Measurement of surface roughness parameter using a neural network and laser scattering

The quality of surfaces is obtained by the utilization of scattered laser light examinedby a neural network. Features are extracted from the scattered angular spectrum which are then used as inputs to a hierarchical neural net. The net is “trained” by a selected set of machined surfaces whose quality has already been independently established. These samples are repeatedly presented to the sensors and the network will, each time, make a decision about the surface roughness which is then compared to the correct answer, and the error is used to modify the connection weights. Following this training period, the net is able to identify the quality of new surfaces presented to it. Experimental results, using a set of lapped surfaces are discussed with regard to fusion of different features in order to obtain an adequate measure of surface roughness using the neural network. It is shown that the system is able to measure the roughness parameter, R_a, in the micron range to sub-micron accuracy. Furthermore, this non-contact measurement is performed in the millisecond time range which can be used for on-line quality control.