A novel evaluation method of measurement sensitivities on common faults in VAV HVAC systems

Abstract

Today, a high volume of operation interval data can be efficiently captured by a diverse range of measurements including sensors, control signals and meters, which are deployed in building automation systems (BAS). Hence, advanced data analytics tools such as fault detection and diagnostic (FDD) can be developed to analyze the operational performance of heating, ventilation and air conditioning (HVAC) systems. In the past, enormous efforts have been made to develop various FDD approaches, assuming interval data contains essential information for identifying fault signatures. However, a “data rich, but information poor” phenomenon exists due to the fact that not all measurements are sensitive to faults in HVAC systems. This highlights a significant research gap, the lack of systematic analysis of measurement sensitivity to different HVAC system faults, which is vital for FDD development, measurement deployment optimization, and control system design. To address this gap, this study introduces a novel approach to assess the sensitivity of BAS measurements in relation to various HVAC fault types. We propose two sensitivity indices (SI), the SI of fault (SI_fault) and the global measurement SI (SI_measurement_global) to quantify measurement sensitivities. The SI_fault quantifies the measurement's sensitivity to a particular fault, while the SI_measurement_global assesses its sensitivity across all fault types. These indices integrate probability distributions, enhancing the interpretability and scalability. Utilizing the HVACSIM+ fault simulation dataset, which includes 15 common faults at varying severity levels and 89 different measurements within an HVAC system, we conducted an extensive analysis of measurement sensitivities by looking at the proposed SIs.