Characteristics of the acoustic emission during horizontal single grit scratch tests: Part 2 classification and grinding tests

The second part of this work follows on the work carried out in Part 1 where the investigations were made between the grinding phenomena: cutting, ploughing and rubbing. The demarcation between each of the phenomenon was identified from Acoustic Emission (AE) signals being converted to the frequency-time domains using Short-Time Fourier Transforms (STFTs). Other digital signal processing techniques were used and discussed; however, the more update and successful tests only required STFTs. This part of the paper looks at the classification using both Neural Networks (NNs) and fuzzy-c clustering/Genetic Algorithm (GA) techniques. After the cutting, ploughing and rubbing gave a high confidence in terms of classification accuracy, 1 μm and 0.1 mm grinding test data were applied to the classifiers. Interesting output results sufficed from both classifiers signifying a distinction that there is more cutting utilisation than both ploughing and rubbing as the interaction between grit and workpiece become more in contact with one another (measured depth of cut increases)