State of charge prediction for electric loader battery based on extreme learning machine

In order to accurately predict the state of charge of electric loader batteries, a multi-strategy improved dung beetle optimization algorithm (MIDBO) was proposed to optimize the state of charge (SOC) prediction method of extreme learning machine (ELM). Firstly, principal component analysis (PCA) was used to screen the input features to reduce dimensionality. Secondly, logstic chaos mapping was introduced in the population initialization stage to improve the diversity and quality of the population, the dynamic spiral search strategy was used in the breeding stage of the dung beetle algorithm, and the Lévy flight mechanism was introduced in the foraging stage to jump out of the local optimum. Finally, the adaptive t-distribution variation and dynamic selection strategy were used to update the position of the dung beetle to improve the convergence speed of the algorithm. This enables accurate prediction of the state of charge of the electric loader battery. Experiments with real vehicle data of electric loader show that the accuracy of MIDBO-ELM model reaches 99.985% and the error is less than 5‰. The robustness of the model is verified by adding different types of noise simulation measurement errors. In addition, the accuracy of the MIDBO algorithm is verified by the test function, and the generalization ability of the algorithm on the battery charge state prediction is verified by the public data set.