CN114136992A - Novel real-time online detection system and method for surface defects of strip steel - Google Patents

Novel real-time online detection system and method for surface defects of strip steel Download PDF

Info

Publication number
CN114136992A
CN114136992A CN202111414357.0A CN202111414357A CN114136992A CN 114136992 A CN114136992 A CN 114136992A CN 202111414357 A CN202111414357 A CN 202111414357A CN 114136992 A CN114136992 A CN 114136992A
Authority
CN
China
Prior art keywords
module
strip steel
production line
soc
detection
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
CN202111414357.0A
Other languages
Chinese (zh)
Inventor
蒙敏荣
成小乐
杨伟
王伟
王明亮
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.)
Shaanxi Jinzhili Electronic Technology Co ltd
Original Assignee
Shaanxi Jinzhili Electronic 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 Shaanxi Jinzhili Electronic Technology Co ltd filed Critical Shaanxi Jinzhili Electronic Technology Co ltd
Priority to CN202111414357.0A priority Critical patent/CN114136992A/en
Publication of CN114136992A publication Critical patent/CN114136992A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C3/00Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
    • G07C3/14Quality control systems
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/12Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

The invention provides a novel real-time online detection system and a method for strip steel surface defects, wherein the system comprises an LED light source module, an industrial high-speed camera module, an SOC module, a switch module and a production line monitoring center, wherein the SOC module is connected with a data storage module, an image processing defect detection module, a transmission system and an alarm module; the invention also provides a detection method of the system, and by the system, the steps of 1: the strip steel is transmitted, and the camera acquires image signals; step 2: the SOC module stores the image signal, and the image processing defect detection module detects the image signal; and step 3: and the production line monitoring center analyzes the detection result and controls the start and stop of the production line and the alarm according to the analysis result. The invention ensures the reliable acquisition, storage and processing of real-time system data; the reliability and the real-time performance of the transmission of the interactive information are improved; and the data real-time processing capacity of the system is enhanced.

Description

Novel real-time online detection system and method for surface defects of strip steel
Technical Field
The invention belongs to the technical field of industrial detection, and particularly relates to a novel real-time online detection system for surface defects of strip steel, and a novel real-time online detection method for surface defects of strip steel.
Background
Strip steel is an important product in the modern steel industry. With the continuous improvement of industrial manufacturing, the demand for strip steel is also increasing. However, as productivity increases, the demand for strip quality also increases. Hot rolling is an important step in strip steel manufacture and is widely used in strip steel manufacture in various steel mills. In the manufacturing process of hot-rolled strip steel, the defect-free surface of the strip steel is an important index for evaluating the quality of products. The surface defects of various hot-rolled strip steels seriously affect the product quality and reduce the quality of the hot-rolled strip steels. Surface defects of hot rolled steel strip include pressed scale, patches, cracks, pitting, inclusions and scratches. Various defects have complicated causes. Hot rolled strip may occur due to factors such as raw materials, rolling processes, and manufacturing environments. Various defects appear on the surface of the steel. The defects may have different shapes and may show point, line or surface defects. In the modern hot rolled strip steel production, the strip steel has high yield and high transmission speed, and the precision and the speed of detecting the surface defects of the strip steel are higher. With the development of a large number of CCD (Charge Coupled device) cameras and various machine learning methods, the detection method based on the hot-rolled strip steel surface defect picture becomes a research hotspot in the current strip steel surface defect detection field.
Disclosure of Invention
The invention aims to provide a novel real-time online detection system and method for the surface defects of strip steel, and solves the problem that the identification efficiency of the existing strip steel surface defect equipment needs to be further improved.
One technical solution adopted by the present invention is that,
the novel real-time online detection system for the surface defects of the strip steel comprises an LED light source module, an industrial high-speed camera module, an SOC module, a switch module and a production line monitoring center, wherein the SOC module is connected with a data storage module, an image processing defect detection module, a transmission system and an alarm module; wherein:
the LED light source module is used for providing a visible light source for the detected strip steel;
the industrial high-speed camera module is used for acquiring image signals of the surface of the detected strip steel;
the SOC module is used for controlling the LED light source module, the industrial high-speed camera module, the data storage module, the switch module, the image processing defect detection module, the transmission system and the alarm module;
the image processing defect detection module is used for detecting image signals acquired by the industrial high-speed camera module;
the switch module is used for transmitting the detection result processed by the image processing defect detection module to the production line monitoring center;
the production line monitoring center is used for performing man-machine interaction by using a PC (personal computer), controlling the start and stop of the system, transmitting parameters to the SOC module and receiving feedback information from the SOC module.
The present invention is also characterized in that,
the SOC module comprises a multi-core ARM sub-module, a multi-core DSP sub-module, an ISP sub-module, a GPU sub-module and a neural network sub-module.
The industrial high-speed camera module includes a number of high-speed GigE industrial cameras.
The switch module comprises a subnet switch module and a central switch module;
the sub-network switch module is used for accessing four identical sub-network switch modules for a strip steel production line, and each sub-network switch module serves a strip steel defect detection system;
the central switch module is used for accessing four subnet switch modules for one production line, and the four strip steel defect detection systems are accessed into the central switch module and transmit detection results to a production line monitoring center for production line monitoring.
The data storage system adopts 64 bitsDDR.
And the production line monitoring center and the SOC module perform information interaction through a gigabit Ethernet.
In another technical solution of the present invention,
the novel real-time online detection method for the surface defects of the strip steel comprises the following steps:
providing a novel real-time online detection system for the surface defects of the strip steel;
step 1: the transmission system and the alarm module convey the detected strip steel to a detection position, and the SOC module controls the LED light source module to irradiate the surface of the detected strip steel and controls the industrial high-speed camera module to acquire image signals;
step 2: the SOC module stores the image signal into a data storage system and transmits the image signal to an image processing defect detection module, the image processing defect detection module detects the image signal, then stores the detection result into the data storage system and waits for the next calling;
and step 3: the SOC module extracts a detection result from the data storage system and transmits the detection result to the production line monitoring center through the switch module, the production line monitoring center analyzes the detection result, if the detection result is abnormal, the production line monitoring center sends an instruction to the SOC module, and the SOC module controls the multi-core ARM sub-module to immediately stop the operation of the production line and send alarm information through the transmission system and the alarm module; if the detection result is not abnormal, the detected strip steel is conveyed out to the designated position through the transmission system.
The novel real-time online detection system for the surface defects of the strip steel has the advantages that the novel real-time online detection system for the surface defects of the strip steel is an online real-time detection system for a plurality of strip steel production lines, and aims to monitor the plurality of strip steel production lines simultaneously and ensure that the quality of strip steel products output on each strip steel production line is qualified; the high-speed GigE camera and the high-integration SOC module are integrated, and the SOC module has rich peripheral interfaces and can reliably communicate with various peripherals; the production line monitoring center and the SOC module adopt gigabit Ethernet for information interaction, which also aims to ensure that processed data results can be transmitted to the production line monitoring center in real time and improve the reliability and real-time performance of interactive information transmission.
Drawings
FIG. 1 is a schematic structural diagram of a novel real-time online detection system for surface defects of strip steel according to the present invention;
FIG. 2 is a schematic diagram showing the distribution of cameras in the novel real-time online detection system for the surface defects of the strip steel;
FIG. 3 is a schematic diagram of the positions of a light source, a camera and a strip steel in the novel strip steel surface defect real-time online detection system.
Detailed Description
The novel real-time online detection system and method for the surface defects of the strip steel are further described in detail with reference to the accompanying drawings and the detailed description.
Examples
The embodiment provides a novel real-time online detection system for surface defects of strip steel, as shown in fig. 1, the system comprises an LED light source module, an industrial high-speed camera module, an SOC module (including a multi-core ARM submodule, a multi-core DSP submodule, an ISP submodule, a GPU submodule and a neural network submodule), a switch module and a man-machine interaction production line monitoring center. The SOC module is connected with the data storage system, the image processing defect detection module, the transmission system and the alarm module.
LED light source module: providing a proper visible light source for the surface of the detected strip steel.
The surface of the strip steel to be detected is as follows: the light source acts on the surface of the strip steel to be detected, reflected light images of the surface of the strip steel are collected, and whether the surface of the strip steel has defects or not is judged according to an image recognition defect algorithm.
As shown in fig. 2, the industrial high-speed camera module: and a high-speed GigE industrial camera and a gigabit Ethernet interface are adopted to realize high-speed acquisition and high-speed remote reliable transmission of images.
An SOC module: and a highly integrated SOC system is selected, so that the size of a product can be reduced while the defect detection task of the algorithm is completed. The SOC comprises a multi-core ARM sub-module, a multi-core DSP sub-module, an ISP sub-module, a GPU sub-module and a neural network accelerator sub-module.
A multi-core ARM submodule: the initialization of a detection system, code loading, logic control, task synchronization and task scheduling are realized; and communication and control between the multi-core DSP submodule, the GPU submodule, the ISP submodule and the neural network submodule are realized. And sending alarm information to a production line monitoring center according to the operation result of the defect algorithm.
ISP submodule: and the pre-processing and post-processing of the acquired image are realized.
A multi-core DSP submodule: and realizing the real-time realization of the defect detection algorithm.
GPU sub-modules: and the multi-core DSP submodule is cooperated to realize parallelization processing and real-time realization of the defect detection algorithm.
Image processing defect detection: and the multi-core DSP sub-module, the GPU sub-module and the ISP sub-module are used for jointly completing the real-time realization of the strip steel surface detection algorithm.
A neural network accelerator submodule: the module is used for rapidly classifying the detected surface defects of the strip steel, and provides for further expansion of system functions.
And the data storage system adopts a high-bit-width DDR memory to access the ARM end to realize the caching of the input image data. The hard disk can also be mounted to be used as a large amount of data backup storage.
The transmission control and alarm module: and when the image processing defect detection module detects a defect, the multi-core ARM sub-module sends alarm information to a production line monitoring center. And after the production line monitoring center receives the alarm information, error correction processing of production line problems caused by defects is carried out, if the defects exist, the production line monitoring center sends an instruction to the SOC module, and the SOC module controls the multi-core ARM sub-module to immediately stop the operation of the production line so as to prevent unqualified products from being produced continuously in the production line and wasting resources.
Switch modules (subnet switch modules, central switch modules).
A subnet switch module: and the subnet switches are accessed into four modules which are completely the same as the hardware modules, and each subnet switch module serves a strip steel defect detection system.
A central switch module: four subnet switch modules are connected into one production line, and four strip steel defect detection systems are connected into a central switch module and transmit detection results to a production line monitoring center for production line monitoring.
Production line monitoring center: and the PC is used for carrying out man-machine interaction, controlling the start and stop of the system, carrying out parameter transmission on the SOC module and receiving feedback information from the SOC module. The production line monitoring center judges whether the defects exist according to the result information processed by the algorithm of the SOC module, thereby simultaneously monitoring and managing a plurality of production lines and ensuring that the running production lines all produce band steel with qualified quality.
The invention discloses a novel real-time online detection method for surface defects of strip steel, which comprises the following steps:
as shown in fig. 3, a strip steel to be detected is placed at a detection position, an SOC module controls an LED light source module to irradiate the surface of the strip steel, a high-speed industrial camera shoots the detection position, the shot image data is transmitted to the SOC module, the SOC module is stored in a data storage system, meanwhile, the image data is transmitted to an image processing defect detection module for processing, the result of image calculation is stored in the data storage system by means of a strip steel surface detection algorithm, the detection result is convenient for subsequent system calling, a neural network accelerator module rapidly classifies the processed detection result, and the SOC module extracts the detection result processed by the image processing defect detection module from the data storage system and transmits the detection result to a production line monitoring center by means of a subnet switch module and a center switch module. If the detection result is abnormal, the production line monitoring center sends an instruction to the SOC module, and the SOC module controls the multi-core ARM sub-module to immediately stop the operation of the production line and send alarm information by controlling the transmission system and the alarm module; if the detection result is not abnormal, the detected strip steel is transmitted to the designated position through the transmission system, and then the steps are repeated again.
The novel real-time online detection system and method for the surface defects of the strip steel ensure the reliable acquisition of real-time system data, the real-time storage of the data and the real-time processing of the acquired images of a production line; the reliability and the real-time performance of the transmission of the interactive information are improved; the time of data access is saved, the real-time data processing capacity of the system is enhanced, and reliable guarantee is provided for the real-time processing of images; the added value of the product is improved.

Claims (7)

1. The novel real-time online detection system for the surface defects of the strip steel is characterized by comprising an LED light source module, an industrial high-speed camera module, an SOC module, a switch module and a production line monitoring center, wherein the SOC module is connected with a data storage module, an image processing defect detection module, a transmission system and an alarm module; wherein:
the LED light source module is used for providing a visible light source for the detected strip steel;
the high-speed camera module is used for acquiring image signals of the surface of the detected strip steel;
the SOC module is used for controlling the LED light source module, the industrial high-speed camera module, the data storage module, the image processing defect detection module, the transmission system and the alarm module;
the image processing defect detection module is used for detecting image signals acquired by the industrial high-speed camera module;
the switch module is used for transmitting the detection result processed by the image processing defect detection module to the production line monitoring center;
the production line monitoring center is used for performing man-machine interaction by using a PC (personal computer), controlling the start and stop of the system, transmitting parameters of the SOC module and receiving feedback information from the SOC module.
2. The novel real-time online detection system for the surface defects of the strip steel according to claim 1, is characterized in that: the SOC module comprises a multi-core ARM sub-module, a multi-core DSP sub-module, an ISP sub-module, a GPU sub-module and a neural network sub-module.
3. The novel real-time online detection system for the surface defects of the strip steel according to claim 1, is characterized in that: the industrial high-speed camera module includes a number of high-speed GigE industrial cameras.
4. The novel real-time online detection system for the surface defects of the strip steel according to claim 1, is characterized in that: the switch module comprises a subnet switch module and a central switch module;
the sub-network switch modules are used for accessing the completely same sub-network switch modules and jointly serve for detecting the defects of a strip steel production line;
the central switch module is used for accessing a plurality of subnet switch modules for different production lines, accessing a plurality of production lines into the central switch, and accessing into the current production line detection center for monitoring the production line.
5. The novel real-time online detection system for the surface defects of the strip steel according to claim 1, is characterized in that: the data storage module adopts 64 bitsDDR.
6. The novel real-time online detection system for the surface defects of the strip steel according to claim 1, is characterized in that: and the production line monitoring center and the SOC module perform information interaction through a gigabit Ethernet.
7. The novel real-time online detection method for the surface defects of the strip steel is characterized by comprising the following steps of:
providing a novel real-time online detection system for the surface defects of the strip steel;
step 1: the transmission system and the alarm module convey the detected strip steel to a detection position, and the SOC module controls the LED light source module to irradiate the surface of the detected strip steel and controls the industrial high-speed camera module to acquire image signals;
step 2: the SOC module stores the image signal into a data storage system and transmits the image signal to an image processing defect detection module, the image processing defect detection module detects the image signal, then stores the detection result into the data storage system and waits for the next calling;
and step 3: the SOC module extracts a detection result from the data storage system and transmits the detection result to the production line monitoring center through the switch module, the production line monitoring center analyzes the detection result, if the detection result is abnormal, the production line monitoring center sends an instruction to the SOC module, and the SOC module controls the multi-core ARM sub-module to immediately stop the operation of the production line and send alarm information through the transmission system and the alarm module; if the detection result is not abnormal, the detected strip steel is conveyed out to the designated position through the transmission system.
CN202111414357.0A 2021-11-25 2021-11-25 Novel real-time online detection system and method for surface defects of strip steel Pending CN114136992A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111414357.0A CN114136992A (en) 2021-11-25 2021-11-25 Novel real-time online detection system and method for surface defects of strip steel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111414357.0A CN114136992A (en) 2021-11-25 2021-11-25 Novel real-time online detection system and method for surface defects of strip steel

Publications (1)

Publication Number Publication Date
CN114136992A true CN114136992A (en) 2022-03-04

Family

ID=80391908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111414357.0A Pending CN114136992A (en) 2021-11-25 2021-11-25 Novel real-time online detection system and method for surface defects of strip steel

Country Status (1)

Country Link
CN (1) CN114136992A (en)

Similar Documents

Publication Publication Date Title
CN102621156B (en) Image-processing-based automatic micro part sorting system
JP6867555B2 (en) Automated optical inspection system based on CPU + GPU + FPGA architecture
Wu et al. Design of online surface inspection system of hot rolled strips
CN104949990A (en) Online detecting method suitable for defects of woven textiles
CN105044126A (en) Visual detection system for large-width continuous surface defects
CN205538710U (en) Inductance quality automatic check out system based on machine vision
CN112179910B (en) Real-time detection processing method and system for defects of lithium battery pole piece
CN103033476A (en) Equipment and method for online detecting tobacco leaves with stems based on infrared imaging
CN104952754A (en) Coated silicon chip sorting method based on machine vision
CN103592312A (en) On-line detection method for cables on basis of machine vision
CN102539442A (en) Online visual inspection system for cold-forged product
CN106383121B (en) It is a kind of can adaptive multi-brand visible detection method and system
CN111229648A (en) Solar cell panel flaw detection system and detection method based on machine vision
CN111431986A (en) Industrial intelligent quality inspection system based on 5G and AI cloud edge cooperation
CN101807061A (en) Vision detection control system and method for integrated circuit tendon-cut system
CN202700832U (en) Dynamic identification device of inferior products in production
CN104132945A (en) On-line surface quality visual inspection device for bar based on optical fiber conduction
CN114136992A (en) Novel real-time online detection system and method for surface defects of strip steel
CN201681051U (en) Visual detecting system for chip encapsulating and forming quality of integrated circuit
CN209156466U (en) A kind of SSD hard disk discharging device
CN108548822A (en) A kind of wide cut continuous surface defective vision detecting system
CN202351182U (en) Online high-speed detection system for defects on surface of tinplate
CN111948228A (en) Industrial production line overall process visual detection system based on 5G communication cloud test
CN110866901A (en) Quality inspection method and system based on edge computing technology
CN203164738U (en) Machine vision control system based on cloud computing

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