A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Estimation of an incipient fault using an adaptive neurofuzzy sliding-mode observer
Highlights A fuzzy relational sliding mode observer is proposed to estimate the magnitude of incipient faults. An on-line learning fault identification scheme is used for model update and fault identification periodically. Description of the air-side fouling fault in cooling coil subsystem of HVAC equipment. Sensitivity discussion for the parameters in neuro-fuzzy sliding mode observer fault estimation scheme. Long-term performance of the fault estimation scheme.
Abstract A fault, especially an incipient fault has to be detected as early as possible to avoid serious damage occurring in the controlled system. A fuzzy relational sliding mode observer (FRSMO) is proposed to estimate the magnitude of slowly evolving faults in information-poor and non-linear systems. To reduce modelling errors, an on-line learning fault identification scheme is used to update the model and identify the fault in a periodical mode. The performance of the proposed methods is evaluated using a cooling-coil subsystem of an air-conditioning plant in a simulated environment. The simulation results of the actuator fault and flow reduction fault estimation confirm the effectiveness of the proposed methods.
Estimation of an incipient fault using an adaptive neurofuzzy sliding-mode observer
Highlights A fuzzy relational sliding mode observer is proposed to estimate the magnitude of incipient faults. An on-line learning fault identification scheme is used for model update and fault identification periodically. Description of the air-side fouling fault in cooling coil subsystem of HVAC equipment. Sensitivity discussion for the parameters in neuro-fuzzy sliding mode observer fault estimation scheme. Long-term performance of the fault estimation scheme.
Abstract A fault, especially an incipient fault has to be detected as early as possible to avoid serious damage occurring in the controlled system. A fuzzy relational sliding mode observer (FRSMO) is proposed to estimate the magnitude of slowly evolving faults in information-poor and non-linear systems. To reduce modelling errors, an on-line learning fault identification scheme is used to update the model and identify the fault in a periodical mode. The performance of the proposed methods is evaluated using a cooling-coil subsystem of an air-conditioning plant in a simulated environment. The simulation results of the actuator fault and flow reduction fault estimation confirm the effectiveness of the proposed methods.
Estimation of an incipient fault using an adaptive neurofuzzy sliding-mode observer
Zhou, Yimin (author) / Liu, Jingjing (author) / Dexter, Arthur L. (author)
Energy and Buildings ; 77 ; 256-269
2014-02-01
14 pages
Article (Journal)
Electronic Resource
English
Estimation of an incipient fault using an adaptive neurofuzzy sliding-mode observer
| Online Contents | 2014
Adaptive Neurofuzzy Computing Technique for Evapotranspiration Estimation
| British Library Online Contents | 2007
Neurofuzzy estimation of liquefaction induced lateral spreading: NEFLAS
| British Library Conference Proceedings | 2005
Robust State Estimation Based on Sliding Mode Observer for Aeroelastic System
| British Library Online Contents | 2005