基于ANN-GA集成的ORC混合工质智能筛选与性能优化OA

To overcome the challenges of time-consuming screening and incomplete thermophysical property data in selecting mixed working fluids for organic Rankine cycle(ORC)systems,this study proposes an integrated data-driven optimization framework combining artificial neural networks(ANN)and genetic algorithms(GA).The objective is to enable rapid performance evaluation and intelligent selection of optimal mixed working fluids and operating parameters.First,a rigorous thermodynamic model is established using Aspen Plus,and 1600 sets of sample data for five pure working fluids and their binary mixtures are generated using Latin hypercube sampling.Then,a multilayer feedforward ANN model is constructed in MATLAB to achieve high-precision prediction(R2≥0.999)of thermal efficiency(η)and net work per unit(Wnet).Finally,the GA was applied to perform multi-objective optimization,which was transformed into a single-objective form using the weighting coefficient method to determine the optimal working fluids and operating parameters.The results show that R123/R601 achieves a better thermal efficiency(12.76％)when prioritizing thermal efficiency(w1≤0.6),and when prioritizing net work output(w1＞0.6),R601/R245fa becomes the optimal mixture,achieving 61.4 kW with a 26％increase than that of pure working fluids.The proposed ANN-GA integrated framework provides a fast,accurate,and generalizable approach for mixed working fluid optimization,effectively reducing the optimization time and offering a practical tool for future ORC system design.