Supercapacitor module quality prewarning based on the improved whale optimization algorithm and GM (1,1) gray prediction model
Abstract
This paper proposes an algorithm combining the improved whale optimization algorithm (WOA) and GM (1,1) to predict the number of qualified products in the test batches of supercapacitor modules. Based on this algorithm, a quality prewarning system is developed on LabVIEW software. First, the GM (1,1) gray prediction model is established with the number of qualified products in the test batch as the original sequence, and then a nonlinear iterative parameter is proposed to improve the WOA. The improved WOA is used to optimize the background value sequence in the GM (1,1) gray prediction model, to obtain the optimal prediction algorithm. Then, on the LabVIEW software platform, the simulation of the GM (1,1) gray prediction model, the algorithm combining WOA and GM (1,1) and the algorithm combining the improved WOA and GM (1,1) are carried out for fifty groups of original data series. Taking one group of simulation data results as an example, the relative error of the prediction value of the algorithm combining the improved WOA and GM (1,1) is 0.0004%, which is better than 0.0112% of the algorithm combining the WOA and GM (1,1) and 1.5429% of the GM (1,1) gray prediction model. Finally, the quality prewarning system of the supercapacitor module is developed by using LabVIEW software, which provides a more accurate quality prewarning function for the test process of the supercapacitor module.
DOI: 10.61416/ceai.v25i2.8343