Fault detection and diagnosis methods in HVAC systems

Heating, ventilation and air conditioning systems are the biggest energy consumers in buildings. A more efficient system, which would consume less energy, can be achieved by timely fault detection. Increasing attention is being paid to different methods for fault detection and diagnosis in heating, ventilation and air conditioning systems due to the adoption of building automation systems and the advancement of data and machine learning techniques. These methods can be divided into model-based, knowledge-based, and data-driven methods. The paper provides an overview of different methods, and the greatest attention is paid to data-driven methods due to their high accuracy and faster and cheaper model development.