Hub Type Test

Share

Issue Time: 2021/11/1 12:55:56

Summary

In order to improve productivity of wheel hub recognition, machine vision system is used for intelligent recognition of automobile wheel hub.

Background

　Requirement Description:

　　1. After hub production and transportation, different types of hub need to be classified for subsequent sorting and packaging.

　　2. Manual detection method has low efficiency, high labor cost and low accuracy.

　　Technical requirements:

　　1. Recognition accuracy: > 99.9%

　　2. Types of wheel hub identification: > 200

Structure

The wheel hub type detection system uses Hikrobot 5 million high-resolution camera, large area medium aperture surface light source, and deep learning classification tool to realize automatic identification and classification of various wheel hubs in the state of random mixed flow on the production line conveyor belt.

Advantages

1. Recognition accuracy: 80-100 samples are collected for each type of initial model training, and the comprehensive recognition rate can reach more than 99%. Through field iteration, the final identification accuracy rate is more than 99.99%.

2. Large recognition capacity: deep learning classification algorithm uses the advantages of convolutional neural network and big data samples to improve the recognition capacity.