSM (vector matrix of 150 × 1) as output, constructing a naive Bayes classifier, and training to obtain a classifier Model 1; similarly, for high edge bars, a classifier Model2 is available; for bumps, a classifier Model3 is available; for the fork ear, classifier Model4 was available, for the seal groove, classifier Model5 was available, and for the bore series, classifier Model6 was available.
In the specific implementation process, the data set can be divided into a training set and a testing set, the training set is used for training, meanwhile, the testing set is used for testing, and the accuracy and the recall rate of the classifier model are verified.
The classifier obtained by the training method can quickly and accurately identify the target part and directly output the label matrix, different label matrices can be quickly and accurately output through different classifier models after the characteristic matrix is input, whether the target part has the structural characteristics corresponding to the classifier models can be quickly judged through the label matrix, then the obtained result is matched with a preset knowledge base to obtain the corresponding process rule, the compiling efficiency is greatly improved, the process rule correspondingly matched through different structural characteristics is more in line with the actual manufacturing requirement of the target part, the compiled part process rule is more accurate, and the error is smaller.
In one embodiment, the classifier in the present application may be a decision tree, a logistic regression, a naive bayes, etc., and may classify samples in data mining, where the decision tree is a decision analysis method that, based on the probability of occurrence of various known situations, finds a probability that an expected value of a net present value is greater than or equal to zero by constructing the decision tree, evaluates a risk of a project, and determines feasibility of the decision analysis method, and is a graphical method that intuitively uses probability analysis, and when there are many categories, an error may increase more rapidly, the logistic regression is a generalized linear regression analysis model, but its own characteristics cannot be screened, and sometimes needs to be screened by other methods, and because the form of logistic regression is very simple, it is difficult to fit true distribution of data, and accuracy is not high, and the naive bayes classifier has solid basic mathematics, and stable classification efficiency, few parameters to be estimated by the naive Bayes classifier model, insensitivity to missing data and simple algorithm, and theoretically, the naive Bayes classifier model has the smallest error rate compared with a decision tree and a logistic regression method.
In one embodiment, an axonometric view and a top view of a part are selected for feature extraction, and according to compilation experience, structural features required for compilation of the part can be acquired by views with the least quantity under the coordination of the axonometric view and the top view, so that the model training efficiency is improved under the condition of ensuring the model accuracy.
In one embodiment, a principal component analysis method is adopted to perform feature extraction on a plurality of views with different visual angles in each data set, and feature vectors of the plurality of views in each data set are obtained.
In one embodiment, in order to optimize the recognized and read information and avoid meaningless recognition of features irrelevant to the process rules, the structural features and the process information most relevant to the part process rules are selected for recognition, and specifically, the structural features include: the process information comprises at least one of material, attribute and special inspection information, and can be directly obtained by CATIA (computer aided three-dimensional Interactive application) reading part parameters, and the material characteristics comprise aluminum alloy materials and titanium alloy materials; the attribute features comprise general components, important components and key components; the special inspection features include penetration inspection and ultrasonic flaw detection.
The combination of the structural characteristics and the process information basically covers the characteristics of parts in newly-researched projects, for individual special parts, a general process rule can be compiled by the method, corresponding process rules are compiled independently according to the specific structural characteristics or the process information, the structural characteristics and the process information are arranged and combined to obtain a combined scheme of the material (2) attribute (3) special inspection information (2) single-double-sided (2) high-edge strip (2) bulge (2) fork lug (2) sealing groove (2) hole system (2), 768 different process flows are obtained, corresponding standard process parameters exist in each process flow, the characteristic information does not need to be judged manually, after a target part is read, a preset knowledge base is directly matched, the compiled process rule is output, and the compiling efficiency is greatly improved, structural characteristics of the parts are reflected in the form of a label matrix, and related personnel can judge structural information of the target parts more intuitively and quickly.
For the target part V, based on the operation, obtaining a 1-300-dimensional axonometric feature vector ZCT of the partvAnd 1 x 300 dimensional top view feature vector FSTvThen to ZCTvAnd FSTvAnd splicing and standardizing, and finally identifying the structural features of the parts one by one based on a classifier obtained by training.
After the operation is completed, the structural characteristics and the process information of the target part are matched in the preset knowledge base one by one, the refined different characteristic combinations are combined with different process information, the obtained process rules can be more accurate, the obtaining speed is high, the error of the obtained result is smaller, the obtained target part information can be taken as the information of the preset knowledge base to be brought in, the readable information quantity of the preset knowledge base is enriched, the identification, the matching and the process rule compilation of the target part can be faster and more accurate, and the coverage range of the part compilation is further expanded.
Referring to fig. 4, based on the same inventive concept as the previous embodiment, the embodiment of the present application further provides a part process rule compiling device applied to an electronic device, the device including:
the acquisition module is used for acquiring part information of the target part, wherein the part information comprises an image, a characteristic vector, a structural characteristic and process information;
the query module is used for acquiring a target process rule matched with the target part from a preset knowledge base according to the part information;
and the output module is used for outputting the process rules of the target part.
It should be understood by those skilled in the art that the division of each module in the embodiment is only a division of a logic function, and all or part of the division may be integrated onto one or more actual carriers in actual application, and all of the modules may be implemented in a form called by a processing unit through software, may also be implemented in a form of hardware, or implemented in a form of combination of software and hardware, and it should be noted that each module in the part process procedure compiling apparatus in the embodiment corresponds to each step in the part process procedure compiling method in the foregoing embodiment one by one, and therefore, the specific implementation manner of the embodiment may refer to the implementation manner of the foregoing part process route determining method, and is not described herein again.
Based on the same inventive concept as that in the foregoing embodiments, embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and when the computer program is loaded and executed by a processor, the method for compiling the part process rule provided in the embodiments of the present application is implemented.
Further, based on the same inventive concept as the aforementioned embodiments, embodiments of the present application also provide an electronic device, comprising a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is used for loading and executing the computer program so as to enable the electronic equipment to execute the part process rule programming method provided by the embodiment of the application.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a multimedia terminal (e.g., a mobile phone, a computer, a television receiver, or a network device) to execute the method according to the embodiments of the present application.
In summary, the part process rule compiling method, the device, the storage medium and the electronic device provided by the application can accurately identify different structural characteristics of the target part, and compare the process information with the existing information in the preset knowledge base, so that the process rule of the target part is compiled quickly and accurately, and the compiling quality and efficiency are greatly improved.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A part process rule compiling method is applied to electronic equipment and comprises the following steps:
acquiring a feature vector of a part image of a target part;
inputting the feature vector into a trained classifier to obtain structural features of the target part;
acquiring a target process rule matched with the target part from a preset knowledge base based on the structural characteristics of the target part and the process information of the target part; the preset knowledge base comprises a plurality of parts and process procedures corresponding to the parts.
2. The part recipe preparation method of claim 1, wherein prior to the step of obtaining feature vectors for part images of a target part, the method further comprises:
the method comprises the steps of obtaining images of a plurality of existing parts, classifying the images of the existing parts based on structural features of the existing parts, and forming a plurality of data sets corresponding to a plurality of structural features; wherein each data set comprises an image of an existing part corresponding to a structural feature, each existing part image comprising a plurality of views from different perspectives;
extracting features of a plurality of views at different visual angles in each data set to obtain feature vectors of the views in each data set;
splicing and standardizing the feature vectors of the multiple views to obtain a feature matrix of the multiple existing parts;
defining labels of the structural features of the existing parts, and obtaining label matrixes of the existing parts based on the feature matrixes;
and training a classifier by taking the characteristic matrix as input and the label matrix as output to form the trained classifier.
3. The part specification compilation method of claim 2 wherein the classifier is a naive bayes classifier.
4. The part process specification compilation method of claim 2 wherein the plurality of views from different perspectives comprises an isometric view and a top view.
5. The part process specification compilation method of claim 2, wherein the step of extracting features from the plurality of views from different perspectives in each data set to obtain feature vectors for the plurality of views in each data set comprises:
and performing feature extraction on the multiple views at different view angles in each data set by adopting a principal component analysis method, and acquiring feature vectors of the multiple views in each data set.
6. The part recipe compilation method of any of claims 1-5, wherein the structural features comprise: the process information comprises at least one of material, property and special inspection information.
7. A classifier training method is applied to electronic equipment and comprises the following steps:
the method comprises the steps of obtaining images of a plurality of existing parts, classifying the images of the existing parts based on structural features of the existing parts, and forming a plurality of data sets corresponding to a plurality of structural features; wherein each data set comprises an image of an existing part corresponding to a structural feature, each existing part image comprising a plurality of views from different perspectives;
extracting features of a plurality of views at different visual angles in each data set to obtain feature vectors of the views in each data set;
splicing and standardizing the feature vectors of the multiple views to obtain a feature matrix of the multiple existing parts;
defining labels of the structural features of the existing parts, and obtaining label matrixes of the existing parts based on the feature matrixes;
and training a classifier by taking the characteristic matrix as input and the label matrix as output to form the trained classifier.
8. A part process rule compiling device applied to electronic equipment is characterized by comprising:
the acquisition module is used for acquiring part information of the target part, wherein the part information comprises an image, a characteristic vector, a structural characteristic and process information;
the query module is used for acquiring a target process rule matched with the target part from the preset knowledge base according to the part information;
and the output module is used for outputting the process rule of the target part.
9. A computer-readable storage medium storing a computer program, wherein the computer program, when loaded and executed by a processor, implements a part recipe preparation method as claimed in any one of claims 1 to 6.
10. An electronic device comprising a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is configured to load and execute the computer program to cause the electronic device to perform the part process specification method as defined in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119200.5A CN113901647B (en) | 2021-09-24 | 2021-09-24 | Part technical specification compiling method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119200.5A CN113901647B (en) | 2021-09-24 | 2021-09-24 | Part technical specification compiling method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113901647A true CN113901647A (en) | 2022-01-07 |
| CN113901647B CN113901647B (en) | 2024-08-13 |
Family
ID=79029113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111119200.5A Active CN113901647B (en) | 2021-09-24 | 2021-09-24 | Part technical specification compiling method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113901647B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114065406A (en) * | 2022-01-17 | 2022-02-18 | 成都飞机工业（集团）有限责任公司 | Design method, device and equipment of process hole and storable medium |
| CN116976208A (en) * | 2023-07-28 | 2023-10-31 | 沈阳飞机工业（集团）有限公司 | Aviation fastener dividing method based on machine learning |
| CN118114408A (en) * | 2024-04-30 | 2024-05-31 | 成都飞机工业（集团）有限责任公司 | Group hole characteristic numerical control processing model construction method, device, medium and equipment |
| CN118504694A (en) * | 2024-07-22 | 2024-08-16 | 成都飞机工业（集团）有限责任公司 | Aviation part technical specification reasoning method, system, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101670533A (en) * | 2009-09-25 | 2010-03-17 | 南京信息工程大学 | Cutting-tool wear state evaluating method based on image analysis of workpiece machining surface |
| US20170337733A1 (en) * | 2016-05-17 | 2017-11-23 | Fujitsu Limited | Method and apparatus for searching a database of 3d items using descriptors |
| CN109117822A (en) * | 2018-08-31 | 2019-01-01 | 贵州大学 | A kind of part case segmentation recognition method based on deep learning |
| CN109657708A (en) * | 2018-12-05 | 2019-04-19 | 中国科学院福建物质结构研究所 | Workpiece recognition device and its method based on image recognition-SVM learning model |
| CN110135514A (en) * | 2019-05-22 | 2019-08-16 | 国信优易数据有限公司 | A kind of workpiece classification method, device, equipment and medium |
| CN110659541A (en) * | 2018-06-29 | 2020-01-07 | 深圳云天励飞技术有限公司 | Image recognition method, device and storage medium |
| WO2020164278A1 (en) * | 2019-02-14 | 2020-08-20 | 平安科技（深圳）有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN112949724A (en) * | 2021-03-08 | 2021-06-11 | 深圳先进技术研究院 | Training method of image classification network model, image classification method and related equipment |
-
2021
- 2021-09-24 CN CN202111119200.5A patent/CN113901647B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101670533A (en) * | 2009-09-25 | 2010-03-17 | 南京信息工程大学 | Cutting-tool wear state evaluating method based on image analysis of workpiece machining surface |
| US20170337733A1 (en) * | 2016-05-17 | 2017-11-23 | Fujitsu Limited | Method and apparatus for searching a database of 3d items using descriptors |
| CN110659541A (en) * | 2018-06-29 | 2020-01-07 | 深圳云天励飞技术有限公司 | Image recognition method, device and storage medium |
| CN109117822A (en) * | 2018-08-31 | 2019-01-01 | 贵州大学 | A kind of part case segmentation recognition method based on deep learning |
| CN109657708A (en) * | 2018-12-05 | 2019-04-19 | 中国科学院福建物质结构研究所 | Workpiece recognition device and its method based on image recognition-SVM learning model |
| WO2020164278A1 (en) * | 2019-02-14 | 2020-08-20 | 平安科技（深圳）有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN110135514A (en) * | 2019-05-22 | 2019-08-16 | 国信优易数据有限公司 | A kind of workpiece classification method, device, equipment and medium |
| CN112949724A (en) * | 2021-03-08 | 2021-06-11 | 深圳先进技术研究院 | Training method of image classification network model, image classification method and related equipment |
Non-Patent Citations (3)
| Title |
|---|
| 刘更谦, 高金莲, 张明路, 岳宏: "基于浓度特征向量的目标识别与分类", 高技术通讯, no. 11, 28 November 2004 (2004-11-28), pages 65 - 68 * |
| 尹伟为;张振明;田锡天;刘书暖;: "基于参数化典型工艺的快速工艺生成技术", 航空制造技术, no. 04, 15 March 2008 (2008-03-15), pages 86 - 89 * |
| 郭兰申, 李世杰, 曲云霞, 刘瑞素: "基于神经网络的零件信息输入技术在蜗轮蜗杆CAPP中的应用", 机械科学与技术, no. 04, 30 July 2002 (2002-07-30), pages 675 - 676 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114065406A (en) * | 2022-01-17 | 2022-02-18 | 成都飞机工业（集团）有限责任公司 | Design method, device and equipment of process hole and storable medium |
| CN116976208A (en) * | 2023-07-28 | 2023-10-31 | 沈阳飞机工业（集团）有限公司 | Aviation fastener dividing method based on machine learning |
| CN118114408A (en) * | 2024-04-30 | 2024-05-31 | 成都飞机工业（集团）有限责任公司 | Group hole characteristic numerical control processing model construction method, device, medium and equipment |
| CN118504694A (en) * | 2024-07-22 | 2024-08-16 | 成都飞机工业（集团）有限责任公司 | Aviation part technical specification reasoning method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113901647B (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113901647A (en) | Part process rule compiling method and device, storage medium and electronic equipment | |
| CN111767228B (en) | Interface testing method, device, equipment and medium based on artificial intelligence | |
| US8549478B2 (en) | Graphical user interface input element identification | |
| CN109901996A (en) | Method, apparatus, electronic equipment and the readable storage medium storing program for executing of subtest | |
| CN110955590A (en) | Interface detection method, image processing method, device, electronic equipment and storage medium | |
| US20230021551A1 (en) | Using training images and scaled training images to train an image segmentation model | |
| CN113377667B (en) | Scene-based testing method and device, computer equipment and storage medium | |
| CN112527676A (en) | Model automation test method, device and storage medium | |
| CN111783812A (en) | Method and device for identifying forbidden images and computer readable storage medium | |
| CN111124863A (en) | Intelligent equipment performance testing method and device and intelligent equipment | |
| CN112381092A (en) | Tracking method, device and computer readable storage medium | |
| CN112633341A (en) | Interface testing method and device, computer equipment and storage medium | |
| CN115964432A (en) | User operation abnormity analysis method and system based on big data visualization | |
| US11823086B2 (en) | Membership analyzing method, apparatus, computer device and storage medium | |
| CN115631374A (en) | Control operation method, control detection model training method, device and equipment | |
| CN113627755A (en) | Test method, device, equipment and storage medium for intelligent terminal factory | |
| CN112950167A (en) | Design service matching method, device, equipment and storage medium | |
| CN110851349A (en) | Page abnormal display detection method, terminal equipment and storage medium | |
| CN113111713B (en) | Image detection method and device, electronic equipment and storage medium | |
| CN110308905B (en) | Page component matching method and device | |
| CN116401151A (en) | Precision testing method and system for picture identification algorithm | |
| CN116385838A (en) | Model training and defect detection method, device, medium, equipment and program product | |
| CN118012552A (en) | Interface information processing method, apparatus, device, medium, and computer program product | |
| CN113408600A (en) | Sample data preprocessing method and device and computer readable storage medium | |
| CN114375465A (en) | Picture classification method and device, storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |