Suzhou Electric Appliance Research Institute
期刊号: CN32-1800/TM| ISSN1007-3175

Article retrieval

文章检索

首页 >> 文章检索 >> 往年索引

基于ILSO-DELM的燃气轮机压气机故障预警方法

来源:电工电气发布时间:2024-06-03 12:03 浏览次数:318

基于ILSO-DELM的燃气轮机压气机故障预警方法

马梦甜1,茅大钧1,蒋欢春2
(1 上海电力大学 自动化工程学院,上海 200090;
2 上海明华电力科技有限公司,上海 200090)
 
    摘 要:压气机结构复杂,运行特性为非线性的特点加大了燃气轮机压气机故障预警的难度,为了提高燃气轮机压气机故障预警能力,提出了一种基于改进的狮群优化算法 (ILSO) 优化深度极限学习机 (DELM) 的故障预警方法。通过皮尔逊相关分析得到与预警参数相关性高的测点,构建 ILSO-DELM 预测模型,得到正常状态下预警参数的绝对值,通过参数估计确定阈值,根据残差绝对值是否超过预警线来间接判断压气机的运行情况。以上海某燃机电厂的运行数据进行分析,通过验证表明:该方法能够对压气机故障提前预警,并且相比于 DELM 模型预测精度更高。
    关键词: 压气机;深度极限学习机;狮群优化算法;故障预警
    中图分类号:TK478     文献标识码:B     文章编号:1007-3175(2024)05-0063-06
 
Fault Warning Method for Gas Turbine Compressor Based on ILSO-DELM
 
MA Meng-tian1, MAO Da-jun1, JIANG Huan-chun2
(1 College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China;
2 Shanghai Minghua Electric Power Technology Co., Ltd, Shanghai 200090, China)
 
    Abstract: The complexity of the compressor structure and the nonlinear characteristics of its operation pose challenges in predicting faults in gas turbine compressors. To enhance the fault prediction capability of gas turbine compressor, a novel approach is proposed using an improved lion swarm optimization (ILSO) to optimize deep extreme learning machine (DELM) for fault prediction. Through Pearson correlation analysis, the measurement points with high correlation with the early warning parameters are obtained, the ILSO-DELM prediction model is constructed, the absolute value of the early warning parameters under normal conditions is obtained, the threshold is determined by parameter estimation, and the operation of the compressor is indirectly judged according to whether the absolute value of the residual exceeds the early warning line. Based on the analysis of the operation data of a gas turbine power plant in Shanghai, the verification shows that the proposed method can give early warning of compressor faults, and the prediction accuracy is higher than that of the DELM model.
    Key words: compressor; deep extreme learning machine; lion swarm optimization algorithm; fault warning
 
参考文献
[1] 蒋洪德,任静,李雪英,等. 重型燃气轮机现状与发展趋势[J]. 中国电机工程学报,2014,34(29) :5096-5102.
[2] 李世尧,李振林,王颖,等. 部件性能退化对燃气轮机运行状态的影响[J]. 油气储运,2019,38(8) :911-918.
[3] 彭道刚,姬传晟,涂煊,等. 基于 LSTM-SVM 的燃气轮机压气机故障预警研究[J] . 动力工程学报,2021,41(5) :394-399.
[4] 党伟. 燃气轮机叶片断裂故障诊断方法研究[D]. 北京:北京化工大学,2020.
[5] 陆永卿,涂雷,茅大钧. 基于 MSET 的压气机故障预警研究[J]. 上海电力大学学报,2021,37(2) :133-137.
[6] ZHANG Y, GONG D, HU Y, et al.Feature selection algorithm based on bare bones particle swarm optimization[J].Neurocomputing,2015,148 :150-157.
[7] 刘宏,何鸿燊,何江. 基于狮群优化极限学习机的数据融合算法[J]. 计算机工程与设计,2023,44(2) :321-327.
[8] 曾亮,雷舒敏,王珊珊,等. 基于 OVMD-SSA-DELM-GM 模型的超短期风电功率预测方法[J] . 电网技术,2021,45(12) :4701-4710.
[9] 颜学龙,马润平. 基于深度极限学习机的模拟电路故障诊断[J]. 计算机工程与科学,2019,41(11) :1911-1918.
[10] 杨化动. 积垢的形成机理及其对轴流式压气机性能的影响研究[D]. 北京:华北电力大学,2014.
[11] 杨天南,蔡晋. 积垢对轴流压气机性能的影响分析[J].航空发动机,2017,43(6) :39-43.
[12] 周浩豪,茅大钧,李玉珍. 基于 SSAPSO-LightGBM 的火电厂引风机故障预警方法[J] . 热能动力工程,2023,38(2) :153-160.
[13] 董渊博,茅大钧,章明明. 基于 CNN-LSTM 的燃气轮机 NOx 排放预测研究[J]. 热能动力工程,2021,36(9) :132-138.
[14] DONG M, WU H Y, HU H, et al.Deformation prediction of unstable slopes based on real-time monitoring and DeepAR model[J].Sensors,2020,21(1) :14.