3D Roughness Prediction Modeling and Evaluation of Textured Liner of Piston Component-cylinder System

Abstract

Abstract In this study, a machine vision method is proposed to characterize 3D roughness of the textured surface on cylinder liner processed by plateau honing. The least absolute value (L∞) regression robust algorithm and Levenberg-Marquardt (LM) algorithm are employed to reconstruct image reference plane. On this basis, a single-hidden layer feedforward neural network (SLFNN) based on the extreme learning machine (ELM) is employed to model the relationship between high frequency information and 3D roughness. The characteristic parameters of Abbott-Firestone curve and 3D roughness measured by a confocal microscope are used to construct ELM-SLFNN prediction model for 3D roughness. The results indicate that the proposed method can effectively characterize 3D roughness of the textured surface of cylinder liner.