Development and demonstration of a method to detect refrigerant charge level for variable refrigerant volume systems

Unlike traditional direct expansion systems, variable refrigerant flow (VRF) systems have longer routing, more complicated setup, and sophisticated controls and require much more refrigerant for proper operation. Proper refrigerant charge becomes more critical to their operations. Intensive studies have investigated refrigerant charge faults for VRF systems. Due to the daunting complexity, few studies use knowledge-based fault detection and diagnosis (FDD) methods. Most of them use data-driven FDD methods to study this fault. Although they seem promising, these methods can only handle single faults and are not scalable or interpretable. This paper proposes a decoupling-based FDD method to detect and diagnose improper refrigerant charge in VRF systems. This method was originally proposed by our previous work for rooftop units (RTUs) and split systems, which has been tested and validated by extensive studies. Due to the differences between VRF and RTU, the original method - virtual refrigerant charge sensor (VRC) for VRF is modified, analyzed, and investigated in detail. Data filter criteria were implemented to eliminate noisy data. The modified VRC, when combined with a data filter, was tested on two systems in the field. The results demonstrated its effectiveness in detecting an undercharged system, specifically a 30 % undercharge.