首页|基于深度神经网络的电液伺服泵控系统健康评估研究

基于深度神经网络的电液伺服泵控系统健康评估研究

扫码查看
原文链接
  • 万方数据
  • 维普
电液伺服泵控系统具备功重比高、响应快等优点,在多领域得到广泛应用,但如何针对该系统开展更有效健康评估,进一步保障系统的安全性和可靠性成为必须面对的问题.按照明确原理、建立数学模型、建立仿真模型、仿真分析的思路针对健康评估方法开展研究,提出油液体积含气量、气隙磁密、泄漏系数3个健康评估指标并确定阈值,构建了LGA(LSTM-GRNN-ANN)深度神经网络健康评估方法并进行仿真分析,结果显示该方法准确率约为97.48％,比LSTM、GRNN健康评估方法具有更高的准确率,为继续深入开展电液伺服泵控系统健康评估的研究提供了理论支持.
Research on Health Assessment of Electro-Hydraulic Servo Pump Control System Based on Deep Neural Network
The electro-hydraulic servo pump control system has the advantages of high power to weight ratio and fast response,and is widely used in various fields.But how to conduct more effective health assessments for the system and further ensure its safety and re-liability has become a necessary issue to face.Research on health assessment methods was conducted according to clearing principles,establishing mathematical models,establishing simulation models,and making simulation experiments.Three health assessment indicators as oil volume gas content,air gap magnetic density,and leakage coefficient,were proposed and their thresholds were determined.Then a LGA(LSTM-GRNN-ANN)deep neural network health assessment method was constructed and simulation analysis was conducted.The results show that the accuracy of this method is about 97.48％,which is higher than LSTM and GRNN health assessment methods.This provides theoretical support for further research on health assessment of electro-hydraulic servo pump control systems.

electro-hydraulic servo pump control systemhealth assessmentLGA deep neural networksimulation analysis

刘克毅、李渊、王飞、陈革新、王梦、张亚欧

展开 >

新疆工程学院新疆煤炭资源绿色开采教育部重点实验室,新疆乌鲁木齐 830023

新疆工程学院机电工程学院,新疆乌鲁木齐 830023

吉林大学机械与航空航天工程学院,吉林长春 130022

燕山大学机械工程学院,河北秦皇岛 066004

展开 >

电液伺服泵控系统 健康评估 LGA深度神经网络 仿真分析

新疆维吾尔自治区自然科学基金新疆维吾尔自治区自然科学基金新疆维吾尔自治区自然科学基金新疆煤炭资源绿色开采教育部重点实验室自主课题

2022D01A512022D01B1352022D01A244KLXGY-Z2402

2024

10.3969/j.issn.1001-3881.2024.09.026

机床与液压
中国机械工程学会 广州机械科学研究院有限公司

机床与液压

CSTPCD北大核心
影响因子：0.32
ISSN：1001-3881
年,卷(期)：2024.52(9)