AP聚类改进免疫算法用于航空发动机故障诊断
|
摘要
在免疫算法训练过程中引入近邻传播(AP)聚类与熵权法,对训练样本进行聚类与权值计算,将权值引入免疫算法中样本选择阈值的计算,以解决训练过程采用固定选择阈值所造成的检测器在部分区域过拟合,部分区域欠拟合的问题。结果表明:改进的免疫算法用于典型非线性函数的寻优时,迭代性能均优于传统免疫算法,并在大部分情况下优于粒子群算法与量子遗传算法,在进行某型发动机故障诊断的实例实验时,改进后的算法的诊断准确率达到98.06%,高于传统免疫算法的92.60%。
In the process of immune algorithm training,the affinity propagation(AP)clustering and entropy weight method were introduced,the training samples were clustered and weighted,and the weights were introduced into the calculation of the sample selection threshold in the immune algorithm to solve the problem of a fixed selection threshold in the training process,which led to over fitting of the detector in a partial area,and under-fitting of the partial area.Result showed that,when the improved immune algorithm was used for the optimization of typical nonlinear functions,the iterative performance was better than the traditional immune algorithm.In most cases it was better than the particle swarm optimization algorithm and the quantum genetic algorithm,in the case of a certain type of engine fault diagnosis.The improved algorithm had a diagnostic accuracy of 98.06%,which was higher than 92.60% of the traditional immune algorithm.
In the process of immune algorithm training,the affinity propagation(AP)clustering and entropy weight method were introduced,the training samples were clustered and weighted,and the weights were introduced into the calculation of the sample selection threshold in the immune algorithm to solve the problem of a fixed selection threshold in the training process,which led to over fitting of the detector in a partial area,and under-fitting of the partial area.Result showed that,when the improved immune algorithm was used for the optimization of typical nonlinear functions,the iterative performance was better than the traditional immune algorithm.In most cases it was better than the particle swarm optimization algorithm and the quantum genetic algorithm,in the case of a certain type of engine fault diagnosis.The improved algorithm had a diagnostic accuracy of 98.06%,which was higher than 92.60% of the traditional immune algorithm.
引文
[1]程超,汪久根.双列角接触球轴承的免疫算法优化设计[J].航空动力学报,2015,30(11):2810-2816.CHENG Chao,WANG Jiugen.Optimization design of immune algorithm for double row angular contact ball bearings[J].Journal of Aerospace Power,2015,30(11):2810-2816.(in Chinese)
[2]宋丹,樊晓平,文中华.模糊非基因信息记忆的双克隆选择算法[J].电子与信息学报,2017,39(2):255-262.SONG Dan,FAN Xiaoping,WEN Zhonghua.Double clonal selection algorithm for fuzzy non-genetic information memory[J].Journal of Electronics and Information Technology,2017,39(2):255-262.(in Chinese)
[3]张弛,贾丽媛,王加阳.改进的混合免疫算法在约束函数优化中的应用[J].中南大学学报,2016,47(6):1940-1946.ZHANG Chi,JIA Liyuan,WANG Jiayang.Application of improved hybrid immune algorithm in constraint function optimization[J].Journal of Central South University,2016,47(6):1940-1946.(in Chinese)
[4]PAN Guo,LI Kenli,OUYANG Aijia.Hybrid immune algorithm based on greedy algorithm and delete-cross operator for solving TSP[J].Soft Computing,2016,20(2):555-566.
[5]LIU Xufei,CHUNG T.A modified immunoglobulin-based artificial immune system algorithm for solving the permutation flow shop scheduling problem[J].Journal of Industrial and Production Engineering,2017,34(7):542-550.
[6]YU Xiao,ZHOU Zijie,RIHA K.Blurred infrared image segmentation using new immune algorithm with minimum mean distanceimmune field[J].Spectroscopy and Spectral Analysis,2018,38(11):3645-3652.
[7]魏明军,王月月,金建国.一种改进免疫算法的入侵检测设计[J].西安电子科技大学学报,2016,43(2):126-131.WEI Mingjun,WANG Yueyue.JIN Jianguo.An intrusion detection design based on improved immune algorithm[J].Journal of Xidian University,2016,43(2):126-131.(in Chinese)
[8]ZHANG Weiwei,GAO Kui,ZHANG Weizheng.A hybrid clonal selection algorithm with modified combinatorial recombination and success-history based adaptive mutation for numerical optimization[J].Applied Intelligence,2019,49(2):819-836.
[9]ZHANG Hanye.An improved immune algorithm for simple assembly line balancing problem of type 1[J].Journal of Algorithms and Computational Technology,2017,11(4):317-326.
[10]GOSCINIAK I.Discussion on semi-immune algorithm behaviour based on fractal analysis[J].Soft Computing,2017,21(14):3945-3956.
[11]李海林,魏苗.基于近邻传播的限定簇数聚类方法研究[J].电子科技大学学报,2018,47(5):733-739.LI Hailin,WEI Miao.Research on clustering method of limited cluster number based on neighbor propagation[J].Journal of University of Electronic Science and Technology of China,2018,47(5):733-739.(in Chinese)
[12]徐青山,娄藕蝶,郑爱霞,等.基于近邻传播聚类和遗传优化的非侵入式负荷分解方法[J].电工技术学报,2018,33(16):3868-3878.XU Qingshan,LOU Oudie,ZHENG Aixia,et al.Nonintrusive load decomposition method based on neighbor propagation clustering and genetic optimization[J].Transactions of China Electrotechnical Society,2018,33(16):3868-3878.(in Chinese)
[13]张伟,许爱强,平殿发,等.基于近邻传播聚类的航空电子部件LMK诊断模型[J].北京航空航天大学学报,2018,44(8):1693-1704.ZHANG Wei,XU Aiqiang,PING Dianfa,et al.Diagnostic model of avionics components based on near-neighbor propagation clustering[J].Journal of Beijing University of Aeronautics and Astronautics,2018,44(8):1693-1704.(in Chinese)
[14]李海林,王成,邓晓懿.基于分量属性近邻传播的多元时间序列数据聚类方法[J].控制与决策,2018,33(4):649-656.LI Hailin,WANG Cheng,DENG Xiaowei.Multivariate time series data clustering method based on component attribute neighbor propagation[J].Control and Decision,2018,33(4):649-656.(in Chinese)
[15]徐明亮,王士同,杭文龙,一种基于同类约束的半监督近邻反射传播聚类方法[J].自动化学报,2016,42(2):255-269.XU Mingliang,WANG Shitong,HANG Wenlong.A semisupervised nearest neighbor reflection propagation clustering method based on similar constraints[J].Acta Automatica Sinica,2016,42(2):255-269.(in Chinese)
[16]孙文舟,殷晓东,李树军,基于熵权重的水下载体导航信息融合方法[J].武汉大学学报,2018,43(10):1465-1471.SUN Wenzhou,YIN Xiaodong,LI Shujun.Underwater carrier navigation information fusion method based on entropy weight[J].Journal of Wuhan University,2018,43(10):1465-1471.(in Chinese)
[17]李文璟,李梦,刑宁哲,等.基于熵权-灰色模型的电力数据网风险预测[J].北京邮电大学学报,2018,41(3):39-45.LI Wenbiao,LI Meng,XING Ningzhe,et al.Risk prediction of power data network based on entropy weight-gray model[J].Journal of Beijing University of Posts and Telecommunications,2018,41(3):39-45.(in Chinese)
[18]陈秀明,刘业政.基于熵权的多粒度犹豫模糊语言VIKOR群推荐方法[J].控制与决策,2018,33(1):111-118.CHEN Xiuming,LIU Yezheng.Multi-granular hesitant fuzzy language VIKOR group recommendation method based on entropy weight[J].Control and Decision,2018,33(1):111-118.(in Chinese)
[19]焦李成,杜海峰,刘芳,等.免疫优化计算、学习与识别[M].北京科学出版社,2006.
[2]宋丹,樊晓平,文中华.模糊非基因信息记忆的双克隆选择算法[J].电子与信息学报,2017,39(2):255-262.SONG Dan,FAN Xiaoping,WEN Zhonghua.Double clonal selection algorithm for fuzzy non-genetic information memory[J].Journal of Electronics and Information Technology,2017,39(2):255-262.(in Chinese)
[3]张弛,贾丽媛,王加阳.改进的混合免疫算法在约束函数优化中的应用[J].中南大学学报,2016,47(6):1940-1946.ZHANG Chi,JIA Liyuan,WANG Jiayang.Application of improved hybrid immune algorithm in constraint function optimization[J].Journal of Central South University,2016,47(6):1940-1946.(in Chinese)
[4]PAN Guo,LI Kenli,OUYANG Aijia.Hybrid immune algorithm based on greedy algorithm and delete-cross operator for solving TSP[J].Soft Computing,2016,20(2):555-566.
[5]LIU Xufei,CHUNG T.A modified immunoglobulin-based artificial immune system algorithm for solving the permutation flow shop scheduling problem[J].Journal of Industrial and Production Engineering,2017,34(7):542-550.
[6]YU Xiao,ZHOU Zijie,RIHA K.Blurred infrared image segmentation using new immune algorithm with minimum mean distanceimmune field[J].Spectroscopy and Spectral Analysis,2018,38(11):3645-3652.
[7]魏明军,王月月,金建国.一种改进免疫算法的入侵检测设计[J].西安电子科技大学学报,2016,43(2):126-131.WEI Mingjun,WANG Yueyue.JIN Jianguo.An intrusion detection design based on improved immune algorithm[J].Journal of Xidian University,2016,43(2):126-131.(in Chinese)
[8]ZHANG Weiwei,GAO Kui,ZHANG Weizheng.A hybrid clonal selection algorithm with modified combinatorial recombination and success-history based adaptive mutation for numerical optimization[J].Applied Intelligence,2019,49(2):819-836.
[9]ZHANG Hanye.An improved immune algorithm for simple assembly line balancing problem of type 1[J].Journal of Algorithms and Computational Technology,2017,11(4):317-326.
[10]GOSCINIAK I.Discussion on semi-immune algorithm behaviour based on fractal analysis[J].Soft Computing,2017,21(14):3945-3956.
[11]李海林,魏苗.基于近邻传播的限定簇数聚类方法研究[J].电子科技大学学报,2018,47(5):733-739.LI Hailin,WEI Miao.Research on clustering method of limited cluster number based on neighbor propagation[J].Journal of University of Electronic Science and Technology of China,2018,47(5):733-739.(in Chinese)
[12]徐青山,娄藕蝶,郑爱霞,等.基于近邻传播聚类和遗传优化的非侵入式负荷分解方法[J].电工技术学报,2018,33(16):3868-3878.XU Qingshan,LOU Oudie,ZHENG Aixia,et al.Nonintrusive load decomposition method based on neighbor propagation clustering and genetic optimization[J].Transactions of China Electrotechnical Society,2018,33(16):3868-3878.(in Chinese)
[13]张伟,许爱强,平殿发,等.基于近邻传播聚类的航空电子部件LMK诊断模型[J].北京航空航天大学学报,2018,44(8):1693-1704.ZHANG Wei,XU Aiqiang,PING Dianfa,et al.Diagnostic model of avionics components based on near-neighbor propagation clustering[J].Journal of Beijing University of Aeronautics and Astronautics,2018,44(8):1693-1704.(in Chinese)
[14]李海林,王成,邓晓懿.基于分量属性近邻传播的多元时间序列数据聚类方法[J].控制与决策,2018,33(4):649-656.LI Hailin,WANG Cheng,DENG Xiaowei.Multivariate time series data clustering method based on component attribute neighbor propagation[J].Control and Decision,2018,33(4):649-656.(in Chinese)
[15]徐明亮,王士同,杭文龙,一种基于同类约束的半监督近邻反射传播聚类方法[J].自动化学报,2016,42(2):255-269.XU Mingliang,WANG Shitong,HANG Wenlong.A semisupervised nearest neighbor reflection propagation clustering method based on similar constraints[J].Acta Automatica Sinica,2016,42(2):255-269.(in Chinese)
[16]孙文舟,殷晓东,李树军,基于熵权重的水下载体导航信息融合方法[J].武汉大学学报,2018,43(10):1465-1471.SUN Wenzhou,YIN Xiaodong,LI Shujun.Underwater carrier navigation information fusion method based on entropy weight[J].Journal of Wuhan University,2018,43(10):1465-1471.(in Chinese)
[17]李文璟,李梦,刑宁哲,等.基于熵权-灰色模型的电力数据网风险预测[J].北京邮电大学学报,2018,41(3):39-45.LI Wenbiao,LI Meng,XING Ningzhe,et al.Risk prediction of power data network based on entropy weight-gray model[J].Journal of Beijing University of Posts and Telecommunications,2018,41(3):39-45.(in Chinese)
[18]陈秀明,刘业政.基于熵权的多粒度犹豫模糊语言VIKOR群推荐方法[J].控制与决策,2018,33(1):111-118.CHEN Xiuming,LIU Yezheng.Multi-granular hesitant fuzzy language VIKOR group recommendation method based on entropy weight[J].Control and Decision,2018,33(1):111-118.(in Chinese)
[19]焦李成,杜海峰,刘芳,等.免疫优化计算、学习与识别[M].北京科学出版社,2006.