Development of surface texture evaluation system for highly sparse data-driven machining domains

Abstract

ABSTRACT Dimensional, geometrical and surface texture tolerances are significant issues to be addressed by manufacturing industries. Dimensional and geometrical tolerance estimation systems are used by several machining industries, whereas surface texture tolerance estimation systems are rare. In general-purpose machines, several machining operations are performed and huge machining data are required for the development of surface texture tolerance estimation model. The necessity for sparse data modeling is the need of the hour and such modeling techniques reduce costly trial and error approaches. Shoulder milling operations are performed on mild steel workpieces. Experimentation is performed at diverse cutting conditions, and surface texture tolerances of the machined components are measured. Big data computation is being accomplished by contemporary tools compared to sparse data evaluation. The novelty of this work is to develop a system capable of surface texture tolerance evaluation from highly sparse learning data, as big data generation involves cost and time for experimentation. Flower Pollination Algorithm (FPA) models are developed for the highly sparse data for surface roughness estimation. Two different FPA techniques, namely, Maximum (Max) and Average (Avg) are used, and a comparison between the methods mentioned above is made. An operator-friendly adaptive performance enhancement system is developed to evaluate the corresponding surface texture tolerance for the given operating parameters.