CN117252486A - Automobile part defect detection method and system based on Internet of things - Google Patents
Automobile part defect detection method and system based on Internet of things Download PDFInfo
- Publication number
- CN117252486A CN117252486A CN202311509665.0A CN202311509665A CN117252486A CN 117252486 A CN117252486 A CN 117252486A CN 202311509665 A CN202311509665 A CN 202311509665A CN 117252486 A CN117252486 A CN 117252486A
- Authority
- CN
- China
- Prior art keywords
- automobile
- spare
- internal
- production
- parts
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 283
- 238000001514 detection method Methods 0.000 title claims abstract description 120
- 238000004519 manufacturing process Methods 0.000 claims abstract description 241
- 238000000034 method Methods 0.000 claims abstract description 198
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 230000002950 deficient Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000004381 surface treatment Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
- G01N29/4418—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison with a model, e.g. best-fit, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/25—Manufacturing
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Manufacturing & Machinery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Game Theory and Decision Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- General Factory Administration (AREA)
Abstract
A method and a system for detecting defects of automobile parts based on the Internet of things relate to the technical field of defect detection and comprise the following steps: obtaining surface data and internal data of automobile parts; obtaining surface defect spare parts and internal defect spare parts; constructing a surface defect detection model of the automobile spare and accessory part, and judging whether the surface defect exists in the automobile spare and accessory part or not; constructing an internal defect detection model of the automobile spare and accessory part, and judging whether the automobile spare and accessory part has an internal defect or not; obtaining defect probability and judging whether abnormal production conditions exist or not; according to the technical scheme, the unfinished automobile spare and accessory parts with defects can be timely found, the subsequent production sub-process is stopped, timely damage stopping is facilitated, and the total cost of the production of the automobile spare and accessory parts is reduced.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to an automobile part defect detection method and system based on the Internet of things.
Background
The defect detection of automobile parts refers to detecting whether the automobile parts have defects, such as damage, deformation, poor quality and the like, so as to ensure the safety and reliability of the automobile, and common detection methods comprise appearance inspection, physical test, electronic detection, material analysis and the like, and in the modern automobile industry, the manufacturing and detection of a plurality of automobile parts are realized by the technologies of automation, deep learning and the like;
in the prior art, defect detection is performed on automobile parts after the automobile parts are produced, the production process of the automobile parts can be generally divided into different sub-processes, a plurality of automobile parts with defects in the sub-processes cannot be found in time, and then the next sub-process is continuously processed and manufactured.
Disclosure of Invention
The invention aims to provide an automobile part defect detection method and system based on the Internet of things.
The aim of the invention can be achieved by the following technical scheme: the automobile spare and accessory part defect detection method based on the Internet of things comprises the following steps of:
step S1: the method comprises the steps of obtaining a production complete process of automobile parts, dividing the production complete process to obtain a plurality of production sub-processes, and collecting and storing surface data and internal data of the automobile parts in each production sub-process;
step S2: the method comprises the steps of obtaining the spare and accessory part standard of the automobile spare and accessory part, respectively judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and obtaining corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
step S3: constructing a surface defect detection model of the automobile spare and accessory part according to the surface data of the surface defect spare and accessory part, judging whether the surface defect exists in the unfinished automobile spare and accessory part according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory part;
step S4: constructing an internal defect detection model of the automobile spare and accessory part according to the internal data of the internal defect spare and accessory part, judging whether the unfinished automobile spare and accessory part has an internal defect or not according to the internal defect detection model, and stopping production when the internal defect of the automobile spare and accessory part occurs;
step S5: and obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
Further, the process of obtaining the production complete flow of the automobile spare part and dividing the production complete flow to obtain a plurality of production sub-flows includes:
the method comprises the steps of collecting the whole production process of the automobile parts, dividing the obtained whole production process of the automobile parts into a plurality of production sub-processes.
Further, the process of collecting and storing the surface data and the internal data of the automobile parts in each production sub-process includes:
setting a surface acquisition unit and an internal acquisition unit, and respectively acquiring surface data and internal data of the automobile parts after each production sub-process through the surface acquisition unit and the internal acquisition unit;
setting a database, naming the surface data and the internal data of the automobile parts obtained in each production sub-process, and uploading the named surface data and internal data to the database for storage.
Further, the process of obtaining the standard of the spare and accessory parts of the automobile, judging whether the produced spare and accessory parts of the automobile have surface defects according to the standard of the spare and accessory parts, and obtaining the corresponding spare and accessory parts with the surface defects comprises the following steps:
collecting the part standards of the automobile parts, wherein the part standards comprise part surface standards and part internal standards;
and comparing the obtained surface standard of the spare and accessory part with the surface data of the finished automobile spare and accessory part to judge whether the automobile spare and accessory part has surface defects or not, and obtaining the corresponding surface defect spare and accessory part.
Further, the process of judging whether the produced automobile spare and accessory parts have internal defects according to the spare and accessory part standard and obtaining the corresponding internal defect spare and accessory parts comprises the following steps:
and comparing the obtained internal standard of the spare and accessory parts with the internal data of the produced spare and accessory parts of the automobile to judge whether the spare and accessory parts of the automobile have internal defects or not, and obtaining corresponding spare and accessory parts with the internal defects.
Further, a surface defect detection model of the automobile part is constructed according to the surface data of the surface defect part, whether the surface defect exists in the unfinished automobile part is judged according to the surface defect detection model, and when the surface defect exists in the automobile part, the production stopping process comprises the following steps:
the number of the surface defect detection models is the same as that of the production sub-processes, and the surface defect detection models are named respectively;
and constructing a surface defect detection model of each production sub-process according to the surface data of all the surface defect parts in each production sub-process, and detecting the surface defects of the automobile parts in the corresponding production sub-process according to the constructed surface defect detection model to judge whether the surface defects exist or not, wherein when judging that the surface defects of the automobile parts occur in the current production sub-process, the surface defects are not included in the next production sub-process.
Further, an internal defect detection model of the automobile spare part is constructed according to the internal data of the internal defect spare part, whether the unfinished automobile spare part has an internal defect or not is judged according to the internal defect detection model, and when the internal defect occurs in the automobile spare part, the production stopping process comprises the following steps:
the number of the internal defect detection models is the same as that of the production sub-processes, and the internal defect detection models are named respectively;
and constructing an internal defect detection model of each production sub-process according to the internal data of all the internal defect spare parts in each production sub-process, detecting the internal defects of the automobile spare parts in the corresponding production sub-process according to the constructed internal defect detection model to judge whether the internal defects exist or not, and not incorporating the internal defects of the automobile spare parts into the next production sub-process when judging that the internal defects of the automobile spare parts occur in the current production sub-process.
Further, the process of obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating the corresponding abnormal production signal comprises the following steps:
setting a production period, and when one production period is reached, obtaining the number of automobile parts and the number of defect parts in the current production period, obtaining the defect probability of each production sub-process, and obtaining the probability coefficient of each production sub-process;
setting a probability coefficient threshold, comparing the probability coefficient with the probability coefficient threshold, judging whether abnormal production conditions exist in each production sub-process according to the comparison result, and generating corresponding abnormal production signals.
The automobile spare and accessory part defect detection system based on the Internet of things comprises a main control center, wherein the main control center is in communication connection with a flow acquisition module, a sample acquisition module, a surface detection module, an internal detection module and a production monitoring module;
the process acquisition module is used for acquiring a production complete process of the automobile parts, dividing the production complete process to acquire a plurality of production sub-processes, and acquiring and storing surface data and internal data of the automobile parts in each production sub-process;
the sample acquisition module is used for acquiring the spare and accessory part standard of the automobile spare and accessory part, judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and acquiring corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
the surface detection module is used for constructing a surface defect detection model of the automobile spare and accessory parts according to the surface data of the surface defect spare and accessory parts, judging whether the surface defect exists in the unfinished automobile spare and accessory parts according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory parts;
the internal detection module is used for constructing an internal defect detection model of the automobile spare and accessory parts according to the internal data of the internal defect spare and accessory parts, judging whether the unfinished automobile spare and accessory parts have internal defects according to the internal defect detection model, and stopping production when the internal defects occur in the automobile spare and accessory parts;
the production monitoring module is used for obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
Compared with the prior art, the invention has the beneficial effects that:
1. dividing the whole production process of the automobile spare and accessory parts into a plurality of production sub-processes, respectively obtaining surface data and internal data of each production sub-process, obtaining surface defect spare and accessory parts and internal defect spare and accessory parts according to spare and accessory part standards of the automobile spare and accessory parts, constructing a surface defect detection model and an internal defect detection model of each production sub-process according to the surface defect detection model and the internal defect detection model of each production sub-process, judging whether the automobile spare and accessory parts of each production sub-process have defects according to the surface defect detection model and the internal defect detection model, and unlike the traditional method for detecting defects based on the finished automobile spare and accessory parts, the invention creatively detects the defects of the automobile spare and accessory parts in stages in the production process of the automobile spare and accessory parts, can timely find the unfinished automobile spare and accessory parts with defects, stop the subsequent production sub-processes, and is beneficial to timely stopping loss and reducing the total cost of the production of the automobile spare and accessory parts;
2. the defect probability of the defective part of each production sub-process is obtained, whether the abnormal production condition exists in each production sub-process is judged according to the defect probability, the production of the automobile part in different production sub-processes can be fed back in a targeted mode, workers can find the production sub-process with abnormal production in time, overhaul the production sub-process in time, and the number of the defective parts can be effectively reduced.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of the present invention.
Detailed Description
As shown in fig. 1, the method for detecting defects of automobile parts based on the internet of things comprises the following steps:
step S1: the method comprises the steps of obtaining a production complete process of automobile parts, dividing the production complete process to obtain a plurality of production sub-processes, and collecting and storing surface data and internal data of the automobile parts in each production sub-process;
step S2: the method comprises the steps of obtaining the spare and accessory part standard of the automobile spare and accessory part, respectively judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and obtaining corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
step S3: constructing a surface defect detection model of the automobile spare and accessory part according to the surface data of the surface defect spare and accessory part, judging whether the surface defect exists in the unfinished automobile spare and accessory part according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory part;
step S4: constructing an internal defect detection model of the automobile spare and accessory part according to the internal data of the internal defect spare and accessory part, judging whether the unfinished automobile spare and accessory part has an internal defect or not according to the internal defect detection model, and stopping production when the internal defect of the automobile spare and accessory part occurs;
step S5: and obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
It should be further noted that, in the specific implementation process, the process of obtaining the whole production process of the automobile parts and components and dividing the whole production process to obtain a plurality of production sub-processes includes:
taking any automobile part as an example, collecting the whole production process of the automobile part, wherein the whole production process of the automobile part refers to the whole process of processing the automobile part from raw materials to finished products step by step, and taking the production process of a screw as an example, the production process of the screw can be completed only through the processes of material preparation, cold heading, heat treatment, thread rolling, surface treatment and the like;
the whole production process of the obtained automobile spare and accessory parts is divided into a plurality of production sub-processes according to the production condition of the automobile spare and accessory parts in the whole production process, wherein the production condition can be different production equipment or production nodes with obvious differences in the same production equipment, and the production sub-processes are determined by staff, for example: the whole production process of the screw can be divided into production sub-processes of material preparation, cold heading processing, heat treatment, thread rolling, surface treatment and the like.
It should be further noted that, in the implementation process, the process of collecting and storing the surface data and the internal data of the automobile parts in each production sub-process includes:
in the embodiment of the invention, the whole production process of the automobile spare part is divided into 5 production sub-processes, and the production sub-processes are respectively named as a first production sub-process, a second production sub-process, a third production sub-process, a fourth production sub-process and a fifth production sub-process;
when any production sub-process is finished, the surface acquisition unit is used for acquiring the surface data of the automobile spare and accessory parts after the production sub-process, and the specific steps are as follows: collecting surface images of automobile parts, and detecting the surface images of the automobile parts by adopting an image segmentation technology to obtain surface characteristic points of the automobile parts, wherein the surface characteristic points comprise but are not limited to scratches, bubbles, burrs, chromatic aberration, deformation, paint film cracking, oxidized spots and the like, and the surface data are whether the surface characteristic points and the corresponding surface characteristic point number of the automobile parts exist or not;
when any production sub-process is finished, the internal data of the automobile parts after the production sub-process is collected by the internal collecting unit, and the specific steps are as follows: four sound wave detection points are uniformly arranged on the periphery of the automobile part, the automobile part is sequentially detected on the sound wave detection points by utilizing an ultrasonic detection technology to obtain internal characteristic points of the automobile part, the internal characteristic points comprise but are not limited to air holes, inclusions, cracks, loose areas, abnormal tissues and the like, and the internal data are whether the internal characteristic points exist in the automobile part or not and the corresponding number of the internal characteristic points;
setting a database, namely naming surface data and internal data obtained in each production sub-process of the automobile parts respectively, for example: the surface data and the internal data obtained in the first production sub-process are respectively named as first surface data and first internal data, the surface data and the internal data obtained in the second production sub-process are respectively named as second surface data and second internal data, and the like, all the surface data and the internal data are respectively named, and all the surface data and the internal data which are named are uploaded to a database for storage.
It should be further noted that, in the specific implementation process, the process of obtaining the spare and accessory part standard of the automobile spare and accessory part, judging whether the produced automobile spare and accessory part has the surface defect according to the spare and accessory part standard, and obtaining the corresponding surface defect spare and accessory part includes:
taking any automobile part as an example, collecting part standards of the automobile part, wherein the part standards refer to specifications and requirements formulated for unifying and standardizing design, production, test and quality control of the automobile part, the part standards comprise part surface standards and part internal standards, in the embodiment of the invention, the part surface standards specifically comprise whether surface feature points are allowed to exist and the number of the surface feature points are allowed to exist, the part internal standards specifically comprise whether the internal feature points are allowed to exist and the number of the internal feature points are allowed to exist, and the obtained part standards are uploaded to a database for storage;
because the invention divides the whole production process of the automobile spare and accessory parts into 5 production sub-processes, the invention takes the fifth surface data of the automobile spare and accessory parts obtained in the fifth production sub-process as the surface data of the automobile spare and accessory parts which have finished production, and compares the obtained spare and accessory part surface standard with the fifth surface data to judge whether the surface defect exists in the automobile spare and accessory parts;
the method comprises the following specific steps: judging whether surface feature points which are not allowed to exist in the fifth surface data exist according to the surface standard of the spare and accessory parts, if so, marking the surface feature points as surface defect spare and accessory parts, if not, marking the surface feature points as surface normal spare and accessory parts, and meanwhile judging whether the number of the surface feature points which are allowed to exist in the fifth surface data is larger than that allowed in the surface standard of the spare and accessory parts, if so, marking the surface feature points as surface defect spare and accessory parts, and if not, marking the surface feature points as surface normal spare and accessory parts.
It should be further noted that, in the specific implementation process, the process of judging whether the manufactured automobile spare part has the internal defect according to the spare part standard and obtaining the corresponding internal defect spare part includes:
because the invention divides the whole production process of the automobile spare and accessory parts into 5 production sub-processes, the invention takes the fifth internal data obtained in the fifth production sub-process of the automobile spare and accessory parts as the internal data of the automobile spare and accessory parts which have finished production, and compares the obtained internal standard of the spare and accessory parts with the fifth internal data to judge whether the automobile spare and accessory parts have internal defects or not;
the method comprises the following specific steps: judging whether the internal feature points which are not allowed to exist in the fifth internal data exist according to the internal standards of the spare and accessory parts, if so, marking the internal feature points as internal defect spare and accessory parts, if not, marking the internal feature points as internal normal spare and accessory parts, and meanwhile judging whether the number of the internal feature points which are allowed to exist in the fifth internal data is larger than that allowed in the internal standards of the spare and accessory parts, if so, marking the internal feature points as internal defect spare and accessory parts, and if not, marking the internal feature points as internal normal spare and accessory parts.
It should be further noted that, in the implementation process, a surface defect detection model of the automobile spare part is constructed according to the surface data of the surface defect spare part, whether the surface defect exists in the unfinished automobile spare part is judged according to the surface defect detection model, and when the surface defect exists in the automobile spare part, the production stopping process comprises:
the number of the surface defect detection models is the same as that of the production sub-processes, namely, each production sub-process is provided with a corresponding surface defect detection model and is respectively named as a first surface defect detection model, a second surface defect detection model and … …;
taking the construction process of the third surface defect detection model as an example, obtaining third surface data of all surface defect parts, dividing the obtained third surface data into a training set and a test set, selecting a deep learning model as an initial third surface defect detection model, training the initial third surface defect detection model by using the training set, evaluating and optimizing the trained third surface defect detection model by using the test set, and taking the latest optimized third surface defect detection model as a current third surface defect detection model;
and according to the constructed third surface defect detection model, detecting the surface defect of the automobile part which completes the third production sub-process (and does not enter the next production sub-process) so as to judge whether the automobile part has the corresponding surface defect, wherein the surface defect detection process is consistent with the surface defect judging process of the automobile part which completes the production according to the part standard, and when the automobile part is judged to have the surface defect in the third production sub-process, the subsequent production sub-process of the automobile part is stopped, namely the automobile part is not brought into the next production sub-process.
It should be further noted that, in the implementation process, an internal defect detection model of the automobile spare part is constructed according to the internal data of the internal defect spare part, whether the automobile spare part which is not produced has an internal defect or not is judged according to the internal defect detection model, and when the internal defect occurs in the automobile spare part, the process of stopping production comprises:
the number of the internal defect detection models is the same as that of the production sub-processes, namely, each production sub-process is provided with a corresponding internal defect detection model and is respectively named as a first internal defect detection model, a second internal defect detection model and … …;
taking the construction process of a third internal defect detection model as an example, obtaining third internal data of all internal defect spare and accessory parts, dividing the obtained third internal data into a training set and a test set, selecting a deep learning model as an initial third internal defect detection model, training the initial third internal defect detection model by using the training set, evaluating and optimizing the trained third internal defect detection model by using the test set, and taking the latest optimized third internal defect detection model as a current third internal defect detection model;
and detecting the internal defects of the automobile parts which finish the third production sub-process (and do not enter the next production sub-process) according to the constructed third internal defect detection model to judge whether the corresponding internal defects exist or not, wherein the internal defect detection process is consistent with the judging process of whether the internal defects exist in the automobile parts which finish production according to the part standards, and when the internal defects of the automobile parts are judged to exist in the third production sub-process, the subsequent production sub-process of the automobile parts is stopped, namely the automobile parts are not brought into the next production sub-process.
It should be further noted that, in the specific implementation process, the process of obtaining the defect probability of the defective parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating the corresponding abnormal production signal includes:
when the production period is set and one production period is reached, respectively counting the number of automobile parts produced by each production sub-process and the number of the defect parts in the current production period, taking a third production sub-process as an example, and marking the number of the automobile parts produced by the third production sub-process as S a Marking the number of defective parts appearing in the third production sub-process as S b Obtaining the defect probability of the third production sub-process and marking the defect probability as P 3 ；
Similarly, the defect probability of each production sub-process is obtained by adopting the same method and is respectively marked as P i Where i=1, 2, … …, n, where n is the number of production sub-flows, the probability coefficient for each production sub-flow is obtained and labeled R i ；
Setting a probability coefficient threshold R 0 Comparing the obtained probability coefficient with a set probability coefficient threshold value, judging whether abnormal production conditions exist in each production sub-process according to the comparison result, if R i ≤R 0 Judging that the abnormal production condition does not exist, and performing no other operation on the abnormal production condition, if R i ＞R 0 And judging that the abnormal production condition exists, generating an abnormal production signal and feeding the abnormal production signal back to a worker.
As shown in fig. 2, the automobile spare and accessory part defect detection system based on the internet of things comprises a main control center, wherein the main control center is in communication connection with a flow acquisition module, a sample acquisition module, a surface detection module, an internal detection module and a production monitoring module;
the process acquisition module is used for acquiring a production complete process of the automobile parts, dividing the production complete process to acquire a plurality of production sub-processes, and acquiring and storing surface data and internal data of the automobile parts in each production sub-process;
the sample acquisition module is used for acquiring the spare and accessory part standard of the automobile spare and accessory part, judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and acquiring corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
the surface detection module is used for constructing a surface defect detection model of the automobile spare and accessory parts according to the surface data of the surface defect spare and accessory parts, judging whether the surface defect exists in the unfinished automobile spare and accessory parts according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory parts;
the internal detection module is used for constructing an internal defect detection model of the automobile spare and accessory parts according to the internal data of the internal defect spare and accessory parts, judging whether the unfinished automobile spare and accessory parts have internal defects according to the internal defect detection model, and stopping production when the internal defects occur in the automobile spare and accessory parts;
the production monitoring module is used for obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (9)
1. The automobile spare and accessory part defect detection method based on the Internet of things is characterized by comprising the following steps of:
step S1: the method comprises the steps of obtaining a production complete process of automobile parts, dividing the production complete process to obtain a plurality of production sub-processes, and collecting and storing surface data and internal data of the automobile parts in each production sub-process;
step S2: the method comprises the steps of obtaining the spare and accessory part standard of the automobile spare and accessory part, respectively judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and obtaining corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
step S3: constructing a surface defect detection model of the automobile spare and accessory part according to the surface data of the surface defect spare and accessory part, judging whether the surface defect exists in the unfinished automobile spare and accessory part according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory part;
step S4: constructing an internal defect detection model of the automobile spare and accessory part according to the internal data of the internal defect spare and accessory part, judging whether the unfinished automobile spare and accessory part has an internal defect or not according to the internal defect detection model, and stopping production when the internal defect of the automobile spare and accessory part occurs;
step S5: and obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
2. The method for detecting defects of automobile parts based on the internet of things according to claim 1, wherein the steps of obtaining a production complete process of the automobile parts and dividing the production complete process to obtain a plurality of production sub-processes comprise:
the method comprises the steps of collecting the whole production process of the automobile parts, dividing the obtained whole production process of the automobile parts into a plurality of production sub-processes.
3. The internet of things-based automobile part defect detection method of claim 2, wherein the process of collecting and storing surface data and internal data of the automobile part in each production sub-process comprises:
setting a surface acquisition unit and an internal acquisition unit, and respectively acquiring surface data and internal data of the automobile parts after each production sub-process through the surface acquisition unit and the internal acquisition unit;
setting a database, naming the surface data and the internal data of the automobile parts obtained in each production sub-process, and uploading the named surface data and internal data to the database for storage.
4. The method for detecting defects of automobile parts based on the internet of things according to claim 3, wherein the process of obtaining the part standards of the automobile parts, judging whether the produced automobile parts have surface defects according to the part standards, and obtaining the corresponding surface defect part comprises the following steps:
collecting the part standards of the automobile parts, wherein the part standards comprise part surface standards and part internal standards;
and comparing the obtained surface standard of the spare and accessory part with the surface data of the finished automobile spare and accessory part to judge whether the automobile spare and accessory part has surface defects or not, and obtaining the corresponding surface defect spare and accessory part.
5. The internet of things-based automobile part defect detection method of claim 4, wherein the process of judging whether the produced automobile part has the internal defect according to the part standard and obtaining the corresponding internal defect part comprises the following steps:
and comparing the obtained internal standard of the spare and accessory parts with the internal data of the produced spare and accessory parts of the automobile to judge whether the spare and accessory parts of the automobile have internal defects or not, and obtaining corresponding spare and accessory parts with the internal defects.
6. The internet of things-based automobile part defect detection method of claim 5, wherein the step of constructing a surface defect detection model of the automobile part according to the surface data of the surface defect part, judging whether the surface defect exists in the unfinished automobile part according to the surface defect detection model, and stopping the production when the surface defect exists in the automobile part comprises the following steps:
the number of the surface defect detection models is the same as that of the production sub-processes, and the surface defect detection models are named respectively;
and constructing a surface defect detection model of each production sub-process according to the surface data of all the surface defect parts in each production sub-process, and detecting the surface defects of the automobile parts in the corresponding production sub-process according to the constructed surface defect detection model to judge whether the surface defects exist or not, wherein when judging that the surface defects of the automobile parts occur in the current production sub-process, the surface defects are not included in the next production sub-process.
7. The internet of things-based automobile part defect detection method of claim 6, wherein the process of constructing an internal defect detection model of an automobile part according to internal data of the internal defect part, judging whether an unfinished automobile part has an internal defect according to the internal defect detection model, and stopping production when the internal defect occurs in the automobile part comprises the steps of:
the number of the internal defect detection models is the same as that of the production sub-processes, and the internal defect detection models are named respectively;
and constructing an internal defect detection model of each production sub-process according to the internal data of all the internal defect spare parts in each production sub-process, detecting the internal defects of the automobile spare parts in the corresponding production sub-process according to the constructed internal defect detection model to judge whether the internal defects exist or not, and not incorporating the internal defects of the automobile spare parts into the next production sub-process when judging that the internal defects of the automobile spare parts occur in the current production sub-process.
8. The method for detecting defects of automobile parts based on the internet of things according to claim 7, wherein the steps of obtaining the defect probability of defective parts of each production sub-process, judging whether abnormal production conditions exist in each production sub-process according to the defect probability, and generating corresponding abnormal production signals comprise:
setting a production period, and when one production period is reached, obtaining the number of automobile parts and the number of defect parts in the current production period, obtaining the defect probability of each production sub-process, and obtaining the probability coefficient of each production sub-process;
setting a probability coefficient threshold, comparing the probability coefficient with the probability coefficient threshold, judging whether abnormal production conditions exist in each production sub-process according to the comparison result, and generating corresponding abnormal production signals.
9. The automobile spare and accessory part defect detection system based on the Internet of things is characterized by being used for realizing the automobile spare and accessory part defect detection method according to any one of claims 1 to 8, and comprising a main control center, wherein the main control center is in communication connection with a flow acquisition module, a sample acquisition module, a surface detection module, an internal detection module and a production monitoring module;
the process acquisition module is used for acquiring a production complete process of the automobile parts, dividing the production complete process to acquire a plurality of production sub-processes, and acquiring and storing surface data and internal data of the automobile parts in each production sub-process;
the sample acquisition module is used for acquiring the spare and accessory part standard of the automobile spare and accessory part, judging whether the produced automobile spare and accessory part has surface defects and internal defects according to the spare and accessory part standard, and acquiring corresponding surface defect spare and accessory parts and internal defect spare and accessory parts;
the surface detection module is used for constructing a surface defect detection model of the automobile spare and accessory parts according to the surface data of the surface defect spare and accessory parts, judging whether the surface defect exists in the unfinished automobile spare and accessory parts according to the surface defect detection model, and stopping production when the surface defect exists in the automobile spare and accessory parts;
the internal detection module is used for constructing an internal defect detection model of the automobile spare and accessory parts according to the internal data of the internal defect spare and accessory parts, judging whether the unfinished automobile spare and accessory parts have internal defects according to the internal defect detection model, and stopping production when the internal defects occur in the automobile spare and accessory parts;
the production monitoring module is used for obtaining the defect probability of the defective spare and accessory parts of each production sub-process, judging whether the abnormal production condition exists in each production sub-process according to the defect probability, and generating corresponding abnormal production signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311509665.0A CN117252486B (en) | 2023-11-14 | 2023-11-14 | Automobile part defect detection method and system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311509665.0A CN117252486B (en) | 2023-11-14 | 2023-11-14 | Automobile part defect detection method and system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117252486A true CN117252486A (en) | 2023-12-19 |
| CN117252486B CN117252486B (en) | 2024-02-02 |
Family
ID=89131616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311509665.0A Active CN117252486B (en) | 2023-11-14 | 2023-11-14 | Automobile part defect detection method and system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117252486B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246369A (en) * | 2008-03-18 | 2008-08-20 | 东华大学 | Vehicle element size quality control system and method |
| CN103808734A (en) * | 2014-03-07 | 2014-05-21 | 上海齐宏检测技术有限公司 | Full-automatic detection device of automobile parts |
| CN108897925A (en) * | 2018-06-11 | 2018-11-27 | 华中科技大学 | A kind of casting technological parameter optimization method based on casting defect prediction model |
| CN108918657A (en) * | 2018-07-24 | 2018-11-30 | 广东工业大学 | A kind of workpiece, defect detection system |
| CN109934821A (en) * | 2019-03-22 | 2019-06-25 | 杭州睿工科技有限公司 | A kind of part defect detection method and system |
| CN213180110U (en) * | 2020-07-14 | 2021-05-11 | 江苏金陵交运集团德立信供应链管理有限公司 | Automatic detection equipment for automobile spare and accessory parts |
| CN113361958A (en) * | 2021-06-30 | 2021-09-07 | 李炳集 | Defect early warning method and system |
| CN114881425A (en) * | 2022-04-18 | 2022-08-09 | 天津玉昆模具有限公司 | Method and device for monitoring production in real time, electronic equipment and medium |
| CN115496892A (en) * | 2022-11-07 | 2022-12-20 | 合肥中科类脑智能技术有限公司 | Industrial defect detection method and device, electronic equipment and storage medium |
| CN115866502A (en) * | 2022-10-18 | 2023-03-28 | 电子科技大学长三角研究院(湖州) | Microphone part surface defect online detection process |
| CN115856250A (en) * | 2022-12-21 | 2023-03-28 | 株洲新科硬质合金有限公司 | Method for detecting internal defects of hard alloy extruded blank |
| CN116618639A (en) * | 2023-06-05 | 2023-08-22 | 合肥南方汽车零部件有限公司 | Monitoring system with quality detection function for automobile part casting machine |
| CN116805311A (en) * | 2023-08-18 | 2023-09-26 | 长春师范大学 | Automobile part surface defect monitoring method based on robot vision |
| CN116977241A (en) * | 2022-04-18 | 2023-10-31 | 华晨宝马汽车有限公司 | Method, apparatus, computer readable storage medium and computer program product for detecting defects in a vehicle component |
| CN117030724A (en) * | 2023-10-09 | 2023-11-10 | 诺比侃人工智能科技(成都)股份有限公司 | Multi-mode industrial defect analysis method and system based on deep learning |
-
2023
- 2023-11-14 CN CN202311509665.0A patent/CN117252486B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246369A (en) * | 2008-03-18 | 2008-08-20 | 东华大学 | Vehicle element size quality control system and method |
| CN103808734A (en) * | 2014-03-07 | 2014-05-21 | 上海齐宏检测技术有限公司 | Full-automatic detection device of automobile parts |
| CN108897925A (en) * | 2018-06-11 | 2018-11-27 | 华中科技大学 | A kind of casting technological parameter optimization method based on casting defect prediction model |
| CN108918657A (en) * | 2018-07-24 | 2018-11-30 | 广东工业大学 | A kind of workpiece, defect detection system |
| CN109934821A (en) * | 2019-03-22 | 2019-06-25 | 杭州睿工科技有限公司 | A kind of part defect detection method and system |
| CN213180110U (en) * | 2020-07-14 | 2021-05-11 | 江苏金陵交运集团德立信供应链管理有限公司 | Automatic detection equipment for automobile spare and accessory parts |
| CN113361958A (en) * | 2021-06-30 | 2021-09-07 | 李炳集 | Defect early warning method and system |
| CN114881425A (en) * | 2022-04-18 | 2022-08-09 | 天津玉昆模具有限公司 | Method and device for monitoring production in real time, electronic equipment and medium |
| CN116977241A (en) * | 2022-04-18 | 2023-10-31 | 华晨宝马汽车有限公司 | Method, apparatus, computer readable storage medium and computer program product for detecting defects in a vehicle component |
| CN115866502A (en) * | 2022-10-18 | 2023-03-28 | 电子科技大学长三角研究院(湖州) | Microphone part surface defect online detection process |
| CN115496892A (en) * | 2022-11-07 | 2022-12-20 | 合肥中科类脑智能技术有限公司 | Industrial defect detection method and device, electronic equipment and storage medium |
| CN115856250A (en) * | 2022-12-21 | 2023-03-28 | 株洲新科硬质合金有限公司 | Method for detecting internal defects of hard alloy extruded blank |
| CN116618639A (en) * | 2023-06-05 | 2023-08-22 | 合肥南方汽车零部件有限公司 | Monitoring system with quality detection function for automobile part casting machine |
| CN116805311A (en) * | 2023-08-18 | 2023-09-26 | 长春师范大学 | Automobile part surface defect monitoring method based on robot vision |
| CN117030724A (en) * | 2023-10-09 | 2023-11-10 | 诺比侃人工智能科技(成都)股份有限公司 | Multi-mode industrial defect analysis method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117252486B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11836967B2 (en) | Method and device for small sample defect classification and computing equipment | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| US20220076404A1 (en) | Defect management apparatus, method and non-transitory computer readable medium | |
| CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
| CN108393744B (en) | Multi-sensing monitoring method for cutter state | |
| CN117252486B (en) | Automobile part defect detection method and system based on Internet of things | |
| CN114565314A (en) | Hot rolled steel coil end face quality control system and method based on digital twinning | |
| KR20220046824A (en) | Inspection method for welding portion in lithium secondary battery | |
| CN111738991A (en) | Method for creating digital ray detection model of weld defects | |
| CN116339262A (en) | Numerical control processing production quality monitoring system based on artificial intelligence | |
| US20240169510A1 (en) | Surface defect detection model training method, and surface defect detection method and system | |
| TWI777307B (en) | Method, computer program, and computer readable medium of using electroluminescence images to identify defect of solar cell based on deep learning technology | |
| CN109063218A (en) | A kind of control method and system of statistic processes | |
| CN114897863A (en) | Defect detection method, device and equipment | |
| CN111257422B (en) | Wheel axle defect identification model construction method and defect identification method based on machine vision | |
| CN116977241A (en) | Method, apparatus, computer readable storage medium and computer program product for detecting defects in a vehicle component | |
| CN108133261B (en) | Automobile rubber hose mandrel quality evaluation method based on BP neural network | |
| CN114637893A (en) | FMEA database system and processing method thereof | |
| CN117741090B (en) | Quality defect detection method for precision casting of gearbox | |
| CN111724352B (en) | Patch LED flaw labeling method based on kernel density estimation | |
| CN116611850B (en) | System for detecting and tracing engine assembly quality curve | |
| TWI745767B (en) | Optical inspection secondary image classification method | |
| CN111551552B (en) | Appearance quality detection method for round hole punching net | |
| CN117250209B (en) | Automatic optical screening image processing system and method for pipeline connecting ring | |
| CN116433194B (en) | Centralized area management informatization system for railway tunnel steel member processing |
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 |