A novel deep learning method for on-line monitoring of grate bar defects in sintering machine system

Abstract

The defective grate bars at the bottom of the sintering machine system pose a serious safety risk to steel enterprises. Cracking and missing of these grate bars lead to severe production accidents and economic losses. Implementation of an efficient defect monitoring system plays a crucial role in ensuring continuous and stable sintering production. This paper presents a novel on-line grate bar defects monitoring method to address the following two key challenges. Firstly, a light-weight location model called Multi Scale Separated Convolutional Attention Network-LiteSeg (MSSCAN-LiteSeg) is proposed to identify the optimal shooting position of the moving trolley and simultaneously segment the horizontal and vertical grate bars. By separating the attention calculation into independent channel spaces, MSSCAN-LiteSeg can effectively handle the imbalanced sample distributions. Secondly, an innovative few-shot segmentation network named Response Forgetting Attention-Hypercorrelation Squeeze Network (RFA-HSNet) is proposed for defect detection by employing a "Forgetting-Enhancing-Recalling" method. Extensive experiments have demonstrated that our method can achieve a precision rate of 93.3% and provide a satisfactory performance in the on-line grate bar defects monitoring system.