IoT Predictive Maintenance
A large food retail chain with over 4,000 stores, identified maintenance related challenges across key equipment groups within their estate. Equipment groups such as: refrigeration cabinets, cold rooms and HVAC systems. The challenges revolved around poor visibility of faults that result in costly repeat work orders, spiralling call- out charges and differing work order volumes per site and equipment type.
Their current monitoring systems did not allow for an estate-wide analysis of the problem to be completed.
The project had a 5 key targets:
1) Understand what volume per type work orders were being raised and why (plant failure, cold room doors open, case over temperature)
2) Understand the frequency of repeat work orders
3) Benchmark sites in relation to volume and repeat work orders being raised
4) Identify problem equipment at a group and/or single unit level
5) Using the data collected make clear and reportable improvements in maintenance costs
![](/media/8d8819f6adb78b8/en-img-1.png?anchor=center&mode=crop&width=1120&height=700&rnd=132490636966100000)
![](/media/8d87b7c9286b696/solution.jpg?anchor=center&mode=crop&width=1920&height=937&rnd=132485419565800000)
Return on Investment
After 12 months the retailer experienced a 32% reduction in work orders raised, a reduction of c19,000 in 2018 to c13,000 in 2019. These improvements have led the retailer to report that for every £1 spent on LoweConex the company have seen a reduction of £8 in maintenance costs alone.