IoT technology has the potential to greatly increase field service efficiency, increasing consumer satisfaction and reducing costs.
Resolving jobs efficiently and quickly – can be difficult to achieve if personnel are unable to obtain necessary details prior to arrival on the job site, necessitating return trips. Embedding smart devices into field-based equipment enables sending service signals immediately and logging performance data in real-time. Service calls will eventually be greatly reduced as the machines will inform techs of issues directly, before the customer is even aware there’s a problem. General Electric (GE) currently uses IoT in a number of ways including embedding data-collecting sensors on industrial equipment, like airplane engines; connecting information received across multiples sensors to make efficient decisions; and using data and data-collecting sensors to improve operational and industrial efficiency.
There’s an important distinction to be made between preventative, and predictive maintenance. Preventive maintenance is the process of performing maintenance on equipment proactively – based on expected deterioration and lifespan of the equipment. The problem with is that it isn’t completely efficient as it follows a regular maintenance schedule, sometimes mean replacing parts that don’t need to be replaced. Predictive maintenance, on the other hand, takes the actual condition of the equipment into account when setting schedules for repairing or replacing. The condition and performance of the equipment is monitored using IoT sensors and data-driven insights and when performance falls below a set threshold, a maintenance request is initiated. The advantage to this approach is that maintenance is more likely to be performed when it is actually needed. The Salt River Project in Arizona has been using predictive maintenance as a part of their monitoring and diagnostics process since 2012 and has resolved more than 800 issues, all of which they define as predictive “catches”. These resolutions minimize downtime, power outages, and improve customer satisfaction.
In the past, customer satisfaction was measured by surveys, but fewer customers answer surveys every year. When customers opt-in, a data stream can be opened between customer devices and an IoT Complex Event Processor, enabling field service organizations to analyze connected products, mobile devices, website clicks, social media posts and mobile text messages. Using artificial intelligence algorithms, software can crunch data from different sources to determine customer satisfaction based on multiple digital behaviors.
