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.     

Review of machining metal matrix composites

Monotonic fault progression is an important assumption for a number of prognostic models. This assumption can be violated through human intervention and self‐healing and result in non-monotonic degradation data which not only increases the uncertainty but also may cause model failure. Methods to analyze and handle non-monotonic degradation in repairable systems are practically nonexistent in the literature. In this research, we intend to consider repairable systems in which self‐healing is possible and human interventions are desirable. We presented a novel example of self-healing for fatigue cracks analyzed by acoustic emission. The aim of the present paper is to initiate a new research area on using non-monotonic measures in degradation-based prognostics. However, this research is not a review of trend analysis techniques, and therefore, there are more techniques to be considered or developed in future studies. In effect, trend analysis should be considered as an integral part of prognostics and health management. This study considers trend analysis for three classes of data, (1) prognostic parameters, (2) degradation waveform, and (3) multivariate data. A new form of crest factor is introduced for more effective waveform analysis of non-monotonic data. In addition, two algorithms are introduced to treat non-monotonic trend. The prognostic model used in this research does not produce results without treating non-monotonicity. These kinds of algorithm have promising potential to treat non-monotonicity and deal with arbitrary stationary noise in degradation data.     

Rotating machinery prognostics: State of the art,challenges and opportunities

Machinery prognosis is the forecast of the remaining operational life, future condition, or probability of reliable operation of an equipment based on the acquired condition monitoring data. This approach to modern maintenance practice promises to reduce downtime, spares inventory, maintenance costs, and safety hazards. Given the significance of prognostics capabilities and the maturity of condition monitoring technology, there have been an increasing number of publications on rotating machinery prognostics in the past few years. These publications covered a wide spectrum of prognostics techniques. This review article first synthesises and places these individual pieces of information in context, while identifying their merits and weaknesses. It then discusses the identified challenges, and in doing so, alerts researchers to opportunities for conducting advanced research in the field. Current methods for predicting rotating machinery failures are summarised and classified as conventional reliability models, condition-based prognostics models and models integrating reliability and prognostics. Areas in need of development or improvement include the integration of condition monitoring and reliability, utilisation of incomplete trending data, consideration of effects from maintenance actions and variable operating conditions, derivation of the non-linear relationship between measured data and actual asset health, consideration of failure interactions, practicability of requirements and assumptions, as well as development of performance evaluation frameworks.     

Integrated approach for diagnostics and prognostics of HP LNG pump based on health state probability estimation

Effective machine fault prognostic technologies can lead to elimination of unscheduled downtime and increase machine useful life and consequently lead to reduction of maintenance costs as well as prevention of human casualties in real engineering asset management. This paper presents a technique for accurate assessment of the remnant life of machines based on health state probability estimation technique and historical failure knowledge embedded in the closed loop diagnostic and prognostic system. To estimate a discrete machine degradation state which can represent the complex nature of machine degradation effectively, the proposed prognostic model employed a classification algorithm which can use a number of damage sensitive features compared to conventional time series analysis techniques for accurate long-term prediction. To validate the feasibility of the proposed model, the five different level data of typical four faults from High Pressure Liquefied Natural Gas (HP-LNG) pumps were used for the comparison of intelligent diagnostic test using five different classification algorithms. In addition, two sets of impeller-rub data were analysed and employed to predict the remnant life of pump based on estimation of health state probability using the Support Vector Machine (SVM) classifier. The results obtained were very encouraging and showed that the proposed prognostics system has the potential to be used as an estimation tool for machine remnant life prediction in real life industrial applications.     

Prognostics and health management design for rotary machinery systems—Reviews,methodology and applications

Much research has been conducted in prognostics and health management (PHM), an emerging field in mechanical engineering that is gaining interest from both academia and industry. Most of these efforts have been in the area of machinery PHM, resulting in the development of many algorithms for this particular application. The majority of these algorithms concentrate on applications involving common rotary machinery components, such as bearings and gears. Knowledge of this prior work is a necessity for any future research efforts to be conducted; however, there has not been a comprehensive overview that details previous and on-going efforts in PHM. In addition, a systematic method for developing and deploying a PHM system has yet to be established. Such a method would enable rapid customization and integration of PHM systems for diverse applications. To address these gaps, this paper provides a comprehensive review of the PHM field, followed by an introduction of a systematic PHM design methodology, 5S methodology, for converting data to prognostics information. This methodology includes procedures for identifying critical components, as well as tools for selecting the most appropriate algorithms for specific applications. Visualization tools are presented for displaying prognostics information in an appropriate fashion for quick and accurate decision making. Industrial case studies are included in this paper to show how this methodology can help in the design of an effective PHM system.     

Condition monitoring scheme via one-class support vector machine and multivariate control charts

A condition-based maintenance (CBM) has been widely employed to reduce maintenance cost by predicting the health status of many complex systems in prognostics and health management (PHM) framework. Recently, multivariate control charts used in statistical process control (SPC) have been actively introduced as monitoring technology. In this paper, we propose a condition monitoring scheme to monitor the health status of the system of interest. In our condition monitoring scheme, we first define reference data set using one-class support vector machine (OC-SVM) to construct the control limit of multivariate control charts in phase I. Then, parametric control chart or non-parametric control chart is selected according to the results from multivariate normality tests. The proposed condition monitoring scheme is applied to sensor data of two anemometers to evaluate the performance of fault detection power.

     

Single-machine-based predictive maintenance model considering intelligent machinery prognostics

As an increasing number of manufacturers are beginning to realize the importance of maintaining throughput, many maintenance models have been developed to enable machines to achieve near-zero downtime. However, previous maintenance models usually ignore machine’s deterioration process. Therefore, this paper develops a novel data-driven machinery prognostic approach for machine performance assessment and prediction. With this prognostic information, a predictive maintenance model is proposed for a repairable deteriorating machine. As machine performance can be assessed, once it reaches the maintenance threshold, a maintenance operation is performed to restore the machine. Moreover, an operational cost is introduced to meet real manufacturing process. In this predictive maintenance model, the optimal maintenance threshold and maintenance cycle number are obtained with the aim to minimize the long-term average cost. Finally, a case study is presented. The computational results show the efficiency of this proposed predictive maintenance model.     

Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications

Research studies on data-driven approaches to rotating components and rolling element bearing (REB) prognostics have recently witnessed a rapid increase. These data-driven methods rely on sensor data for condition monitoring and degradation assessments; however, the problem of mining features from these sophisticated data using appropriate intelligent methods and choosing a practically reliable predictive model(s) has become a global concern. Vibration monitoring for REBs have over the years shown great effectiveness. Although monotonic statistical features serve as reliable health indicators (HIs), relying on a single feature for optimal bearing degradation assessment is inefficient. By fusing highly monotonic features using appropriate methods, a more reliable HI can be constructed and from this, various degradation states/stages and time to start prediction (TSP) can be identified by mapping known failure modes/degradation states to cluster points from clustering algorithms. Emphatically, the choice of regression algorithms for prognostics poses more concern as engineers and data scientists are faced with choosing between Bayessian machine learning (ML) and deep learning (DL) methods. This study presents a methodology for constructing a reliable HI for bearing prognostics, choosing a reliable TSP, and provides a comparison between ML and DL methods for bearing prognostics. As representatives of both domains, the Gaussian process regression (GPR) and the deep belief network (DBN) are introduced and compared. The results provide a reliable paradigm for prognosible feature representation for REBs and for choosing between both domains while considering their dependencies, efficiencies, and deficiencies.

     

An intelligent approach to machine component health prognostics by utilizing only truncated histories

Numerous techniques and methods have been proposed to reduce the production downtime, spare-part inventory, maintenance cost, and safety hazards of machineries and equipment. Prognostics are regarded as a significant and promising tool for achieving these benefits for machine maintenance. However, prognostic models, particularly probabilistic-based methods, require a large number of failure instances. In practice, engineering assets are rarely being permitted to run to failure. Many studies have reported valuable models and methods that engage in maximizing both truncated and failure data. However, limited studies have focused on cases where only truncated data are available, which is common in machine condition monitoring. Therefore, this study develops an intelligent machine component prognostics system by utilizing only truncated histories. First, the truncated Minimum Quantization Error (MQE) histories were obtained by Self-organizing Map network after feature extraction. The chaos-based parallel multilayer perceptron network and polynomial fitting for residual errors were adopted to generate the predicted MQEs and failure times following the truncation times. The feed-forward neural network (FFNN) was trained with inputs both from the truncated MQE histories and from the predicted MQEs. The target vectors of survival probabilities were estimated by intelligent product limit estimator using the truncation times and generated failure times. After validation, the FFNN was applied to predict the machine component health of individual units. To validate the proposed method, two cases were considered by using the degradation data generated by bearing testing rig. Results demonstrate that the proposed method is a promising intelligent prognostics approach for machine component health.     

A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction

Health monitoring and prognostics of equipment is a basic requirement for condition-based maintenance (CBM) in many application domains. This paper presents an age-dependent hidden semi-Markov model (HSMM) based prognosis method to predict equipment health. By using hazard function (h.f.), CBM is based on a failure rate which is a function of both the equipment age and the equipment conditions. The state values of the equipment condition considered in CBM, however, are limited to those stochastically increasing over time and those having non-decreasing effect on the hazard rate. The previous HSMM based prognosis algorithm assumed that the transition probabilities are only state-dependent, which means that the probability of making transition to a less healthy state does not increase with the age. In the proposed method, in order to characterize the deterioration of equipment, three types of aging factors that discount the probabilities of staying at current state while increasing the probabilities of transitions to less healthy states are integrated into the HSMM. With an iteration algorithm, the original transition matrix obtained from the HSMM can be renewed with aging factors. To predict the remaining useful life (RUL) of the equipment, hazard rate is introduced to combine with the health-state transition matrix. With the classification information obtained from the HSMM, which provides the current health state of the equipment, the new RUL computation algorithm could be applied for the equipment prognostics. The performances of the HSMMs with aging factors are compared by using historical data colleted from hydraulic pumps through a case study.     

A joint model of production scheduling and predictive maintenance for minimizing job tardiness

As increasingly diverse tasks are being processed on single multi-functional machine, production scheduling has become a critical issue in the planning and management of manufacturing processes. However, the majority of production scheduling literature ignores machine availability and assumes that machine is available all the time. In reality, machines physically deteriorate with increased usage and time. Thus, there is an intense need for manufacturing industries to reduce unexpected breakdowns and remain competitive, and motivating maintenance operations should be integrated into production scheduling models. With the advancements in sensor and prognostic technologies, machine’s condition can be monitored and assessed over time through conducting predictive maintenance. Hence, based on this scheme, this study proposes a single-machine-based scheduling model incorporating production scheduling and predictive maintenance. A machine’s effective age and remaining maintenance life are introduced to describe machine degradation. Finally, a numerical example is given; the computational results show that this integrated scheduling model has better performance than those existing models, which proves its efficiency.     

CBM标准化研究现状及发展趋势

基于状态的维护（ＣBM）是一种新的设备维护模式，建立CBM方式的设备维护系统是一个复杂的系统工程，为规范相关软硬件产品的研制开发、提高不同厂商产品的可互换性与可互操作性，IEEE、ISO、OSA—CBM、MIMOSA等组织相继制定了一些标准，对CBM技术的发展起到了很好的促进作用。本文介绍了国际上CBM标准化研究的现状及相关成果，分析了CBM标准化研究的发展趋势，介绍了作者在CBM研究方面的成果，并对我国CBM标准化研究工作提出了建议。     

Application of grey model for machine degradation prognostics

Predicting machine degradation before final failure occurs is very important. This paper presents a method to predict the future state of machine degradation based on grey model and one-step-ahead forecasting technique. Specifically, the feasibility of grey model as a predictor for machine degradation prognostics system has been investigated. Grey model GM(1,1) has employed to forecast the future state of machine degradation, but the result is not satisfactory. Finally, a modification of GM(1,1) has made to improve the accuracy of prediction. However the model was built by using only four input data, it is able to track closely the sudden change of machine degradation condition. Real trending data of low methane compressor acquired from condition monitoring routine are employed for evaluating the proposed method.     

Prognostic modelling options for remaining useful life estimation by industry

Over recent years a significant amount of research has been undertaken to develop prognostic models that can be used to predict the remaining useful life of engineering assets. Implementations by industry have only had limited success. By design, models are subject to specific assumptions and approximations, some of which are mathematical, while others relate to practical implementation issues such as the amount of data required to validate and verify a proposed model. Therefore, appropriate model selection for successful practical implementation requires not only a mathematical understanding of each model type, but also an appreciation of how a particular business intends to utilise a model and its outputs.This paper discusses business issues that need to be considered when selecting an appropriate modelling approach for trial. It also presents classification tables and process flow diagrams to assist industry and research personnel select appropriate prognostic models for predicting the remaining useful life of engineering assets within their specific business environment. The paper then explores the strengths and weaknesses of the main prognostics model classes to establish what makes them better suited to certain applications than to others and summarises how each have been applied to engineering prognostics. Consequently, this paper should provide a starting point for young researchers first considering options for remaining useful life prediction. The models described in this paper are Knowledge-based (expert and fuzzy), Life expectancy (stochastic and statistical), Artificial Neural Networks, and Physical models.     

Multiple optimized online support vector regression for adaptive time series prediction

Data-driven prognostics based on sensor or historical test data have become appropriate prediction means in prognostics and health management (PHM) application. However, most traditional data-driven prognostics methods are off-line which would be seriously limited in many PHM systems needed on-line predicting or real-time processing. Furthermore, even in some on-line prediction algorithms such as Online Support Vector Regression (Online SVR) and Incremental learning algorithm, there are conflicts and trade-offs between prediction efficiency and accuracy. Therefore, in different PHM applications, prognostics algorithms should be on-line, flexible and adaptive to balance the prediction efficiency and accuracy. An on-line adaptive data-driven prognostics strategy is proposed with five various optimized on-line prediction algorithms based on Online SVR. These five algorithms are improved with kernel combination and sample reduction to realize higher precision and efficiency. These algorithms can achieve more accurate results by data pre-processing and model optimization, moreover, faster operating speed and lower computational complexity can be obtained by optimization of training process with on-line data reduction. With these different improved Online SVR methods, varies of prediction with different precision and efficiency demands could be fulfilled by an adaptive strategy. To evaluate the proposed prognostics strategy, we have executed simulation experiments with Tennessee Eastman (TE) process. In addition, the prediction strategies are also applied and evaluated by traffic mobile communication data from China Mobile Communications Corporation Heilongjiang Co., Ltd. Experiments and test results prove its effectiveness and confirm that the algorithms can be effectively applied to the on-line status prediction with increased performance in both precision and efficiency.     

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.     

基于机器视觉的隧道衬砌裂缝检测算法综述

《公路隧道养护技术规范》中明确指出隧道裂缝的调查是专项检查项目之一。目前常采用人工检测,漏检不可避免,为克服此缺点,用机器视觉的方法实现自动化检测已成为近年来该领域里国内外主要研究手段。在机器视觉研究方法的背景下,对目前国内外关于隧道混凝土衬砌裂缝检测算法的研究进行了较全面的综述,包括衬砌图像预处理、裂缝的检测、干扰的剔除、裂缝宽度的测量及误差分析4个部分,并对所采用的算法进行了优势及不足的比较,最后给出结论和未来设想。     

深度学习在设备故障预测与健康管理中的应用

在智能制造背景下,大数据驱动的设备故障预测与健康管理日益受到各界重视。深度学习能够在层次结构的特征提取过程中发现更多的隐藏知识,在领域自适应方面具有良好的数据适应性,近年来逐渐成为设备故障预测与健康管理的研究热点,并在设备故障诊断和预测中得到了广泛的应用。通过系统回顾近年来深度学习在设备故障预测与健康管理中应用,总结、分类和解释关于这一热点主题的主要文献,讨论了各种体系结构和相关理论。在此基础上,阐述了深度学习在设备故障诊断和预测方面所取得的主要成果、面临的挑战、以及未来的发展趋势,为设备故障预测与健康管理领域选择、设计或实现深度学习架构,提供明确的方向。     

风力发电机组故障诊断与预测技术研究综述

随着风力发电机组装机容量的快速发展,累计运行时间的持续增长,风电机组的维护问题日益突出,迫切需要研发有效的风电机组故障诊断与预测系统。从故障诊断和故障预测两个方面,归纳风力发电机组的主要故障特点;针对故障诊断难点问题,分析和总结基于振动、电气信号分析和模式识别算法的故障诊断方法的研究现状,指出各种方法的技术特点、局限性和今后的发展趋势;针对风电机组中机械结构和电子系统性能退化的各自特点,归纳当前的研究进展,提出物理失效模型和数据驱动模型融合的故障预测方法;最后,归纳了利用风力发电机组数据采集与监控系统(SCADA)数据进行故障诊断与预测的最新进展及需要进一步研究的问题。     

锂离子电池高精度机理建模、参数辨识与寿命预测研究进展

拥有高能量密度、低自放电率和长寿命的锂离子电池是电动车辆的主要储能单元,其性能直接影响了车辆的动力性和安全性。然而,锂离子电池是复杂的电化学系统,其内部状态具有时变性和不可观测性。此外,电池在使用过程中性能将不断衰减,将给车辆的安全性带来隐患。为保证电池在车用工况下的高效、安全和可靠运行,需要对电池实施有效管理。电池模型是管理算法的理论基础,参数辨识是模型应用的前提,而寿命预测是保证电池安全的关键技术。针对上述实际应用需求,综述了锂离子电池高精度电化学-热耦合机理建模、模型参数辨识和寿命预测的最新研究进展。重点关注宏观电化学模型中模型重构和模型简化两种模型降阶方法,对比分析参数辨识中试验测量和非拆解式辨识方法的特点,全面总结寿命预测中基于模型、基于数据驱动和融合式算法的算法架构。在此基础上,总结现有研究的不足并对未来研究方向提出展望。