End-to-End Defect Detection in Automated Fiber Placement Based on Artificially Generated Data

TL;DR

This paper introduces an end-to-end deep learning approach for AFP defect detection using artificially generated data, enabling scalable and adaptable inspection without extensive real-world data.

Contribution

It formulates AFP defect detection as an image segmentation task trained on synthetic data, reducing reliance on handcrafted features and domain-specific tuning.

Findings

Effective defect detection with minimal real data

Scalable to new defect types and measurement devices

Utilizes synthetic data for training deep neural networks

Abstract

Automated fiber placement (AFP) is an advanced manufacturing technology that increases the rate of production of composite materials. At the same time, the need for adaptable and fast inline control methods of such parts raises. Existing inspection systems make use of handcrafted filter chains and feature detectors, tuned for a specific measurement methods by domain experts. These methods hardly scale to new defects or different measurement devices. In this paper, we propose to formulate AFP defect detection as an image segmentation problem that can be solved in an end-to-end fashion using artificially generated training data. We employ a probabilistic graphical model to generate training images and annotations. We then train a deep neural network based on recent architectures designed for image segmentation. This leads to an appealing method that scales well with new defect types and measurement devices and requires little real world data for training.