电子测量与仪器学报

蒋龙陈,王红军,张顺利.燃气轮机气流激振深度置信网络故障诊断模型[J].电子测量与仪器学报,2021,35(2):115-121

燃气轮机气流激振深度置信网络故障诊断模型

Flow excitation fault diagnosis model of gasturbine based on deep belief network

DOI：

英文关键词:gas turbine airflow excitation fault diagnosis deep belief network

基金项目:国家自然科学基金（51975058）资助项目

作者	单位
蒋龙陈	1.北京信息科技大学机电工程学院北京100192； 2.北京信息科技大学高端装备制造智能感知与控制北京市国际科技合作基地北京100192；3.北京信息科技大学机电系统测控北京市重点实验室北京100192；
王红军	1.北京信息科技大学机电工程学院北京100192； 2.北京信息科技大学高端装备制造智能感知与控制北京市国际科技合作基地北京100192；3.北京信息科技大学机电系统测控北京市重点实验室北京100193；
张顺利	4.中国航发西安航空发动机集团有限公司设计所西安710021

Author	Institution
Jiang Longchen	1.School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University, Beijing 100192, China;2. Beijing Highend Equipment Intelligent Perception and Control International Cooperation Base, Beijing Information Science&Technology University, Beijing 100192,China;3. Beijing Key Laboratory of Measurement and Control of Mechanical andElectrical System, Beijing Information Science & Technology University,Beijing 100192,China;
Wang Hongjun	1.School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University, Beijing 100192, China;2. Beijing Highend Equipment Intelligent Perception and Control International Cooperation Base, Beijing Information Science&Technology University, Beijing 100192,China;3. Beijing Key Laboratory of Measurement and Control of Mechanical andElectrical System, Beijing Information Science & Technology University,Beijing 100192,China;
Zhang Shunli	4 AECC Xi′an AeroEngine Ltd, Xi′an 710021,China

摘要点击次数: 447

全文下载次数: 4

中文摘要:

气流激振故障是燃汽轮机由于工作介质引发的常见故障,针对某型燃气轮机气流激振故障,建立峰值保持降采样算法和粒子群算法优化的深度置信网络故障诊断模型。使用峰值保持降采样法对振动数据进行缩减,并以之作为深度置信神经网络的输入,降低模型训练时间,同时采取粒子群算法对深度置信网络结构参数寻优,搜索诊断性能最好的深度置信模型所对应的网络结构参数。实例结果表明,优化后的模型不仅降低模型训练时间，实现网络结构参数智能寻优，还有效实现燃气轮机气流激振故障诊断,测试准确率约为998%。

英文摘要:

The Flow excitation fault is a common fault of gas turbine due to the working medium. Aiming at the flow excitation fault of the gas turbine, deep belief network (DBN) model is established to realize fault diagnosis based on the peak hold down sampling (PHDS) algorithm and particle swarm optimization (PSO) algorithm. The vibration data which is compressed by the PHDS algorithm is used as the input of the DBN to reduce the training time of the model. The PSO algorithm is adopted to optimize the structure parameters of the DBN to find the model with the best diagnostic effect. The results of example show that the optimized model not only reduces the training time of the model, realizes the intelligent optimization of network structure parameters, but also diagnoses the flow excitation faults of gas turbine effectively and the accuracy of the test was about 998%.

查看全文查看/发表评论下载PDF阅读器