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。     

基于改进粒子滤波的锂离子电池剩余寿命预测

针对锂离子电池剩余寿命预测精度不高的问题,提出一种基于随机扰动无迹粒子滤波的锂离子电池剩余寿命预测方法.首先采用无迹卡尔曼滤波算法改进粒子滤波的重要性采样过程,随机扰动重采样算法改进粒子滤波的重采样过程,提出随机扰动无迹粒子滤波算法;然后采用双指数经验模型拟合的方法得到模型参数的初始值;最后采用随机扰动无迹粒子滤波算法...     

融合多源数据的非线性退化建模与剩余寿命预测

针对目前基于单个传感器剩余寿命预测方法存在预测精度不高的问题,该文提出一种融合多源传感器数据的非线性退化建模与剩余寿命预测方法。该方法包括复合健康指标的构建、模型参数的估计和传感器融合系数的确定,在确定融合系数后,结合设备历史寿命数据与实时监测数据,利用Bayesian参数更新公式推导出设备的剩余寿命概率分布,实现设备的剩余寿命在线预测。最后通过由商用模块化航空推进系统仿真生成的发动机退化数据集进行仿真实验,结果表明该文所提方法能够有效提高设备剩余寿命预测的准确性。     

联合频域相关分析和改进粒子滤波的滚动轴承寿命预测方法

为了解决滚动轴承退化状态识别难、剩余使用寿命（Remaining Useful Life, RUL）预测误差大这两个关键问题，提出一种联合频域特征相关分析及改进粒子滤波的寿命预测方法。基于滚动轴承在退化过程中频域特征存在短期相似性和长期差异性这一特点，对不同时间序列傅里叶变换后的幅值谱进行相关分析，构建平均相关系数（Average Correlation Coefficient, ACC）曲线。当ACC达到设定阈值时，利用初始故障时间（Degradation Initial Timepoint, DIT）将轴承状态划分为正常和损伤两阶段。利用损伤阶段的归一均方根值作为观测样本输入，构建考虑了全局指数式退化趋势与局部波动双重因素的粒子滤波（Dual Factor Particle Filter, DFPF）模型，实现粒子分布校正并完成RUL预测。试验结果表明，所提方法相比传统的均方根值法和峭度法能够更准确地识别轴承初始故障时间。在寿命预测精度方面，相比传统粒子滤波（Particle Filter, PF）算法，所提方法减小了异常观测值对预测趋势的影响，具有更高的RUL预测精度。     

基于EMD的灰色模型的疲劳剩余寿命预测方法研究

工程上的振动信号多为非线性非平稳信号,为了利用工程振动信号预测机械产品的疲劳剩余寿命,提出改进的经验模态分解方法对振动信号进行分解,分离故障特征频率到某本征模态函数中,计算全寿命周期各阶段故障特征频率所在本征模态函数的均方根值、峭度等时域特征指标,将其作为刻画机械产品健康状态的退化特征量,形成退化特征量序列,根据经验设定机械产品完全失效对应的退化特征量阈值.用退化特征量序列训练灰色模型,然后用训练好的灰色模型预测退化特征量的变化趋势,判断不同退化特征量用于刻画机械产品退化过程的可行性,估计可用退化特征量达到退化特征量阈值的时间并据此预测机械产品的剩余疲劳寿命.通过6205深沟球轴承全寿命周期振动信号对其进行验证,结果表明,可用的退化特征量结合该方法可以有效地预测小型球轴承的疲劳剩余寿命.     

考虑随机效应的两阶段退化系统剩余寿命预测方法

针对退化过程呈现两阶段特征的随机退化系统剩余寿命预测问题,建立两阶段维纳过程退化模型,并引入随机效应描述样本间差异性。基于时间-空间变化方法以及变点处退化值的随机特性,给出首达时间意义下系统寿命分布解析表达形式。提出一种基于期望最大化(expectation maximization, EM)算法和贝叶斯理论的模型参数离线辨识和在线更新算法。最后,结合液力耦合器(liquid coupling device, LCD)的实际退化数据,验证所提方法的可行性与有效性,并说明其工程应用价值。     

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。     

在役金属材料剩余寿命预测技术

本文论述了预测在役金属材料剩余寿命的重要性 ,并介绍了利用蠕变空洞对在役材料剩余寿命进行定性和定量的预测技术     

基于高斯粒子滤波的当前统计模型跟踪算法

对于非线性系统估计问题,高斯粒子滤波器可以获得近似最优解,与粒子滤波器相比其优点是不需要重采样步骤和不存在粒子退化现象.采用高斯粒子滤波代替当前模型自适应跟踪算法中的卡尔曼滤波,将高斯粒子滤波与当前统计模型的优点相结合,提出了一种新的当前统计模型自适应跟踪算法,用于非线性非高斯系统的机动目标跟踪.MonteCarlo仿真表明,该算法跟踪精度优于标准的交互多模型算法和当前统计模型自适应跟踪算法,实时性好于交互多模型粒子滤波算法.     

基于粒子滤波算法的风力发电塔地震动力响应预测

建立有限元分析模型过程中产生的误差和不确定性可导致试验和有限元分析结果之间显著的差异性,量化此类不确定性对结构动力响应预测尤为重要。基于粒子滤波算法对有限元计算结果的不确定性进行量化,提出了一个用于结构动力响应预测的概率贝叶斯估计计算框架,并通过风力发电塔振动台试验动力响应观测结果对计算方法的合理性与有效性进行验证。结果表明：随地震波输入幅值的增大,有限元计算结果的误差显著增大,考虑试验观测值修正之后可以显著减小此类不确定性的影响;粒子滤波算法用于结构动力响应预测精度较好,预测值与试验实测值具有很好的一致性;将粒子滤波算法与振动台试验相结合能够对结构动力响应进行有效预测,具有一定的工程应用参考价值。     

Remaining useful life prediction for lithium-ion batteries using a quantum particle swarm optimization-based particle filter

ABSTRACT

A novel RUL prediction approach for lithium-ion batteries using quantum particle swarm optimization (QPSO)-based particle filter (PF) is proposed. Compared to particle swarm optimization (PSO)-based PF, QPSO-based PF is proved to have a better performance in global searching and has fewer parameters to control, which makes QPSO-PF easier for applications. Moreover, fewer particles are required by QPSO-PF to accurately track the battery's health status, leading to a reduction of computation complexity. RUL prediction results using real data provided by NASA and compared with benchmark approaches demonstrates the superiority of the proposed approach.     

基于Gamma退化过程的直升机主减速器行星架剩余寿命预测模型

鉴于Gamma过程具有平稳、独立增量等退化建模所需的属性,将其用于描述设备退化过程,并针对缺乏故障数据时难以进行剩余寿命预测的问题,利用设备运行中采集的表征其退化状态的大量间接状态参数和少量直接状态参数,建立了基于Gamma退化过程的剩余寿命预测模型;针对经验最大化算法中似然函数难以解析求解的问题,引入粒子滤波算法实现了模型参数估计;最后将模型应用于直升机主减速器行星架的剩余寿命预测,得到了不同时刻的预测结果及95%置信区间,验证了预测模型的有效性和准确性。     

Remaining useful life prediction for hard failures using joint model with extended hazard

In this paper, we investigate a joint modeling method for hard failures where both degradation signals and time‐to‐event data are available. The mixed‐effects model is used to model degradation signals, and extended hazard model is used for the time‐to‐event data. The extended hazard is a general model which includes two well‐known hazard rate models, the Cox proportional hazards model and accelerated failure time model, as special cases. A two‐stage estimation approach is used to obtain model parameters, based on which remaining useful life for the in‐service unit can be predicted. The performance of the method is demonstrated through both simulation studies and a real case study.     

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.     

Prognosis of gas turbine remaining useful life using particle filter approach

Gas turbines are commonly used in distributed power generation. Because of high speed nature, they require good maintenance for increased reliability and availability. Remaining useful life prediction is therefore an essential part of condition‐based maintenance to better foresee future state hence guaranteeing design efficiency, reduced maintenance cost, and improved safety. Gas turbines also contain a lot of sensors data that need to be processed for better prediction. In this paper, a probabilistic approach called particle filter is used for prediction. The proposed approach is tested using Turbofan degradation data provided by NASA as a benchmark problem. Meanwhile, through time the gas turbines experiences a change from normal state to degraded state attributed to aging, corrosion and erosion etc. Hence, in the context of abundant data, it is helpful to know the transition between states. For the same reason, the present paper suggests a statistical approach called Z‐test. The test results show that the proposed technique provides score and MAPE values of 559.9 and 21.6 respectively, comparable to past reported performance.     

Remaining useful life prediction for multivariable stochastic degradation systems with non-Markovian diffusion processes

Multivariable stochastic degradation system (MSDS) is quite common in industries such as blast furnace ironmaking, vehicle transportation, and aerospace manufacturing. Large-scale complex equipments may be affected by multiple factors, resulting in not just a single deteriorating performance characteristic. It is difficult to handle unknown failure structures of practical systems by using traditional univariate degradation modeling methods. A novel health index (HI) is constructed to quantitatively analyze the health state for the overall system. Considering the interaction between internal reactions and external environments, the fractional Brownian motion (FBM), a typical non-Markovian diffusion process, is added for the purpose of reflecting stochastic uncertainties and memory effects. Based on the wavelet estimators and the maximum likelihood estimation (MLE) algorithm, multi-sensor observations of degradation variables are analyzed simultaneously to identify model parameters. A closed-form distribution of system-level remaining useful life (RUL) is obtained with a mild two-layer approximation. Relevant case studies are then handled that adequately demonstrate the effectiveness and the practical utility of the proposed method.     

Remaining useful life prediction via a variational autoencoder and a time-window-based sequence neural network

The prediction of remaining useful life (RUL) has attracted much attention, and it is also a key section for predictive maintenance. In this study, a novel hybrid deep learning framework is proposed for RUL prediction, where a variational autoencoder (VAE) and time-window-based sequence neural network (twSNN) are integrated. Among it, VAE is used to extract the hidden and low-dimensional features from the raw sensor data, and a loss function is designed to extract useful data features; by using a sliding time window, twSNN can predict RUL dynamically; meanwhile, it can simplify the network architecture in the time dimension. Furthermore, to achieve higher performance on various failure conditions, long short-term memory (LSTM) cell and convolutional LSTM (ConvLSTM) cell are designed for twSNN respectively. A case study is completed with a dataset of aircraft turbine engines. It is found that the proposed frameworks with LSTM cell and ConvLSTM cell have better performance on both single failure mode and multiple failure modes. The results also show that the prediction accuracy is averagely improved by 6.65% for single failure mode and 15.05% for multiple failure modes respectively.     

An ensemble model considering health index based classification for remaining useful life prediction

Accurate prediction of remaining useful life (RUL) plays an important role in the formulation of maintenance strategies. However, due to the diversity of the failure mode of equipment, there are significant differences between the degradation data, which greatly affects the accuracy of RUL prediction. In this case, an ensemble prediction model considering health index-based (HI-based) classification is proposed in this paper. Firstly, the stacked autoencoder (SAE) is employed to construct the HI. Then, the time window is used to sequentially process the HI sequence, so that many data segments with the same length can be achieved. To differentiate the data with the similar degradation process, K-means and Xgboost are selected to construct offline and online data classification models respectively. Finally, according to the results of the data classification, the ensemble model that integrates multiple machine learning methods are separately trained and then adaptively used for RUL prediction. In addition, integrating multiple methods helps to improve the generalization ability of the model. The NASA C-MAPSS dataset is applied to verify the effectiveness of the proposed method, and the results show that the proposed method achieves a higher prediction accuracy and shorter computational time than other existing prediction models.     

Remaining service life prediction based on gray model and empirical Bayesian with applications to compressors and pumps

In this study, a three-step remaining service life (RSL) prediction method, which involves feature extraction, feature selection, and fusion and prognostics, is proposed for large-scale rotating machinery in the presence of scarce failure data. In the feature extraction step, eight time-domain degradation features are extracted from the faulty variables. A fitness function as a weighted linear combination of the monotonicity, robustness, correlation, and trendability metrics is defined and used to evaluate the suitability of the features for RSL prediction. The selected features are merged using a canonical variate residuals-based method. In the prognostic step, gray model is used in combination with empirical Bayesian algorithm for RSL prediction in the presence of scarce failure data. The proposed approach is validated on failure data collected from an operational industrial centrifugal pump and a compressor.