Search for: All records

The number of published manufacturing science digital articles available from scientifc journals and the broader web have exponentially increased every year since the 1990s. To assimilate all of this knowledge by a novice engineer or an experienced researcher, requires signifcant synthesis of the existing knowledge space contained within published material, to fnd answers to basic and complex queries. Algorithmic approaches through machine learning and specifcally Natural Language Processing (NLP) on a domain specifc area such as manufacturing, is lacking. One of the signifcant challenges to analyzing manufacturing vocabulary is the lack of a named entity recognition model that enables algorithms to classify the manufacturing corpus of words under various manufacturing semantic categories. This work presents a supervised machine learning approach to categorize unstructured text from 500K+manufacturing science related scientifc abstracts and labelling them under various manufacturing topic categories. A neural network model using a bidirectional long-short term memory, plus a conditional random feld (BiLSTM+CRF) is trained to extract information from manufacturing science abstracts. Our classifer achieves an overall accuracy (f1-score) of 88%, which is quite near to the state-of-the-art performance. Two use case examples are presented that demonstrate the value of the developed NER model as a Technical Language Processing (TLP) workfow on manufacturing science documents. The long term goal is to extract valuable knowledge regarding the connections and relationships between key manufacturing concepts/entities available within millions of manufacturing documents into a structured labeled-property graph data structure that allow for programmatic query and retrieval. 

Abstract Deep neural networks have shown promising success towards the classification and retrieval tasks for images and text data. While there have been several implementations of deep networks in the area of computer graphics, these algorithms do not translate easily across different datasets, especially for shapes used in product design and manufacturing domain. Unlike datasets used in the 3D shape classification and retrieval in the computer graphics domain, engineering level description of 3D models do not yield themselves to neat distinct classes. The current study looks at an improved form of the 3D shape deep learning algorithm for classification and retrieval through the use of techniques such as relaxed classification, use of prime angled camera angles for capturing feature detail and transfer learning for reducing the amount of data and processing time needed to train shape recognition algorithms. The proposed algorithm (MVCNN++) builds on top of multi-view convolutional neural network (MVCNN) algorithm, improving its efficacy for manufacturing part classification by enabling use of part metadata, yielding an improvement of almost 6% over the original version. With the explosive growth of 3D product models available in publicly available repositories, search and discovery of relevant models is critical to democratizing access to design models. 

Abstract Data driven advanced manufacturing research is dependent on access to large datasets made available from across the product lifecycle — from the concept design phase all the way down to end use and disposal. Despite such data being generated at a rapid pace, most product design data is archived in inaccessible silos. This is particularly acute in academic research laboratories and with data generated during product design and manufacturing courses. This project seeks to create an infrastructure that allow users (academia and the general public) to easily upload project data and related meta-data. Current manufacturing research must shift from siloed repositories of product manufacturing data to a federated, decentralized, open and inter-operable approach. In this regard, we build ‘FabWave’ a cyber-infrastructure tool designed to capture manufacturing data. In its first pilot implementation, we focused our attention to gathering information rich 3D Mechanical CAD data and related meta-data associated with them, with the intent to make it easier for users to upload and access product design data. We describe workflows that we have initially tested out within the two academic universities and under two different course structures. We have also developed automated workflows to gather license appropriate CAD assemblies from commercial repositories. Our intent is to create the only known largest available CAD model set within academia for enabling research in data-driven computational research in digital design, fabrication and quality control.