齿轮箱状态识别与剩余寿命预测的MoG-BBN法

基于混合高斯输出贝叶斯信念网络模型的齿轮箱退化状态识别与剩余寿命预测新方法,应用聚类评价指标对全寿命过程退化状态数进行优化,通过计算待识别故障特征向量的概率值来确定齿轮箱退化状态,在退化状态识别的基础上,提出了剩余寿命计算方法。再利用齿轮箱全寿命实验数据对此进行验证。结果表明,该方法可以有效地识别齿轮箱故障状态并实现剩余寿命预测,平均预测正确率为96.47 %,为齿轮箱的健康管理提供参考。     

基于CHMM的齿轮箱状态识别研究

针对离散隐Markov模型(HMM)在状态识别中的不足,结合齿轮箱全寿命实验数据,研究了基于连续隐Markov模型(CHMM)的状态识别方法。建立了基于齿轮箱原始振动信号的CHMM状态识别框架,提出了基于K均值算法和交叉验证相结合的状态数优化方法,通过计算待确定观测数据的极大似然概率值来确定齿轮箱当前状态。结果表明,用原始振动信号作为CHMM的输入可以实现状态识别,验证了模型的有效性,为齿轮箱基于状态的维修提供了科学依据。     

基于混合高斯输出贝叶斯信念网络模型的设备退化状态识别与剩余使用寿命预测方法研究

提出了基于混合高斯输出贝叶斯信念网络模型的设备退化状态识别与剩余使用寿命预测新方法,将变量消元和期望最大化算法相结合对模型进行推理,应用聚类评价指标对状态数进行优化,通过计算待识别特征向量的概率值来确定设备当前的退化状态,在退化状态识别的基础上,提出了剩余使用寿命预测方法。最后,分别应用50组轴承全寿命仿真数据和3组轴承全寿命实验数据对模型进行验证。结果表明,该模型可有效地识别设备的退化状态并对剩余使用寿命进行预测。     

基于小波包与倒频谱分析的风电机组齿轮箱齿轮裂纹诊断方法

为实现风电机组齿轮箱及时有效地监测和维护,提出基于小波包与倒频谱分析的风电机组齿轮箱齿轮裂纹诊断方法。该方法针对齿轮裂纹振动信号为转速频率对啮合频率及其倍频调制的特点,利用小波包分解来识别振动信号中的故障特征,通过小波包频带能量监测得到故障部位的啮合频率范围;考虑到倒频谱可以分离和提取难以识别的密集调制信号的周期成分,基于倒频谱识别故障部位的转速频率,综合利用两种频谱分析方法得到的啮合频率和转速频率,能诊断故障部位和类型。实验研究表明,该方法能精确地诊断齿轮裂纹故障,并可以实现对风电机组齿轮在复杂环境中退化状态的监测,预防断齿等重大故障的发生。     

基于ARX模型的齿轮箱建模方法

齿轮箱是一个结构复杂的系统,输入输出的影响因素众多,于是单输入单输出的系统传递特性必然无法准确地反映实际工况中齿轮箱的运行特征,针对此问题本文提出了基于ARX模型的齿轮箱多输入多输出建模方法,并使用两个输入信号（输入轴扭矩和转速信号）及三个输出信号（输出轴扭矩、转速信号和箱体上采集的振动加速度信号）,将齿轮箱建模为一个二输入三输出的系统。实验结果显示：ARX模型从系统固有特性的角度来分析齿轮箱的状态,可以有效区分不同的故障状态。     

基于EEMD和SVR的单自由度结构状态趋势预测

为了解决结构早期损伤难以正确识别的问题,本文结合聚类经验模式分解（EEMD）解决随机不确定性问题和支持向量机（SVM）解决预测问题这两者的优势,提出了一种基于EEMD特征提取的支持向量机回归（SVR）结构状态趋势预测方法。先对单自由度结构渐进损伤的加速度振动信号进行EEMD,再进行希尔伯特变换（HT）,计算瞬时频率,然后用回归支持向量机对反映结构健康状态的瞬时频率进行趋势预测。研究表明：对于渐变损伤该方法可以准确地、高精度地预测结构状态趋势。     

基于混沌激励与吸引子分析的结合面损伤识别方法

工程结构在使用寿命周期内,各种环境因素会导致结合面出现损伤,从而威胁结构的完整性和功能性,甚至诱发安全事故。研究了一种利用混沌激励与吸引子几何特性进行结合面损伤识别的方法,采用混沌振动信号激励待测结构,对采集到的加速度响应信号进行相空间重构,并构造了一种基于吸引子局部方差计算的特征参量用于损伤识别,同时研究了影响特征参量的主要参数。设计了悬臂梁结合面损伤识别实验,控制固定端螺栓预紧力的下降来模拟结合面损伤,利用上述方法对结合面的损伤状态进行了识别。结果表明：本文方法能够识别结合面的损伤状态,所构造的特征参量随损伤程度改变单调变化,响应测点配置、特征参量计算参数等对损伤识别的效果有影响。     

船用齿轮箱系统抗冲击特性数值仿真

研究了船用齿轮箱系统抗冲击特性的分析方法。采用静力学、非线性接触有限元法计算某大型船用齿轮箱箱体、轮齿正常工况的等效静应力,在NX.NASTRAN的结果文件中提取各应力分量。建立齿轮箱系统的箱体-轴承-轴-齿轮耦合有限元模型,用DDAM法计算其在水下爆炸冲击产生的动应力。应用弹塑性力学知识,将相应单元的静、动应力的分量按照MISES准则重新合成,引入无量纲强度剩余系数,评估该齿轮箱系统的抗冲击性能。采用衰减正弦基波组合的时间历程对冲击谱进行匹配,模拟水下爆炸环境,用模态加速度法,得到齿轮箱系统的加速度瞬态响应特性。研究结果为船用齿轮箱的抗冲击性能评估提供了理论基础,同时为抗冲击设计及冲击隔离提供数据支撑。     

内激励作用下齿轮箱动态响应与振动噪声分析

综合考虑齿轮时变啮合刚度及齿轮误差等内部激励的影响,建立了齿轮箱稳态动响应分析模型。采用模态叠加法进行求解,得到了齿轮箱节点位移动响应时域历程,对激励中各谐波成分对齿轮箱动响应的影响做出了分析。采用声固耦合的方法对齿轮箱噪声辐射进行求解,得到了齿轮箱噪声谱。计算了齿轮箱各板面对声场总声压的贡献度,依据板面贡献度计算结果,提出了模型改进方案,并对各改进方案的降噪效果做出了评估,为齿轮箱的设计提供了理论依据     

基于FEM和BEM法的大型立式齿轮箱振动噪声计算及测试分析

根据某大型立式行星传动齿轮箱的结构和安装特点,基于FEM法建立了该齿轮箱的和有限元模型,对其进行了振动模态分析,计算了其模态频率和稳态不平衡响应;基于BEM法建立了该齿轮箱的外声场边界元模型,导入了齿轮箱振动稳态不平衡响应结果作为声学边界条件,对辐射声场进行了数值计算和仿真分析。通过对齿轮箱进行现场振动和噪声测试分析,得到的测试结果与理论计算结果较为一致,表明了理论计算的可行性和准确性     

粒子滤波参数估计方法在齿轮箱剩余寿命预测中的应用研究

针对非线性非高斯系统的剩余寿命（RUL）预测问题,本文提出了一种基于粒子滤波（PF）理论的设备剩余寿命预测方法。首先建立设备的非线性状态空间模型（含有未知的时变参数）,然后通过粒子滤波算法估计出设备状态的概率密度函数（PDF）,从而根据该PDF计算出设备的RUL。此外,计算设备RUL的期望值和95%置信区间,并对模型的预测效果进行评估,验证预测的有效性和准确性。最后通过齿轮箱的全寿命实验,对本文所提方法的有效性进行实例验证,将实验结果和传统的比例风险模型（PHM）预测结果对比分析,结果表明本文提出的剩余寿命预测方法要优于传统的PHM预测方法。     

加筋复合材料结构分层损伤的贝叶斯诊断及预测

针对复合材料结构疲劳损伤的在线监测和预测问题,提出了一种基于结构健康监测 (Structural health monitoring, SHM) 和贝叶斯理论的结构分层损伤诊断及结构剩余使用寿命预测方法。在贝叶斯概率理论框架下,采用指数模型描述复合材料结构疲劳分层损伤面积的先验演化规律,融合在线SHM数据对结构分层损伤状态,以及损伤面积演化模型的参数进行联合后验估计,即为损伤诊断结果。进一步通过后验估计得到的损伤状态和模型参数预测未来时刻结构分层损伤面积的演化,从而得到当前复合材料结构的剩余使用寿命预测结果。通过有限元仿真的加筋复合材料结构疲劳分层扩展对所提出的方法进行了验证。结果表明,方法可以在线准确地诊断结构分层损伤状态以及预测结构的剩余使用寿命。      

Remaining useful life prediction via long-short time memory neural network with novel partial least squares and genetic algorithm

Advancements in information technology have made various industrial equipment increasingly sophisticated in recent years. The remaining useful life (RUL) of equipment plays a crucial important role in the industrial process. It is difficult to establish a functional RUL model as it requires the fusion of time-series data across different scales. This paper proposes a long-short term memory neural network, which integrates a novel partial least square based on a genetic algorithm (GAPLS-LSTM). The parameters are first analyzed by PLS to obtain the parameter fusion function of the health index (HI). The GA then searches the optimal coefficients of the function; the expected HI values can be calculated with the fusion function. Finally, the RUL of the equipment is predicted with the LSTM method. The proposed GAPLS-LSTM was applied to RUL prediction of a marine auxiliary engine to validate it by comparison against GAPLS-BP and GAPLS-RNN methods. The results show that the proposed method is capable of effective RUL prediction.     

基于GA-ELM的锂离子电池RUL间接预测方法

针对锂离子电池在线剩余寿命预测时容量难以直接测量及预测精度不高等问题,提出一种间接预测方法。首先,分析电池寿命状态特征参数,选取等压降放电时间作为锂电池间接健康因子;其次,引入遗传算法优化极限学习机模型参数,建立锂电池剩余使用寿命间接预测模型;最后,基于NASA锂电池实验数据和自主实验数据验证该预测方法的正确性和有效性。实验结果表明,相较高斯过程回归方法和极限学习机方法,该方法准确有效、测试速度快,并且预测结果输出稳定,精度较高。     

Condition Based Structural Health Monitoring and Prognosis of Composite Structures under Uniaxial and Biaxial Loading

This paper presents a condition based structural health monitoring (SHM) and prognosis approach to estimate the residual useful life (RUL) of composite specimens in real time. On-line damage states, which are estimated using real time sensing information, are fed to an off-line predictive model to update future damage states and RUL. The on-line damage index or damage state at any given fatigue cycle is estimated using correlation analysis. Based on the on-line information of the previous and current damage states, an off-line model is developed to predict the future damage state and estimate the RUL. The off-line model is a stochastic model which is developed based on the Gaussian process approach. In this paper, the condition based prognosis model is used to estimate the cumulative fatigue damage in composite test structures under constant amplitude fatigue loading. The proposed procedure is validated under uniaxial fatigue loading as well as biaxial fatigue loading. Experimental validations demonstrate that the prediction capability of the prognosis algorithm is effective in predicting the RUL under complex stress states.     

Remaining useful life prediction of lithium-ion battery using a novel health indicator

Remaining useful life (RUL) prediction plays a significant role in the health prognostic of lithium-ion batteries (LIBs). The capacity or internal resistance is commonly used to quantify degradation process and predict RUL of LIB, but those two indicators are difficult to be obtained due to complex operational conditions and high costs, respectively. To address this issue, we extract a novel health indicator (HI) from the battery current profiles that can be directly measured online. Furthermore, the indicator is optimized by Box-Cox transformation and evaluated by correlation analysis for degradation modeling accurately. Finally, relevance vector machine (RVM) algorithm is utilized to make a probabilistic prediction for battery RUL based on the extracted HI. The correlation analysis verifies the effectiveness of the novel HI, and comparative experiments demonstrate the proposed method can predict RUL of LIB more accurately.     

Utilizing Accelerated Degradation and Field Data for Life Prediction of Highly Reliable Products

For newly developed, highly reliable, and long‐lifespan products, it is quite difficult to implement effective remaining useful life (RUL) prediction in the early usage under limited time cost. However, accelerated degradation testing (ADT) is generally used for lifetime evaluation for such products with harsher test conditions and shorter test time in the late research and development phase. Thus, in this paper, we propose a life prediction framework to integrate the information from ADT to conduct field RUL prediction for highly reliable products. Because ADT belongs to reliability testing used for inferring the population information from the selected test samples, we at first present the modified Wiener process (MWP) model. Different from traditional methods that embody both the random variability and unit‐to‐unit variability into the diffusion coefficient, the proposed method describes them separately in ADT analysis. Then, the MWP model from ADT is used as a prior for field RUL prediction of the target product during which the strong tracking filtering algorithm is introduced for updating the hidden state and computing the RUL prediction results when the new monitoring data are available. Because of the complexity of the MWP model, the Markov chain Monte Carlo method is provided to estimate the unknown parameters. Finally, the simulation study and the light‐emitting diode application verify the effectiveness of the proposed framework that can achieve reasonable life prediction results for highly reliable products for both linear and nonlinear scenarios. Copyright © 2015 John Wiley & Sons, Ltd.     

Transfer learning based deep learning model and control chart for bearing useful life prediction

The remaining useful life (RUL) of the machine is one of the key information for predictive maintenance. If there is a lack of predictive maintenance strategy, it will increase the maintenance and breakdown costs of the machine. We apply transfer learning techniques to develop a new method that predicts the RUL of target data using degradation trends learned from complete bearing test data called source data. The training length of the model plays a crucial role in RUL prediction. First, the exponentially weighted moving average (EWMA) chart is used to identify the abnormal points of the bearing to determine the starting point of the model's training. Secondly, we propose transfer learning based on a bidirectional long and short-term memory with attention mechanism (BiLSTMAM) model to estimate the RUL of the ball bearing. At the same time, the public data set is used to compare the estimation effect of the BiLSTMAM model with some published models. The BiLSTMAM model with the EWMA chart can achieve a score of 0.6702 for 11 target bearings. The accuracy of the RUL estimation ensures a reliable maintenance strategy to reduce unpredictable failures.