Neural network-based learning and estimation of battery state-of-charge: A comparison study between direct and indirect methodology

Faced with the ever-increasing urban environmental pollution, the electric vehicles (EVs) have received increasing attention in the automotive industry. Lithium-ion batteries, serving as electrochemical power storage, have been extensively used in EVs because of the lightweight, no local pollution and high power density. The increasing awareness on the safe operation and reliability of the battery requires an efficient battery management system (BMS), among the parameters monitored by which, state-of-charge (SOC) is critical in preventing overcharge, deep discharge, and irreversible damage. This article investigates the neural network (NN)-based modeling, learning, and estimation of SOC by comparing two different methodologies, that is, direct structure with SOC as network output and indirect structure with voltage as output. Firstly, the nonlinear autoregressive exogenous neural network (NARX-NN) is introduced, in which SOC is directly deemed as an NN output for learning and estimation. Secondly, a radial basis function (RBF)-based NN with unscented Kalman filter (RBFNN-UKF) is proposed, in which the terminal voltage is used as output. Instead, SOC is deemed as an internal state which would be estimated indirectly based on the feedback error of voltage. Experimental results demonstrate that both estimators can achieve accurate SOC estimation for regular cases, in spite of the inaccurate initial conditions. However, the direct NN structure is revealed as not capable of dealing with the cases with sensor bias, which, however, can be well accommodated in the indirect structure by extending the sensor bias as an augmented state. Benefiting from the uncertainty augmentation and feedback compensation, the indirect RBFNN-UKF shows superiority over the direct estimation in the practical experiments, depicting a promising prospect in the future onboard EV-BMS application.     

基于神经网络的电动汽车电池SOC估算研究

论文首先分析了当前电动汽车电池管理系统中存在的问题,特别是电池电压的精确测量和剩余电量的准确预测问题一直亟待突破,因此,论文在分析电池荷电状态(SOC)影响因素的基础上,进行了动力电池的充放电实验,建立了BP网络电池模型,通过对网络进行训练,应用神经网络模型进行SOC估算,实验表明:建立的BP网络具有较好的适应性,能有效预测锂离子动力电池电压、电流和放电容量间的映射关系。可以准确地对电动汽车电池进行SOC估算。     

An active balancer with rapid bidirectional charge shuttling and adaptive equalization current control for lithium-ion battery strings

This article proposes an active balancer, which features bidirectional charge shuttling and adaptive equalization current control, to fast counterbalance the state of charge (SOC) of cells in a lithium-ion battery (LIB) string. The power circuit consists of certain bidirectional buck-boost converters to transfer energy among the different cells back and forth. Owing to the characterization of the open-circuit voltage (OCV) vs SOC in LIB being relatively smooth near the SOC middle range, the SOC-inspected balance strategy can achieve more precise and efficient equilibrium than the voltage-based control. Accordingly, a compensated OCV-based SOC estimation is put forward to take into account the discrepancy of SOC estimation. Besides, the varied-duty-cycle (VDC) and curve-fitting modulation (CFM) methods are devised herein to tackle the problems of slow equalization rate and low balance efficacy, which arise from the diminution in balancing current as the SOC difference between the cells decreases in the later duration of equalization especially. The proposed strategies have taken the battery nonlinear characteristic and circuit parameter nonideality into account and can adaptively modulate the duty cycle with the SOC difference to keep balancing current constant throughout the balancing cycle. Simulated and experimental results are given to demonstrate the feasibility and effectiveness of the same prototype constructed. Compared with the fixed duty cycle and the VDC methods, the proposed CFM has the best balancing efficiency of 81.4%, and the balance time is shortened by 27.1% and 18.6%, respectively.     

基于IP核的芯片级测试结构研究

分析了芯片级测试的特点以及与传统板级测试区别,对SOC测试结构的核心部分测试访问机制(TAM)和Wrapper进行了详细的论述,分析了系统级芯片的测试结构及其优化.     

几种CMOS VLSI的低功耗BIST技术

在分析全扫描内建自测试(BIST)较高测试功耗的基础上,总结出几种CMOS VLSI的低功耗BIST技术方案,包括减少待测电路(CUT)输入端的翻转次数、简化线性反馈移位寄存器(LFSR)结构、部分扫描低功耗BIST方法等.分析结果表明,这些方法不但在保证测试覆盖率的条件下,降低了测试平均功耗和峰值功耗,而且综合应用这几种方法将会使系统功耗指标达到最佳.     

散粒体的自组织临界性与非均匀介质的元胞自动机模型

目前,普遍认为自组织临界性的发生与尺度效应和组织原则有关。尺度效应以各国开展的沙堆试验为基础,而组织原则未见有人讨论。首先,进行了不同级配的散粒体沙坡试验,发现散粒体自组织临界性与粒径的非均匀系数有关。随着非均匀系数的逐渐增大,散粒体呈现出不同的试验现象和统计结果,并且散粒体系统的动力行为由准周期到自组织临界性再到准周期进行演化。其次,设计了能够描述非均匀介质和体现非均匀系数的元胞自动机模型,即引入由于摩擦力造成的能量损耗作为表征沙粒表面不同粗糙度的物理量。通过调整能量损耗和半径的取值,可以进行不同非均匀系数、不同规模的元胞自动机数值模拟,其统计结果与真实散粒体沙堆试验相类似。通过沙堆试验和计算机模拟,发现组织原则与系统的鲁棒性和敏感性是否达到平衡有关。只有当非均匀散粒体维持整体的鲁棒性和敏感性的平衡时,才可能突破尺度局限,使大尺度的系统仍呈现自组织临界性;但当非均匀系数继续增大,使系统的鲁棒性占优,而敏感性消失或减弱,两者的平衡被破坏时,非均匀散粒体仍不能呈现自组织临界性现象。因此系统的鲁棒性和敏感性达到平衡是系统呈现自组织临界性现象的必要条件之一。     

用于混合信号系统的模/数分块一体化测试技术

为了解决混合信号系统中三种模块:模拟、数字和存储器接口之间存在的难以测试的问题,讨论了一种模拟/数字一体化的测试技术,包括三种模块的测试方法、系统测试的分块、可测性设计(DFT)、自测试策略和方案等,并说明了互连测试和准静态电流IDDQ测试法可为该项新技术提供有效的解决方案.     

注入无功功率的链式电池储能系统荷电状态均衡控制策略

针对链式电池储能系统相内电池组荷电状态(SOC)不均衡问题,分析了单位功率因数下均衡控制策略在SOC极度不均衡时导致过调制的边界条件,并提出了一种注入无功功率的新型相内SOC均衡控制策略。通过在各H桥调制信号中叠加有功和无功电压分量,重新分配有功和无功功率,保证SOC处于极端状态的电池组主要进行有功功率交换,其余电池组主要进行无功功率交换,实现极端模块调制比有效降低,非极端模块调制比略有增长,避免过调制。与单位功率因数均衡控制策略相比,该策略通过控制功率因数角充分协调各模块调制比,可以在各电池组SOC差异更大的情况下实现均衡控制,扩大适用范围。仿真结果验证了所提策略的正确性和有效性。     

基于MC9S12与LTC6811的储能电站电池管理系统设计

设计了一种用于储能电站的电池管理系统(BMS)。基于储能电站BMS拓扑结构及锂电池的特性,设计了一种以Freescale单片机和ADI电池管理芯片(MC9S12与LTC6811)为核心的BMS。该BMS可实现对多路电池电压、温度采集及均衡控制;同时,可根据采样数据利用改进型安-时积分法进行电池荷电状态(SOC)计算。根据现场实际数据,将电池电压、温度的采样值与实际值比较,同时对电池均衡效果及SOC进行分析。试验结果证明,设计的BMS具有较高的采样精度和采样速度,均衡控制合理,SOC估算值误差较小,验证了所设计BMS的实用性。     

基于SOH及离线数据分段矫正的锂电池SOC估计

锂离子动力电池在电动车辆上应用时,受工况、环境等随机因素影响,SOC具有很强的时变非线性,对电动车辆动力电池SOC估计进行研究具有理论意义和应用价值。安时积分法是目前工程中常用的SOC估计方法,在应用过程中存在的难点是积分过程中累积误差的消除。首先利用电池健康状态估算出电池当前时刻的实际可用容量,作为安时积分法中的除数项,对SOC估计值进行矫正;其次,利用离线数据对安时积分法中的累积误差进行分段消除。仿真结果表明,所提方法比传统的安时积分法具有更高的精度,能够较好地消除累积误差。