No abstract

A three-state Kalman tracker Is described for tracking a moving target, such as an aircraft, making use of the position and rate measurements oblalned by a track-whlle-scan radar sensor which employs pulsed Doppler processing, such as the moving target detector providing unambiguous Doppler data. The steady-state ruter parameters have been analytically obtained under the assun.,tlon of while noise maneuver capabllily. The numerical computallons of these parameters are In exceUent agreement with those obtained from the recursive Kalman filter matrix equations. The solutIon for the case when only the range measurements are available Is obtained as a special case of this model Graphs of normalized covariances and gains are presented to Iliustrate how the solution depends on different parameters.

Fault diagnosis of gearboxes plays an important role in increasing the availability of machinery in condition monitoring. An effort has been made in this work to develop an artificial neural networks (ANN) based fault detection system to increase reliability. Two prominent fault conditions in gears, worn-out and broken teeth, are simulated and five feature parameters are extracted based on vibration signals which are used as input features to the ANN based fault detection system developed in MATLAB, a three layered feed forward network using a back propagation algorithm. This ANN system has been trained with 30 sets of data and tested with 10 sets of data. The learning rate and number of hidden layer neurons are varied individually and the optimal training parameters are found based on the number of epochs. Among the five different learning rates used the 0.15 is deduced to be optimal one and at that learning rate the number of hidden layer neurons of 9 was the optimal one out of the three values considered. Then keeping the training parameters fixed, the number of hidden layers is varied by comparing the performance of the networks and results show the two and three hidden layers have the best detection accuracy.

No abstract

No abstract