In order to save energy and improve the performance of building environment regulation, there is an increasing need for fault detection and diagnosis (FDD). This paper investigates the effectiveness of tree-structured learning method for FDD of building cooling system. Researchers have been tackling building FDD task with a wide variety of techniques, such as analytical model-based, signal-based and knowledge-based methods. Recently data-driven method has shown its advantage in dealing with complex systems with random penetrations. Existing work on data-driven FDD merely formulates the task as a pure fault type classification problem, whereas fault severity levels and their inter-dependence have long been ignored. We propose a novel data-driven strategy that adopts structured labeling to include the dependence information and describe the severity levels in a large margin learning framework. A Tree-structured Fault Dependence Kernel (TFDK) method is derived and a corresponding on-line learning algorithm is developed for streaming data. As an improvement of traditional classification methods (e.g. SVM), TFDK encodes tree-structured fault dependence in its feature mapping, and takes regularized misclassification cost as learning objective. Following the ASHRAE Research Project 1043 (RP-1043), the strategy is applied to the FDD of a 90-ton centrifugal water-cooled chiller. Experimental results show that compared to previous data-driven methods, TFDK can greatly improve the FDD performance as well as recognize the fault severity levels with high accuracy. (C) 2016 Elsevier B.V. All rights reserved.