Our case studies highlight some of the ways we’re contributing to the global data-driven revolution. They show how we’ve used key analytical technologies to keep machines running as smoothly and productively as possible.
With a tyre building machine, one process needs to finish properly before the next one can start. If this doesn’t happen, an operator needs to step in and put things right before restarting the machine. We began by identifying recurring issues and then used machine learning to monitor where things were going off track. An auto-correction system was set up inside the machine to iron out any errors, so there was less need for human intervention and downtime.
With a tyre building machine, one process needs to finish properly before the next one can start.
A deep data analysis of all the processes happening inside our tyre-building machines meant we could take steps to reduce inconsistencies in individual units. This process stabilisation allows for smoother, more consistent operation, so the machine can be used for longer and produce more tyres.
Cloud Data Analysis
We used data from the factory floor and real-time information from production machines to get a deep understanding of how our tyre mixer machines were performing. Supported by Amazon Web Services, we captured 126 parameters across all our mixers every second. This meant we could carry out detailed analysis of each process within the mixer, identifying areas where we could drive efficiency gains. Benchmarking and standardising processes across our machines has helped us increase productivity, leading to energy savings and lower CO2 emissions.