AI Program: discover Hospital Facilities

How to improve hospital facilities management through predictive maintenance? Discover VINCI Facilities solution, one of the twelve projects resulting from Leonard's Artificial Intelligence program (cohort 2021). It's objective? Help VINCI teams become more autonomous by implementing AI use cases, with a high business impact.

The availability of rooms and operating theatres in hospitals is an extremely critical issue today, especially with the current health crisis. Indeed, an unavailable operating theatre leads to postponed surgeries, lowering hospital service quality and causing serious inconveniences to patient. The motto being “Patient First”, it is necessary to work on this problem in order to offer a better experience to patients.

 For this reason, Predictive maintenance (PdM) has become a very important topic for maintaining hospital infrastructures. PdM relies on predictive analytics and AI models to increase the visibility on asset degradation state; it leverages operating data to detect early warning signs of a failure allowing to act before it actually fails. The increased visibility enables to increase asset availability by lowering failure frequency and by optimizing maintenance operations. Major gains have already been made within VINCI thanks to predictive maintenance projects, for example with Lisea-Mesea.

Health care industry, a domain for predictive maintenance

Hospital environment is a special case for predictive maintenance. Firstly, because of its criticality, as explained earlier. Secondly, because of its complexity. Indeed, one of the challenges of asset management in hospitals is the variety of assets managed. Within a single hospital hundreds of different types of equipment are under maintenance contracts! That is why a general approach that can be easily transferable from a piece of equipment to another should be preferred.

In this context, Facility managers, whose role is to take care of the infrastructure and the associated assets daily, are under high pressure. On the other hand, Facilities Managers enjoy a favorable central position for getting the most out of a predictive maintenance approach: firstly, they have access to all manufacturers being the natural centralizer collector for all new data sources; secondly, they are directly in contact with hospitals enabling them to have a clear vision of the customer’s needs; and last but not the least, they have all the experience and historical knowledge on the maintenance operations performed.

For all these reasons, VINCI Facilities, with the support of Leonard, the VINCI Group’s foresight and innovation platform, has decided to develop a solution and an internal team to carry out predictive maintenance projects for a general asset.

The solution relies on three key pillars: data quality and management, AI and predictive models and a solid agile team.

Data, one of the key elements to perform better

An in-depth study of the available data sources, their quality and the actual understanding has been performed. This stage was extremely instructive for assessing the company data maturity and identifying areas for improvement. One of the key findings was that setting an efficient and clear communication between manufacturers and facilities managers is game-changing for getting the most out of the new telemetry data available. Moreover, the definition of a data quality auditing and management process allows to rapidly identify what are the asset on which a predictive maintenance approach is feasible.

Towards AI and predictive maintenance

An AI-based tool has been designed to accelerate the deployment of predictive maintenance projects. The tool simplifies the exploration of sensor data (e.g. pump’s motor frequency, chiller’s flow temperature) to identify the most relevant models and quickly test their performance.

Finally, an internal team has been structured with complementary skills allowing VINCI Facilities to accelerate the diffusion of the predictive maintenance within its activities.

This article is part of a series involving the participants of the AI program by Leonard. The program has been specifically designed to accelerate the adoption of IA technologies within the group VINCI. It consists in a five-month incubation period where selected VINCI collaborators follow a learn by doing process where they codevelop an AI-based use case under the coaching and mentoring of Leonard’s team and consultants from Eleven Strategy.

> More about Leonard’s AI program 

What do we do?

The VINCI Group created Leonard to tackle the challenges posed by the transformation of regions and lifestyles. Our goal is to unite a community of key stakeholders in order to build the city of the future together.