北京工业大学学报
北京工業大學學報
북경공업대학학보
Journal of Beijing University of Technology
2015年
11期
1711-1717
,共7页
杨建武%高亚举%谷力超%刘志峰%亢太体%赵成斌
楊建武%高亞舉%穀力超%劉誌峰%亢太體%趙成斌
양건무%고아거%곡력초%류지봉%항태체%조성빈
旋转机械%故障诊断%模糊隶属度%模糊支持向量机
鏇轉機械%故障診斷%模糊隸屬度%模糊支持嚮量機
선전궤계%고장진단%모호대속도%모호지지향량궤
rotating machinery%fault diagnosis%fuzzy membership%fuzzy support vector machine
针对旋转机械故障诊断中采集到的振动信号存在强烈噪声及野值干扰,故障特征提取后,利用传统的支持向量机( support vector machine,SVM)进行模式识别会造成最优超平面的模糊性,影响分类效果,引入模糊C均值聚类算法( fuzzy C-means,FCM)与支持向量机结合进行故障诊断. FCM用来求解样本模糊隶属度,但其迭代求解聚类中心及样本模糊隶属度矩阵时容易陷入局部最优,而粒子群算法( particle swarm optimization,PSO)具有全局优化搜索的优点. 基于此,提出了基于改进模糊支持向量机( fuzzy support vector machine,FSVM)的旋转机械故障诊断算法. 首先,利用经验模态分解( empirical mode decomposition, EMD)提取故障信号的能量特征指标;然后,由PSO优化FCM求解样本的模糊隶属度;最后,将模糊隶属度引入SVM,构建改进的模糊支持向量机模型,并实现故障判别. 实验结果表明:改进的FSVM比传统的FSVM算法有更好的抗造性能以及分类效果.
針對鏇轉機械故障診斷中採集到的振動信號存在彊烈譟聲及野值榦擾,故障特徵提取後,利用傳統的支持嚮量機( support vector machine,SVM)進行模式識彆會造成最優超平麵的模糊性,影響分類效果,引入模糊C均值聚類算法( fuzzy C-means,FCM)與支持嚮量機結閤進行故障診斷. FCM用來求解樣本模糊隸屬度,但其迭代求解聚類中心及樣本模糊隸屬度矩陣時容易陷入跼部最優,而粒子群算法( particle swarm optimization,PSO)具有全跼優化搜索的優點. 基于此,提齣瞭基于改進模糊支持嚮量機( fuzzy support vector machine,FSVM)的鏇轉機械故障診斷算法. 首先,利用經驗模態分解( empirical mode decomposition, EMD)提取故障信號的能量特徵指標;然後,由PSO優化FCM求解樣本的模糊隸屬度;最後,將模糊隸屬度引入SVM,構建改進的模糊支持嚮量機模型,併實現故障判彆. 實驗結果錶明:改進的FSVM比傳統的FSVM算法有更好的抗造性能以及分類效果.
침대선전궤계고장진단중채집도적진동신호존재강렬조성급야치간우,고장특정제취후,이용전통적지지향량궤( support vector machine,SVM)진행모식식별회조성최우초평면적모호성,영향분류효과,인입모호C균치취류산법( fuzzy C-means,FCM)여지지향량궤결합진행고장진단. FCM용래구해양본모호대속도,단기질대구해취류중심급양본모호대속도구진시용역함입국부최우,이입자군산법( particle swarm optimization,PSO)구유전국우화수색적우점. 기우차,제출료기우개진모호지지향량궤( fuzzy support vector machine,FSVM)적선전궤계고장진단산법. 수선,이용경험모태분해( empirical mode decomposition, EMD)제취고장신호적능량특정지표;연후,유PSO우화FCM구해양본적모호대속도;최후,장모호대속도인입SVM,구건개진적모호지지향량궤모형,병실현고장판별. 실험결과표명:개진적FSVM비전통적FSVM산법유경호적항조성능이급분류효과.
In fault diagnosis of rotating machinery, the strong noise and outliers interference are usually contained in the vibration signals. After fault feature extraction, the method of traditional support vector machine ( SVM ) for the pattern recognition causes the fuzzy of optimal hyperplane and affects the classification results. So a fuzzy C-means ( FCM) clustering algorithm was introduced in this paper. FCM was used to solve the problem of fuzzy membership. However, the FCM had its own defects. The clustering result was sensitive to the initial center, and often cannot achieve the result of the global optimal. Improved by particle swarm optimization ( PSO) which has advantages of global optimization search, the FCM achieved better fuzzy memberships for each sample. So, the fault diagnosis algorithm of rotating machinery based on the improved fuzzy support vector machine ( FSVM) was proposed. First, fault features were extracted by using the empirical mode decomposition ( EMD) . Second, the problem of fuzzy membership was solved by using FCM which was optimized by PSO. At last the fuzzy memberships were put into SVM,the improved FSVM was founded and fault recognition was realized. Results of the experiment show that the improved FSVM has better anti-noise performance and the classification effect is better than that of the traditional FSVM algorithm.