Topography scanning as a part of process monitoring in power cable insulation process

TL;DR

This paper introduces a new topography scanning system for XLPE cable core monitoring, combining advanced measurement tech and deep learning to detect surface defects and analyze geometry errors in real time.

Contribution

It presents a novel integrated system that uses high-performance computing and deep learning for detailed 3D surface mapping and defect detection in power cable insulation.

Findings

Convolutional neural networks effectively detect surface defects in real time.

The system identifies melt homogeneity as a key factor affecting geometry errors.

High-resolution 3D surface maps enable detailed analysis of cable core surface quality.

Abstract

We present a novel topography scanning system developed to XLPE cable core monitoring. Modern measurement technology is utilized together with embedded high-performance computing to build a complete and detailed 3D surface map of the insulated core. Cross sectional and lengthwise geometry errors are studied, and melt homogeneity is identified as one major factor for these errors. A surface defect detection system has been developed utilizing deep learning methods. Our results show that convolutional neural networks are well suited for real time analysis of surface measurement data enabling reliable detection of surface defects.