Approach towards sensor placement, selection and fusion for real-time condition monitoring of precision machines

被引:16
作者
Er, Poi Voon [1 ]
Teo, Chek Sing [2 ]
Tan, Kok Kiong [3 ]
机构
[1] Natl Univ Singapore, Dept Elect & Comp Engn, SIMTech NUS Joint Lab Precis Mot Syst, Singapore 117582, Singapore
[2] ASTAR, Singapore Inst Mfg Technol, SIMTech NUS Joint Lab Precis Mot Syst, Singapore 638075, Singapore
[3] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117582, Singapore
关键词
Sensor placement; Sensor location ranking; Sensitivity; Fisher Information; Radial Basis Function; Discrete Fourier Transform; ORBIT MODAL IDENTIFICATION; LOCATION;
D O I
10.1016/j.ymssp.2015.07.008
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Moving mechanical parts in a machine will inevitably generate vibration profiles reflecting its operating conditions. Vibration profile analysis is a useful tool for real-time condition monitoring to avoid loss of performance and unwanted machine downtime. In this paper, we propose and validate an approach for sensor placement, selection and fusion for continuous machine condition monitoring. The main idea is to use a minimal series of sensors mounted at key locations of a machine to measure and infer the actual vibration spectrum at a critical point where it is not suitable to mount a sensor. The locations for sensors' mountings which are subsequently used for vibration inference are identified based on sensitivity calibration at these locations moderated with normalized Fisher Information (NFI) associated with the measurement quality of the sensor at that location. Each of the identified sensor placement location is associated with one or more sensitive frequencies for which it ranks top in terms of the moderated sensitivities calibrated. A set of Radial Basis Function (RBF), each of them associated with a range of sensitive frequencies, is used to infer the vibration at the critical point for that frequency. The overall vibration spectrum of the critical point is then fused from these components. A comprehensive set of experimental results for validation of the proposed approach is provided in the paper. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:105 / 124
页数:20
相关论文
共 31 条
[1]   Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system [J].
Aliustaoglu, Cuneyt ;
Ertunc, H. Metin ;
Ocak, Hasan .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (02) :539-546
[2]  
[Anonymous], 1990, CIRP Annals-Manufacturing Technology, DOI [DOI 10.1016/S0007-8506, DOI 10.1016/S0007-8506(07)61012-9, 10.1016/s0007-8506]
[3]  
[Anonymous], 2011, IND AEROSPACE AUTOMO
[4]  
[Anonymous], 2007, Exploratory Data Analysis Using Fisher Information
[5]   SENSOR PLACEMENT IN OPTIMAL FILTERING AND SMOOTHING PROBLEMS [J].
ARBEL, A .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1982, 27 (01) :94-98
[6]   Optimal sensor placement for modal parameter identification using signal subspace correlation techniques [J].
Cherng, AP .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2003, 17 (02) :361-378
[7]  
CHUNG YT, 1993, P 11 INT MOD AN C
[8]   Real time monitoring of tool wear using multiple modeling method [J].
Ertunc, HM ;
Loparo, KA ;
Ozdemir, E ;
Ocak, H .
IEMDC 2001: IEEE INTERNATIONAL ELECTRIC MACHINES AND DRIVES CONFERENCE, 2001, :687-691
[9]   Layered Neural Networks with Gaussian Hidden Units as Universal Approximations [J].
Hartman, Eric J. ;
Keeler, James D. ;
Kowalski, Jacek M. .
NEURAL COMPUTATION, 1990, 2 (02) :210-215
[10]   Machine condition monitoring using principal component representations [J].
He, Qingbo ;
Yan, Ruqiang ;
Kong, Fanrang ;
Du, Ruxu .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (02) :446-466