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

Article retrieval

文章檢索

首頁 >> 文章檢索 >> 往年索引

基于ILSO-DELM的燃?xì)廨啓C壓氣機故障預(yù)警方法

來源:電工電氣發(fā)布時間:2024-06-03 12:03 瀏覽次數(shù):200

基于ILSO-DELM的燃?xì)廨啓C壓氣機故障預(yù)警方法

馬夢甜1,茅大鈞1,蔣歡春2
(1 上海電力大學(xué) 自動化工程學(xué)院,上海 200090;
2 上海明華電力科技有限公司,上海 200090)
 
    摘 要:壓氣機結(jié)構(gòu)復(fù)雜,運行特性為非線性的特點加大了燃?xì)廨啓C壓氣機故障預(yù)警的難度,為了提高燃?xì)廨啓C壓氣機故障預(yù)警能力,提出了一種基于改進的獅群優(yōu)化算法 (ILSO) 優(yōu)化深度極限學(xué)習(xí)機 (DELM) 的故障預(yù)警方法。通過皮爾遜相關(guān)分析得到與預(yù)警參數(shù)相關(guān)性高的測點,構(gòu)建 ILSO-DELM 預(yù)測模型,得到正常狀態(tài)下預(yù)警參數(shù)的絕對值,通過參數(shù)估計確定閾值,根據(jù)殘差絕對值是否超過預(yù)警線來間接判斷壓氣機的運行情況。以上海某燃機電廠的運行數(shù)據(jù)進行分析,通過驗證表明:該方法能夠?qū)簹?/span>機故障提前預(yù)警,并且相比于 DELM 模型預(yù)測精度更高。
    關(guān)鍵詞: 壓氣機;深度極限學(xué)習(xí)機;獅群優(yōu)化算法;故障預(yù)警
    中圖分類號:TK478     文獻標(biāo)識碼:B     文章編號: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
 
參考文獻
[1] 蔣洪德,任靜,李雪英,等. 重型燃?xì)廨啓C現(xiàn)狀與發(fā)展趨勢[J]. 中國電機工程學(xué)報,2014,34(29) :5096-5102.
[2] 李世堯,李振林,王穎,等. 部件性能退化對燃?xì)廨啓C運行狀態(tài)的影響[J]. 油氣儲運,2019,38(8) :911-918.
[3] 彭道剛,姬傳晟,涂煊,等. 基于 LSTM-SVM 的燃?xì)?span style="font-size: 12px;">輪機壓氣機故障預(yù)警研究[J] . 動力工程學(xué)報,2021,41(5) :394-399.
[4] 黨偉. 燃?xì)廨啓C葉片斷裂故障診斷方法研究[D]. 北京:北京化工大學(xué),2020.
[5] 陸永卿,涂雷,茅大鈞. 基于 MSET 的壓氣機故障預(yù)警研究[J]. 上海電力大學(xué)學(xué)報,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] 劉宏,何鴻燊,何江. 基于獅群優(yōu)化極限學(xué)習(xí)機的數(shù)據(jù)融合算法[J]. 計算機工程與設(shè)計,2023,44(2) :321-327.
[8] 曾亮,雷舒敏,王珊珊,等. 基于 OVMD-SSA-DELM-GM 模型的超短期風(fēng)電功率預(yù)測方法[J] . 電網(wǎng)技術(shù),2021,45(12) :4701-4710.
[9] 顏學(xué)龍,馬潤平. 基于深度極限學(xué)習(xí)機的模擬電路故障診斷[J]. 計算機工程與科學(xué),2019,41(11) :1911-1918.
[10] 楊化動. 積垢的形成機理及其對軸流式壓氣機性能的影響研究[D]. 北京:華北電力大學(xué),2014.
[11] 楊天南,蔡晉. 積垢對軸流壓氣機性能的影響分析[J].航空發(fā)動機,2017,43(6) :39-43.
[12] 周浩豪,茅大鈞,李玉珍. 基于 SSAPSO-LightGBM 的火電廠引風(fēng)機故障預(yù)警方法[J] . 熱能動力工程,2023,38(2) :153-160.
[13] 董淵博,茅大鈞,章明明. 基于 CNN-LSTM 的燃?xì)廨啓C NOx 排放預(yù)測研究[J]. 熱能動力工程,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.