Safety performance detection method for automobile power battery

The invention belongs to the technical field of automobile power battery detection, and discloses a safety performance detection method for an automobile power battery, which comprises the following steps: step 1, constructing an NARX neural network, and training the NARX neural network to obtain a battery voltage prediction model; step 2, respectively collecting current and voltage of the battery according to a sampling period; current values and voltage values at t-n, t-(n-1),..., t-2 and t-1 moments are used as input parameters of a battery voltage prediction model, and the battery voltage prediction model outputs predicted voltage at the t moment; wherein n is greater than or equal to 5 and is an integer, and t-n represents a t-n moment; and step 3, determining the safety level of the battery according to the predicted voltage at the t moment based on a four-score box diagram strategy. 本发明属于汽车动力电池检测技术领域，公开了一种汽车动力电池的安全性能检测方法，包括：步骤一、构建NARX神经网络，并对所述NARX神经网络进行训练，得到电池电压预测模型；步骤二、按照采样周期分别采集电池的电流和电压；以t-n，t-（n-1），