西安科技大学学报2025，Vol.45Issue(2)：372-382,11.DOI:10.13800/j.cnki.xakjdxxb.2025.0215
基于Mamba的井下皮带异物无监督检测模型研究
Research on an unsupervised detection model for underground belt foreign objects based on Mamba
摘要
Abstract
To solve the problems such as the inaccurate positioning of foreign objects on underground conveyor belts and excessive computational costs,an unsupervised foreign object detection model for coal conveyor belts based on Mamba was proposed.This model consisted of a pre-trained encoder and a Mamba-based decoder.In the Mamba decoder,the FHSS hybrid state space module incorporated Hil-bert scan position encoding,Fourier transform,and Einstein diagonal matrix computation into the Mam-ba network to enhance both channel modeling and feature sequence modeling.By combining the advan-tages of reconstruction-based methods and multi-class unsupervised anomaly detection,it addressed the challenges of scarce and difficult-to-collect underground anomaly datasets.The results indicate that the accuracy of this model has improved by 22.2%,10.9%,5.9%,and 2.1%,respectively,compared to four classical anomaly detection models.Its parameter counts and FLOPs are only 26.109 M and 8.497 G,respectively.Compared to traditional detection methods,it not only effectively handles detec-tion uncertainties caused by factors such as noise and occlusion,ensuring the robustness and reliability of foreign object detection,but also features a smaller model size,significantly reducing the computa-tional complexity during the inference process.This improvement is of great significance for practical applications in coal mines,as it can better ensure the safety and stability of the conveying system.关键词
井下皮带异物检测/Mamba/无监督训练/异常检测/空间状态模型Key words
underground belt foreign object detection/Mamba/unsupervised training/anomaly detec-tion/state space model分类
矿业与冶金引用本文复制引用
马莉,吴伟雪,代新冠..基于Mamba的井下皮带异物无监督检测模型研究[J].西安科技大学学报,2025,45(2):372-382,11.基金项目
陕西省重点产业链项目(2021ZDLGY07-08) （2021ZDLGY07-08）
