In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional...In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional input variables, in our developed model the features extracted from the available observations are regarded as the input variables by adopting the higher-order statistics(HOS) technique. Such a constructed model is also applied to a practical railway carriage system, simulation results indicate that the developed neurofuzzy model possesses strong identification and fault diagnosis ability.展开更多
Experiments were conducted to investigate the forced convective heat transfer and flow friction of turbulent airflow in a rectangular duct with cross-ribs attached at the two principal walls in the Reynolds number ran...Experiments were conducted to investigate the forced convective heat transfer and flow friction of turbulent airflow in a rectangular duct with cross-ribs attached at the two principal walls in the Reynolds number range from 5000 to 40000. The effect of the rib cross angle (45° 60° 75° and the height (4 mm, 5 mm) of the cross-ribs on the forced convection and flow friction were tested. Non-dimensional correlations for the duct average Nusselt number and friction factor of cross-ribs duct were developed from the test data. Experiments were also conducted for the corresponding parallel ribs to compare their relative performance. The experimental results show that both of the convective heat transfer coefficient and friction factor were increased with cross-ribs, with 45°cross-ribs being the best. Compared with parallel ribs normal to the flow direction under identical flow rate and identical pumping power constraints, the cross-ribs can enhance heat transfer in the lower Reynolds number region, while展开更多
文摘In this paper, we suggest a novel parsimonious neurofuzzy model realized by RBFNs for railway carriage system identification and fault diagnosis. To overcome the curse of dimensionality resulting from high dimensional input variables, in our developed model the features extracted from the available observations are regarded as the input variables by adopting the higher-order statistics(HOS) technique. Such a constructed model is also applied to a practical railway carriage system, simulation results indicate that the developed neurofuzzy model possesses strong identification and fault diagnosis ability.
基金The work described in this paper has been supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. PolyU 5156/99E).
文摘Experiments were conducted to investigate the forced convective heat transfer and flow friction of turbulent airflow in a rectangular duct with cross-ribs attached at the two principal walls in the Reynolds number range from 5000 to 40000. The effect of the rib cross angle (45° 60° 75° and the height (4 mm, 5 mm) of the cross-ribs on the forced convection and flow friction were tested. Non-dimensional correlations for the duct average Nusselt number and friction factor of cross-ribs duct were developed from the test data. Experiments were also conducted for the corresponding parallel ribs to compare their relative performance. The experimental results show that both of the convective heat transfer coefficient and friction factor were increased with cross-ribs, with 45°cross-ribs being the best. Compared with parallel ribs normal to the flow direction under identical flow rate and identical pumping power constraints, the cross-ribs can enhance heat transfer in the lower Reynolds number region, while
