中文摘要：

针对电池容量预测问题,将模糊逻辑方法应用于预测VRLA蓄电池的荷电状态。分别将蓄电池的工作电压、工作电流和荷电状态参数模糊化,制定其对应的模糊子集,设计合理的模糊规则,从而实现对蓄电池SOC进行预测,实验结果发现该方法在蓄电池放电初、末期预测值准确率较高。而粒子群算法具有较好的全局优化能力,因此提出一种蓄电池SOC预测的粒子群算法和模糊逻辑相结合方法。设计了VRLA蓄电池荷电状态的模糊逻辑和粒子群-模糊逻辑预测模型。实验结果表明,基于粒子群-模糊逻辑方法的预测精度优于模糊逻辑方法,验证了粒子群-模糊逻辑方法的有效性。

英文摘要：

A fuzzy logic method was used to predict the battery state of charge（SOC） of the valve regulated lead acid（VRLA） battery. The battery＇s working voltages, currents and true SOC values were fuzzified respectively, and their fuzzy subsets also formulated correspondingly. The rational fuzzy rules were designed to achieve prediction of SOC.Found that the fuzzy logic method was able to predict the true values of SOC through the actual magnitudes of discharge voltages and currents with high precision at the beginning and end. So introduced the Particle swarm optimization（PSO） combining with the fuzzy logic method in SOC prediction of VRLA battery, and modeled the two models. The results showed that the fuzzy logic method could predict the SOC of the VRLA battery, but the precision was bad than the PSO-fuzzy method.