Bosch, a German manufacturing and technology company, today announced that it will be using a decentralized machine learning network built by, an artificial intelligence lab based in the British city of Cambridge, to predict potential failures in manufacturing machinery.

Fast facts

  • The Bosch research team will be initiating machine learning trials on the Collective Learning Network, according to a company statement shared with Forkast.News. The trials aim to evaluate the feasibility and effectiveness of the system for predictive maintenance — to predict potential failures in machinery before they happen — to improve the efficiency of Bosch’s manufacturing operations.
  • The Collective Learning Network is a tool that enables parties to work together to train machine learning models without sharing underlying data or trusting any of the individual participants. The tool utilizes blockchain technology and AI learning capabilities to train the network to learn from private data without having access to it, according
  • Bosch Research — which focuses on research and implementation of innovative new technologies — entered into its first collaboration with in 2019 and deployed a node on a Fetch test network in early 2021.
  • Maintenance issues caused by machines failing can have significant effects on manufacturing processes. According to research by Deloitte, unplanned downtime costs industrial manufacturers an estimated US$50 billion each year.
  • “Using machine learning to identify equipment failures is a difficult problem to solve as these events occur very infrequently,” said Jonathan Ward, CTO at “The collective learning system enables the different manufacturers that use Bosch’s equipment to share information with each other without sharing the raw data, thereby greatly improving their ability to detect failures, and thus improv[ing] the efficiency of their operations.”