Unique identification of machine parts is critical to production and maintenance, repair and overhaul (MRO) processes in the aerospace industry. Despite recent advances in automating these identification processes, many are still performed manually. This is time-consuming, labour-intensive and prone to error, particularly when dealing with visually similar objects that lack distinctive features or markings or when dealing with parts that lack readable identifiers due to factors such as dirt, wear and discolouration. Automation of these processes has the potential to alleviate these problems. However, due to the high visual similarity of components in the aerospace industry, commonly used object identifiers are not directly transferable to this domain. This work focuses on the challenging component spectrum engine tubes and aims to understand which identification method using only object-inherent properties can be applied to such problems. Therefore, this work investigates and proposes a comprehensive set of methods using 2D image or 3D point cloud data, incorporating digital image processing and deep learning approaches. Each of these methods is implemented to address the identification problem. A comprehensive benchmark problem is presented, consisting of a set of visually similar demonstrator tubes, which lack distinctive visual features or markers and pose a challenge to the different methods. We evaluate the performance of each algorithm to determine its potential applicability to the target domain and problem statement. Our results indicate a clear superiority of 3D approaches over 2D image analysis approaches, with PointNet and point cloud alignment achieving the best results in the benchmark.
Keywords: machine vision; neural networks; object-inherent features; similar object; visual part identification.