A Manufacturer of Material Handling Equipment (conveyor-belts, automated weighing scales, etc) has sold hundreds of automated and semi-automated warehouse systems around the world, and is renowned for their excellent After Sales Service offering. In fact the service and maintenance division is a significant contributor to the company’s revenue and bottom line.
A major challenge for the company (and many companies in the MRO industry) is the unpredictability of the maintenance need: if you service the assets too early, you spend money and engineering resources to replace parts that do not need replacement just yet; if you service the assets too late, the machine breaks down before the scheduled maintenance. In the latter case an Engineer is urgently needed to investigate the problem (often outside office hours), orders the Spare Parts that are needed urgently by hand-carry or Express freight to repair the machine and reduce downtime. The company was looking for a way to reduce downtime, better plan machine maintenance and reduce express freight cost.
The Manufacturer approached FS2D to provide the sensor technology, Data collection and data analytics tools to identify machine Wear & Tear at an early stage. Combined with the Company’s own Domain expertise we are developing not only an early warning system to detect potential machine maintenance needs; based on analysis of big data we also build a self-learning algorithm that is able to narrow down or widen the acceptable tolerance levels for “normal” behavior. Furthermore the data model will link to the company’s asset Management system and Logistics applications to optimize the replenishment and location of critical spare parts across the network of Field Stock Locations.
The Manufacturer of the Material Handling Equipment will be able to offer a more competitive and responsive MRO service that reduces inventory carrying cost of MRO items, Logistics cost for express deliveries, Engineering expenses outside office hours and optimizes the planning of maintenance jobs.