# Scope for Machine Learning in Digital Manufacturing

**Authors:** Martin Baumers, Ender Ozcan  
**arXiv:** [1609.05835](https://arxiv.org/abs/1609.05835)  
**Date:** 2016-09-19  
**Summary page:** https://www.summarizepaper.com/en/paper/1609.05835v1/

## Key points

- The paper provides an overview of the optimization problem in Digital Manufacturing
- Digital Manufacturing is evolving to encompass computerized manufacturing, supply chain processes, and information utilization throughout the product life cycle
- Additive Manufacturing is used as an example to identify an integrated multi-objective optimization problem in Digital Manufacturing
- Data science and optimization can be concurrently applied to address this problem
- Challenges include compliance with new standards and integration of data science techniques into existing manufacturing environment
- The paper references a position paper on machine learning in manufacturing, which explores its application in predictive maintenance, demand forecasting, process monitoring, and optimization
- Machine learning and optimization techniques have the potential to enhance digital manufacturing processes by improving efficiency and productivity through data science integration.

## Summary

This paper titled "Scope for Machine Learning in Digital Manufacturing" provides an overview of the underlying optimization problem in the emerging field of Digital Manufacturing. It discusses how the concept is evolving from software tools for integrating production and design functions to a broader concept that encompasses computerized manufacturing and supply chain processes as well as information collection and utilization throughout the product life cycle. The authors use Additive Manufacturing as an example to identify an integrated multi-objective optimization problem that underlies Digital Manufacturing. They highlight the opportunity for concurrent application of data science and optimization in addressing this problem and outline a set of challenges arising from it, emphasizing on compliance with new standards and integration of data science techniques into existing manufacturing environment. The paper references a position paper presented at Royal Society Workshop on Realizing the Benefits of Machine Learning in Manufacturing which aimed to explore how machine learning techniques can be applied to various aspects of manufacturing such as predictive maintenance, demand forecasting, process monitoring and optimization. This paper highlights potential for machine learning and optimization techniques to enhance digital manufacturing processes by leveraging opportunities for improved efficiency and productivity through integration of data science into manufacturing environments.