Recognition of Additive Manufacturing Parts Based on Neural Networks and Synthetic Training Data: A Generalized End-to-End Workflow

Abstract

Additive manufacturing (AM) is becoming increasingly relevant among established manufacturing processes. AM parts must often be recognized to sort them for part- or order-specific post-processing. Typically, the part recognition is performed manually, which represents a bottleneck in the AM process chain. To address this challenge, a generalized end-to-end workflow for automated visual real-time recognition of AM parts is presented, optimized, and evaluated. In the workflow, synthetic training images are generated from digital AM part models via rendering. These images are used to train a neural network for image classification, which can recognize the printed AM parts without design adaptations. As each production batch can consist of new parts, the workflow is generalized to be applicable to individual batches without adaptation. Data generation, network training and image classification are optimized in terms of the hardware requirements and computational resources for industrial applicability at low cost. For this, the influences of the neural network structure, the integration of a physics simulation in the rendering process and the total number of training images per AM part are analyzed. The proposed workflow is evaluated in an industrial case study involving 215 distinct AM part geometries. Part classification accuracies of 99.04% (top three) and 90.37% (top one) are achieved.

Keywords

• computer vision
• deep learning
• image classification
• synthetic training data
• additive manufacturing