摘要
神经网络是一种类似于人类神经系统的人工智能模型,利用神经网络可以对传统的监测数据进行组合和筛选,以提高故障检测的准确度。为提升液压机状态监测系统的故障评估性能,利用基于神经网络的机器学习方法的优势,提出一种设备状态监测解决新方案。对大量数据进行神经网络模型训练及特征提取,从而实现对液压机监测系统故障的准确识别。
Neural network is an artificial intelligence model similar to the human nervous system,which can combine and filter traditional monitoring data to improve the accuracy of fault detection.To improve the fault evaluation performance of the hydraulic press status monitoring system,a new solution for equipment status monitoring is proposed by utilizing the advantages of neural network-based machine learning methods.Neural network model was trained and features were extracted from a large amount of data to achieve accurate identification of faults in hydraulic press monitoring systems.
作者
王建军
郝素兰
WANG Jianjun;HAO Sulan(School of Mechanical Engineering,Anhui Technical College of Mechanical and Electrical Engineering,Wuhu Anhui 241002,China)
出处
《重庆科技学院学报（自然科学版）》
CAS
2024年第3期36-41,共6页
Journal of Chongqing University of Science and Technology：Natural Sciences Edition
基金
安徽省高校自然科学研究重点项目“基于云平台的液压机液压系统故障智能诊断技术研究”(KJ2020A1108)
安徽省2021年高校学科(专业)拔尖人才学术资助项目“大型运载装备多机分布式协同控制智能化和关键技术研究”(GXBJZD2021100)
安徽机电职业技术学院2019年特色高水平专业建设项目“机械设计与制造专业”(2019TGZY01)。
关键词
神经网络
液压机
状态监测
机器学习
neural networks
hydraulic presses
state monitoring
machine learning
