Image Classification Method Based on Multi-Agent Reinforcement Learning for Defects Detection for Casting

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 14; p. 5143
• Main Authors: Liu, Chaoyue, Zhang, Yulai, Mao, Sijia
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 08.07.2022; MDPI
• Subjects: Algorithms; Casting defects; casting defects detection; casting image classification; Classification; Computing time; Datasets; Experiments; Image classification; multi-agent reinforcement learning; Neural networks; Teaching methods
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22145143

A casting image classification method based on multi-agent reinforcement learning is proposed in this paper to solve the problem of casting defects detection. To reduce the detection time, each agent observes only a small part of the image and can move freely on the image to judge the result together. In the proposed method, the convolutional neural network is used to extract the local observation features, and the hidden state of the gated recurrent unit is used for message transmission between different agents. Each agent acts in a decentralized manner based on its own observations. All agents work together to determine the image type and update the parameters of the models by the stochastic gradient descent method. The new method maintains high accuracy. Meanwhile, the computational time can be significantly reduced to only one fifth of that of the GhostNet.