Application of Adaptive Resonance Theory neural networks to monitor solar hot water systems and detect existing or developing faults

被引:16
作者
He, Hongbo [1 ]
Caudell, Thomas P. [2 ]
Menicucci, David F. [1 ]
Mammoli, Andrea A. [1 ]
机构
[1] Univ New Mexico, Dept Mech Engn, Albuquerque, NM 87131 USA
[2] Univ New Mexico, Dept Elect & Comp Engn, Albuquerque, NM 87131 USA
关键词
Solar hot water; Reliability; Fault detection; Neural network; Simulation; Training; PATTERN-CLASSIFICATION; QUANTITATIVE MODEL; BUILDING SYSTEMS; PART II; DIAGNOSIS; PROGNOSTICS;
D O I
10.1016/j.solener.2012.05.015
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Reliability is the Achilles' heel of domestic solar hot water (SHW) systems, which otherwise offer a cost-effective way of reducing energy consumption and related emissions. Using a solar hot water system reliability testbed developed for this purpose, novel neural-network-based monitoring and fault detection methods were developed. It is argued that these methods could easily be incorporated in control or supervisory software, thereby allowing rapid detection and correction of faults. This would in turn prevent further damage, and ensure continued energy savings. In particular, the Adaptive Resonance Theory (ART) class of neural networks was used to detect and classify anomalies. Compared with other network types, ART networks are fast, efficient learners and retain memory while learning new patterns. Various ART networks were trained using simulation, and tested in the field using the testbed. The results show that simulation-based training is representative of real-life operating conditions, and that faults are correctly detected in the field. Using this technology, it will be possible to improve the reliability of SHW systems with little or no additional sensing equipment compared to typical installations. (c) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:2318 / 2333
页数:16
相关论文
共 29 条
[1]  
[Anonymous], 2009, Sustainable Energy-without the hot air
[2]   FUZZY ART - FAST STABLE LEARNING AND CATEGORIZATION OF ANALOG PATTERNS BY AN ADAPTIVE RESONANCE SYSTEM [J].
CARPENTER, GA ;
GROSSBERG, S ;
ROSEN, DB .
NEURAL NETWORKS, 1991, 4 (06) :759-771
[3]   A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].
CARPENTER, GA ;
GROSSBERG, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115
[4]   NIRS - LARGE-SCALE ART-1 NEURAL ARCHITECTURES FOR ENGINEERING DESIGN RETRIEVAL [J].
CAUDELL, TP ;
SMITH, SDG ;
ESCOBEDO, R ;
ANDERSON, M .
NEURAL NETWORKS, 1994, 7 (09) :1339-1350
[5]  
CAUDELL TP, 1993, WCNN'93 - PORTLAND, WORLD CONGRESS ON NEURAL NETWORKS, VOL IV, P166
[6]   Review of long-term fault detection approaches in solar thermal systems [J].
de Keizer, A. C. ;
Vajen, K. ;
Jordan, U. .
SOLAR ENERGY, 2011, 85 (07) :1430-1439
[7]  
de KeizIer A., 2008, P GLEISDORF SOLAR, V3, P2008
[8]  
Fairey P., 2004, FSECRR5604 U CENTR F
[9]   A simple model of PV system performance and its use in fault detection [J].
Firth, S. K. ;
Lomas, K. J. ;
Rees, S. J. .
SOLAR ENERGY, 2010, 84 (04) :624-635
[10]  
GROSSBERG S, 1976, BIOL CYBERN, V23, P187