For the past 13 years, ServiceMax has been enabling the digital transformation of field service organizations through our asset-centric field service management solution. Today, we are the only leading software application that is 100% dedicated to equipment and asset maintenance. Our focus on equipment and asset maintenance has brought the idea of asset-centricity to the forefront for many service businesses and is allowing them to move from reactive maintenance to proactive maintenance. This focus on the asset has also led to our ground-breaking joint solution with Salesforce Field Service—Asset 360 for Salesforce.
As we look to the future of field service management technology, we see emerging technologies like artificial intelligence, augmented reality and the Internet of things playing a big role in advancing asset-centric field service management and supporting new outcome-based business models. This article will look specifically at the role of artificial intelligence and machine learning in asset-centric field service management.
ServiceMax sees a very clear and immediate application for artificial intelligence (AI) and machine learning (ML) technologies in today’s asset and equipment maintenance services. We also see additional functional areas where AI and ML will most likely gravitate to in the near future.
Today’s Opportunities for Leveraging AI and ML
Assisted Technician Selection and Dispatching
Based on business rules surrounding education, training, competence scale, site access, work order type, asset type, location, and time available, an AI application would be used to scan the open work orders, make a recommendation on which is the best technician to send, improving productivity and reducing overtime.
Unplanned Maintenance Triage, Parts Identification, and improved access to the most appropriate knowledge management content
With access to past work orders for a specific asset type, an AI application would be able to review thousands of reported error codes or problem descriptions, investigate positive outcomes, and recommend required parts, tools, and technician skills/education to repair the reported problem. It would also be able to suggest the most relevant knowledge management content to assist in the repair for attachment to the work order.
Balance Planned Maintenance Schedules
Given asset performance history, an AI should be able to evaluate and make recommendations on changes in Planned Maintenance cycles, periods, or schedules, reducing the number of required touches of the equipment while still maintaining equipment uptime.
Future Applications of AI and ML
In the future, we envisage a much broader utilization of AI and ML. Among these are:
Moving from planned to predictive maintenance
With broader adoption of the Internet of Things (IoT) and the embrace of connected devices, we see the corresponding ability of service providers to monitor the condition of the asset in its environment. We envision that AI will begin to build “profiles” of optimally operating assets and also begin to measure those devices’ operational capability deteriorates over time and use. Given a sufficient number of failures over a sufficient amount of time, we see that AI alerting service providers that a specific part will fail within a specific window of time, allowing providers to transition away from corrective maintenance to 100% planned maintenance over time.
More informed Dispatching
As AI becomes progressively better at identifying the best technician and improving the recommended dispatch process, we see the role of the dispatcher becoming far more informed, focused, and productive. This increased accuracy on the part of the system will enable the dispatcher to be far more confident in their decisions and significantly reduce the amount of time and effort dedicated to the dispatching function.
Territory Management and Planning
Given access to the work order history, install base data, and available manpower resources, we envision AI and ML will be able to make well-based suggestions on staffing, location, and geography mapping in the near future. Comparing the installed-based assets, locations, failure rates, mean time to install, repair, service, and assuming an element of predictive maintenance, we see AI suggesting staffing levels, locations, and skills requirements.
Medical Device Applications
Leveraging the remote data provided by the Internet of Things (IoT), and managing that data through the tools available in ServiceMax, AI will be able to analyze the asset data and make predictive recommendations and decisions on optimization of parts & inventory (Supply Chain), predictive (preventive) maintenance, and improve regulatory compliance through predictive corrective actions. AI can augment Regulatory Compliance Management by predictive detection of potential Corrective Action & Preventive Action (CAPA) events, thereby lowering risks for patients and customers as well as reducing overall cost.
Accurate Asset Data is the First Step
Our point of view on AI and ML is that they will play a huge role in the future success of asset and equipment maintenance service providers. We see their penetration into the market now and understand how in a matter of time they will dominate a variety of specific service-related areas. We also understand that the application of Artificial Intelligence and Machine Learning in field service management is dependent upon the absolute necessity of clean, usable, accurate asset data. That is why, in preparation for the arrival of AI and ML, we have focused so deeply on the asset, because that holistic view of the history and performance of the asset is the information that AI will absolutely require in order to make autonomous decisions that will drive a digitally transformed business. It all begins with a deep knowledge of the asset.