Ming J. Zuo

University of Alberta | UAlberta · Department of Mechanical Engineering

Gearbox tooth crack diagnosis under Time-Varying Operating Conditions (TVOC) is a challenging issue. TVOC induce both Amplitude Modulation (AM) and Frequency Modulation (FM) effects into gearbox vibration signals, which results in difficulties in tooth crack diagnosis. To overcome this problem, the TVOC-induced AM and FM effects on vibration signal...

A ridge in a time-frequency graph (TFG) describes the relationship of a signal component's instantaneous frequencies over time. Accurate ridge extraction from TFGs is beneficial for assessing machine health conditions without rotational speed measurement. This paper proposes a new automated and adaptive ridge extraction (AARE) method. The AARE deve...

Tooth crack diagnosis is important to ensure the reliability of gearboxes. However, most reported studies on tooth crack diagnosis only involved the scenario of one tooth crack in a gearbox, which is not always the case since gearboxes may also suffer from multiple tooth cracks in the industry. To overcome this problem, this study first brings some...

For a rotary machine vibration signal collected under variable speed conditions, its time–frequency representation (TFR) contains abundant oscillatory components with time-varying amplitudes and frequencies. A single component with a sequence of peaks in the TFR is called a ridge. Accurate ridge detection from TFRs can boost rotary machine health c...

Rotating machinery often operates under varying speed conditions. Fault detection is necessary to prevent sudden failures and enable condition-based maintenance. Existing autoencoder-based (AE-based) fault detection methods did not address the effects of speed variations, and thus leave room for improvement at varying speed conditions. This paper p...

A novel tribo-dynamic model of a spur gearbox considering both tooth lubrication and tooth crack is proposed, which integrates an elastohydrodynamic lubrication (EHL) model of a spur gear pair into a gearbox lumped parameter model. The combined stiffness and combined damping of a spur gear pair with a tooth crack are obtained using the oil film sti...

Reliability analysis with multiple failure modes is needed because more than one failure mode exists in many engineering applications. Kriging-based surrogate model is widely adopted for component reliability analysis because of its high computational efficiency. Compared with Kriging-based component reliability analysis, selecting the sample point...

A situation often encountered in the condition monitoring (CM) and health management of gearboxes is that a large volume of CM data (e.g., vibration signal) collected from a healthy state is available but CM data from a faulty state unavailable. Fault detection under such a situation is usually tackled by modeling the baseline CM data and then dete...

Deep learning methods have shown great potential to provide reliable remaining useful life (RUL) predictions in Prognostics and Health Management applications. However, deep learning models, particularly supervised learning methods, are strongly dependent on a large number of failure histories. In practice, engineering assets are generally replaced...

Gearboxes often operate under variable speed condition which makes the collected vibration signal, a widely employed type of condition monitoring data, becomes non-stationary. This paper proposes a sparse linear parameter varying vector auto-regression (LPV-VAR) model-based method for fault detection of gearboxes under variable speed condition. The...

This paper proposes a new feature extraction method using time–frequency image data for fault diagnosis of variable-speed rotating machinery. Time-frequency representation (TFR) is widely used to analyze time-varying behaviors of rotating machinery. Recently, methods have been developed to extract fault-related features from TFR image data. However...

Diagnosis of gearbox tooth cracks at an early stage is important to prevent catastrophic failures. The time synchronous average (TSA) of vibration signals of gearboxes with a tooth crack mainly consists of the gear meshing frequency (GMF) and its harmonics, the crack-related amplitude modulation and frequency modulation (AM-FM) and the crack induce...

Variable speed conditions introduce Amplitude Modulation (AM) and Frequency Modulation (FM) effects into gearbox vibration signals, which makes it difficult to distinguish between changes of tooth crack severity and speed changes. To overcome this problem, the AM and FM effects caused by speed variation need to be removed. Order tracking techniques...

In some engineering fields, systems are required to complete a mission over a period. However, for some safety-critical systems, the survival of systems often has higher priority than the successful achievement of the mission. In these cases, a mission needs to be aborted when a certain criterion is met, and a rescue procedure would be carried out...

Vibration signals from rotating machineries are usually of multi-component and modulated signals. Hilbert–Huang transform (HHT), hereby referring to the combination of empirical mode decomposition (EMD) and normalized Hilbert transform (NHT), is an effective method to extract useful information from the multi-component and modulated signals. Howeve...

Vibration signals related to planetary gearbox faults under non-stationary conditions will be equipped with sinusoidal modulation laws in their amplitude modulation (AM) and frequency modulation (FM) modes. Extracting fault features implied in the AM and FM modes is the key issue to detect inner gear faults occurring in planetary gearboxes. However...

Traditionally, the risk priority number (RPN) is used to compute the failure risk by multiplying occurrence, detection, and severity factors. Claiming that the key feature of multiplying the three factors together to get the RPN is a limitation of this method, existing studies have developed the multiple criteria decision making (MCDM) approach. In...

Planetary gearbox systems are critical mechanical components in heavy machinery such as wind turbines. They may suffer from various failure modes, due to the harsh working environment. Dynamic modeling is a useful method to support early fault detection for enhancing reliability and reducing maintenance costs. However, reported studies have not con...

This paper presents methods for the 2019 PHM Conference Data Challenge developed by the team named "Angler". This Challenge aims to estimate the fatigue crack length of a type of aluminum structure using ultrasonic signals at the current load cycle and to predict the crack length at multiple future load cycles (multiple-step-ahead prediction) as ac...

In industry (e.g., wind power), gearboxes often operate under random speed variations. A condition monitoring system is expected to detect faults and assess their severity using vibration signals collected under different speed profiles. A few studies have been reported for condition monitoring of gearboxes under random speed variations, including...

In real-world applications, fault detection and diagnosis of planetary gearboxes are vital if it can be employed to avert catastrophic failure consequences in rotating machinery. Fault diagnosis usually starts with collecting vibration signals from rotating machinery. These vibration signals are usually produced in non-stationary operating conditio...

Driven by the potential applications of sliding bearings in planetary gearboxes for wind turbines, the wear prognosis of heavy loaded sliding bearings under low rotational speeds is an important aspect. The aims of this study are to identify an adequate condition monitoring technique and demonstrate the potential of data-driven wear monitoring for...

Interpreting and understanding vibration characteristics are the cornerstone for health condition monitoring schemes of a planetary gearbox. Phenomenological modeling provides a concise and efficient mathematical description of sensor-related vibration measurements, thus allowing prior guidance for spectrum analysis to be relied on. In this paper,...

Gearboxes often operate under variable operating conditions, which lead to non-stationary vibration. Vibration signal analysis is a widely used condition monitoring technique. Time series model-based methods have been developed for the study of non-stationary vibration signals, and subsequently, for fault diagnosis of gearboxes under variable opera...

This paper presents methods for the 2019 PHM Conference Data Challenge developed by the team named "Angler". This Challenge aims to estimate the fatigue crack length of a type of aluminum structure using ultrasonic signals at the current load cycle and to predict the crack length at multiple future load cycles (multiple-step-ahead prediction) as ac...

Rotating machinery like wind turbines often operates under varying speed conditions. Measuring speed signals is critical for vibration-based condition monitoring of rotating machines. However, in real applications, sometimes it is difficult to install speed sensors to collect speed signals due to physical space and/or cost restrictions. Considering...

Time series model-based approaches are widely employed for condition monitoring of gearboxes. These approaches rely on accurate time series modeling of the baseline vibration signals. This paper proposes a sparse functional pooled-vector auto-regression (FP-VAR) model for representing multichannel non-stationary baseline vibration signals from a ge...

Gear wear is inevitable during the service life of gearboxes and may lead to catastrophic failure. As an important micro-level wear feature, tooth surface roughness directly affects the gear wear progression (lubrication regimes, wear mechanisms and wear rates) and lifespan of a gearbox. Therefore, it is important to monitor surface roughness chang...

Long-term reliable health condition monitoring (HCM) of a wind turbine is an essential method to avoid catastrophic failure results. Existing unsupervised learning methods, such as auto-encoder (AE) and de-noising auto-encoder (DAE) models, are utilized to the condition monitoring of wind turbines. The critical bottleneck of these models for monito...

Special assembly manner provides planetary gearboxes unique transmission characteristics, meanwhile brings the diagnostic complexity via a fixed sensor due to the irregular dynamic nature of gear fault meshing positions. This paper proposes a systematic scheme to explore the motion periods of the sun gear fault meshing positions in a planetary gear...

Gear tooth crack fault detection and severity assessment using vibration analysis rely on the extraction of fault induced periodic impulses. Singular value decomposition (SVD)-based methods have been used by researchers for periodic impulses extraction. Most such methods extract high-energy signal components (SCs) but ignore weak-energy SCs. A newl...

The rotating speed information is significant for condition-based monitoring of rotating machines which are often operated under varying speed conditions. To automatically extract rotating speed from vibration signals, a deep learning model named many-to-many-to-one bi-directional long short-term memory (MMO-BLSTM) model is proposed. The proposed m...

Data-driven based intelligent fault pattern recognition methods of rolling element bearings have made fruitful achievements in recent years. However, for real-world diagnostic occasions, a hypothesis of identical distribution between training and test datasets of current deep learning approaches is natural to be violated. Though reported transfer l...

The critical issue for fault diagnosis of wheelset bearings in high-speed trains is to extract fault features from vibration signals. To handle high complexity, strong coupling and low signal-to-noise ratio of the vibration signals, this paper proposes a novel multi-branch and multi-scale convolutional neural network that can automatically learn an...

The large load capacity, compact size and high-power density have made planetary gearboxes widely applied in heavy machinery such as wind turbines. Although well designed, planetary gearboxes are vulnerable to fatigue crack because of harsh working environment such as high loads. Fatigue crack may eventually cause failures of planetary gearboxes if...

Planetary gearboxes are widely used in machinery such as wind turbines and helicopters. To maximize their effectiveness over their lifecycle, condition monitoring is often used, and proper health indexes can be developed utilizing condition monitoring data. A reported study treats health index development for electric motors as a regression problem...

An important challenge in structural reliability is to reduce the number of calls to evaluate the performance function, especially the complex implicit performance functions. To reduce the computational burden and improve the reliability analysis efficiency, a new active learning method is developed to consider the probability density function of s...

Railway faults are usually observed as impulses in the vibration signal, but they are mostly immersed in noise. To effectively remove noise and identify the impulses, an improved morphological filter is proposed in this article. The proposal focuses on two aspects: a novel gradient convolution operator is proposed for feature extraction, and a new...

As an extension of binary system model, multistate systems (MSSs) are more flexible for modeling reliabilities of real-life engineering systems. In the conventional MSS theory, it is usually assumed that the performance of the system and components can be characterized by one measure. However, the assumption is difficult to be satisfied for some co...

A module of a fault tree is an independent subtree that has no input from the rest of the tree and no output to the rest, except the top events. Modularization is an important technique to reduce the computation cost for large, complex fault tree analysis. This article presents a new linear-time algorithm that is more efficient and easier to code f...

Localized tooth crack in gearboxes may be reflected in impulse components of gearbox vibration signals. Crack induced impulses have been used for crack detection and fault diagnosis. In reported studies, researchers have used statistical indicators of the identified impulses, such as root mean square (RMS) and kurtosis, to track the growth of crack...

Time series model-based approach (TSMBA) is promising in processing vibration signals and assessing the health condition of gearboxes. Accurate time series modeling of the baseline vibration is critical to the TSMBA. Gearboxes often operate under time-varying speed condition, which makes the baseline vibration non-stationary. To accurately model su...

Many products and systems are subject to multiple degradation processes, such as ageing, wear, and so on, as well as random shocks induced by the external environment. Some models have been proposed to represent the degradation processes concerning random shocks. However, most reported models have only focused on degradation due to the effects of a...

A general discrete competing risks model with age- and state-dependent random shocks is developed in this research. This model allows for a more generalized structure of dependence by considering the current degradation state. Random shocks are classified into fatal shocks and nonfatal shocks with corresponding probability. Fatal shocks can bring i...

Wind farm layout optimization results depend on the optimization objectives, such as power output and variance. This paper investigates an alternative strategy for wind farm layout optimization by trading off the mean wind power output and power variance. Two optimization schemes, the weighted optimization and confidence interval optimization are c...

This paper introduces an upgraded synchroextracting transform (SET), namely ameliorated synchroextracting transform (ASET), to deal with fast time-varying and strong frequency modulated signals for time and frequency analysis (TFA). SET is a recently developed time-frequency representation (TFR) method with an exceptional capability to enhance the...

This paper presents a bibliometric analysis of process system failure and reliability studies. This analysis attempts to answer following questions, related to the evolution of failure and reliability engineering in process system: (i) What are the key areas? (ii) What are the major tools and their evolution and frequency of use? (iii) How much glo...

This special issue of the Annals of Operations Research is related to the Asia–Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM 2016), held during 24–26 August 2016, at the Hanyang University, Seoul, South Korea. It focuses on new international research in theoretical and related applications to solve quality...

For the data-driven remaining useful life (RUL) prediction for rolling bearings, the traditional machine learning-based methods generally provide insufficient feature representation and adaptive extraction. Although deep learning-based RUL prediction methods can solve these problems to some extent, they still do not yield satisfactory predictive re...

Frequency band selection (FBS)in rotating machinery fault diagnosis aims to recognize frequency band location including a fault transient out of a full band spectrum, and thus fault diagnosis can suppress noise influence from other frequency components. Impulsiveness and cyclostationarity have been recently recognized as two distinctive signatures...

Maintenance optimization has received special attention among the wind energy research community over the past two decades. This is mainly because of the high degree of uncertainties involved in the execution of operation and maintenance (O&M) activities throughout the lifecycle of wind farms. The increasing complexity in offshore maintenance execu...

The d-MP is a special state vector such that the maximal flow is d in the related network and any state vector less than d-MP is not a d-MP. The d-MP is one of the major tools in evaluating the reliability of a multistate flow network. The d-MPs for all d problem is to search for all d-MPs for all possible d. Decision-makers may use them to choose...

This paper presents a modeling method, an optimization method, and two applications for the safe region concept that has been developed for the health assessment of wheelset bearings of high-speed trains. The proposed safe region model uses support vector data description to handle cases in high-speed trains where only normal data are available. Th...

Fault diagnosis is vital for the health management of rotating machinery. The non-stationary working conditions is one of the major challenges in this field. The key is to extract working-condition-invariant but fault-discriminative features. Traditional methods use expert knowledge on the machines and signal processing to extract fault features fr...

The sideband energy ratio (SER) method has been proved effective for fixed-shaft gearbox fault detection. In this paper, we utilize a reported model of the vibration signal from a planetary gearbox and derive a modified sideband energy ratio (MSER) indicator for fault detection of planetary gearboxes. In addition, recognizing that measured speed va...

Rotating machines are widely used in industry and often work under harsh and varying speed conditions. Fault diagnosis under varying speed conditions is needed to prevent major shutdowns. This paper aims to develop an intelligent rotating machinery fault diagnosis strategy based on deep neural networks (DNNs) and order tracking (OT). The developed...

Frequency contents have been widely investigated to understand the vibration behaviors of planetary gearboxes. Appearances of certain sideband peaks in the frequency spectrum may indicate the occurrence of gear fault. However, analyzing too many sidebands will create problems and uncertainty of fault diagnoses. To this end, it is of vital importanc...

Induction motor-planetary gearbox drivetrains are widely used for industrial productions, including machine tools in manufacturing systems. For fault diagnosis of planetary gearboxes in such electromechanical systems, motor current signal analysis provides an effective alternative approach, because: motor current signals have easier accessibility a...

Traditional intelligent diagnosis methods and current popular deep learning based diagnosis methods basically adopt the way of batch learning, which is inefficient since they need to discard the previous learning outcomes and retrain the model based on the newly added data and prior data. Moreover, manual feature extraction is a necessary step for...

This paper presents a novel signal processing scheme by combining an improved Vold-Kalman filter and the multi-scale sample entropy (IVKF-MSSE) for planetary gearboxes under non-stationary working conditions. In this scheme, we propose a method based on the characteristic frequency ratio (CFR) to select the VKF bandwidth. First, a CFR is adopted to...

The existence of randomness in external load of geared systems is widely known. Stochastic load induces more vibration and noise than deterministic load. In this paper, a nonlinear dynamic model is developed considering time-varying mesh stiffness, backlash, sliding friction, and stochastic external load. Friction is first introduced in a spur gear...

In this paper, we consider the problem of assigning a given reliability improvement target of an existing series system to its constituent subsystems in view of the failure risk and improvement cost. Previous research has solved this problem by developing an allocation weight under the assumption that the failure risk and improvement cost are indep...

To achieve planetary gearbox fault classification, vibration signal analysis has been widely employed with rich information about the health status and easy measurement. It is critical to extract features with enough health status information for fault classification. The self-adaptation of ensemble empirical mode decomposition (EEMD) indicates the...

Crack detection in beams and beam-like structures is an important issue in industry and has attracted numerous investigations. A local crack leads to global system dynamics changes and produce non-linear vibration responses. Many researchers have studied these non-linearities for beam crack diagnosis. However, most reported methods are based on imp...

Time-varying mesh stiffness is one of the main internal excitation sources of gear dynamics. Accurate evaluation of gear mesh stiffness is crucial for gear dynamic analysis. This study is devoted to developing new models for spur gear mesh stiffness evaluation. Three models are proposed. The proposed model 1 can give very accurate mesh stiffness re...

Surrogate-models have proven to be an effective strategy for structural systems with expensive-to-evaluate simulations and are very useful for structural reliability analysis. Many kriging model based adaptive sequential sampling methods have been developed recently for efficient reliability analysis. In this paper, a new learning function based on...

Gearbox is widely used in industrial and military applications. Due to high service load, harsh operating conditions or inevitable fatigue, faults may develop in gears. If the gear faults cannot be detected early, the health will continue to degrade, perhaps causing heavy economic loss or even catastrophe. Early fault detection and diagnosis allows...

Surrogate models are often used to alleviate the computational burden for structural systems with expensively time-consuming simulations. In this paper, a new adaptive surrogate model based efficient reliability method is proposed to address the issues that many existing adaptive sequential sampling reliability methods are limited to the Kriging mo...