Construction of Industrial Robot Manipulator Sorting System based on Convolution Neural Network

With the development of intelligent manufacturing, the application of intelligent algorithms in manufacturing industry is gradually enriched. This research combines convolutional neural network with industrial manipulator, and uses the image feature extraction advantages of convolutional neural network to build a manipulator sorting system. The results show that the average accuracy of the system for sorting parts is more than 70%, and when compared with other systems, its accuracy value is also greater than that of other systems. It can be seen that the identification and positioning accuracy of this system is stronger and the performance is better.

I. Introduction

In the field of intelligent robot, the most widely used is the manipulator system. Its strong flow production capacity and accuracy make it widely popular in many fields [1 –3]. In the field of intelligent operation, the advantages of convolutional neural network for image feature processing make it popular in the field of image recognition [4] –[6]. The manufacturing industry has higher and higher requirements for accuracy, which opens an important direction for the application of convolutional neural network in industrial robots [7 –10].