Optimization of BP neural network model by chaotic krill herd algorithm

• Published in: Alexandria engineering journal Vol. 61; no. 12; pp. 9769 - 9777
• Main Authors: Yu, Lihong, Xie, Linyang, Liu, Chunmei, Yu, Song, Guo, Yongxia, Yang, Kejun
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2022; Elsevier
• Subjects: BP neural network; Chaos theory; Kidney bean; Krill herd algorithm; Optimize; Yield; Kidney bean; BP neural network; Yield; Chaos theory; Optimize; Krill herd algorithm
• ISSN: 1110-0168; 2090-2670
• DOI: 10.1016/j.aej.2022.02.033

Taking kidney bean as the research object, row spacing, fertilizer application and planting density were selected as experimental factors, production for the response indicators, the chaos theory, krill herd algorithm is introduced into the BP neural network, the minimum error in training as a target, the model of weight and threshold as variables to optimize the BP neural network and chaotic krill herd algorithm BP neural network prediction model was set up (C-KHA-BP). The RMSE of C-KHA-BP model is 191.93 kg/hm2、MAE is 153.18 kg/hm2, and MAPE is 12.67%, the correlation coefficient R2 is 0.95.By solving the global optimal solution of C-KHA-BP model, the optimal row spacing of kidney bean was 72.63 cm, the fertilizer application rate was 103.91 kg/hm2, and the planting density was 30 × 104 plants /hm2. The next year, the validation test was conducted in the same test area, and the yield of kidney bean under the test scheme was 2843.2 kg /hm2, the relative error between the test result and the simulation optimization result (2949.5 kg /hm2) was only −3.65%, indicating that the fitting function of C-KHA-BP prediction model was precision and the optimization result was accurate. The results of this study can provide a new approach to the prediction and optimization of similar models in the field of grain production.