Automated Marble Plate Classification System Based On Different Neural Network Input Training Sets and PLC Implementation

TL;DR

This paper presents an automated marble plate classification system using neural networks trained on various input sets, implemented on a PLC for real-time, cost-effective industrial sorting.

Contribution

It introduces a novel approach combining different neural network input training sets for marble surface classification, optimized for simple, real-time PLC implementation.

Findings

High classification accuracy achieved with texture histograms, DCT, and Wavelet inputs.

System operates quickly and effectively in real-time industrial settings.

Implementation on standard PLC devices reduces costs and complexity.

Abstract

The process of sorting marble plates according to their surface texture is an important task in the automated marble plate production. Nowadays some inspection systems in marble industry that automate the classification tasks are too expensive and are compatible only with specific technological equipment in the plant. In this paper a new approach to the design of an Automated Marble Plate Classification System (AMPCS),based on different neural network input training sets is proposed, aiming at high classification accuracy using simple processing and application of only standard devices. It is based on training a classification MLP neural network with three different input training sets: extracted texture histograms, Discrete Cosine and Wavelet Transform over the histograms. The algorithm is implemented in a PLC for real-time operation. The performance of the system is assessed with each one of the input training sets. The experimental test results regarding classification accuracy and quick operation are represented and discussed.