(10 min each)
Join this session to learn two tried and tested proof of concepts for AI that service leaders are executing with solution partners. You'll have an opportunity to select which service leaders and their solutions providers that you would like to meet with for a hands-on session in the afternoon.
Case Study 1: From Digital to Optimised: 17% More Efficient Routes at Scale Presented by Timefold
Case Study Most field service organisations have already digitised workforce scheduling. But when thousands of jobs, technicians, skills, time windows, and travel constraints interact, better planning tools don't necessarily produce better plans.
In this customer case, Timefold and e-switch show how a major European transport operator is moving beyond digital workforce planning to optimisation at scale. By combining advanced solver technology with deep SAP S/4HANA integration, the solution is designed to optimise assignments and routes for more than 1,000 field technicians and 50,000 maintenance jobs per year.
Early results show routes becoming 17% more efficient. Dispatchers can also stop manually solving an increasingly complex scheduling problem and focus on the exceptions where human judgment adds the most value.
Geoffrey De Smet, Co-Founder and CTO, Timefold
Florian Gross, Senior Sales Consultant, e-switch Solutions
Case Study 2: From Prediction to Action: The Business Case for AI in Maintenance at Van Oord
Predicting a failure is step one. Acting on it is step two, and that is where the value of AI lies. Van Oord, a Dutch marine contractor, selected IFS Cloud as the platform for its Founding the Future programme. Robert Kool uses Van Oord as an example to show how a sensor reading becomes a planned work order, and how to build the business case for it: four value drivers, one calculation using your own data, and a go/no-go decision at every step. The session puts AI at the centre. Robert shows where AI does the work in maintenance. It flags abnormal readings while they are still small, forecasts when a part needs replacing, ranks which vessel and job come first, and drafts the work order for a person to approve.
Key takeaways:
- Where your organisation stands on AI maturity, and what the next level asks of you
- What AI can already do in maintenance, from flagging exceptions to drafting work orders
- How to calculate the value of predictive maintenance using your own data
- How to decide what AI may prepare, what it may do and when a person signs off
Robert Kool, Solution Architect, Eqeep