Intersecting Machining Feature Localization and Recognition via Single Shot Multibox Detector

Abstract

In Industrie 4.0, machines are expected to become autonomous, self-aware and self-correcting. One important step in the area of manufacturing is feature recognition that aims to detect all the machining features from a 3D model. In this research area, recognising and locating a wide variety of highly intersecting features are extremely challenging as the topology information of features is substantially damaged because of the feature intersection. Motivated by the single shot multibox detector (SSD), this paper presents a novel deep learning approach named SsdNet to tackle the machining feature localisation and recognition problem. The typical SSD is designed for 2D image objection detection rather than 3D feature recognition. Therefore, the network architecture and output of SSD are modified to fulfil the purpose of this research. In addition, some advanced techniques are also utilised to further enhance the recognition performance. Experimental results on the benchmark dataset confirm that the proposed method achieves the state-of-the-art feature recognition performance (95.20% F-score), localisation performance (90.62% F-score) and recognition efficiency (243.85 milliseconds per model).

Adaptive recognition of machining features in sheet metal parts based on a graph class-incremental learning strategy

“…Many works approached AFR from a 2D perspective, such as multiple sectional view network (MsvNet) and single shot multibox detector network (SsdNet) proposed by Refs. 28,29 , which used 2D CNNs to learn 2D views of the 3D part models from different angles. However, 2D-view based methods lost the geometric and topological information of 3D part models and even had difficulty accurately locating the machined surfaces.…”

Manufacturing feature recognition method based on graph and minimum non-intersection feature volume suppression

“…However, the performance of learning-based methods highly relies on the accuracy of feature segmentation. It is rather difficult to accurately segmenting intersecting features according to the shape information, since the topology information of the features might be destroyed because of feature intersection [32]. Moreover, when a new feature is introduced to the system, the model must be entirely retrained using all training features.…”

Approaching STEP file analysis as a language processing task: A robust and scale-invariant solution for machining feature recognition

“…The 2D images produced are segmented to isolate individual features using the selective search algorithm, then individual feature representations are used as the input to a 2D CNN which performs feature recognition. This architecture was improved on in [13], which presented SsdNet, in which segmentation and feature recognition are combined into a single process based on the single shot multibox detector (SSD) [14]. In [15], PointNet++ [10], a hierarchical network which makes use of point cloud data, is used to perform both single-feature classification and multi-feature recognition.…”