Request for quotation
Get your solutions for steel industry machine vision system
Billets, hot coils, cold coils, ultra-thin plates, special rods, profiles, belts, tobacco
Such as video particle size analyzer, foam analyzer (flotation, reverse flotation), billet slab volume detection
Such as video cut-to-length, continuous billet length and width measurement, billet cross-section measurement
Such as license plate, billet number, roll number recognition, high-line PF hook number recognition, packaging (milk, cigarette case) character recognition
Such as steel billet or round steel, quantity of cigarettes, counting and dividing system; speed measurement, such as video speed detection, belt speed (stall, slip)
Such as video positioning, video centering, video displacement, visual behavior and dangerous area detection, status detection of sintering trolley, unmanned rear of cooling bed, that is, AI automatic chain bed project
Such as video grayscale conversion temperature, such as furnace top TV, tuyere TV, rotary kiln temperature, slag detection, temperature field distribution (steel billet temperature analysis), flame temperature, converter slag detection system, tuyere thermal imaging temperature measurement, sintering machine Tail section (analysis of red burning layer), hot metal tank number and tank leakage risk AI identification system, etc.
Blast furnace tuyere platform intelligent inspection robot, power distribution room, substation inspection robot
Focusing on visual system solutions for the metallurgical industry, we have a core R&D team and property rights algorithms for measurement, detection, identification, positioning, and deep learning
Adopt machine vision and computer automatic counting technology, increases the speed and precision rate of steel bar counting.
Long-term measurement error of casting powder addition ≤ 5%. The casting powder covers the liquid steel surface evenly, and there is no blind spot.
The machine adopts a high-energy laser printing way, with no post-processing consumables. and it has an independent cooling circulation system. The marking speed is fast, and the number will never fall off (even if scratched).
With machine vision as the core, DBM can provide intelligent equipment R&D, manufacturing and transformation services such as unmanned factories in the metallurgical industry and other industries, machine vision, and robot application design.
Tell us your needs and a technician will contact you immediately.
Machine vision technology has the advantages of non-contact measurement, intuitive, intelligent, and easy remote operation.
In the iron and steel industry, there are a large number of high-temperature, toxic and other dangerous working environments that are not suitable for manual work, such as the monitoring of the steel flow in the converter and the safety inspection of the piston in the gas cabinet. There are also many traditional methods that cannot realize automatic operation and rely on human eyes. Look at jobs that do a lot of repetitive operations. These situations are ideal for applying machine vision technology to increase production efficiency and automation.
Therefore, DBM has developed the key technology of machine vision in the iron and steel industry to solve the production process automation problem under complex and harsh working conditions in the iron and steel industry.
The steel industry machine vision system is mainly composed of cameras, image processing systems, sensors and control systems. According to the principle of optical detection, the machine vision system uses a camera to convert the detected target into a 2D or 3D image signal and transmits it to a dedicated image processing system. The image processing system processes these signals based on information such as pixel distribution, brightness, colour, and coordinates. Various operations are used to extract the characteristics of the target, and then use statistical or self-learning algorithms and combine process production conditions to output analysis results, such as offset, curvature, number, pass/fail, presence/absence, etc. The final control system integrates the results of other sensors and image processing, makes the optimal operation decision according to the current process production status, and controls the execution equipment to complete the corresponding actions.
The steel industry machine vision technology developed by DBM realizes industrial automation and the intelligent process by taking pictures of industrial production scenes with cameras instead of manual observation. Basic technologies such as image reconstruction, image classification, edge extraction, object detection, image segmentation, and neural network algorithms are integrated with steel production experience and process knowledge.
1) Non-contact detection, long service life of equipment;
2) Simulate human visual inspection and intuitive operation;
3) The equipment is cheap, easy to install and less investment;
4) The technical framework is fixed, mainly relying on algorithms and software to realize different process functions, which is easy to transplant.
The steel rolling heating furnace occupies an important position in the iron and steel enterprises. Its task is to heat the steel slab so that the temperature and temperature distribution of the steel slab meet the rolling requirements. The heating furnace feeding device is a device for transporting billets to the heating furnace. It is mainly composed of a feeding platform, a steel retaining hook, a steel fork and a conveying roller. Put it on the loading platform, and then the stepping drive device of the loading platform and the steel retaining hook cooperate with the production rhythm of the heating furnace to transport the billets one by one to the steel fork, and the steel fork places the steel billet Above the conveying roller table, the roller table then runs to send the billet to the heating furnace.
At present, the automatic feeding of the billet from the roller table to the furnace is mainly realized by installing metal detection elements on both sides of the roller table, but the transportation process of the billet from the loading table to the roller table needs to be observed by human eyes. After shifting the state of the steel fork, manually operate the driving device of the feeding table to transport the billets to the shifting fork one by one. The hot billet is deformed due to uneven cooling. The whole operation process is mechanical and boring. Manual long-term operation is prone to fatigue, causing operation errors and failures.
In order to solve the problem of automatic loading of heating furnaces, DBM has developed a heating furnace feeding system based on image recognition and positioning technology. The system sets up multiple high-definition cameras in the area of the loading platform, uses the latest image analysis technology to calculate the position and state of the billet, and simulates the manual loading steps to drive the loading platform, the steel retaining hook, and the furnace. Roller table and other equipment to realize the conveying of billets. The system can be applied to various types of heating furnaces, including pusher type, roller type, bench type, etc.
The strip steel surface quality inspection system can detect the strip steel surface quality online, eliminating the need for manual inspection steps in the later uncoiling. The system uses a high-speed camera to capture moving strip surface images, uses a dynamic threshold segmentation algorithm to extract defect images on the strip surface, uses a feature extraction algorithm to analyze defect features, and establishes a classification library for various defects. When the number of defects accumulated in the defect library reaches a certain scale, the convolutional neural network can be used to train the defect classification model, which can be used for grading judgment of strip steel.
The system can greatly reduce the workload of manually determining defects, save labour costs, and improve the production process according to the defects.
When the crane is loading materials to the heating furnace loading platform, the platform should stop stepping to reduce the impact of the crane on the platform, but the traditional detection method cannot detect the position of the crane spreader, and can only rely on the operator to visually see that the spreader is close Manually suspending the stepping operation while on the bench, the operation process is very cumbersome.
The crown crane position recognition system uses image analysis technology combined with artificial intelligence algorithms to accurately identify and locate the position of the spreader. When the spreader is close to the stand, the system automatically controls the stop and step of the stand, which greatly simplifies the operation steps of the operator and improves Improve equipment reliability and improve the automation level of steel enterprises.
The charging process of the heating furnace is not allowed to send the bent billet into the furnace. The bent billet may cause faults such as roller jamming or blocking the furnace door. In the past, the operator could only rely on the operator to visually observe the billet straightness to identify the billet.
The bending billet recognition system accurately calculates the bending rate of the billet through visual inspection technology and big data deep learning algorithm and automatically rejects the billet with excessive bending rate. The use of this system reduces the work tasks of the operators, realizes the digitization and standardization of the feeding process, and improves the equipment automation level of the enterprise.
Get your solutions for steel industry machine vision system
1) The application of machine vision technology replaces manual operations in harsh environments, ensuring the safety of workers;
2) The application of machine vision technology reduces the burden of manual labour and improves production efficiency. The application of machine vision technology improves the detection accuracy and realizes the standardization and standardization of operations;
3) The application of machine vision technology has promoted the progress of production informatization.
DBM is committed to promoting and popularizing the application of machine vision technology in the iron and steel industry, helping iron and steel enterprises improve the intelligence and automation level of equipment, bringing substantial economic benefits to enterprises, and improving the core competitiveness of enterprises.
The machine vision system is to use machines instead of human eyes for measurement and judgment. The vision system refers to converting the ingested target into an image signal through a machine vision product (that is, an image capture device, which is divided into two types: CMOS and CCD), and sending it to a dedicated image processing system. Digitized signals; the image system performs various operations on these signals to extract the characteristics of the target, and then controls the on-site equipment actions according to the results of the discrimination. Is a valuable mechanism for production, assembly or packaging. It is invaluable in its ability to detect defects and prevent defective products from being shipped to consumers.
The machine vision system is characterized by improving the flexibility and automation of production. In some dangerous working environments that are not suitable for manual work or where artificial vision is difficult to meet the requirements, machine vision is often used to replace artificial vision; at the same time, in the process of mass industrial production, the efficiency and accuracy of using artificial vision to check product quality is low. , the use of machine vision inspection methods can greatly improve production efficiency and production automation. Moreover, machine vision is easy to realize information integration, and it is the basic technology to realize computer-integrated manufacturing. It can measure, guide, detect, and identify products on the fastest production line, and can complete production tasks with quality and quantity.
1. Non-contact measurement will not cause any damage to the observer and the observed, thereby improving the reliability of the system.
2. It has a wide spectral response range, such as using infrared measurements that are invisible to the human eye, expanding the visual range of the human eye.
3. Work stably for a long time. It is difficult for humans to observe the same object for a long time, while machine vision can perform measurement, analysis and identification tasks for a long time.
Lighting is an important factor affecting the input of the machine vision system, which directly affects the quality and application effect of the input data. Since there is no general machine vision lighting equipment, for each specific application instance, the corresponding lighting device should be selected to achieve the best effect.
Usually, the light sources we use include LED ring light sources, low-angle light sources, backlight sources, strip light sources, coaxial light sources, cold light sources, point light sources, linear light sources, parallel light sources, etc.
In order to better capture different objects, we will use different lenses to collect beams, such as standard, telecentric, wide-angle, close-up and telephoto lenses. In the vision system, the lens is mainly used for beam modulation. and signal transmission.
Lens selection should pay attention to:
①Focal length ②Target height ③Image height ④Magnification ⑤Distance from image to target ⑥Center point/node ⑦Distortion
According to different standards, it can be divided into standard-resolution digital cameras and analogue cameras. Different cameras and high-resolution cameras should be selected according to different practical applications: line scan CCD and area array CCD; black and white camera and colour camera.
In machine vision, the role of industrial cameras is to convert the collected optical signals into electrical signals, and in the complex environment of manufacturing, we require them to have more stable anti-interference and transmission capabilities.
A frame grabber is only one component of a complete machine vision system, but it plays a very important role. The frame grabber directly determines the interface of the camera: black and white, colour, analogue, digital, and so on.
In the whole detection system, we use vision software to analyze the electronic signal converted by the industrial camera and give a judgment signal according to the comparison result, so as to link the operation of the next automatic program.