计及数据不可靠性的动力电池组SOC估计方法研究
发布时间：2018-12-12 11:37
【摘要】：锂离子电池具有较高的能量密度与功率密度,被广泛用于电动汽车(Electric vehicle,EV)储能。电池管理系统(Battery management system,BMS)是电动车关键技术之一,BMS对电池组的能量优化管理以及对电池的有效保护均依赖于电池荷电状态(State of charge, SOC)的准确估计。SOC不能被直接测量,传统SOC估计方法存在参数选取困难、准确性低、通用性差等缺点。近年来以机器学习为代表的数据驱动建模方法蓬勃发展,此类方法通常有着良好的非线性逼近能力,且具有较好的可移植性。电动车运行过程中所产生的大量状态数据也给数据驱动建模方法提供了有利条件。然而,数据驱动建模方法受制于数据自身的可靠程度,而车载数据采集设备有限的精度以及电动车的复杂的工作环境使得数据中的噪声、离群点无可避免。且由于数据驱动模型基于“黑箱”假设,难以分析误差来源,因而可靠性难以保证。为了减少SOC估计误差对BMS系统所造成的负面影响,考虑到数据不可靠性的多个来源并且结合机器学习方法自身的特点,本文从多个角度开展研究,以降低不可靠数据对模型产生的不利影响,并且通过估计所得到SOC的后验概率,降低BMS误动作风险。首先,考虑到最小二乘支持向量机(Least square support vector machine, LSSVM)具有良好的泛化性能,第二章中将最小二乘支持向量机回归方法应用于SOC估计问题,并通过粒子群算法提高模型精度、优化运算效率。利用磷酸铁锂(LiFePO4,LFP)单电池恒定电流放电实验比较了几种常用的核函数在SOC估计中的实际效果,并通过动力电池组交替充放电实验,模拟电动车动力电池工作状态,验证了算法的有效性,并分析了该方法存在的不足。其次,为降低数据噪声对回归模型所产生的影响,首次提出了一种加权模糊支持向量机回归方法,根据样本受噪声污染的程度动态调整权重,以提高估计的可靠性。由于不同数据特征中噪声相对独立,为了综合评估多维数据样本的置信程度,提出了一种基于T-S模糊模型的权值函数。此外,为度量不同特征量与估计结果的相关性,首次提出了一种夹角非线性相关性度量方法。基于丰田COMS电动汽车实验平台,通过实测数据验证了所提出方法的有效性。接着,针对荷电状态回归问题的中异方差、非平稳性,建立了一种灵活的混合高斯过程(Gaussian mixture regression,GMR)荷电状态估计方法。该方法通过多高斯分量线性组合的方式从实测数据中抽取数据信息,利用高斯过程回归(Gaussian process regression,GPR)对每个子高斯分量进行估计,最后将子系统的估计结果加权求和以获得最终SOC估计结果。针对混合高斯模型(Gaussian mixture model,GMM)的优化问题提出了一种进化期望最大化算法(Evolutionary expectation maximum,EEM),数据分布较为集中的高斯分量通过对附近数据分布稀疏的高斯分量吞噬实现进化,不断迭代最终获得最优模型数量以及超参数。此外,首次提出了一种Pearson非线性相关性特征选择算法,以降低模型过拟合风险。最后,深入研究了离群点对支持向量机、神经网络以及高斯过程回归模型所造成的影响,针对高维数据中的离群点问题,首次提出了一种加权高斯过程回归方法(Weighted Gaussian process regression,WGPR),分别从权重空间以及函数空间的角度进行推导。此外,提出了一种改进的密度离群检测方法,避免了高维数据离群检测中性能劣化的问题。实验中将所提出的算法分别用于解决荷电状态估计问题以及光伏发电系统短期功率估计问题。
[Abstract]:The lithium ion battery has higher energy density and power density and is widely used for electric vehicle (EV) energy storage. The battery management system (BMS) is one of the key technologies of the electric vehicle, and the energy-optimized management of the BMS and the effective protection of the battery depend on the accurate estimation of the state of charge (SOC). the SOC cannot be directly measured, and the traditional SOC estimation method has the disadvantages of difficulty in selecting parameters, low accuracy, poor universality and the like. In recent years, the data-driven modeling method, which is represented by machine learning, is developing vigorously, and the method has good non-linear approximation ability and has good portability. The large number of state data generated during the operation of the electric vehicle also provides favorable conditions for the data-driven modeling method. However, the data-driven modeling method is limited by the reliability of the data itself, and the limited accuracy of the on-board data acquisition device and the complex working environment of the electric vehicle make the noise in the data, and the outliers are inevitable. and because the data driving model is based on the 鈥渂lack box鈥，
本文编号：2374488
[Abstract]:The lithium ion battery has higher energy density and power density and is widely used for electric vehicle (EV) energy storage. The battery management system (BMS) is one of the key technologies of the electric vehicle, and the energy-optimized management of the BMS and the effective protection of the battery depend on the accurate estimation of the state of charge (SOC). the SOC cannot be directly measured, and the traditional SOC estimation method has the disadvantages of difficulty in selecting parameters, low accuracy, poor universality and the like. In recent years, the data-driven modeling method, which is represented by machine learning, is developing vigorously, and the method has good non-linear approximation ability and has good portability. The large number of state data generated during the operation of the electric vehicle also provides favorable conditions for the data-driven modeling method. However, the data-driven modeling method is limited by the reliability of the data itself, and the limited accuracy of the on-board data acquisition device and the complex working environment of the electric vehicle make the noise in the data, and the outliers are inevitable. and because the data driving model is based on the 鈥渂lack box鈥，
本文编号：2374488
本文链接：https://www.wllwen.com/kejilunwen/dianlidianqilunwen/2374488.html
