1L PET Bottle Containers KVIS-B Bottle Vision Inspection Machine

Equipment features:

Equipment overview

The overall equipment integrates mechanical mechanisms, visual optical hardware and detection system software, defective product rejection and counting devices. The normal detection speed is 150 pieces per minute. The entrance and exit of the detection machine can be integrated with the on-site conveyor line and can be independently matched Leak detectors, balers and other related equipment can be operated 7*24 hours a day, which greatly improves production efficiency.

The overall detection equipment, with 10 sets of high-resolution industrial cameras, can comprehensively detect the appearance defects of the outside of the bottle, the mouth and the bottom of the bottle. After the system collects the sample image, the image processing software and the standardized sample are compared and analyzed to determine whether the product is good or not. Good products and defective products will be automatically rejected online. After finished products are detected, the counting function can be realized, and the counting accuracy rate is 100%. The software will open the sample comparison standard, and the production personnel on the customer site can control the comparison accuracy and choose the accuracy standard most suitable for their own production conditions, thereby controlling the defect rate.

The overall equipment structure is shown in the figure below:

This detecting equipment uses deep learning to detect the appearance of the bottle. At present, our company does not have a better solution for the positioning of the bottle handle. Therefore, the handle occlusion area and the part of the handle and the bottle body cannot be detected. The handle itself is defective. The presence or absence of the handle can be detected.

The detection process is as follows:

1. Detection for the side surface of the bottle body. Considering the characteristics of the bottle body and the height of the bottle body beyond the single-camera viewing angle range, the plan is designed to install cameras on the upper and lower parts, each using 4 sets of industrial cameras, a total of 8 sets of industrial cameras , divided into 2 groups of optical integrating cavity modules, imaging does not interfere with each other, the acquisition angle range of each camera is shown in the figure above.

2. Detection for the outer bottom surface of the bottle. Use the clamping mechanism to suspend the outer bottom of the bottle, and install 1 set of industrial cameras underneath, and use it with the visual light source to collect the image of the outer bottom for processing.

3. Detection of the bottle mouth area. 1 set of industrial cameras are installed on the top of the bottle body to use with the visual light source to collect images of the inner side of the bottle mouth for processing.

 Detecting content:

Hardware:

• Camera: We use our own developed camera (the chip is from Japan), which has clearer image recognition and is more compatible with our own software.
• Light source: We have a dedicated optical team to develop various light sources to adapt to the optical scene requirements of different industrial scenes.
• Embedded computer: The KEYE team independently developed the embedded computer NPU computing box, which replaced the traditional PLC industrial computer; it is not afraid of sudden power outages and high temperature scenes, and can better adapt to the high temperature environment.

Software:

• Algorithm: We use the latest AI deep learning algorithm. Most products only need a small amount of sample learning to complete a new product model; the machine can continuously learn some defects and good samples like the human brain, making the detection effect better and better.
• Software: The latest KEYE V16.0 software can realize a variety of data statistics and human-computer interaction functions, and the touch screen operation is simpler.
• KEYE cloud platform: The AI cloud platform can create its own cloud platform account for each customer, and the pictures of each training operation will be saved in its own account; even if the algorithm is lost due to software algorithms or other problems, all previous data can be retrieved through an independent cloud platform account. (KEYE team has technicians who regularly maintain this platform).
• After-sales service: Provide long-term remote service, customers only need to keep the device in good network connection.

Cooperation Partners

KEYETECH has always been committed to the application of artificial intelligence in the field of vision technology, replacing human eyes and brain decision with machine vision and AI reasoning calculations, and integrating the quality detection and sorting to industrial products in traditional manufacturing to make the production more digitization , Intelligence, visualization, and persistence. Also greatly improves the efficiency and accuracy of industrial detection, and enhances the intelligent level of the manufacturing industry.