This article focuses on minimizing product costs by using the newly developed political optimization algorithm (POA), the Archimedes 'optimization algorithm (AOA), and the levy flight algorithm (LFA) in product de...
详细信息
This article focuses on minimizing product costs by using the newly developed political optimization algorithm (POA), the Archimedes 'optimization algorithm (AOA), and the levy flight algorithm (LFA) in product development processes. Three structural optimization methods, size optimization, shape optimization, and topology optimization, are extensively applied to create inexpensive structures and render designs efficient. Using size, shape, and topology optimization in an integrated way, It is possible to obtain the most efficient structures in industry. The political optimization algorithm (POA) is a metaheuristic algorithm that can be used to solve many optimization problems. This study investigates the search capability and computational efficiency of POA for optimizing vehicle structures. By examining the results obtained, we prove the apparent superiority of the POA to other recent famous metaheuristics such as the Archimedes optimization algorithm and the levy flight algorithm. The most important result of this paperwill be to provide an impressive aid for industrial companies to fill the gaps in their product design stages.
A model for predicting the end-point temperature and end-point carbon content of RH refining steel based on an improved whale optimization algorithm and a stochastic configuration network (LWOA-SCN) is proposed to sol...
详细信息
A model for predicting the end-point temperature and end-point carbon content of RH refining steel based on an improved whale optimization algorithm and a stochastic configuration network (LWOA-SCN) is proposed to solve the existing problem of inaccurate detection of the steel composition in the ladle during the steelmaking process. The algorithm has an implicit layer structure that can be generated adaptively based on the training effect and has the ability of strong generalization performance, simple structure, fast convergence, high accuracy, and jumping out of local optimum. Firstly, the LWOA-SCN algorithm is used to construct the prediction model. Secondly, the model was tested against RBF, GA-BP, and PSO-SVM models, and the results showed that the LWOA-SCN model had the highest predicted effect. Finally, the LWOA-SCN model was tested in industrial production applications, and the results showed that the hit rate is 90.6%, 95.6%;93.7%, 94.3% for refining end-point temperature and end-point carbon content error within +/- 5 degrees C, +/- 10 degrees C;and +/- 0.005%, +/- 0.01%, respectively. which can well meet the practical needs of a steel mill. The model provides theoretical guidance and production guidance for studying the control of refining end-point temperature and end-point carbon content.
Photovoltaic (PV) power classification model has become a significant alternative to PV power point forecasting model in which classes of future PV powers are estimated. In this work, a novel PV power classification m...
详细信息
Photovoltaic (PV) power classification model has become a significant alternative to PV power point forecasting model in which classes of future PV powers are estimated. In this work, a novel PV power classification model which could be realized using feed forward neural network (FFNN) trained with a hybrid meta-heuristic approach is proposed to forecast the classes of future PV powers. The insisted classification model is implemented to classify three classes of PV power for the location Oregon city of United States of America (USA) with latitude${43.8041<^>0}N$43.80410N, longitude ${120.5542<^>0}W$120.55420W, and altitude of $1124$1124 m. The meta-heuristic approach comprising of levyflight (levy)-Sine Cosine algorithm (SCA)-Particle Swarm Optimization (PSO) is utilized for training the parameters of FFNN by minimizing the root mean square error$\left({{\rm{RMSE}}} \right)$RMSE. The results disclose that the proposed approach attained the most accurate prediction of PV power with $\% {\rm{MAPE}} = 2.38$%MAPE=2.38 for the month of November as well as high classification accuracy with ${\rm{PCA}} = 94.96\% $PCA=94.96% in the month of April. Based on the obtained results, the proposed LF-SCA-PSO trained FFNN outperformed the existing hybrid models in both prediction and classification and hence possess the potential to be a new alternative to assist engineers in predicting the PV power of solar systems at short- and long-time horizons.
暂无评论