Application of Particle Swarm Optimization to Fault Condition Recognition Based on Kernel Principal Component Analysis

Panicle swarm optimization （PSO） is an optimization algorithm based on the swarm intelligent principle. In this paper the modified PSO is applied to a kernel principal component analysis （ KPCA ） for an optimal kernel function parameter. We first comprehensively considered within-class scatter and between-class scatter of the sample features. Then, the fitness function of an optimized kernel function parameter is constructed, and the particle swarm optimization algorithm with adaptive acceleration （CPSO） is applied to optimizing it. It is used for gearbox condi- tion recognition, and the result is compared with the recognized results based on principal component analysis （PCA）. The results show that KPCA optimized by CPSO can effectively recognize fault conditions of the gearbox by reducing bind set-up of the kernel function parameter, and its results of fault recognition outperform those of PCA. We draw the conclusion that KPCA based on CPSO has an advantage in nonlinear feature extraction of mechanical failure, and is helpful for fault condition recognition of complicated machines.

Advanced treatment of municipal wastewater by nanofiltration： Operational optimization and membrane fouling analysis

Municipal sewage from an oxidation ditch was treated for reuse by nanofiltration（NF） in this study. The NF performance was optimized, and its fouling characteristics after different operational durations（i.e., 48 and 169 hr） were analyzed to investigate the applicability of nanofiltration for water reuse. The optimum performance was achieved when transmembrane pressure = 12 bar, p H = 4 and flow rate = 8 L/min using a GE membrane. The permeate water quality could satisfy the requirements of water reclamation for different uses and local standards for water reuse in Beijing. Flux decline in the fouling experiments could be divided into a rapid flux decline and a quasi-steady state. The boundary flux theory was used to predict the evolution of permeate flux. The expected operational duration based on the 169-hr experiment was 392.6 hr which is 175% longer than that of the 48-hr one. High molecular weight（MW） protein-like substances were suggested to be the dominant foulants after an extended period based on the MW distribution and the fluorescence characteristics. The analyses of infrared spectra and extracellular polymeric substances revealed that the roles of both humic- and polysaccharide-like substances were diminished, while that of protein-like substances were strengthened in the contribution of membrane fouling with time prolonged. Inorganic salts were found to have marginally influence on membrane fouling. Additionally, alkali washing was more efficient at removing organic foulants in the long term, and a combination of water flushing and alkali washing was appropriate for NF fouling control in municipal sewage treatment.

Multiparameter optimization and configuration comparison of supercritical CO_(2) Brayton cycles based on efficiency and cost tradeoff

Supercritical CO_(2)Brayton cycle has high efficiency,compactness,and excellent power generation potential.In the design of the cycle,some parameters,such as recuperator pinch point temperature difference(ΔTrec,pp),turbine inlet temperature(Ttur,in),and maximum cycle pressure(pmax),are often preset without optimization.Furthermore,different preferences on efficiency and cost tradeoff can significantly affect the optimal design of the cycle,and the influence of different parameters on the design condition and the optimum cycle configuration becomes unclear as the preference changes.In this study,different preferences on efficiency and cost tradeoff are considered,and the effects of cycle configuration and optimization parameter addition on the tradeoff are investigated.In addition,four configurations under different preferences on tradeoff are recommended.Results show that the design condition parametersΔT_(rec,pp) decrease and T_(tur,in) and pmax increase as the preference of thermal efficiency(W_(th))increases.Different optimized parameters affect the results of the design point and cycle performance.In addition,the simple recuperative cycle and reheating cycle are recommended when low cycle initial cost dominates(W_(th)<0.598),and the recompression cycle and intercooling cycle are recommended when high cycle thermal efficiency dominates(W_(th)>0.701).The decision maker can select appropriate configuration according to specific preferences.

Effect of flue gas outlet temperature in evaporator on thermal economic performance of organic Rankine cycle system for sinter waste heat recovery

In order to improve the recovery and utilization rates of sinter waste heat effectively,the organic Rankine cycle(ORC)system with subcritical cycle was designed to recover the low-temperature sinter cooling flue gas waste heat in an annular cooler for power generation.The thermodynamic,economic and multi-objective optimization models of ORC system were established,and R600a was selected as the ORC working medium.Subsequently,the variations in system thermodynamic performance and economic performance with the ORC thermal parameters were discussed in detail,and the optimal ORC thermal parameters were determined.The results show that the system net output power increases with increasing the evaporation temperature and decreasing the condensation temperature and increases first and then,decreases with the increase in superheat degree for a given flue gas outlet temperature in the evaporator,while the heat transfer area per unit net output power appears different variation trends in various ranges of flue gas outlet temperature.Taking the sinter cooling flue gas waste heat of 160℃as the ORC heat source,the optimal thermal parameters of ORC system were the flue gas outlet temperature of 90℃,the evaporation temperature of 95℃,the superheat degree of 10℃,and the condensation temperature of 28℃.