An Experimental Data of Lithium-Ion Battery Time Series Analysis

The experimental data of Lithium-ion battery has its specific sense. This paper is proposed to analyze and forecast it by using autoregressive integrated moving average (ARIMA) and spectral analysis, which has effective and statistical results. The method includes the identification of the data, estimation and diagnostic checking, and forecasting the future values by Box and Jenkins. The analysis shows that the time series models are related with the present value of a series to past values and past prediction errors. After transferring the data by different function, improving autocorrelations are significant. Forecasting the future values of the possible observations show significantly fluctuated such as increasing or decreasing in specific ranges accordingly. In spectral analysis, the parameters of the model were determined by performing spectral analysis of the experimental data to look periodicities or cyclical patterns, and to check the existence of white noise in the data. The Bartlett's Kolmogorov-Smirnov statistic suggests the white noise of the data. The spectral analysis for the series reveals non-11-second cycle of activity for dynamic stress test current, but strong 45-second that highlights the position of the main peak in the spectral density; strong 21-second and 45-second for the urbane dynamometer driver schedule current and voltage, respectively; but no significance for dynamic stress test current.