Machine learning is a scientific discipline that recognizes complex patterns and makes intelligent decisions based on data. With the development of several techniques, the discipline has achieved many milestones but so far limited to research. However, most manufacturing operations — such as repairing an aircraft engine, planning the product mix in cement production or ensuring energy control in a large facility — are still largely dependent on experience-based human decisions. The advent of big data technology, coupled with efficient data storage mechanisms and parallel processing frameworks, has driven new uses for the petabytes of data generated by manufacturing operations. Applying machine learning techniques to the shop floor has increased accuracy in decision-making and improved performance.
This paper explores how machine learning algorithms, in conjunction with big data technologies, can help manufacturers bring about operational and business transformation.The solution for predictive maintenance analytics using logistic regression trained by stochastic gradient decent, as presented in this paper, demonstrates how machine learning can enable accurate prediction of failure events on the press line.
Date published: August 2016
Authors:
- Jiby Joseph, Tata Consulting Services
- Omar Sharif, Tata Consulting Services
- Ajit Kumar, Tata Consulting Services
- Senthil Kumar, Tata Consulting Services
- Simon Jacobson, Gartner
- Ananth Seshan, Fifthgentech
- Elena Heath, TE
- Karen Smiley, ABB
- Gerhard Greeff, Bytes