Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

•A discrete Bayesian Network (DisBN) method is developed to diagnose cross-level faults in HVAC systems.•Weather and schedule-based pattern matching (WPM) method is used to generate the baseline and part of DisBN parameters.•System operation interval data is collected to demonstrate the effectiveness of the developed WPM-DisBN method.•The root causes of cross-level faults can be diagnosed and isolated to address the shortcomings of component-level fault diagnostic solutions.