基于深度学习的大口径火炮健康管理系统研究  

Research on health management system of large-caliber artillery based on deep learning

作　　者：张原[1] 姜焕成 ZHANG Yuan;JIANG Huan-cheng(School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China)

机构地区：[1]西北工业大学电子信息学院,陕西西安710129

出　　处：《计算机工程与科学》2020年第11期2050-2058,共9页Computer Engineering & Science

摘　　要：大口径火炮可以用最小的代价对敌人造成最大范围的行动限制,是战场上十分关键的火力压制武器,但是由于其工作环境严酷,大口径火炮在执行任务时表现十分不稳定。基于大口径火炮健康管理系统研究项目,在做好对大口径火炮工作状态实时监测与记录的同时,结合专家分析等健康管理手段,提出基于深度学习的大口径火炮故障预测与分析设计思路,利用深度置信网络无监督的高效特征提取能力和多层感知机有监督的数据分类能力,建立故障预测深度学习模型,实现对大口径火炮故障状态的预测,为大口径火炮的预先维护保养提供技术支持,从而提高大口径火炮的可靠性。Large-caliber artillery can limit the enemy's movement to the maximum range at the least cost.It is a very critical fire suppression weapon on the battlefield.However,due to its harsh working environment,large-caliber artillery performs very unstable in missions.Based on the research project of the health management system of large-caliber artillery,while monitoring and recording the working status of large-caliber artillery in real time,this paper proposes a design idea of failure prediction and analysis of large-caliber artillery based on deep learning by combining expert analysis and other health ma-nagement methods.The unsupervised and efficient feature extraction capabilities of the deep belief network and the supervised data classification capabilities of the multi-layer perceptron are adopted to establish a fault prediction deep learning model,in order to realize the prediction of the failure state of large-caliber artillery and provide technical support for the pre-maintenance of large-caliber artillery,thereby improving the reliability of large-caliber artillery.

关 键 词：大口径火炮 故障预测 深度置信网络 多层感知机 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]