Siami Mohammad, Barszcz Tomasz, Wodecki Jacek, Zimroz Radoslaw
AMC Vibro Sp. z o.o., Pilotow 2e, 31-462, Kraków, Poland.
Faculty of Mechanical Engineering and Robotics, AGH University, Al. Mickiewicza 30, 30-059, Kraków, Poland.
Sci Rep. 2024 Mar 8;14(1):5748. doi: 10.1038/s41598-024-55864-2.
The belt conveyor (BC) is the main means of horizontal transportation of bulk materials at mining sites. The sudden fault in BC modules may cause unexpected stops in production lines. With the increasing number of applications of inspection mobile robots in condition monitoring (CM) of industrial infrastructure in hazardous environments, in this article we introduce an image processing pipeline for automatic segmentation of thermal defects in thermal images captured from BC idlers using a mobile robot. This study follows the fact that CM of idler temperature is an important task for preventing sudden breakdowns in BC system networks. We compared the performance of three different types of U-Net-based convolutional neural network architectures for the identification of thermal anomalies using a small number of hand-labeled thermal images. Experiments on the test data set showed that the attention residual U-Net with binary cross entropy as the loss function handled the semantic segmentation problem better than our previous research and other studied U-Net variations.
带式输送机（BC）是矿场散装物料水平运输的主要方式。BC模块的突发故障可能导致生产线意外停机。随着检测移动机器人在危险环境下工业基础设施状态监测（CM）中的应用越来越多，在本文中，我们介绍一种图像处理流程，用于使用移动机器人对从BC托辊捕获的热图像中的热缺陷进行自动分割。本研究基于托辊温度的状态监测是预防BC系统网络突发故障的一项重要任务这一事实。我们使用少量手工标注的热图像，比较了三种不同类型的基于U-Net的卷积神经网络架构在识别热异常方面的性能。对测试数据集的实验表明，以二元交叉熵作为损失函数的注意力残差U-Net在处理语义分割问题上比我们之前的研究以及其他研究的U-Net变体表现更好。
