{"title":"Classification of Initial Stripe Height Patterns using Radial Basis Function Neural Network for Proportional Gain Prediction","authors":"Prasit Wonglersak, Prakarnkiat Youngkong, Ittipon Cheowanish","country":null,"institution":"","volume":52,"journal":"International Journal of Computer and Information Engineering","pagesStart":377,"pagesEnd":380,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/12622","abstract":"This paper aims to improve a fine lapping process of\r\nhard disk drive (HDD) lapping machines by removing materials from\r\neach slider together with controlling the strip height (SH) variation to\r\nminimum value. The standard deviation is the key parameter to\r\nevaluate the strip height variation, hence it is minimized. In this\r\npaper, a design of experiment (DOE) with factorial analysis by twoway\r\nanalysis of variance (ANOVA) is adopted to obtain a\r\nstatistically information. The statistics results reveal that initial stripe\r\nheight patterns affect the final SH variation. Therefore, initial SH\r\nclassification using a radial basis function neural network is\r\nimplemented to achieve the proportional gain prediction.","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 52, 2011"}