Battery pack capacity estimation for electric vehicles based on enhanced machine learning and field data

Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.

Estimating the grain size of microgranular material using laser-induced breakdown spectroscopy combined with machine learning algorithms

Recent work has validated a new method for estimating the grain size of microgranular materials in the range of tens to hundreds of micrometers using laser-induced breakdown spectroscopy(LIBS).In this situation,a piecewise univariate model must be constructed to estimate grain size due to the complex dependence of the plasma formation environment on grain size.In the present work,we tentatively construct a unified calibration model suitable for LIBS-based estimation of those grain sizes.Specifically,two unified multivariate calibration models are constructed based on back-propagation neural network(BPNN)algorithms using feature selection strategies with and without considering prior information.By detailed analysis of the performances of the two multivariate models,it was found that a unified calibration model can be successfully constructed based on BPNN algorithms for estimating the grain size in the range of tens to hundreds of micrometers.It was also found that the model constructed with a priorguided feature selection strategy had better prediction performance.This study has practical significance in developing the technology for material analysis using LIBS,especially when the LIBS signal exhibits a complex dependence on the material parameter to be estimated.

Packing问题的计算复杂性

本文讨论了离散模型与连续问题的关系以及图灵机的计算能力,在此基础上扩充了问题及 NP完全问题的定义,根据解空间的拓扑结构特点将NP完全的Packing问题分为三类,并对多边形 Packing问题进行了有益的探讨。这对设计Packing问题的求解算法具有借鉴意义。

Algorithms for single machine scheduling with availability constraints

It is a NP-hard problem to schedule a list of nonresumable jobs to the available intervals of an availability-constrained single machine to minimize the scheduling length. This paper transformed this scheduling problem into a variant of the variable-sized bin packing problem, put forward eight bin packing algorithms adapted from the classic one-dimensional bin packing problem and investigated their performances from both of the worst-case and the average-case scenarios. Analytical results show that the worst-case performance ratios of the algorithms are not less than 2. Experimental results for average cases show that the Best Fit and the Best Fit Decreasing algorithm outperform any others for independent and precedence-constrained jobs respectively.

Enhanced Wolf Pack Algorithm (EWPA) and Dense-kUNet Segmentation for Arterial Calcifications in Mammograms

Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)methods have been introduced for automatic BAC detection and quantification with increased accuracy.Previously,classification with deep learning had reached higher efficiency,but designing the structure of DL proved to be an extremely challenging task due to overfitting models.It also is not able to capture the patterns and irregularities presented in the images.To solve the overfitting problem,an optimal feature set has been formed by Enhanced Wolf Pack Algorithm(EWPA),and their irregularities are identified by Dense-kUNet segmentation.In this paper,Dense-kUNet for segmentation and optimal feature has been introduced for classification(severe,mild,light)that integrates DenseUNet and kU-Net.Longer bound links exist among adjacent modules,allowing relatively rough data to be sent to the following component and assisting the system in finding higher qualities.The major contribution of the work is to design the best features selected by Enhanced Wolf Pack Algorithm(EWPA),and Modified Support Vector Machine(MSVM)based learning for classification.k-Dense-UNet is introduced which combines the procedure of Dense-UNet and kU-Net for image segmentation.Longer bound associations occur among nearby sections,allowing relatively granular data to be sent to the next subsystem and benefiting the system in recognizing smaller characteristics.The proposed techniques and the performance are tested using several types of analysis techniques 826 filled digitized mammography.The proposed method achieved the highest precision,recall,F-measure,and accuracy of 84.4333%,84.5333%,84.4833%,and 86.8667%when compared to other methods on the Digital Database for Screening Mammography(DDSM).

数据驱动的动力电池包侧面柱碰撞安全性预测方法

电动汽车电池包在侧面柱碰撞下极易失效并可能发生着火。为准确、快速地评估电池包在侧面柱碰撞下安全性,采用区域细化的电池包模型,在不同的碰撞速度、碰撞角度、碰撞位置和车辆装载状态下开展了仿真分析,采用优化拉丁超立方采样策略设计了仿真矩阵,并通过图像识别的方法批量提取电池包碰撞响应生成数据集。对研究参数进行组合生成了新特征,并对参数进行相关性分析,确定了模型训练的输入特征。采用支持向量机、随机森林方法和反向传播神经网络(back propagation neural network, BPNN)机器学习方法建立了数据驱动的预测模型。结果表明,支持向量机模型性能最优,模型预测参数的平均决定系数R2为0.96。在训练数据集中引入标准差不同的高斯噪声,对模型的鲁棒性进行了检验,BPNN机器学习方法的鲁棒性较优。采用建立的数据驱动模型能够预测电池包侧面柱碰撞下的变形情况,评估电池包的碰撞安全性。

基于机器视觉的电池PACK装配线装配工艺研究

为了提高动力电池PACK自动化行业的产品质量和生产效率,通过机器视觉识别模块和壳体组件来组装螺栓孔的位置和状态,机器人执行模块抓取和螺栓拧紧,并在指定的姿势下实现模块壳体组装和螺栓紧固工作。

Lifetime and Aging Degradation Prognostics for Lithium-ion Battery Packs Based on a Cell to Pack Method

Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.

基于改进CNN-SVM的动力电池组故障诊断研究

针对卷积神经网络(CNN)在动力电池组故障诊断中容易过拟合和准确度低的问题,提出了一种改进的基于卷积神经网络的锂离子电池故障诊断模型。首先,对CNN网络的结构和参数进行调整和优化,利用小波包变换将故障信息提取到CNN中,然后用支持向量机(SVM)代替CNN中的SoftMax分类器构建CNN-SVM模型,再利用粒子群算法(PSO)对SVM中的超参数进行优化,以得到用于电池组故障诊断的最优模型,最后,通过故障实验对比来验证所提出方法的优越性。实验结果表明,CNN-SVM模型的故障分类准确率可达97%以上,远高于传统深度学习网络,对锂离子电池组的故障诊断具有实际意义。

基于分组遗传算法的数据中心虚拟机节能映射

近年来,随着人们对云计算业务需求持续增长,数据中心能耗日益增加,由此不仅增加了运营成本,巨大的碳排放对生态环境也产生严重的影响,数据中心节能已成为当前亟须解决的重要难题。对云数据中心的虚拟机放置(Virtual Machine Placement,VMP)进行优化能有效地提高资源利用率,同时,VMP也是减少数据中心能耗的重要技术之一;针对数据中心的能耗感知VMP问题,提出一种基于分组遗传算法的节能算法EEGGA(Energy-Efficient Grouping Genetic Algorithm),算法将节能VMP问题视为装箱问题(Bin Packing Problem,BPP),并应用基于分组编码的遗传算法对其进行求解,通过减少活动物理主机的数量(装箱数量)以实现降低数据中心能耗的目标;在算法迭代过程的交叉和变异等阶段,设计了多种启发优化策略提升子代染色体的适应度,从而提高算法的节能性能和加快迭代收敛的速度;通过仿真实验,在收敛速度和求解性能等方面将提出的算法与传统的节能遗传算法进行对比,实验结果表明:提出的算法能够有效地减少数据中心的能耗,在节能性能和求解收敛速度方面均优于其他算法。

半自动吸塑包装机关键构件力学特性模拟分析

为研究吸塑包装机关键构件力学特性,以半自动吸塑包装机为例,对其刀架与转轴关键构件力学特性进行模拟分析。通过数字建模与物理建模方法构建关键构件多刚体力学模拟模型,利用ADAMS动力学自动分析软件和ANSYS有限元软件,模拟分析关键构件的动态力学性能和静态力学性能。分析结果显示:关键构件的位移变化与角速度、加速度变化符合实际运动规律,当转轴受到49.52 N垂直方向力的影响时,转轴最大位移为0.928 mm,最大应力为31.25 MPa,符合选材规定范围,具有良好的模拟性能。

小盒商标纸在线压痕装置的设计与应用

目的解决中支双铝包小盒商标纸因模切压痕不稳定出现的烟包小盒侧边弹开翻折、烟包变形等问题。方法设计小盒商标纸在线压痕装置,该装置包括机架、传动轴、辗送轮、压痕件、导纸轮、对压轮、压痕避让部和托纸轮,同时开展正交试验,获取压痕件半径、刃缘弧长和包装机作业速度最佳参数组合。结果应用在线压痕装置后,小盒商标纸压痕挺度的平均绝对误差由6.0减小至1.9,次品烟包频率由37.6包/班次降低至8.4包/班次,改进后比改进前降低了77.7%。结论设计的小盒商标纸在线压痕装置可使商标纸挺度处于适宜水平,降低了该类缺陷烟包频率,提高了烟包包装质量。该技术可为提高双铝包包装机的产品质量、作业效率及稳定性提供支持。

面向循环寿命最优的电池组串-并混联结构设计方法研究

在电池系统中,由于其单体间不可避免的差异性,使得系统在循环老化速率方面远快于其中单体。而这一老化速率,又同时受到单体间老化分布与模组内串并联结构等多因素的影响。如何在给定模组规模与单体参数分布条件下,通过对组内最优串并混联结构的选取,实现对系统整体寿命的延长,成为亟待解决的关键问题。为此,在经典电池动态模型的基础上添加了对其老化与不一致行为的描述;在此基础上,通过对典型成组结构的老化仿真,与非典型结构的机器学习推衍,实现了对任意拓扑需求下最佳串并组合结构的选取。并结合不同锂离子电池组老化实验证明了方法在寿命预测与最优结构选取方面的有效性。

仿烟支空头标准件的研究与设计

本文将软木材质与组合工装设计相结合,设计研究一种仿烟支缺陷标准件代替实物缺陷样品。采用单因子实验法,研究标准件的材质和外观,并对ZB45型包装机烟支空头检测进行模拟检验,对标准件的剔除准确率、耐用性和设备运行状态进行验证。试验表明:软木材质优于其他材质,剔除准确率达到99%,设备运行稳定,耐用不易变形;组合工装设计的剔除准确率更加稳定。

基于可解释机器学习的固体填充床储热装置快速设计研究

为了解决填充床储热装置性能计算耗时、设计方法匮乏、难以满足多种储热场景需求的问题,提出了一种具有一定通用性、能够快速给出准确设计结果的固体填充床储热装置设计方法。首先,建立了固体填充床储热装置储热效能数据集,基于此训练了可准确预测装置储热效能的人工神经网络模型;其次,采用SHapley Additive exPlanation方法对人工神经网络模型的预测进行解释,量化了材料物性、装置结构尺寸以及运行参数对装置储热效能的影响;最后,建立了固体填充床储热装置储热效能关联式,基于储热效能关联式提出了适用于多种储热场景的填充床储热装置设计流程,并以西班牙Andasol 1光热电站中的储热装置为实例进行了计算分析。研究结果表明:储热效能关联式计算结果与数值模拟结果的相对偏差在10%以内,可用于填充床储热装置储热效能的快速计算和准确预测;与传统数值模拟方法相比,所提方法的计算效率提高了5个数量级,设计方案经济上可行,证明了该储热效能关联式在工程实践中的便利性和实用性。

CDAlky■烷基化反应器填料层压差上升问题的分析与处理措施

烷基化工艺技术是生产清洁燃料的重要炼油技术,一般采用硫酸法烷基化CDAlky■静态混合反应器技术。然而硫酸法烷基化反应工艺在运行时仍存在一些问题,如反应器填料层压差上升导致装置运行负荷降低,严重影响装置产能。基于此,从初始填料层压差、原料杂质含量、循环酸过滤器精度、机封白油杂质含量4个方面对可能影响填料层压差上升的因素进行排查,并相应地提出了处理措施,有效解决了CDAlky■烷基化填料层压差上升的问题,可为行业内的其他装置技术人员提供技术参考。

基于初始种群优化策略的虚拟机整合算法

基于种群更新策略的启发式算法是解决多目标虚拟机整合问题的常用算法.然而,多数这类算法未考虑到初始种群的优化问题,存在收敛慢的问题.为解决此慢收敛问题,以遗传算法为例,提出了一种多目标敏感的初始种群优化方法,其核心思想是分析各目标的资源特性,建立优化初始种群的约束模型,提高初始种群的质量.仿真实验结果表明,该方法能显著提升遗传算法的搜索性能,且优于其他两种对比的改进策略.

基于ISSA-KELM的锂离子电池组SOC预测

针对锂离子电池组荷电状态SOC(state-of-charge)难以预测的问题,提出改进麻雀搜索算法ISSA(improved sparrow search algorithm)优化核极限学习机KELM(kernel extreme learning machine)的SOC预测模型。首先,引入Logistic混沌映射改进标准SSA,获取最优种群个体;其次,采用改进算法优化KELM的核函数参数S和惩罚系数C,建立ISSA-KELM预测模型;最后,利用某储能设备的历史数据进行仿真研究,对比分析ELM、KELM和ISSA-KELM模型的预测结果,并选用其他工况数据验证模型的鲁棒性。结果表明,SOC预测均方根误差和平均绝对误差分别减小至2.06%和1.54%,证明所提模型的预测精度提高,具有良好的收敛性、泛化性及鲁棒性。

ZB45B包装机烟包成型通道的改进

为解决YB45B型5.4 mm×100 mm规格细支硬盒包装机冷机启动时机器不能全速运行,频繁触发8号轮出口堵塞信号的问题,需以200包/分的速度运行30~40 min后才能全速运行。为此在原输送通道的基础上设计一种YB45B新型烟包成型通道底板。新型烟包成型通道由输送通道、上下输送带、聚甲醛底板、簧片、带轮、张紧装置及翻转器构成。以昆明卷烟厂生产的“云烟(细支云龙)”牌卷烟为对象进行测试,结果表明,应用改进的新型烟包成型通道后,冷机启动后机器即可全速运行,单机台每天可增加产量1.44~1.92箱。该技术可提高设备连续运行能力,为提高卷烟包装设备的维保效率提供支持,提升设备有效作业率,降低了维护成本及生产成本。

基于机器学习的UHPC抗压强度预测及配合比优化

结合试验设计、机器学习及紧密堆积模型提出了一种超高性能混凝土(UHPC)抗压强度预测和配合比优化方法,并对比了预测结果与实测结果。此外,还将支持向量回归-粒子群优化算法(SVR-PSO)模型与其他常见抗压强度预测模型进行了对比,并基于SVR-PSO模型设计开发了图形用户界面预测软件。结果表明:SVR-PSO模型在稳定性和预测精度方面具有明显优势,抗压强度预测值和实测值误差在5%以内;采用所提出的UHPC配合比设计方法,可基于原材料数据快速生成满足抗压强度要求的UHPC配合比。