To evaluate the credit risk of customers in power market precisely, the new chaotic searching and fuzzy neural network (FNN) hybrid algorithm were proposed. By combining with the chaotic searching, the learning abilit...To evaluate the credit risk of customers in power market precisely, the new chaotic searching and fuzzy neural network (FNN) hybrid algorithm were proposed. By combining with the chaotic searching, the learning ability of the FNN was markedly enhanced. Customers’ actual credit flaw data of power supply enterprises were collected to carry on the real evaluation, which can be treated as example for the model. The result shows that the proposed method surpasses the traditional statistical models in regard to the precision of forecasting and has a practical value. Compared with the results of ordinary FNN and ANN, the precision of the proposed algorithm can be enhanced by 2.2% and 4.5%, respectively.展开更多
Reinforcement inside the concrete is protected from corrosion and its damages until several years after the construction. After corrosion initiation, the cross section of reinforcement begins to reduce and often load ...Reinforcement inside the concrete is protected from corrosion and its damages until several years after the construction. After corrosion initiation, the cross section of reinforcement begins to reduce and often load bearing of the reinforced concrete structure will be reduced significantly. Corrosion of reinforcements in concrete in polluted and contaminated areas can occur in two ways: chloride and carbonation. In this work, meta-heuristic approach of charged system search(CSS) is used to calculate corrosion occurrence probability due to chloride ions penetration. The model efficiency is verified by comparing the available examples in technical literature and results of Monte Carlo analysis. According to the analyses performed, using different probabilistic distributions regardless of probabilistic moments based on real distribution leads to diverse results. In addition, influence of each effective parameter in corrosion occurrence varies by changing other parameters.展开更多
基金Project(50579101) supported by the National Natural Science Foundation of China
文摘To evaluate the credit risk of customers in power market precisely, the new chaotic searching and fuzzy neural network (FNN) hybrid algorithm were proposed. By combining with the chaotic searching, the learning ability of the FNN was markedly enhanced. Customers’ actual credit flaw data of power supply enterprises were collected to carry on the real evaluation, which can be treated as example for the model. The result shows that the proposed method surpasses the traditional statistical models in regard to the precision of forecasting and has a practical value. Compared with the results of ordinary FNN and ANN, the precision of the proposed algorithm can be enhanced by 2.2% and 4.5%, respectively.
文摘Reinforcement inside the concrete is protected from corrosion and its damages until several years after the construction. After corrosion initiation, the cross section of reinforcement begins to reduce and often load bearing of the reinforced concrete structure will be reduced significantly. Corrosion of reinforcements in concrete in polluted and contaminated areas can occur in two ways: chloride and carbonation. In this work, meta-heuristic approach of charged system search(CSS) is used to calculate corrosion occurrence probability due to chloride ions penetration. The model efficiency is verified by comparing the available examples in technical literature and results of Monte Carlo analysis. According to the analyses performed, using different probabilistic distributions regardless of probabilistic moments based on real distribution leads to diverse results. In addition, influence of each effective parameter in corrosion occurrence varies by changing other parameters.
