Accelerometers, used as vibration pickups in machine health monitoring systems, need physical connection to the machine tool through cables, complicating physical systems. A non-contact laser based vibration sensor has been developed and used for bearing health monitoring in this article. The vibration data have been acquired under speed and load variation. Hilbert transform (HT) has been applied for denoising the vibration signal. An extraction of condition monitoring indicators from both raw and envelope signals has been made, and the dimensionality of these extracted indicators was deducted with principal component analysis (PCA). Sequential floating forward selection (SFFS) method has been implemented for ranking the selected indicators in order of significance for reduction in the input vector size and for finalizing the most optimal indicator set. Finally, the selected indicators are passed to k-nearest neighbor (kNN) and weighted kNN (WkNN) for diagnosing the bearing defects. The comparative analysis of the effectiveness of kNN and WkNN has been executed. It is evident from the experimental results that the vibration signals obtained from developed non-contact sensor compare adequately with the accelerometer data obtained under similar conditions. The performance of WkNN has been found to be slower compared to kNN. The proposed fault detection methodology compares very well with the other reported methods in the literature. The non-contact fault detection methodology has an enormous potential for automatic recognition of defects in the machine, which can provide early signals to avoid catastrophic failure and unplanned equipment shutdowns.

Thirteen long tibia (bovine) bones were utilized in vitro to experimentally extract modal frequencies in the cranial-caudal (C-C) and medial–lateral (M–L) planes. Bones were instrumented with four single-axis accelerometers uniformly placed along the length of the bone and hammer impacted at different locations in both planes. Frequency response function (FRF) and complex mode indicator function (CMIF) techniques were used to identify the modal frequencies. CMIF has an advantage of detecting closely spaced modes by excluding misinterpreted peaks. It was found that the difference between the two methods did not exceed 2.98%. CMIF data were more consistent when varying impact location. The effect of bone's geometrical attributes on modal frequencies was statistically scrutinized and highly correlated parameters were identified. Bone length exhibited high correspondence to frequencies (p < 0.05) for practically all modes. Also, four simple equations were developed, relating modes 1 and 2 in the C-C and M-L planes to bone length. To determine the first and second modal shapes, subset of 6 tibia bones was further instrumented. Mode shapes were extracted in the C-C and M-L planes.