High Performance Reliability Computing

It is essential for medium-sized suppliers to identify production errors early on. If defective parts are subjected to the random sample-based final inspection or later, if they have been delivered to the OEM or end customer, this not only leads to high warranty costs, but can also lead to a loss of confidence and the withdrawal of the order. The most important characteristic to measure and improve in this context is reliability which indicates how reliable a function assigned to the product or system is fulfilled in a time interval. It is subject to a stochastic process and cannot be measured directly.

To help manufacturers we have a three step approach:

1. Implementation of data analytics on the basis of a Search-Based Application (SBA) environment;

2. Integration of a request-based HPC (High Performance Computing) service module;

3. Machine Learning to detect recurring and new error patterns;

We have already implemented this approach in series production (metal processing) and small batch production (plastics industry).