Predicting Surface Texture in Steel Manufacturing at Speed

TL;DR

This paper introduces a GPU-accelerated machine learning approach using ROCKET in PyTorch to accurately and rapidly predict steel surface texture from inline laser reflection data, enabling real-time quality control.

Contribution

The paper's novelty lies in implementing ROCKET in PyTorch with a custom nonlinear pooling function to enhance speed and enable gradient flow for surface texture prediction.

Findings

GPU implementation significantly speeds up model inference.

The approach improves prediction accuracy over traditional methods.

Real-time feedback control becomes feasible with the proposed method.

Abstract

Control of the surface texture of steel strip during the galvanizing and temper rolling processes is essential to satisfy customer requirements and is conventionally measured post-production using a stylus. In-production laser reflection measurement is less consistent than physical measurement but enables real time adjustment of processing parameters to optimize product surface characteristics. We propose the use of machine learning to improve accuracy of the transformation from inline laser reflection measurements to a prediction of surface properties. In addition to accuracy, model evaluation speed is important for fast feedback control. The ROCKET model is one of the fastest state of the art models, however it can be sped up by utilizing a GPU. Our contribution is to implement the model in PyTorch for fast GPU kernel transforms and provide a soft version of the Proportion of Positive Values (PPV) nonlinear pooling function, allowing gradient flow. We perform timing and performance experiments comparing the implementations