| Summary and Challenges |
- In healthcare institutions such as hospitals and clinics, the Mechanical Ventilation and Air Conditioning (MVAC) system is critical for maintaining stable operations. Water-side equipment, such as chillers, provides essential cooling for medical wards and equipment, while air-side equipment, such as air handling units and exhaust fans, is vital for maintaining airflow and pressure differentials. Malfunctions in either the water-side or air-side equipment can seriously impact infection control measures, affecting the safe working environment of healthcare professionals and disrupting vital clinical services. While operational status and sensor readings are available to duty shift MVAC operators, troubleshooting can often be tedious, leading to overlooked important parameters. Additionally, optimal operating conditions may shift due to equipment aging. Traditionally, corrective maintenance has been performed reactively, following user fault reports, which can be time-consuming and troublesome.
|
| Expected Outcome |
- Develop an early fault detection system that provides operators and users with an intuitive graphical user interface and reports to predict probable malfunctions or sub-optimal operating conditions. The AI-Fault Detection (AI-FDD) model shall predict faults based on operating parameters, IoT sensors, and other relevant data. Furthermore, the AI-FDD model will be self-adaptive, incrementally improving its algorithms based on operator feedback to enhance the operation and performance of the equipment. The objective is to reduce fault occurrences, increase client satisfaction, and improve services to public healthcare institutions.
|
