Development of an RDP neural network for building energy consumption fault detection and diagnosis

• Published in: Energy and buildings Vol. 62; pp. 133 - 138
• Main Authors: MAGOULES, Frédéric, ZHAO, Hai-Xiang, ELIZONDO, David
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier 01.07.2013
• Subjects: Applied sciences; Building technical equipments; Buildings; Buildings. Public works; Computation methods. Tables. Charts; Diagnostic systems; Energy conservation; Energy consumption; Energy management and energy conservation in building; Environmental engineering; Exact sciences and technology; Fault detection; Fault diagnosis; Faults; Mathematics; Neural networks; Numerical Analysis; Recursive; Structural analysis. Stresses; Energy analysis; Energy consumption; Building energy consumption; Buildings; Support vector machine; Neural network; Modeling; Perceptron; Experimental result; Parallel computing; Support vector regression (SVR); Simulation; Multi-core; Parallel computation; Detection; Fault diagnostic; Map-reduce
• ISSN: 0378-7788
• DOI: 10.1016/j.enbuild.2013.02.050

Fault detection and diagnosis (FDD) is an important issue in building energy conservation. This paper proposes a new option for solving this problem at the building level by using a recursive deterministic perceptron (RDP) neural network. Results show a higher than 97% level of generalization in all the designed experiments. Based on this high detection ability of RDP model, a new diagnostic architecture is proposed. Our experiments demonstrate that it is able to not only report correct source of faults but also sort sources in the order of degradation likelihood.