基于多模型鲁棒输入训练神经网络协同的燃气-蒸汽联合循环机组传感器故障诊断方法

doi:10.11930/j.issn.1004-9649.201812068

中国电力 ›› 2019, Vol. 52 ›› Issue (11): 125-133.DOI: 10.11930/j.issn.1004-9649.201812068

基于多模型鲁棒输入训练神经网络协同的燃气-蒸汽联合循环机组传感器故障诊断方法

黄郑¹, 王红星¹, 于海泉², 李逗¹, 司风琪²

1. 江苏方天电力技术有限公司, 江苏南京 211102;
2. 东南大学能源热转换及过程测控教育部重点实验室, 江苏南京 210096

收稿日期:2018-12-25 修回日期:2019-07-13 出版日期:2019-11-05 发布日期:2019-11-05
作者简介:黄郑(1990-),男,硕士,工程师,从事电站优化运行及故障诊断研究,E-mail:hz10@vip.qq.com

Multi-sensor Fault Detection for Natural Gas Combined Cycle Power Plants Based on Multiple Robust Input Training Neural Network Models

HUANG Zheng¹, WANG Hongxing¹, YU Haiquan², LI Dou¹, SI Fengqi²

1. Jiangsu Frontier Electric Technology Co., Ltd., Nanjing 211102, China;
2. Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China

Received:2018-12-25 Revised:2019-07-13 Online:2019-11-05 Published:2019-11-05

摘要/Abstract

摘要： 为提高燃气-蒸汽联合循环机组传感器测量值的准确性及可靠性，提出了一种基于多模型鲁棒输入训练神经网络（RITNN）的燃气-蒸汽联合循环机组传感器故障诊断方法。该方法建立若干燃气-蒸汽联合循环重要参数的数据重构模型，并对各模型进行优先级划分，以串并联方式设定模型间关系，通过可靠参数的逐级生成和传递，有效抑制了多传感器显著故障产生的残差污染，提高了故障诊断的准确性及可靠性，进而给出了传感器故障诊断流程，建立了完整的传感器故障诊断系统。以某200 MW级燃气-蒸汽联合循环机组为研究对象，对多传感器故障进行诊断，并与RITNN单一模型方法和输入训练神经网络（ITNN）单一模型方法进行对比，结果表明，提出的多模型RITNN故障诊断方法诊断精度更高，可保证燃气-蒸汽联合循环机组稳定运行。

关键词: 多模型, 鲁棒输入训练神经网络, 故障诊断, 联合循环

Abstract: In order to enhance the accuracy and reliability of multiple sensor measurements in natural gas combined cycle (NGCC) power plants, a multi-sensor fault detection method based on multi-model robust input training neural network is proposed in this paper, in which multiple robust input training neural network (RITNN) models are built and prioritized for the purpose of sensor faults reconstruction and monitoring. The relationship between the models are set in terms of serial or parallel connections. The influence of numerous failure data with significant errors can be effectively inhibited by virtue of reliable sensor data calculated from cooperative multi-model, such that the accuracy and reliability of fault detection is greatly improved. In addition, the process for sensor fault detection is presented to establish a complete fault dectection system. The proposed method was evaluated in a 200 MW NGCC power plant, where the multi-sensor fault detection was conducted and the results were compared with those from single RITNN model and single input training neural network (ITNN) model detection.The proposed method demonstrated higher accuracy in multiple sensor failure cases than the single RITNN model or the single ITNN model.

Key words: multiple models, RITNN, fault detection, NGCC

中图分类号:

黄郑, 王红星, 于海泉, 李逗, 司风琪. 基于多模型鲁棒输入训练神经网络协同的燃气-蒸汽联合循环机组传感器故障诊断方法[J]. 中国电力, 2019, 52(11): 125-133.

HUANG Zheng, WANG Hongxing, YU Haiquan, LI Dou, SI Fengqi. Multi-sensor Fault Detection for Natural Gas Combined Cycle Power Plants Based on Multiple Robust Input Training Neural Network Models[J]. Electric Power, 2019, 52(11): 125-133.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201812068

https://www.electricpower.com.cn/CN/Y2019/V52/I11/125

参考文献

[1] 焦树建. 燃气-蒸汽联合循环的理论基础[M]. 清华大学出版社, 2003.
[2] OGAJI S O T, SINGH R, PROBERT S D. Multiple-sensor fault-diagnoses for a 2-shaft stationary gas-turbine[J]. Applied Energy, 2002, 71(4):321-339.
[3] OGAJI S O T, SAMPATH S, SINGH R, et al. Parameter selection for diagnosing a gas-turbine's performance-deterioration[J]. Applied Energy, 2002, 73(1):25-46.
[4] 张高强, 付忠广, 王树成, 等. 燃气-蒸汽联合循环进气冷却系统对机组性能影响研究[J]. 中国电力, 2018, 51(12):36-41 ZHANG Gaoqiang, FU Zhongguang, WANG Shucheng, et al. Research on the impacts of gas-steam combined cycle air-inlet cooling system on unit performance[J]. Electric Power, 2018, 51(12):36-41
[5] 黄郑, 殳建军, 于国强, 等. 燃气-蒸汽联合循环机组循环水泵优化管理系统设计与开发[J]. 中国电力, 2019, 52(3):121-126 HUANG Zheng, SHU Jianjun, YU Guoqiang, et al. Cycle pump optimization management system for CCGT power plant[J]. Electric Power, 2019, 52(3):121-126
[6] MESKIN N, NADERI E, KHORASANI K. A multiple model-based approach for fault diagnosis of jet engines[J]. IEEE Transactions on Control Systems Technology, 2013, 21(1):254-262.
[7] NADERI E, MESKIN N, KHORASANI K. Nonlinear fault diagnosis of jet engines by using a multiple model-based approach[J]. Journal of Engineering for Gas Turbines and Power, 2012, 134(1):63-75.
[8] NAPOLITANO M R, AN Y, SEANOR B A. A fault tolerant flight control system for sensor and actuator failures using neural networks[J]. Aircraft Design, 2000, 3(2):103-128.
[9] VANINI Z N S, MESKIN N, KHORASANI K. Multiple-model sensor and components fault diagnosis in gas turbine engines using autoassociative neural networks[J]. Journal of Engineering for Gas Turbines and Power, 2014, 136(9):1429-1445.
[10] XIRADAKIS N, LI Y G. Gas turbine and sensor fault diagnosis with nested artificial neural networks[C]//ASME Turbo Expo 2004:Power for land, sea, and air. Vienna, Austria, 2004:351-359.
[11] PALMÉ T, FAST M, THERN M. Gas turbine sensor validation through classification with artificial neural networks[J]. Applied Energy, 2011, 88(11):3898-3904.
[12] CHEN J, LI H, SHENG D, et al. A hybrid data-driven modeling method on sensor condition monitoring and fault diagnosis for power plants[J]. International Journal of Electrical Power & Energy Systems, 2015, 71:274-284.
[13] 司风琪, 李欢欢, 徐治皋. 基于鲁棒输入训练神经网络的非线性多传感器故障诊断方法及其应用[J]. 东南大学学报(自然科学版), 2011, 41(3):574-578 SI Fengqi, LI Huanhuan, XU Zhigao. Nonlinear multi-sensor fault diagnosis method and its application based on robust input-training neural network[J]. Journal of Southeast University (Natural Science Edition), 2011, 41(3):574-578
[14] OGAJI S O T, SAMPATH S, MARINAI L, et al. Evolution strategy for gas-turbine fault-diagnoses[J]. Applied Energy, 2005, 81(2):222-230.
[15] HU Y, PALMÉ T, FINK O. Fault detection based on signal reconstruction with auto-associative extreme learning machines[J]. Engineering Applications of Artificial Intelligence, 2017, 57:105-117.
[16] HU Y, CHEN H, LI G, et al. A statistical training data cleaning strategy for the PCA-based chiller sensor fault detection, diagnosis and data reconstruction method[J]. Energy and Buildings, 2016, 112:270-278.
[17] CHOI S W, LEE I B. Multiblock PLS-based localized process diagnosis[J]. Journal of Process Control, 2005, 15(3):295-306.
[18] RAHME S, MESKIN N. Adaptive sliding mode observer for sensor fault diagnosis of an industrial gas turbine[J]. Control Engineering Practice, 2015, 38:57-74.
[19] 陈娇, 王永泓, 翁史烈. 广义回归神经网络在燃气轮机排气温度传感器故障检测中的应用[J]. 中国电机工程学报, 2009, 29(32):92-97 CHEN Jiao, WANG Yonghong, WENG Shilie. Application of general regression neural network in fault detection of exhaust temperature sensors on gas turbines[J]. Proceedings of the CSEE, 2009, 29(32):92-97

基于多模型鲁棒输入训练神经网络协同的燃气-蒸汽联合循环机组传感器故障诊断方法

Multi-sensor Fault Detection for Natural Gas Combined Cycle Power Plants Based on Multiple Robust Input Training Neural Network Models

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘贺千, 张健, 张海月, 杨洪达, 陈世玉, 申昱博, 王磊. 基于高频阻抗谱的干式空心电抗器匝间短路故障诊断方法[J]. 中国电力, 2024, 57(10): 218-224.
[2]	黎燕, 程馨, 黄祖梁, 杨琢. 高可靠性三相多功能并网变换器研究[J]. 中国电力, 2023, 56(5): 172-181.
[3]	李刚, 孟坤, 贺帅, 刘云鹏, 杨宁. 考虑特征耦合的Bi-LSTM变压器故障诊断方法[J]. 中国电力, 2023, 56(3): 100-108,117.
[4]	韩伟, 段文岩, 杜兴伟, 姚峰, 马伟东, 刘磊. 基于数字孪生的在运安控系统故障诊断方法[J]. 中国电力, 2023, 56(11): 121-127.
[5]	马海飞, 滕伟, 彭迪康, 柳亦兵, 靳涛. 基于DRS与改进Autogram的风电齿轮箱复合故障特征提取[J]. 中国电力, 2023, 56(10): 71-79.
[6]	王爽, 罗倩, 唐波, 姜岚, 李锦. 考虑样本类内不平衡的CHPOA-DBN变压器故障诊断方法[J]. 中国电力, 2023, 56(10): 133-144.
[7]	张宏杰, 陈贵凤, 闫宏伟, 杨晓龙, 侯天仁, 张伟. 基于SMOTE与Bayes优化的LSTM网络变压器故障诊断[J]. 中国电力, 2023, 56(10): 164-170.
[8]	陈铁, 冷昊伟, 李咸善, 陈一夫. 基于油中气体分析与类重叠特征的变压器分层故障诊断模型[J]. 中国电力, 2022, 55(7): 22-32,41.
[9]	李天辉, 庞先海, 范辉, 甄利, 顾朝敏, 董驰. 基于IEMD和GA-WNN的断路器分合闸线圈故障诊断方法[J]. 中国电力, 2022, 55(5): 111-121.
[10]	郝玲玲, 朱永利, 王永正. 基于DCAE-KSSELM的变压器故障诊断方法[J]. 中国电力, 2022, 55(2): 125-130.
[11]	余斌, 宋兴荣, 周挺, 罗林波, 李辉, 车亮. 基于梅尔倒谱系数特征集的储能变流器开路故障诊断方法[J]. 中国电力, 2022, 55(12): 34-42.
[12]	庄家懿, 杨国华, 郑豪丰, 张鸿皓. 基于多模型融合的CNN-LSTM-XGBoost短期电力负荷预测方法[J]. 中国电力, 2021, 54(5): 46-55.
[13]	张涛, 刘志坦, 干雪, 付忠广, 严志远, 朱鸿飞, 邱振波. 进气加热对燃气-蒸汽联合循环性能影响[J]. 中国电力, 2021, 54(3): 177-184.
[14]	李福志, 郑卫宾, 张文海, 张智勇, 林德锋, 张旭波, 张荣建. 基于回路直流电阻测量的输电线路单相接地故障离线故障定位[J]. 中国电力, 2021, 54(2): 140-146.
[15]	王凯, 李玉刚, 刘志坦, 王波, 邵卫卫, 孙晨. 联合循环电站低负荷烟气成分控制对策研究[J]. 中国电力, 2020, 53(5): 172-178.

模态框（Modal）标题

基于多模型鲁棒输入训练神经网络协同的燃气-蒸汽联合循环机组传感器故障诊断方法

Multi-sensor Fault Detection for Natural Gas Combined Cycle Power Plants Based on Multiple Robust Input Training Neural Network Models

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics