矿用传感器静态特性补偿方法与研究进展

Research progress on the static characteristic compensation methods of mine sensors

随着矿井自动化、监测监控、故障诊断、危险源辨识、信息融合等技术需求的提高,矿用传感器的检测精度受到学术界和工业界的广泛关注。通过分析矿用传感器补偿的必要性及常规静态特性(非线性)补偿方法存在的问题,对近年来传感器静态特性补偿方法的研究进展进行了综述,提出了混沌粒子群优化RBFNN或SVM、遗传粒子群优化RBFNN或SVM等未来适用于矿用传感器静态特性数据补偿算法可能的研究方向。

With the improvement of technology demand of mine automation,monitoring,fault diagnosis,hazard identification and information fusion,the mine sensor detection accuracy was caused extensive attention of academia and industry. By summarizing the research progress of static characteristic compensation method in recent years and analyzing the necessity of compensation of mine sensors and the existing problems in conventional static characteristic（ nonlinear） compensation method,the possible research direction of the RBFNN or SVM of chaotic particle swarm optimization and RBFNN or SVM of genetic particle swarm optimization,which suitable for the data compensation algorithm of mine sensors static characteristic in the future,were proposed.