计算机科学 ›› 2024, Vol. 51 ›› Issue (11): 292-297.doi: 10.11896/jsjkx.230500096
潘连荣1, 张福泉2, 何井龙1, 杨加意1
PAN Lianrong1, ZHANG Fuquan2, HE Jinglong1, YANG Jiayi1
摘要： 为了有效提高基于机器学习的设备异常诊断的精度和效率,提出了一种基于稀疏化支持向量机的故障诊断模型。首先,对异常诊断的原理和特征气体进行了分析,给出了故障类型与特征气体的关系;其次,从4个方面对数据进行预处理,包括清洗、归一化、平衡和划分;然后,针对最小二乘支持向量机普遍存在的稀疏性缺乏问题,提出将数据样本映射到高维的核空间,并通过谱聚类算法对映射后的数据进行核空间距离聚类,以实现最小二乘支持向量机的数据预处理,从而实现其稀疏化;最后,在小样本数据集上进行了具体实验分析。结果表明,对于9种类型的故障,与其他基于不同类型支持向量机的诊断模型相比,所提诊断模型仅需11次迭代就可以获得最大适应度值,平均诊断准确率为96.67%,准确率和效率均更高。
中图分类号:
| [1] SONG L,WANG H,CHEN P.Step-by-step fuzzy diagnosismethod for equipment based on symptom extraction and trivalent logic fuzzy diagnosis theory[J].IEEE Transactions on Fuzzy Systems,2018,26(6):3467-3478. [2] HSU J Y,WANG Y F,LIN K C,et al.Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning[J].IEEE Access,2020,8:23427-23439. [3] GAO J H,ZHANG Y.Fault diagnosis of ship regional distribution power system based on FWA-PSO-MSVM[J].Computer Science,2022,49(S2):956-960. [4] LI X S,ZHANG Z Y.Fault diagnosis algorithm of transformer windings based on bayesian classification[J].Journal of University of Jinan(Science and Technology),2021,35(4):412-416. [5] SAHRI Z B,MALAYSIA U T.Support vector machine-based fault diagnosis of power transformer using k nearest-neighbor imputed DGA dataset[J].Journal of Computer and Communications,2014,2(9):22-31. [6] FENG Z L,XIAO H Q,REN W F,et al.Transformer fault diagnosis based on principal component analysis and seagull optimization support vector machine[J].China Measurement & Testing Technology,2023,49(2):99-105. [7] MENG L,XU T L,MA J Y,et al.There Search of Ls-SVM Based on LMD Morphology filter[J].Journal of Harbin University of Science and Technology,2022,27(1):92-99. [8] BUSTAMANTE S,MANANA M,ARROYO A,et al.Dissolved gas analysis equipment for online monitoring of transformer oil:A review[J].Sensors,2019,19(19):4057-4068. [9] QIAN G,HU J,WANG S,et al.Adsorption and Sensing Pro-perties of Dissolved Gas in Oil on Cr-Doped InN Monolayer:A Density Functional Theory Study[J].Chemosensors,2022,10(1):30-42. [10] ALTMAN E I,IWANICZ-DROZDOWSKA M,LAITINEN EK,et al.Financial distress prediction in an international context:A review and empirical analysis of Altman’s Z-score model[J].Journal of International Financial Management & Accounting,2017,28(2):131-171. [11] DEVORE G R.Computing the Z score and centiles for cross-sectional analysis:a practical approach[J].Journal of Ultrasound in Medicine,2017,36(3):459-473. [12] SOLTANZADEH P,HASHEMZADEH M.RCSMOTE:Range-Controlled synthetic minority over-sampling technique for handling the class imbalance problem[J].Information Sciences,2021,542:92-111. [13] DENG W,YAO R,ZHAO H,et al.A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm[J].Soft Computing,2019,23:2445-2462. [14] XIAO C,XIA W,JIANG J.Stock price forecast based on combined model of ARI-MA-LS-SVM[J].Neural Computing and Applications,2020,32:5379-5388. [15] CHENG Y,ZHU H,WU J,et al.Machine health monitoringusing adaptive kernel spectral clustering and deep long short-term memory recurrent neural networks[J].IEEE Transactions on Industrial Informatics,2018,15(2):987-997. [16] MENG Q J,YAO H C.Information assets behavior anomaly de-tection based on spectral clustering algorithm[J].Journal of Nanjing University of Science and Technology,2021,45(2):205-213. |
|
||
首页