Business Challenge story
An unplanned standstill is one of the most problematic issues that can affect a haulage firm. Apart from the inconvenience for the driver, it creates extra costs for repairs, lost transport revenue and, in the worst-case scenario, a damage to customer reputation. One important prerequisite for reducing the number of unplanned standstills is to be able to predict maintenance needs and to tailor servicing for each individual truck.
The growing business need for predictive maintenance to fulfill the uptime commitments on Volvo Group trucks led to the decision to invest in a new predictive analytics platform using IBM SPSS for vehicle information residing in their enterprise data warehouse. By being able to monitor the truck's usage and the current status of the vehicle's various key components, it is possible to plan maintenance better through preventive maintenance and also to predict component failure while truck is on the road or in the shop.
Volvo applies machine learning techniques to automatically discover patterns and learn from the vast amount of data it collects. The company can now identify the necessary parts and provides repair instructions, even before the truck arrives for service, reducing diagnostic time by up to 70 percent and lowering repair time by more than 20 percent. Additionally, Volvo has consolidated under one roof the people and systems needed to monitor and respond to vehicle issues in real time, including 24/7 support through the company's Action Service and ASIST experts. Both of these process changes allows Volvo to maintain its commitment to core values of quality, safety and environmental care.