Manufacturing meets ML

From members of the Mechanical and AI Lab (MAIL) at Carnegie Mellon University

More from MAILCheck out our GitHub


ManufacturingNet provides a sustainable, open-source ecosystem of modern artificial intelligence tools for tackling diverse engineering challenges.

Written in Python3 and designed for ease of use, ManufacturingNet's machine learning library simplifies AI for manufacturing professionals; no data science background is required, and programming is kept to a minimum.

Interested in trying ManufacturingNet? Visit our documentation to learn how to get started.

The manufacturing industry is one of the largest industries in the world, vitally supporting the economies of many countries across the globe. With the growing deployability of artificial intelligence (AI), manufacturers are turning to AI to turn their production plants into smart factories. Factories based on lean manufacturing have improved worker safety, and can deliver quality products faster to their customers. As the manufacturing industry embraces machine learning, demand grows for user-friendly tools that can deploy complex machine learning models with relative ease. In particular, deep learning tools need a considerable amount of programming knowledge and, thus, remain obscure to engineers inexperienced with programming. In this work, we propose ManufacturingNet, an open-source machine learning tool for engineers based on Scikit-Learn and PyTorch. Along with ManufacturingNet, we curated ten publicly-available datasets and benchmarked the performance using ManufacturingNet‘s machine learning models. We obtained state-of-the-art results for each dataset, and have included pre-trained models with our package. We believe ManufacturingNet will enable engineers around the world to deploy machine learning models with ease.