Skip to main content

Pascal Torres: “Predictive maintenance is the best option to achieve a high level of building performance”

ET Pascal Torres

Pascal Torres: “Predictive maintenance is the best option to achieve a high level of building performance”

Pascal Torres, CEO and co-founder of the French branch of R2M Solution
Lara González Volpe

Pascal TORRES studied General Technical Engineering (industrial maintenance) and Business Management (IAE: Institut d’Administration des Entreprises). In 1994 he launched his professional career with a climate engineering firm based in Nice as a technical salesman responsible for industrial accounts. Pascal has developed a process management program (Supervision). This software evolved naturally into a building management system (BMS). In 2003, he created his own independent climate engineering company, Osmose, on the French Riviera. A synergy of skills (climate engineering, automation, IT) enabled Osmose to establish itself as one of the local leaders in the field of specialised air treatment (controlled dust level facilities, clean rooms, explosive atmosphere, health and safety ventilation). Noting the ever-increasing issues caused by energy constraints, Pascal decided to create a stand-alone entity focused on energy efficiency optimisation for buildings and industrial processes: ENOLEO, located in Monte Carlo, Monaco. ENOLEO offers equipment and software solutions for energy efficiency optimisation in the air conditioning, heating, ventilation, and lighting sectors.

Pascal is the CEO and co-founder of the French branch of R2M Solution, which was created in March 2017 and co-located with OSMOSE in Roquefort-les-Pins on the French Riviera.

LinkedIn profile

BUILD UP (BUP): What is predictive maintenance and how is it applied in the built environment?

PASCAL TORRES (PT): Predictive maintenance is a proactive approach that uses data, technology, and analytics to predict equipment failures, making it possible to establish correlations between the various incidents it detects, and giving operators additional clues to anticipate and resolve these problems. Built environment applications include HVAC systems, elevators, electrical systems, plumbing, security systems, building envelope, and lighting systems. By analysing aggregated data collected by a building management system (BMS), predictive maintenance enables timely scheduling, reduced downtime, extended equipment lifespan, and cost savings. Technologies like sensors, IoT devices, data analytics, and machine learning algorithms are used to optimise maintenance schedules and ensure a comfortable environment.

BUP: Can predictive maintenance technologies improve buildings´ performance?

PT: Predictive maintenance technologies enhance a building's performance by providing building operators with a more global view of all systems (all technical installations) which allows for more in-depth analysis of performance indicators. This saves precious time, allows operators to better understand and process data and to be proactive in avoiding malfunctions that could have serious impacts. Specifically, such technologies are used for increasing equipment reliability, reducing downtime, optimising energy efficiency, extending equipment lifespan, reducing costs, improving comfort and safety, making data-driven decisions, ensuring compliance with safety standards, and offering remote monitoring and management. These technologies also contribute to cost reduction, extended equipment lifespan, and improved occupant satisfaction. By utilising these technologies, facility managers can make informed decisions and maintain efficient, well-performing buildings.

 “Predictive maintenance technologies contribute to cost reduction, extended equipment lifespan, and improved occupant satisfaction”

BUP: How is predictive maintenance linked to digital and smart technologies of the building sector?

PT: Predictive maintenance in the building sector is a result of the integration of digital and smart technologies. Sensors and IoT devices collect real-time data from building systems, enabling real-time insights into performance and health. Advanced data analytics, predictive analytics, remote monitoring, cloud computing, predictive maintenance software, integration with building management systems, energy management, and digital twins help optimise maintenance schedules and improve overall performance. As the building sector adopts these technologies, the effectiveness of predictive maintenance will grow because it recovers static (construction) and dynamic digital data to facilitate its interactions with other systems, and to feed it with real-time data.

BUP: Are there other maintenance strategies that can evaluate the performance of buildings? Is predictive maintenance the best option?

PT: Predictive maintenance technologies are effective for evaluating building performance, but other strategies like preventive maintenance, corrective maintenance, condition-based maintenance, run-to-failure, reliability-centred maintenance, total productive maintenance, risk-based maintenance, proactive facility management, and asset management can be used alongside or as alternatives. These strategies depend on factors like the building's purpose, budget, equipment, and desired performance level. Combining these strategies can ensure the building's performance, longevity, and cost-effectiveness. In my experience, I’ve found that predictive maintenance is the best option to achieve a high level of building performance by detecting deviations to guarantee energy efficiency, a reduction in equipment breakdowns, and therefore better overall continuity of service.

 “Predictive maintenance technologies are effective for evaluating building performance, but other strategies like preventive maintenance, corrective maintenance or condition-based maintenance can be used alongside or as alternatives”

BUP: Can you present an example of a tool that assesses the performance of buildings, and what benefits this provides?

PT: I developed a tool myself called KAIZIS. Kaizis i s a powerful self-learning multi-criteria analysis tool which can be used in buildings of all sizes to provide site managers with decision-making support. Its software connects to a building's existing supervision tools and uses algorithms to create a model by learning from the data collected by the BMS to anticipate breakdowns and prevent energy bottlenecks. Kaizis will detect any energy drift (e.g., abnormal activity on a cooling or heating system) that corresponds to overconsumption or a breakdown. The solution transmits a daily analysis of the data, which is secured from end to end. This report is easy to read, in the form of curves and graphs with colours to highlight sensitive points without any value judgement on the intrinsic performance of the equipment; it is presented as a decision-making aid for the site manager. 

BUP: How do you foresee the evolution of these types of technologies for performance assessment in the future of buildings?

PT: The evolution of predictive maintenance technologies for the built environment will move towards interoperability with standardised models, making them even easier to implement and integrate with smart building systems, enhanced sensor technology, advanced data analytics, real-time monitoring, energy efficiency modelling, proactive spare parts management, building envelope monitoring, digital twins, augmented reality, cybersecurity, and regulatory compliance. These advancements will lead to safer, more efficient and sustainable buildings while reducing operational costs and downtime by predicting equipment failures, recommending spare parts, and ensuring compliance with regulatory standards.

Smart Building technologies
Energy efficiency technologies and solutions
Building Operation and Maintenance