CN113042397A - System for real wood appearance detection - Google Patents

System for real wood appearance detection Download PDF

Info

Publication number
CN113042397A
CN113042397A CN202110264932.7A CN202110264932A CN113042397A CN 113042397 A CN113042397 A CN 113042397A CN 202110264932 A CN202110264932 A CN 202110264932A CN 113042397 A CN113042397 A CN 113042397A
Authority
CN
China
Prior art keywords
real wood
module
real
transmitted
appearance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110264932.7A
Other languages
Chinese (zh)
Inventor
葛石磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ningbo Siyu Intelligent Technology Co ltd
Original Assignee
Ningbo Siyu Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo Siyu Intelligent Technology Co ltd filed Critical Ningbo Siyu Intelligent Technology Co ltd
Priority to CN202110264932.7A priority Critical patent/CN113042397A/en
Publication of CN113042397A publication Critical patent/CN113042397A/en
Pending legal-status Critical Current

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B07SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34Sorting according to other particular properties
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B07SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/36Sorting apparatus characterised by the means used for distribution
    • B07C5/361Processing or control devices therefor, e.g. escort memory
    • B07C5/362Separating or distributor mechanisms

Abstract

The invention provides a real wood appearance detection system, which comprises: the system comprises a visual identification module, a production system, a data acquisition module, an AI identification module, an algorithm tool module, a terminal processor and a storage module, wherein the visual identification module is used for preliminarily identifying real wood through vision and removing unqualified real wood; the method comprises the steps that qualified real wood is transmitted to a data acquisition module through a first conveying device, detection data of the real wood are acquired through the data acquisition module and transmitted to an AI identification module, the detection data are transmitted to an algorithm tool module through the AI identification module and then transmitted to a terminal processor, and the terminal processor feeds back a production system through the detection data.

Description

System for real wood appearance detection
Technical Field
The invention relates to the field of appearance detection, in particular to a real wood appearance detection system.
Background
Along with the vigorous development of electric vehicles, the luxury of the interior of the electric vehicle also becomes higher and higher, the appearance requirement of interior trim parts also becomes stricter, the requirement on interior trim parts of real wood is more and more increased, the appearance detection of the real wood becomes imperative, but the existing real wood appearance detection generally directly passes through visual identification, needs to be identified one by one through workers, and is time-consuming, labor-consuming, high in labor cost and poor in identification effect.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a real wood appearance detection system, which aims to achieve the purposes of good real wood appearance detection effect, high speed and low cost.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a system for the visual inspection of real wood comprising: visual identification module, production system, data acquisition module, AI identification module, algorithm tool module, terminal processor, storage module, operation module, login module, wherein, production system includes: a first conveying device and a second conveying device; the visual identification module is used for carrying out primary identification on real wood through visual sense and rejecting unqualified real wood; the qualified real wood is transmitted to the data acquisition module through the first conveying device, the detection data of the real wood is acquired through the data acquisition module and transmitted to the AI identification module for AI identification, the detection data is transmitted to the algorithm tool module through the AI identification module, the detection data is processed through the algorithm tool module and then transmitted to the terminal processor, the terminal processor feeds back the production system through the detection data, when the real wood is unqualified, the real wood is transmitted away through the second conveying device, and when the real wood is qualified, the real wood is transmitted through the second conveying device; the terminal processor is respectively connected with the operation module and the login module.
Preferably, the first conveying device further comprises: and the turnover device is used for overturning the real wood, a scaling device is further arranged in the turnover device, and the scaling device loosens and places the unqualified real wood on the second conveying device.
Further illustratively, the data collection module includes: the camera is arranged at the upper end of the turnover device, and the distance sensor is arranged at the upper end of the turnover device and positioned on the outer layer of the camera.
Further, the camera is used for collecting image data of the real wood, and the distance sensor is used for collecting the size of the real wood.
Further, the algorithm tool module receives the image data, processes the image data in real time to generate a preprocessed image, and sends the preprocessed image to the terminal processor.
Preferably, the storage module adopts a distributed real-time database and stores the data in a block chain manner.
Further, the operation module is used for manually operating the turnover device and the scaling device.
Preferably, the login module includes: face recognition login, short message login, password login and fingerprint login.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention adopts the traditional vision method and AI algorithm mode to comprehensively detect the product, ensures that the defect appearance can be well presented on the image through professional light path design, and ensures that the algorithm can stably identify defective parts.
2. The production system adopts the combination of the first conveying device, the second conveying device and the turnover device, the unqualified real wood veneers and real wood are conveyed away by the second conveying device, the real wood veneers and the real wood are turned over by the turnover device, and then all-dimensional image and size acquisition is carried out by the data acquisition module to detect whether the real wood veneers and the real wood are qualified or not.
3. The storage module of the invention stores the data in a distributed and block chain mode, thereby ensuring the safety of the data.
Drawings
Fig. 1 is a schematic flow chart of a system for detecting the appearance of a real wood according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments. In the following description, characteristic details such as specific configurations and components are provided only to help the embodiments of the present invention be fully understood. Thus, it will be apparent to those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may be determined from a and/or other information.
With reference to fig. 1, the present invention provides a system for detecting the appearance of a real wood, which includes: visual identification module, production system, data acquisition module, AI identification module, algorithm tool module, terminal processor, storage module, operation module, login module, wherein, production system includes: the visual recognition module is used for preliminarily recognizing real wood through artificial vision, selecting unqualified real wood, eliminating damaged and dirty real wood with larger scratch and size difference, transmitting the qualified real wood to the data acquisition module through the first conveying device, acquiring detection data of the real wood through the data acquisition module and transmitting the detection data to the AI recognition module for AI recognition, and preliminarily recognizing the acquired detection data through the AI recognition and classifying the detection data; the detection data are transmitted to the algorithm tool module through the AI identification module, the detection data are processed through the algorithm tool module and then transmitted to the terminal processor, the algorithm tool module adopts a light path design algorithm, the terminal processor feeds back a production system through the detection data, when the real wood is unqualified, the real wood is transmitted away through the second conveying device, and when the real wood is qualified, the real wood is transmitted through the first conveying device.
Further, the terminal processor is connected to the operation module and the login module, respectively.
Further illustratively, the first conveyor further comprises: the overturning device is also internally provided with a scaling device; the data acquisition module includes: the camera is arranged at the upper end of the turnover device, and the distance sensor is arranged at the upper end of the turnover device and is positioned on the outer layer of the camera.
In one embodiment, the turning device is used for turning the real wood, and the scaling device arranged in the turning device is used for loosening and placing unqualified real wood on the second conveying device. When the true wood transports to turning device through first conveyor, carry out the image shooting to the true wood through the camera, whether carry out the outward appearance to the true wood through distance sensor and detect the damage, whether have the mar, whether the size meets the requirements, when the true wood simultaneously passes through the camera, distance sensor obtains corresponding inspection data, through turning device, overturn the true wood, and repeat above-mentioned step, six faces all pass through the camera with the true wood, distance sensor acquires corresponding detected data, when the true wood meets the requirements, through first conveyor transmission, when the true wood does not meet the requirements, through the device that contracts true wood, transmit to second conveyor, and transmit away unqualified true wood through second conveyor.
Further, the camera is used for collecting image data of the real wood, and the distance sensor is used for collecting the size of the real wood.
Further, the algorithm tool module receives the image data, processes the image data in real time to generate a preprocessed image, and sends the preprocessed image to the terminal processor.
In one embodiment, the storage module adopts a distributed real-time database and stores the data in a block chain manner, and the distributed real-time database can update the data in real time on one hand, and can keep the detected data secret and not easy to lose on the other hand through the block chain distributed storage.
Further, the operation module is used for manually operating the turning device and the scaling device, and when the automatic processing in the terminal processor fails, the turning device and the scaling device can be controlled through the operation module, so that the production system is prevented from being suspended due to the damage of the terminal processor.
Preferably, the login module comprises: the face recognition login, the short message login, the password login and the fingerprint login adopt various login modes, can adapt to various conditions, and prevent the problem that the staff forgets a certain login mode to cause login incapability.
Example 1
When appearance detection is needed to be carried out on real wood veneers, whether the surfaces of the real wood veneers are damaged or not, whether the real wood veneers are dirty or not, whether scratches exist or not, the quantity of textures of the real wood veneers, the directions of the textures and other appearance defects are checked, firstly, the obviously unqualified real wood veneers are removed through visual detection, the real wood veneers are conveyed to a turnover device through a first conveying device, the images of the real wood veneers are shot through a camera, whether the real wood veneers are damaged or not, whether scratches exist or not and whether the sizes meet the requirements or not are detected through an appearance of a distance sensor, collected detection data are transmitted to an AI recognition module for AI recognition, and the AI recognition carries out; the detection data are transmitted to the algorithm tool module through the AI identification module, the detection data are processed through the algorithm tool module and then transmitted to the terminal processor, the terminal processor feeds back the production system through the detection data, when the real wood veneer is unqualified, the real wood veneer is transmitted away through the second conveying device, and when the real wood veneer is qualified, the real wood veneer is transmitted through the first conveying device.
Example 2
When appearance detection is needed to be carried out on real wood, whether the surface of the real wood is damaged or not, whether the real wood is dirty or not, whether scratches exist or not, the number of grains of the real wood, the direction of the grains and other appearance defects are checked, firstly, the obviously unqualified real wood is removed through visual detection, the real wood is conveyed to a turnover device through a first conveying device, the real wood is subjected to image shooting through a camera, whether the appearance detection is damaged or not, whether scratches exist or not and whether the size meets the requirements or not are carried out through a distance sensor, the collected detection data are transmitted to an AI recognition module for AI recognition, and the AI recognition carries out primary recognition on the collected detection data and carries out classification; the detection data are transmitted to the algorithm tool module through the AI identification module, the detection data are processed through the algorithm tool module and then transmitted to the terminal processor, the terminal processor feeds back the production system through the detection data, when the real wood is unqualified, the real wood is transmitted away through the second conveying device, and when the real wood is qualified, the real wood is transmitted through the first conveying device.
Example 3
After injection molding of real wood, detecting whether plastic films on the surfaces of the real wood are adhered or not, detecting whether flash exists in an injection molding area or not, the real wood is damaged or not, and injection molding is lack of materials, firstly, removing the obviously unqualified real wood through visual detection, conveying the real wood to a turnover device through a first conveying device, shooting images of the real wood through a camera, carrying out appearance detection through a distance sensor to determine whether the real wood is damaged or not, whether scratches exist or not, and whether the size meets the requirements or not, transmitting collected detection data to an AI recognition module for AI recognition, and carrying out primary recognition on the collected detection data through AI recognition and classifying; the detection data are transmitted to the algorithm tool module through the AI identification module, the detection data are processed through the algorithm tool module and then transmitted to the terminal processor, the terminal processor feeds back the production system through the detection data, when the real wood is unqualified, the real wood is transmitted away through the second conveying device, and when the real wood is qualified, the real wood is transmitted through the first conveying device.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the invention has been described in detail with reference to the foregoing illustrative embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. A system for detecting the appearance of real wood is characterized by comprising: visual identification module, production system, data acquisition module, AI identification module, algorithm tool module, terminal processor, storage module, operation module, login module, wherein, production system includes: a first conveying device and a second conveying device; the visual identification module is used for carrying out primary identification on real wood through visual sense and rejecting unqualified real wood; the qualified real wood is transmitted to the data acquisition module through the first conveying device, the detection data of the real wood is acquired through the data acquisition module and transmitted to the AI identification module for AI identification, the detection data is transmitted to the algorithm tool module through the AI identification module, the detection data is processed through the algorithm tool module and then transmitted to the terminal processor, the terminal processor feeds back the production system through the detection data, when the real wood is unqualified, the real wood is transmitted away through the second conveying device, and when the real wood is qualified, the real wood is transmitted through the second conveying device; the terminal processor is respectively connected with the operation module and the login module.
2. A system for detecting the appearance of a real wood according to claim 1, wherein said first conveying means further comprises: and the turnover device is used for overturning the real wood, a scaling device is further arranged in the turnover device, and the scaling device loosens and places the unqualified real wood on the second conveying device.
3. A system for detecting the appearance of a real wood according to claim 2, wherein the data acquisition module comprises: the camera is arranged at the upper end of the turnover device, and the distance sensor is arranged at the upper end of the turnover device and positioned on the outer layer of the camera.
4. A system for detecting the appearance of real wood according to claim 3, wherein said camera is used for collecting image data of said real wood, and said distance sensor is used for collecting the size of said real wood.
5. A system for detecting the appearance of a real wood according to claim 4, wherein the algorithm tool module receives the image data, processes the image data in real time to generate a preprocessed image, and sends the preprocessed image to the terminal processor.
6. A real wood appearance detection system according to claim 1, wherein the storage module employs a distributed real-time database and stores the real wood in a block chain manner.
7. A system for detecting the appearance of a real wood according to claim 2, wherein the operation module is used for manually operating the turning device and the scaling device.
8. A system for detecting the appearance of a real wood according to claim 1, wherein the log-in module comprises: face recognition login, short message login, password login and fingerprint login.
CN202110264932.7A 2021-03-11 2021-03-11 System for real wood appearance detection Pending CN113042397A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110264932.7A CN113042397A (en) 2021-03-11 2021-03-11 System for real wood appearance detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110264932.7A CN113042397A (en) 2021-03-11 2021-03-11 System for real wood appearance detection

Publications (1)

Publication Number Publication Date
CN113042397A true CN113042397A (en) 2021-06-29

Family

ID=76511384

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110264932.7A Pending CN113042397A (en) 2021-03-11 2021-03-11 System for real wood appearance detection

Country Status (1)

Country Link
CN (1) CN113042397A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104690007A (en) * 2015-02-10 2015-06-10 浙江集英工业智能机器技术有限公司 Human-machine combined magnetic core on-line detection system and detection method
CN105728339A (en) * 2016-02-05 2016-07-06 湖北工业大学 Visual automatic detecting system for ceramic cartridge
CN110403232A (en) * 2019-07-24 2019-11-05 浙江中烟工业有限责任公司 A kind of cigarette quality detection method based on second level algorithm
CN110479637A (en) * 2019-07-26 2019-11-22 温州职业技术学院 A kind of front and back sides appearance detection of microswitch and screening system
CN112268910A (en) * 2020-11-13 2021-01-26 上海奇信机电设备有限公司 Visual detection system and method for cigarette appearance defects

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104690007A (en) * 2015-02-10 2015-06-10 浙江集英工业智能机器技术有限公司 Human-machine combined magnetic core on-line detection system and detection method
CN105728339A (en) * 2016-02-05 2016-07-06 湖北工业大学 Visual automatic detecting system for ceramic cartridge
CN110403232A (en) * 2019-07-24 2019-11-05 浙江中烟工业有限责任公司 A kind of cigarette quality detection method based on second level algorithm
CN110479637A (en) * 2019-07-26 2019-11-22 温州职业技术学院 A kind of front and back sides appearance detection of microswitch and screening system
CN112268910A (en) * 2020-11-13 2021-01-26 上海奇信机电设备有限公司 Visual detection system and method for cigarette appearance defects

Similar Documents

Publication Publication Date Title
CN109724984B (en) Defect detection and identification device and method based on deep learning algorithm
CN101995223B (en) Chip appearance detection method and system
CN104608799A (en) Information fusion technology based train wheel set tread damage online detection and recognition method
CN105158268A (en) Intelligent online detection method, system and device for defects of fine-blanked parts
CN101819162A (en) Empty bottle wall defect detection method and device
CN105728339B (en) A kind of ceramic cartridge vision automatic checkout system
CN106383121B (en) It is a kind of can adaptive multi-brand visible detection method and system
CN201689063U (en) Empty bottle wall defect inspection device
CN109815856A (en) Status indication method, system and the computer readable storage medium of target vehicle
CN105403147A (en) Embedded bottle pre-form detection system and detection method
CN110610475B (en) Visual defect detection method of deep convolutional neural network
CN104297255A (en) Visual inspection method and system device for paper cup defects
CN201890600U (en) Machine vision belt tearing detecting device
CN112452801A (en) High-efficiency online detection device for defects of glass bottles and working method thereof
CN110220917A (en) A kind of crown plug surface defect online test method based on image procossing
KR101643713B1 (en) Method for inspecting of product using learning type smart camera
CN107121063A (en) The method for detecting workpiece
CN113042397A (en) System for real wood appearance detection
CN111189837A (en) Cigarette appearance online detection method and device
CN114359155A (en) Film laminating method and system
CN105973903B (en) A kind of Oral liquid bottle lid detection method
CN111307817B (en) Online detection method and system for PCB production process of intelligent production line
CN111551559A (en) LCD (liquid Crystal display) liquid crystal screen defect detection method based on multi-view vision system
CN105548210A (en) Detection method for American-standard power source extension wire based on machine vision
CN110756457A (en) Automatic wall and floor tile identifying and classifying system and method

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