A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology

Diagnostics and prognostics are two important aspects in a condition-based maintenance (CBM) program. However, these two tasks are often separately performed. For example, data might be collected and analysed separately for diagnosis and prognosis. This practice increases the cost and reduces the efficiency of CBM and may affect the accuracy of the diagnostic and prognostic results.In this paper, a statistical modelling methodology for performing both diagnosis and prognosis in a unified framework is presented. The methodology is developed based on segmental hidden semi-Markov models (HSMMs). An HSMM is a hidden Markov model (HMM) with temporal structures. Unlike HMM, an HSMM does not follow the unrealistic Markov chain assumption and therefore provides more powerful modelling and analysis capability for real problems. In addition, an HSMM allows modelling the time duration of the hidden states and therefore is capable of prognosis. To facilitate the computation in the proposed HSMM-based diagnostics and prognostics, new forward–backward variables are defined and a modified forward–backward algorithm is developed. The existing state duration estimation methods are inefficient because they require a huge storage and computational load. Therefore, a new approach is proposed for training HSMMs in which state duration probabilities are estimated on the lattice (or trellis) of observations and states. The model parameters are estimated through the modified forward–backward training algorithm. The estimated state duration probability distributions combined with state-changing point detection can be used to predict the useful remaining life of a system.The evaluation of the proposed methodology was carried out through a real world application: health monitoring of hydraulic pumps. In the tests, the recognition rates for all states are greater than 96%. For each individual pump, the recognition rate is increased by 29.3% in comparison with HMMs. Because of the temporal structures, the same HSMMs can be used to predict the remaining-useful-life (RUL) of the pumps.     

Path classification and estimation model based prognosis of pneumatic cylinder lifetime

Prognosis is a key technology to improve reliability,safety and maintainability of products,a lot of researchers have been devoted to this technology.But to improve the predict accuracy of remaining li...     

Integrated Equipment Health Prognosis Considering Crack Initiation Time Uncertainty and Random Shock

With integrated equipment health prognosis, both physical models and condition monitoring data are utilized to achieve more accurate prediction of equipment remaining useful life (RUL). In this paper, an integrated prognostics method is proposed to account for two important factors which were not considered before, the uncertainty in crack initiation time (CIT) and the shock in the degradation. Prognostics tools are used for RUL prediction starting from the CIT. However, there is uncertainty in CIT due to the limited capability of existing fault detection tools, and such uncertainty has not been explicitly considered in the literature for integrated prognosis. A shock causes a sudden damage increase and creates a jump in the degradation path, which shortens the total lifetime, and it has not been considered before in the integrated prognostics framework either. In the proposed integrated prognostics method, CIT is considered as an uncertain parameter, which is updated using condition monitoring data. To deal with the sudden damage increase and reduction of total lifetime, a virtual gradual degradation path with an earlier CIT is introduced in the proposed method. In this way, the effect of shock is captured through identifying an appropriate CIT. Examples of gear prognostics are given to demonstrate the effectiveness of the proposed method.     

动态贝叶斯网络在设备剩余寿命预测中的应用研究

采用动态贝叶斯网络对设备剩余寿命进行预测,建立了基于动态贝叶斯网络模型的设备剩余寿命预测框架模型,运用动态贝叶斯网络的粒子滤波近似推理算法对加工过程中钻头寿命预测进行实例研究,结果表明了该方法的有效性.     

Remaining Useful Life Model and Assessment of Mechanical Products: A Brief Review and a Note on the State Space Model Method

The remaining useful life(RUL) prediction of mechanical products has been widely studied for online system performance reliability, device remanufacturing, and product safety(safety awareness and safety improvement). These studies incorporated many di erent models, algorithms, and techniques for modeling and assessment. In this paper, methods of RUL assessment are summarized and expounded upon using two major methods: physics model based and data driven based methods. The advantages and disadvantages of each of these methods are deliberated and compared as well. Due to the intricacy of failure mechanism in system, and di culty in physics degradation observation, RUL assessment based on observations of performance variables turns into a science in evaluating the degradation. A modeling method from control systems, the state space model(SSM), as a first order hidden Markov, is presented. In the context of non-linear and non-Gaussian systems, the SSM methodology is capable of performing remaining life assessment by using Bayesian estimation(sequential Monte Carlo). Being e ective for non-linear and non-Gaussian dynamics, the methodology can perform the assessment recursively online for applications in CBM(condition based maintenance), PHM(prognostics and health management), remanufacturing, and system performance reliability. Finally, the discussion raises concerns regarding online sensing data for SSM modeling and assessment of RUL.     

基于改进HSMM的设备故障预测方法研究

针对传统隐半马尔科夫模型(HSMM)在故障诊断和预测应用中存在的不足,对传统HSMM做了以下改进:一是将状态持续时间概率分布和监测值概率分布连续化,并假定其服从威布尔分布;二是基于状态开始时间的识别,提出了状态剩余持续时间;三是提出了时变转移概率的概念,给出了各时刻转移概率的计算方法。确立了基于改进HSMM的故障诊断和预测的方法体系,给出了故障诊断判据和设备剩余寿命的计算式。案例研究表明方法是合理有效的。     

基于KPCA和WPHM的滚动轴承可靠性评估与寿命预测

为了评估滚动轴承的可靠性和预测剩余使用寿命,选取能够反映性能退化过程的特征参数作为寿命预测模型的输入参数,提出一种基于核主元分析(kernel principal component analysis,简称KPCA)和威布尔比例故障率模型(Weibull proportional hazards model,简称WPHM)的方法。首先,提取滚动轴承全寿命周期的时域、频域及时频域等多特征参数,从中筛选出有效的特征参数,构建高维相对特征集;其次,进行核主元分析,选取能够反映轴承全寿命周期性能退化过程的核主元,进而作为WPHM的协变量来进行可靠性评估和剩余寿命预测。通过滚动轴承全寿命试验,验证了该方法能够对轴承进行准确的可靠性评估和剩余寿命预测,以提供及时的维修决策。同时,由于提取的是相对特征,降低了同种轴承间在制造、安装及工况的差异,增强了该方法的适用性和稳定性。     

Equipment health diagnosis and prognosis using hidden semi-Markov models

In this paper, the development of hidden semi-Markov models (HSMMs) for equipment health diagnosis and prognosis is presented. An HSMM is constructed by adding a temporal component into the well-defined hidden Markov model (HMM) structures. The HSMM methodology offers two significant advantages over the HMM methodology in equipment health diagnosis and prognosis: (1) it overcomes the modeling limitation of HMM due to the Markov property and therefore improves the power in diagnosis, and (2) it can be directly used for prognosis. The application of the HSMMs to equipment health diagnosis and prognosis is demonstrated with the fault classification application of UH-60A Blackhawk main transmission planetary carriers and prognosis of a hydraulic pump health monitoring application. The effectiveness of the HSMMs is compared with that of the HMMs. The results of the application testing have shown that the HSMMs are capable of identifying the faults under both test cell and on-aircraft conditions while the performance of the HMMs is not comparable with that of the HSMMs. Furthermore, the HSMM-based methodology can be used to estimate the remaining useful life of equipment.     

锂离子电池循环寿命的融合预测方法

针对传统基于粒子滤波的锂离子电池剩余使用寿命预测方法的不足:过度依赖电池经验退化模型和模型输入变量单一的问题,提出了一种相关向量机、粒子滤波和自回归模型融合的锂离子电池剩余寿命预测的方法。通过相关向量机提取电池历史数据的退化趋势,构建趋势方程替换以往的电池经验退化模型,作为粒子滤波算法的状态转换方程。引入自回归模型的长期趋势预测值,替换观测值构建粒子滤波算法的观测方程。将3种方法相融合估计电池剩余寿命。实验结果表明:融合方法不仅预测精度高而且采用数据驱动的方法避免了构建复杂的电池机理退化模型,通用性强。     

Current status of machine prognostics in condition-based maintenance: a review

Condition-based maintenance (CBM) is a decision-making strategy based on real-time diagnosis of impending failures and prognosis of future equipment health. It is a proactive process that requires the development of a predictive model that can trigger the alarm for corresponding maintenance. Prognostic methodologies for CBM have only recently been introduced into the technical literature and become such a focus in the field of maintenance research and development. There are many research and development on a variety of technologies and algorithms that can be regarded as the steps toward prognostic maintenance. They are needed in order to support decision making and manage operational reliability. In this paper, recent literature that focuses on the machine prognostics has been reviewed. Generally, prognostic models can be classified into four categories: physical model, knowledge-based model, data-driven model, and combination model. Various techniques and algorithms have been developed depending on what models they usually adopt. Based on the review of some typical approaches and new introduced methods, advantages and disadvantages of these methodologies are discussed. From the literature review, some increasing trends appeared in the research field of machine prognostics are summarized. Furthermore, the future research directions have been explored.     

基于隐半马尔可夫模型设备退化状态识别方法研究

机械设备从正常到故障往往经历一系列退化状态,正确识别与估计设备当前所处的退化状态,对预防设备进一步退化和故障的发生具有重要意义。隐半马尔可夫模型(Hidden Semi-MarkovModels,HSMM)是隐马尔可夫模型(hidden Markov models,HMM)的一种扩展模型,克服了因马尔可夫链的假设造成HMM建模所具有的局限性,比HMM具有更好的建模能力和分析能力。由状态识别和HMM本质上的相通性,将HSMM引入到机械设备的状态识别中,提出了一种基于HSMM状态识别方法,描述了该模型的拓扑结构和主要参数以及相应的训练和识别算法。最后通过滚动轴承试验系统验证了方法的有效性。     

小波相关特征尺度熵和隐半马尔可夫模型在设备退化状态识别中的应用

为正确识别机械设备当前所处的退化状态,预防设备进一步退化和故障的发生,提出一种基于小波相关特征尺度熵和隐半马尔可夫模型(Hidden semi-Markov models, HSMM)的设备退化状态识别新方法.对采集到的设备振动信号进行小波相关滤波处理,得到信噪比较高的尺度域小波系数,在此基础上结合信息熵理论提出了沿尺度分布的小波相关特征尺度熵概念.构造信号的小波相关特征尺度熵/矢量,并以此矢量作为HSMM的输入进行训练,建立基于HSMM的机械设备运行状态分类器,从而实现设备退化状态的识别.以滚动轴承为例,对正常和几种故障程度不同的滚动体运行状态进行了识别,同时还与基于小波相关特征尺度熵-HMM的状态识别法进行了比较,试验结果表明该方法能有效识别设备的退化状态.     

A review on machinery diagnostics and prognostics implementing condition-based maintenance

Condition-based maintenance (CBM) is a maintenance program that recommends maintenance decisions based on the information collected through condition monitoring. It consists of three main steps: data acquisition, data processing and maintenance decision-making. Diagnostics and prognostics are two important aspects of a CBM program. Research in the CBM area grows rapidly. Hundreds of papers in this area, including theory and practical applications, appear every year in academic journals, conference proceedings and technical reports. This paper attempts to summarise and review the recent research and developments in diagnostics and prognostics of mechanical systems implementing CBM with emphasis on models, algorithms and technologies for data processing and maintenance decision-making. Realising the increasing trend of using multiple sensors in condition monitoring, the authors also discuss different techniques for multiple sensor data fusion. The paper concludes with a brief discussion on current practices and possible future trends of CBM.     

Set-membership methodology for model-based prognosis

This paper addresses model-based prognosis to predict Remaining Useful Life (RUL) of a class of dynamical systems. The methodology is based on singular perturbed techniques to take into account the slow behavior of degradations. The full-order system is firstly decoupled into slow and fast subsystems. An interval observer is designed for both subsystems under the assumption that the measurement noise and the disturbances are bounded. Then, the degradation is modeled as a polynomial whose parameters are estimated using ellipsoid algorithms. Finally, the RUL is predicted based on an interval evaluation of the degradation model over a time horizon. A numerical example illustrates the proposed technique.     

轴承故障诊断与故障预测方法

分析了利用HMM进行故障诊断和HHMM进行故障预测的框架,针对传统HHMM推理算法复杂,推理时间长的问题,将HHMM转化为DBN,并应用交叉树推理算法,缩短了推理时间。最后将HMM和HHMM应用于轴承故障诊断和故障预测或剩余寿命预测(RUL),通过试验结果验证了这种方法的有效性。     

A dynamic multi-scale Markov model based methodology for remaining life prediction

The ability to accurately predict the remaining life of partially degraded components is crucial in prognostics. In this paper, a performance degradation index is designed using multi-feature fusion techniques to represent deterioration severities of facilities. Based on this indicator, an improved Markov model is proposed for remaining life prediction. Fuzzy C-Means (FCM) algorithm is employed to perform state division for Markov model in order to avoid the uncertainty of state division caused by the hard division approach. Considering the influence of both historical and real time data, a dynamic prediction method is introduced into Markov model by a weighted coefficient. Multi-scale theory is employed to solve the state division problem of multi-sample prediction. Consequently, a dynamic multi-scale Markov model is constructed. An experiment is designed based on a Bently-RK4 rotor testbed to validate the dynamic multi-scale Markov model, experimental results illustrate the effectiveness of the methodology.     

Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings

The remaining useful life(RUL) estimation of bearings is critical for ensuring the reliability of mechanical systems. Owing to the rapid development of deep learning methods, a multitude of data-driven RUL estimation approaches have been proposed recently. However, the following problems remain in existing methods: 1) Most network models use raw data or statistical features as input, which renders it di cult to extract complex fault-related information hidden in signals; 2) for current observations, the dependence between current states is emphasized, but their complex dependence on previous states is often disregarded; 3) the output of neural networks is directly used as the estimated RUL in most studies, resulting in extremely volatile prediction results that lack robustness. Hence, a novel prognostics approach is proposed based on a time–frequency representation(TFR) subsequence, three-dimensional convolutional neural network(3 DCNN), and Gaussian process regression(GPR). The approach primarily comprises two aspects: construction of a health indicator(HI) using the TFR-subsequence–3 DCNN model, and RUL estimation based on the GPR model. The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy. Subsequently, the 3 DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs. Finally, the RUL of the bearings is estimated using the GPR model, which can also define the probability distribution of the potential function and prediction confidence. Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence–3 DCNN–GPR approach. The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.     

基于状态空间模型的飞机APU在翼RUL预测方法

为解决利用飞机辅助动力装置(APU)在翼监测数据难以表征其性能状态而造成的性能评估以及剩余使用寿命预测(RUL)难的问题,本文提出一种基于状态空间模型(SSM)与卡尔曼滤波融合的APU在翼RUL预测方法.首先,通过在翼监测数据构造含噪声的性能指标(PI)来表征APU的性能状态,借助维纳过程与建立的含噪声的PI构建状态方...     

一种融合多传感器数据的数模联动机械剩余寿命预测方法

随着传感和信息技术的发展,各式各样的传感器获取了机械装备海量的监测数据,让剩余寿命预测有"据"可依,推动机械剩余寿命预测进入了大数据时代。但由于数据类型多样、量大面广,如何利用丰富的多传感器数据,从中快速挖掘健康状态退化信息,指导寿命预测,成为大数据时代下机械寿命预测的全新挑战。基于模型的寿命预测方法大多仅针对单一监测数据进行建模分析,无法有效利用丰富的大数据资源。数据驱动的方法则过分依赖训练数据,缺乏必要的经验指引,方法的可解释性差。为了有效利用多传感器数据指导寿命预测,从数模联动的思路出发,建立了一种融合多传感器数据的数模联动寿命预测方法。采用一种通用的Wiener过程模型对健康状态退化过程进行描述,分别建立多源观测函数和多源映射函数对状态与数据之间的因果关系和关联关系进行描述,采用粒子滤波算法将多传感器数据与模型进行动态匹配,预测剩余寿命。在提出方法的统一框架指导下,选取三种特定模型对铣刀剩余寿命进行预测,验证了提出方法的有效性。