| 引用本文: | 何德雨,胡茑庆,胡雷,等.基于VR与PNN相结合的机电液控制系统故障诊断方法.[J].国防科技大学学报,2016,38(6):117-123.[点击复制] |
| HE Deyu,HU Niaoqing,HU Lei,et al.Fault diagnosis method of mechanic-electronic-hydraulic control system based on the combined virtual prototyping and probabilistic neural network[J].Journal of National University of Defense Technology,2016,38(6):117-123[点击复制] |
|
| |
|
|
| 本文已被：浏览 8278次 下载 6614次 |
| 基于VR与PNN相结合的机电液控制系统故障诊断方法 |
| 何德雨1,2, 胡茑庆1,2, 胡雷1,2, 陈凌1,2, 郭亦平3 |
|
(1. 国防科技大学 装备综合保障技术重点实验室， 湖南 长沙 410073;2.
2. 国防科技大学 机电工程与自动化学院， 湖南 长沙 410073;3. 中船重工集团 707 研究所九江分部， 江西 九江 332007)
|
| 摘要: |
| 针对大型复杂机电液控制系统故障诊断中存在的数学模型获取困难、历史故障数据匮乏问题，提出了一种将虚拟样机与概率神经网络相结合的故障诊断混合方法。建立系统的虚拟样机，并对其可信性进行校核与验证。在此基础上进行大量随机性故障植入与仿真实验，获取故障仿真数据。经过特征提取与概率神经网络模式识别训练，形成用于诊断的知识库，从而实现故障诊断。以操舵系统作为研究案例，得到了较高的故障检测和隔离精度与较低的虚警及漏警率，验证了该方法的可行性，为大型复杂机电液控制系统故障诊断提供新的思路。 |
| 关键词: 虚拟样机 机电液控制系统 概率神经网络 故障诊断 |
| DOI：10.11887/j.cn.201606019 |
| 投稿日期：2015-08-18 |
| 基金项目:国家自然科学基金资助项目（51475463） |
|
| Fault diagnosis method of mechanic-electronic-hydraulic control system based on the combined virtual prototyping and probabilistic neural network |
| HE Deyu1,2, HU Niaoqing1,2, HU Lei1,2, CHEN Ling1,2, GUO Yiping3 |
|
(1. Laboratory of Science and Technology on Integrated Logistics Support, National University of Defense Technology, Changsha 410073, China;2.
2. College of Mechatronics Engineering and Automation, National University of Defense Technology, Changsha 410073, China;3. The Jiujiang Branch of 707 Research Institution, China Shipbuilding Industry Corporation, Jiujiang 332007, China)
|
| Abstract: |
| In the diagnosis of large-scale mechanic-electronic-hydraulic control system, and for the mathematical model was hard to build and the historic fault data was short, a hybrid fault diagnosis method based on virtual prototyping and PNN (probabilistic neural network) was proposed. Virtual prototyping was first built and its credibility was validated. On this basis, fault injection and simulation were conducted to obtain fault data, which was then extracted as fault features and trained by PNN to form diagnosis knowledge library. A case study of steering system was presented to verify the correctness of the proposed method, which shows that the accuracy of fault detection and isolation is high and the rate of false/missing alarm is low. The proposed method may bring a novel idea for the fault diagnosis of large-scale and complicated mechanic-electronic hydraulic control system. |
| Keywords: virtual prototyping mechanic-electronic-hydraulic control system probabilistic neural network fault diagnosis |
|
|
|
|
|
