Data Fusion Method Based on Mutual Dimensionless

Since data fusion in the process of the traditional fault diagnosis method is not accurate enough, it is difficult to use the dimensionless index to distinguish among fault types of problems. This paper proposes a data fusion method based on mutual dimensionless. This method uses real-time acquisition of original data and dimensionless calculations, obtains five dimensionless indices for each dataset, and then uses support vector machine (SVM) model projections for the dataset to judge fault types. Using dimensionless indices to process raw data, the SVM method for training can more effectively solve the problem due to the imperfection of the old dimensionless index leading to a low accuracy of fault diagnosis. Using a petrochemical rotary machinery experiment, the accuracy of the method of fault diagnosis is higher; in a single experiment, the fault detection accuracy can reach 100%, where compared with the traditional dimensionless index data fusion method, the accuracy is increased by 20.74%. The method has stronger ability to judge failures.

[1]  Mohd Jailani Mohd Nor,et al.  Statistical analysis of sound and vibration signals for monitoring rolling element bearing condition , 1998 .

[2]  P. L. Bogler,et al.  Shafer-dempster reasoning with applications to multisensor target identification systems , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Kai Goebel,et al.  Correcting Sensor Drift and Intermittency Faults With Data Fusion and Automated Learning , 2008, IEEE Systems Journal.

[4]  Shen Yin,et al.  On PCA-based fault diagnosis techniques , 2010, 2010 Conference on Control and Fault-Tolerant Systems (SysTol).

[5]  Huijun Gao,et al.  Fault Detection for Discrete Systems With Network-Induced Nonlinearities , 2014, IEEE Transactions on Industrial Informatics.

[6]  Chih-Jen Lin,et al.  A Comparison of Methods for Multi-class Support Vector Machines , 2015 .

[7]  Liu Yong-an.  Information fusion method for fault diagnosis , 2007 .

[8]  Behzad Moshiri,et al.  Pseudo information measure: a new concept for extension of Bayesian fusion in robotic map building , 2002, Inf. Fusion.

[9]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[10]  Steven X. Ding,et al.  A Review on Basic Data-Driven Approaches for Industrial Process Monitoring , 2014, IEEE Transactions on Industrial Electronics.

[11]  Liang Yan,et al.  High-Accuracy Tracking Control of Hydraulic Rotary Actuators With Modeling Uncertainties , 2014, IEEE/ASME Transactions on Mechatronics.

[12]  Steven X. Ding,et al.  Real-Time Implementation of Fault-Tolerant Control Systems With Performance Optimization , 2014, IEEE Transactions on Industrial Electronics.

[13]  Qinhua Zhang,et al.  Fusion of the Dimensionless Parameters and Filtering Methods in Rotating Machinery Fault Diagnosis , 2014, J. Networks.

[14]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[15]  Philippe Smets,et al.  The Combination of Evidence in the Transferable Belief Model , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Zhenwei Cao,et al.  Intelligent Sensorless ABS for In-Wheel Electric Vehicles , 2014, IEEE Transactions on Industrial Electronics.

[17]  王赟松,et al.  Multisensor Data Fusion for Automotive Engine Fault Diagnosis , 2004 .

[18]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[19]  Qinghua Zhang,et al.  An Information Fusion Fault Diagnosis Method Based on Dimensionless Indicators With Static Discounting Factor and KNN , 2016, IEEE Sensors Journal.

[20]  Chih-Jen Lin,et al.  Formulations of Support Vector Machines: A Note from an Optimization Point of View , 2001, Neural Computation.

[21]  Hee-Jun Kang,et al.  Bearing Defect Classification Based on Individual Wavelet Local Fisher Discriminant Analysis with Particle Swarm Optimization , 2016, IEEE Transactions on Industrial Informatics.

[22]  Jose A. Antonino-Daviu,et al.  Scale Invariant Feature Extraction Algorithm for the Automatic Diagnosis of Rotor Asymmetries in Induction Motors , 2013, IEEE Transactions on Industrial Informatics.

[23]  X. E. Gros,et al.  A Bayesian approach to NDT data fusion , 1995 .

[24]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[25]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[26]  Meng Joo Er,et al.  Robust adaptive control of robot manipulators using generalized fuzzy neural networks , 2003, IEEE Trans. Ind. Electron..

[27]  Qi Wang,et al.  A Diagnosis Method for Rotation Machinery Faults Based on Dimensionless Indexes Combined with -Nearest Neighbor Algorithm , 2015 .

[28]  Adel Belouchrani,et al.  Fault Diagnosis in Industrial Induction Machines Through Discrete Wavelet Transform , 2011, IEEE Transactions on Industrial Electronics.

[29]  Hamid Reza Karimi,et al.  Data-driven design of robust fault detection system for wind turbines , 2014 .

[30]  Jawad Faiz,et al.  Advanced Eccentricity Fault Recognition in Permanent Magnet Synchronous Motors Using Stator Current Signature Analysis , 2014, IEEE Transactions on Industrial Electronics.

[31]  Liu Yan-yan.  Application of data fusion based on fuzzy neural network in transmission line fault diagnosis , 2005 .

[32]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[33]  Shalabh Gupta,et al.  Optimal Sensor Selection and Fusion for Heat Exchanger Fouling Diagnosis in Aerospace Systems , 2016, IEEE Sensors Journal.

[34]  Qin Hu,et al.  Concurrent Fault Diagnosis for Rotating Machinery Based on Vibration Sensors , 2013, Int. J. Distributed Sens. Networks.

[35]  Xing Weiwei,et al.  Research progress of multi-sensor data fusion technology , 2010 .