Search

• Based on exergoeconomic analysis, a TEG was optimized by a M-PSO algorithm. • The accuracy can be improved by a larger mutation factor or particle population. • The acceleration constants affect the speed of convergence for large populations. • Pareto solutions can be acquired through a combined M-PSO and ξ-constraint method. • Used TOPSIS analysis to select an ideal solution from among the Pareto solutions. Efficiency and cost-effectiveness play dominant roles in the commercialization of thermoelectric generator (TEG) technology. In this paper, the exergy analysis of a TEG module with 199 TE couples was considered. Two objective functions, the exergy efficiency and levelized cost of energy (LCOE), were established for exergoeconomic analysis. The geometric structure and working conditions involving TE couple length, base area ratio, working temperature, and load resistance were varied. The particle swarm optimization (PSO) method has excellent convergence and few parameters need to be adjusted. Mutation can increase randomization for the PSO method, making it possible to improve its search direction. Therefore, the mutation-PSO (M-PSO) algorithm was used to optimize the exergy efficiency and LCOE for the TEG. Through the M-PSO algorithm, the optimum corresponds to an exergy efficiency of 29% and LCOE of 1.93 $US/kWh·m2 under a maximum temperature difference of 40 K. In order to achieve a balance between the two exergoeconomic indices, the ξ-constraint combined with the M-PSO method was used to obtain alternatives, named Pareto solutions. Then, these alternatives were ranked to acquire an ideal solution based on a technique for order preference by similarity ideal solution (TOPSIS) method. The TOPSIS ideal solution corresponds to an exergy efficiency of 22.2% and LCOE of 3.02 $US/kWh·m2. [ABSTRACT FROM AUTHOR]

Wind Turbine power output prediction can prevent unexpected failure and financial loss, through the detection of anomalies in turbine performance in advance so operators can proactively address potential problems. This study examines common Supervisory Control And Data Acquisition (SCADA) data over a period of 20 months for 21 pitch regulated 2.3 MW turbines. To identify the most influential parameters on power production among more than 150 signals in the SCADA data, correlation coefficient analysis has been applied. Further, an algorithm is proposed to impute values that are missing, out-of-range, or outliers. It is shown that appropriate combinations of decision tree and mean value for imputation can improve the data analysis and prediction performance. A dynamic ANFIS network is established to predict the future performance of wind turbines. These predictions are made on a scale of 1 h intervals for a total of 5 h into the future. The proposed combination of feature extraction, imputation algorithm, and the dynamic ANFIS network structure has performed well with favourable prediction error levels in comparison with existing models. Thus, the combination may be a valuable tool for turbine power production prediction. [ABSTRACT FROM AUTHOR]