1 Introduction to machine vision
This article refers to the address: http://
Machine vision is to use the machine instead of the human eye to make measurements and judgments. Machine vision system refers to the conversion of the ingested target into an image signal by machine vision products (ie, image capture device, divided into CMOS and CCD), and transmitted to a dedicated image processing system, which is transformed according to pixel distribution, brightness, color, and the like. Digital signals; the image system performs various operations on these signals to extract the characteristics of the target, and then controls the device actions in the field according to the comparison result.
People use machine vision systems to improve the quality of the products produced and the automation of the production line, especially in dangerous working environments that are not suitable for manual work or where the human eye is difficult to meet the requirements. At the same time, in the mass industrial production process, labor is used. Visual inspection products are low in quality and low in precision, and machine vision inspection methods can greatly improve production efficiency and automation of production. Moreover, machine vision is easy to realize information integration, and is the basic technology to realize computer integrated manufacturing. The disciplines associated with machine vision include image processing, computer graphics, pattern recognition, artificial intelligence, artificial neural networks, and the like.
2 Siemens Machine Vision System
The Siemens Machine Vision System is an embedded vision system that is divided into the VS100 series and the VS700 series. The VS100 series is a dedicated vision product and the SIMATIC VS 100 series vision system is used for specific image processing tasks. SIMATIC VS 110 is used for contour detection; SIMATIC VS 120 is used for target search and search; SIMATIC VS 130 is suitable for detection of two-dimensional codes.
The SIMATIC VS 700 Series universal vision system is mainly used for quality inspection and quality control in the production process. This versatile system can be programmed to perform functions such as image acquisition, image processing, load drive, and network communication (via PROFIBUS or Industrial Ethernet), making it ideal for many test tasks in a single test cycle. The new VS720 line is designed to handle more complex tasks such as image capture, image processing, final result generation and communication in a compact process, ideal for several inspection tasks in a single inspection cycle. .
The VS721 CMOS and VS722 basic models represent a more economical solution for a large number of routine tasks. The VS721 with CMOS camera is especially suitable for occasions where the accuracy requirements are not very high and the price is relatively economical. The VS723 is a camera for high-speed photography, such as in the field of packaging technology, and in many areas where performance testing tasks need to be performed, such as surface inspection. The VS724 is a high-resolution sensor that provides up to 1.3 megapixels for very detailed images, making it ideal for high-precision inspection tasks. The VS725 color sensor system has the ability to analyze color and detect specific color values, so you can safely and reliably distinguish parts by color code, detect the color of the label, or identify the beads.
The sensors in the VS720 series offer an integrated Ethernet interface and eight freely configurable digital inputs and outputs. The camera can be easily connected to the network via Ethernet and accessed by almost any PC, greatly simplifying maintenance and diagnostics. The VS link interface module can display images taken by several cameras on a single monitor. It can also be connected to the connection module via PROFIBUS, which eliminates the need for additional PCs for monitoring functions. Moreover, the bandwidth provided by Industrial Ethernet enables quality data and faulty images to be quickly backed up on external devices.
As a configuration software for the VS720 series of sensors, SPECTATION offers a variety of detection function algorithms to create a custom image processing solution through a very user-friendly interface. When no visual sensor is connected online, the simulator can also be used for configuration.
3 Process Description
In the assembly workshop of a new automobile engine joint venture production plant, in order to ensure product quality, it was decided to adopt VS722 to realize the automatic detection of the engine cylinder number marking quality and the visual inspection after the engine assembly was completed.
3.1 cylinder block number checking station
The cylinder check number checking station is located behind the cylinder label marking station. The main function is to check the quality and number of the cylinder label by VS722. There are two series of cylinders: FR (face on the left) and FF (on the right) series. There are 97 different models. In this station, the system needs to automatically read the model of the cylinder to be tested. Compare.
3.2 Engine appearance inspection station after assembly
The engine visual inspection station is located at the end of the outer cable. After the engine is assembled, the five VS722 sensors are used to take photos from the top and left and right sides. Two sensors are installed on the left and right sides. After the workpiece enters the station, the workpiece passes. Positioning up first performs signal recognition, then starts taking pictures, then rotates 90 degrees to take pictures again. This ensures that the engine can be inspected in both the front, rear, left and right directions.
There are a total of 97 types of engines. The inspection items for each type of engine are: whether the drain plug is missing, whether the engine hook is missing, whether the oil dip is missing, the ventilation hose is missing, the outlet connector is misplaced, and the heat shield is Whether the bolt is missing, whether the oil cooling hose is missing, whether the oxygen sensor is mis-installed (black or gray wire harness).
4 system working principle
4.1 Data communication between VS722 and PLC
There are three ways to transfer data between the vision sensor VS722 and the PLC:
VS722 provides 8DI/DO hardware interface, which can be connected with PLC hardware to realize camera triggering instructions, and the result returns simple data transfer.
Simple communication between VS722 and PLC via PROFIBUS or Ethernet. This communication method uses the standard communication function block FC72, which can realize 28K bytes communication through VS LINK with PROFIBUS bus, and can realize 60K byte communication through Ethernet. . In this application, communication between VS722 and PLC is achieved in this way.
If the data communication requirements are higher, you can choose enhanced communication. You can use background script to map virtual I/O through PROFIBUS. If you want to use Ethernet to implement enhanced data communication, you can choose two driving modes: system/data. Connect driver and background script triggers.
In short, the communication method provided by VS722 is very flexible and convenient. In practical applications, the appropriate communication method should be selected according to the actual situation such as data communication volume, real-time feedback speed requirement and project cost.
4.2 Identification of the cylinder number
The cylinder inspection control system consists of the main control PLC, VS722, ELS, TP170B and RFID read/write recognition system. The information transmission of VS722 and PLC is realized by Ethernet.
The cylinder entering the station carries the M/P memory card, and the cylinder number information is stored in the card. The PLC reads the number information from the memory card through the serial port by using the RFID reader, and displays it on the touch screen TP170B. The PLC judges that it is necessary to activate the left or right sensor to take a photo by reading the number information, and displays the physical image of the photograph, and the VS722 performs character recognition immediately after the photograph is completed.
In order to realize the identification of the number, it is necessary to program in the SPECTATION software, create a PRODUCT download to the VS722, and define 16 OCR soft sensors in the PRODUCT.
4.3 Implementation of mis-installation of engine components
The engine visual inspection station consists of a master PLC (CPU313-PtP), VS722, ELS and a user-specified OMRON RFID read/write system. The information transmission of VS722 and PLC is realized by Ethernet. The upper software of the monitoring computer uses WINCC.
The engine workpiece enters the station, the positioning is lifted up and the position is taken, and each sensor is compared to check different parts. If it is found that the workpiece is different from the standard image, an alarm will be issued, and the picture corresponding to the unqualified item will be automatically popped up on the WINCC screen. Since the image display screen captured by the VS722 has been integrated into the WINCC software, if a non-conformity item is generated, the real-time screen will be automatically captured, and the operator will perform final check confirmation based on the screen or the physical object.
For the inspection of misplaced parts of engine components, SPECTATION provides the following soft sensors, Feature Count, Edge Count, Object Find, Template Match, and Math Tools. ). For different inspection sites, select appropriate soft sensors for detection according to different image features.
5 Conclusion
During the implementation of this project, we deeply realized that if you want to make the machine vision system work best, there are three basic elements: choosing the right light source, designing the ideal mechanical structure, and correcting the visual sensor. Programming.
Before the VS722 is used in the engine production line, all relevant inspections need to be set up by the naked eye of the worker. Due to the heavy workload and boring content, it is very prone to human error and missed judgment. The incident once caused a large negative image to the user. After adopting the Siemens machine vision system, the relevant manual positions were cancelled, which greatly improved the work efficiency, ensured the quality of the products, and achieved good economic and social benefits.
Kitchen Exhaust Hood,Gas Hob 4 Burner,Stainless Steel Gas Hob,4 Burner Gas Cooker Hob
Xunda Science & Technology Group Co.ltd , https://www.xundatec.com