Machine Learning Framework for the Sustainable Maintenance of Building Facilities

Valentina Villa,Dario Antonelli,Paolo Piantanida,Khurshid Aliev,Alessandra Corneli,Giulia Bruno

doi:10.3390/su14020681

Valentina Villa, Dario Antonelli + Show 4 more

Open Access

https://doi.org/10.3390/su14020681

Copy DOI

Abstract

The importance of sustainable building maintenance is growing as part of the Sustainable Building concept. The integration and implementation of new technologies such as the Internet of Things (IoT), smart sensors, and information and communication technology (ICT) into building facilities generate a large amount of data that will be utilized to better manage the sustainable building maintenance and staff. Anomaly prediction models assist facility managers in informing operators to perform scheduled maintenance and visualizing predicted facility anomalies on building information models (BIM). This study proposes a Machine Learning (ML) anomaly prediction model for sustainable building facility maintenance using an IoT sensor network and a BIM model. The suggested framework shows the data management technique of the anomaly prediction model in the 3D building model. The case study demonstrated the framework’s competence to predict anomalies in the heating ventilation air conditioning (HVAC) system. Furthermore, data collected from various simulated conditions of the building facilities was utilized to monitor and forecast anomalies in the 3D model of the fan coil. The faults were then predicted using a classification model, and the results of the models are introduced. Finally, the IoT data from the building facility and the predicted values of the ML models are visualized in the building facility’s BIM model and the real-time monitoring dashboard, respectively.

Highlights

The environmental impact of buildings is astonishing
The experiment was divided into two parts: the first was to collect balanced conditional data from the fan coil (FC) motor, and the second was to simulate an unbalanced condition by attaching 15g of mass to one of the FC motor’s blades
The Automatic machine learning (AutoML) function in H2O automates the process of building a large number of models and finds the most suitable model for a given dataset

Summary

Introduction

The environmental impact of buildings is astonishing. Every year, building construction consumes 25% of world wood harvest, 40% of materials entering the global economy,3 billion tons of raw materials transformed into foundations, walls, pipes, and panels, and 50% of copper utilized in the United States [1]. The environmental impact of buildings is astonishing. Every year, building construction consumes 25% of world wood harvest, 40% of materials entering the global economy,. Building construction accounts for half of the worldwide output of greenhouse gases and acid rain agents. As a critical component of a habitat, have an influence on their local and surrounding areas, which can have unintended consequences for people and the community. Addressing the sustainability in building can significantly reduce these negative effects [2]. In Europe, the building maintenance industry accounts for the same amount of building production as the new construction market. Due to the aging buildings, the maintenance industry grows at a rate of 1.5 percent each year [3]. The size and expansion of the existing market needs a greater focus on sustainable building maintenance [4]

Results

Discussion

Conclusion