Elution of bisphenol A (BPA), chlorinated BPAs (i.e., 3-chlorobisphenol A, sum of 3,5-dichlorobisphenol A and 3,3′-dichlorobisphenol A, 3,3′,5-trichlorobisphenol A, and 3,3′,5,5′-tetrachlorobisphenol A) and 2,4,6-trichlorophenol (TCP) from lined pipes coated with two epoxy resins were investigated in a 24-month continuous test passing tap water. BPA, chlorinated BPAs, and TCP were not detected in the tap water at the outlet of lined pipes in most cases. However, all of these chemicals were detected in the tap water after 16 h of retention. The sums of BPA and chlorinated BPAs in the retained tap water were usually high when the residual chlorine levels were low. The residual chlorine was related to temperature, residual chlorine in the tap water at the inlet of lined pipes, and the elapsed time. From the results of leach tests, it was indicated that no marked changes in BPA concentration over the 24 months of the continuous test. Chlorinated BPAs and TCP were accumulated on the surface of lined pipes during the continuous test.
This paper provides a new evolutionary multiobjective optimization method for automatically optimizing the network topology of recurrent neural networks (NNs). To obtain NNs with higher prediction capability for time-series data, the proposed method is constructed by focusing on the intensively exploration of a feasible region including solutions with small training errors on the Pareto frontier, unlike existing evolutionary multiobjective optimization methods, which aim to find a whole set of the Pareto optimal solutions. Our method is characterized by the ideas of self-adaptive mutation probability setting, elite preservation strategies and archive for the preservation of local optimal solutions. Through the comparison with the performances of the most promising existing method by Delgado et al. using benchmark time-series data instances, it is shown that the proposed method is superior to the existing effective algorithm with respect to the capability of time-series prediction.
23 May 2012 in Journal of Multi-Criteria Decision Analysis