Vibration signals used for abnormality detection in machine health monitoring (MHM) are non-stationary in nature. Wavelet packet transform is extensively used in the literature for comprehensive analysis of non-stationary vibration signal but these techniques work only for a specific application lacking in some generalized methodology for selecting appropriate wavelet decomposition level and nodes for optimal performance. This study proposes a framework for inchoate fault detection by selecting the optimal wavelet decomposition level and nodes, named Optimally Parameterized Wavelet Packet Transform (OPWPT). OPWPT uses support vector machine to build the fault diagnostic model. Results in comparison with the existing schemes validate that OPWPT enhances the fault detection accuracy significantly in case of incipient faults when vibration signatures are very weak and overall signal to noise ratio is very poor.
Condition monitoring (CM) of the industrial equipment is growing auspiciously since the last decade or so. Whereas, very little efforts have been exerted on monitoring the vehicles that we ride every day. One of the main reasons is the actual cost of the CM equipment. Today an average level vibration based condition monitoring unit costs around the total price of the vehicle. Thanks to the advancement in the smart phone technology which provides a broad range of sensors and remarkable computational power in a small handheld devices. Owing to the capability of the smartphones to capture the vibrations using an internal built-in accelerometer, this paper proposes a cost effective vibration condition monitoring unit for the motor vehicles. The accelerometer in the smart phone has very limited capacity in terms sampling rate for the data acquisition. This paper proposes an enhanced sampling rate (ESR) technique for capturing the data at an improved sampling rate in spite of device limitation. Though a lot needs to be done both in terms of hardware optimization and fault diagnosis, the focus of this paper is to achieve an efficient data acquisition using smartphone. Experimental results are presented both for the simulated as well actual vibration datasets which validate the practicality and suitability of the proposed technique.