Field service is one of the most successful applications of IoT and it is already generating valuable results for companies. By utilizing sensors to monitor operational conditions, storing historical and real-time data in the cloud and performing analytics, predictive maintenance KPIs make it possible to service equipment based on actual wear and tear instead of scheduled preventive maintenance. The end result is increased productivity, profitability and improved employee safety.

Both government and consulting firms concur that predictive maintenance can unleash substantial equipment and field technician productivity in field service. McKinsey estimates a 10 percent reduction in annual maintenance costs and a 20 percent reduction in downtime with a 25 percent reduction in inspection costs for AI-driven predictive maintenance models.

UPS claims it has already saved millions of dollar by implementing a predictive maintenance to reduce breakdowns and extend the equipment life for their fleet of trucks. Managing over 100,000 vehicles globally they combine over 16 petabytes of data from engines to analyse the performance and condition of their vehicles.

Siemens performs predictive maintenance for NASA’s cooling systems at the Edwards US Air Force base in California by monitoring the performance of fans, pumps, air handlers, and cooling towers. Every time there is a significant status change for a piece of equipment, automatic notifications are sent to NASA and an analyst for review and action.

Deutsche Bahn (DB), Germany’s railway company, and Siemens have launched a pilot application for the predictive servicing and maintenance of the high-speed trains. Siemens has opened a dedicated Mobility Data Services Center in Munich to perform data analysis to predict potential equipment failures.

Predictive Maintenance as a Service

Field service solutions are a much-needed action layer for modern equipment that can self-monitor and diagnose. Once an anomaly is detected, an alert from the IoT cloud can move into a field service management system where it can be scheduled and assigned to a technician. Maintenance KPIs like Mean Time to Diagnose (MTTD), Mean Time to Repair (MTTR), First Time Fix (FTF), and Technician Productivity are all positively impacted when equipment can self-diagnose. It can instantly provide these insights so that technicians know exactly the type of service that is needed and can come prepared with the right tools and inventory. In addition, KPIs like Uptime and Customer Satisfaction are positively impacted. Proactively addressing problems with predictive maintenance programs helps ensure longer equipment lifetime and higher customer satisfaction with uninterrupted performance.

There are a number of vendors that advertise the ability for their components to initiate their own service calls, including Cummins Power Generation, a global firm that makes generators and other power generation equipment. The company’s equipment automatically alerts homeowners and technicians about potential equipment problems or service requirements via a mobile app.

While the amount of data coming out of connected equipment may seem daunting at first, once companies understand the different streams of data that are needed to deliver predictive maintenance and are able to correctly analyze it, then they gain an incredible advantage over their competition. For one, they are able to provide superior service by getting ahead of equipment breaks to deliver just the right amount of maintenance when it is needed.

Manufacturers might even prefer to sell outcomes, such as uninterrupted hours of operation, rather than equipment.

Infrastructure and Security Requirements of Predictive Maintenance

In order for predictive maintenance to become a viable KPI solution, machines, devices, sensors and people need to connect and communicate with one another seamlessly. There needs to be a virtual copy of the physical world in order to make sense of all that data to conceptualize the information. Technologies utilizing artificial intelligence need to be deployed to support decision making and problem solving so digital systems can work, whenever possible, without human intervention.

There is also the challenge of integrating data between different types of equipment and back office systems with a low level of latency. In addition, data needs to be filtered so that manufacturers’ proprietary information and customers’ financial data won’t be hacked. A data management platform can provide the capabilities needed to collect, integrate, process and share huge volumes of data with a high level of performance, security and reliability.

By monitoring machine health and having a way to act based on IoT analytics, manufacturers are able to prevent downtime and extend equipment life, resulting in huge productivity and customer satisfaction gains. The KPIs are so superior that, despite the challenges, predictive maintenance will become the heart and brains of every field service organization.

ABOUT Tsipora Cohen

Avatar photoTsipora Cohen is the global head of marketing for Magic Software. Tsipora served as VP of worldwide marketing at Connance, BluePhoenix Solutions and Keyware Technologies and held responsibities for strategic marketing, product marketing, channel marketing and marketing communication. Previously she served as VP corporate business development at Nuance (formerly L%H). She holds a BA degree in statistics and psychology from Tel Aviv University, where she also completed her graduate coursework for an MS in data processing and information systems. Cohen also attended the Executive Program at the Stanford Graduate School of Business.