Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

Recently,intelligent fault diagnosis based on deep learning has been extensively investigated,exhibiting state-of-the-art performance.However,the deep learning model is often not truly trusted by users due to the lack of interpretability of“black box”,which limits its deployment in safety-critical applications.A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases,and the human in the deci-sion-making loop can be found to deal with the abnormal situa-tion when the models fail.In this paper,we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks,called SAEU.In SAEU,Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks.Based on the SAEU,we propose a unified uncertainty-aware deep learning framework(UU-DLF)to realize the grand vision of trustworthy fault diagnosis.Moreover,our UU-DLF effectively embodies the idea of“humans in the loop”,which not only allows for manual intervention in abnor-mal situations of diagnostic models,but also makes correspond-ing improvements on existing models based on traceability analy-sis.Finally,two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

Denoising Fault-Aware Wavelet Network:A Signal Processing Informed Neural Network for Fault Diagnosis

Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.

Intelligent Fault Diagnosis for Planetary Gearbox Using Transferable Deep Q Network Under Variable Conditions with Small Training Data

Effective fault diagnosis of planetary gearboxes is critical for ensuring the safety and dependability of mechanical drive systems.Nevertheless,variable conditions and inadequate fault data bring huge challenges to its practical fault diagnosis.Taking this into account,this study presents a new intelligent fault diagnosis(IFD)approach for planetary gearbox using a transferable deep Q network(TDQN)that merges deep reinforcement learning(DRL)and transfer learning(TL).First,a DRL environment simulation is designed by a predefined classification Markov decision process.Then,leveraging varied-size convolutions and residual learning,a multiscale residual convolutional neural network agent for TDQN is created to automatically learn meaningful features directly from vibration signals while avoiding model degradation.Next,a large source dataset is obtained from complex conditions,and this agent learns an IFD policy via autonomous interaction with the data environment.Finally,a parameter-based TL strategy is adopted to retrain the model on target datasets with variable conditions and small training data,which is conducted by fine-tuning the model parameters gained from the source task to accomplish target tasks.The results show that this TDQN outperforms not only state-of-the-art methods in a source task with an accuracy of 98.53%but also in two target tasks with 99.63%and 98.37%,respectively.

Challenges and Opportunities of AI-Enabled Monitoring, Diagnosis & Prognosis: A Review

Prognostics and Health Management(PHM),including monitoring,diagnosis,prognosis,and health management,occupies an increasingly important position in reducing costly breakdowns and avoiding catastrophic accidents in modern industry.With the development of artificial intelligence(AI),especially deep learning(DL)approaches,the application of AI-enabled methods to monitor,diagnose and predict potential equipment malfunctions has gone through tremendous progress with verified success in both academia and industry.However,there is still a gap to cover monitoring,diagnosis,and prognosis based on AI-enabled methods,simultaneously,and the importance of an open source community,including open source datasets and codes,has not been fully emphasized.To fill this gap,this paper provides a systematic overview of the current development,common technologies,open source datasets,codes,and challenges of AI-enabled PHM methods from three aspects of monitoring,diagnosis,and prognosis.

A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions

Most gear fault diagnosis(GFD)approaches su er from ine ciency when facing with multiple varying working conditions at the same time.In this paper,a non-negative matrix factorization(NMF)-theoretic co-clustering strategy is proposed specially to classify more than one task at the same time using the high dimension matrix,aiming to o er a fast multi-tasking solution.The short-time Fourier transform(STFT)is first used to obtain the time-frequency features from the gear vibration signal.Then,the optimal clustering numbers are estimated using the Bayesian information criterion(BIC)theory,which possesses the simultaneous assessment capability,compared with traditional validity indexes.Subsequently,the classical/modified NMF-based co-clustering methods are carried out to obtain the classification results in both row and column tasks.Finally,the parameters involved in BIC and NMF algorithms are determined using the gradient ascent(GA)strategy in order to achieve reliable diagnostic results.The Spectra Quest’s Drivetrain Dynamics Simulator gear data sets were analyzed to verify the e ectiveness of the proposed approach.

Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions

Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications.However,the various working conditions would degrade the diagnostic performance and make gear fault diagnosis(GFD)more and more challenging.In this paper,a novel model parameter transfer(NMPT)is proposed to boost the performance of GFD under varying working conditions.Based on the previous transfer strategy that controls empirical risk of source domain,this method further integrates the superiorities of multi-task learning with the idea of transfer learning(TL)to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition(target domain)and another(source domain),and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable.For NMPT implementation,insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task.Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions.The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions.

Multi-Scale Convolutional Gated Recurrent Unit Networks for Tool Wear Prediction in Smart Manufacturing

As an integrated application of modern information technologies and artificial intelligence,Prognostic and Health Management(PHM)is important for machine health monitoring.Prediction of tool wear is one of the symbolic applications of PHM technology in modern manufacturing systems and industry.In this paper,a multi-scale Convolutional Gated Recurrent Unit network(MCGRU)is proposed to address raw sensory data for tool wear prediction.At the bottom of MCGRU,six parallel and independent branches with different kernel sizes are designed to form a multi-scale convolutional neural network,which augments the adaptability to features of different time scales.These features of different scales extracted from raw data are then fed into a Deep Gated Recurrent Unit network to capture long-term dependencies and learn significant representations.At the top of the MCGRU,a fully connected layer and a regression layer are built for cutting tool wear prediction.Two case studies are performed to verify the capability and effectiveness of the proposed MCGRU network and results show that MCGRU outperforms several state-of-the-art baseline models.

AI-Enabled Monitoring, Diagnosis & Prognosis

The emerging and development of Artificial Intelligence(AI),especially deep learning,has stimulated its application in various engineering domains.Monitoring,diagnosis and prognosis,as the key elements of intelligence maintenance of manufacturing systems in the era of Industry 4.0,has also benefited from the advancement of AI technology.The main objective of this special issue aims at bringing scholars to show their research findings in the field of monitoring,diagnosis and prognosis driven by AI,and promote its application in intelligent maintenance of manufacturing system in China.Ten papers have been selected in this special issue after rigorous review and they represent the latest research outcomes in this active area.

Nonlinear dynamic behavior of rotating blade with breathing crack

This study aims at investigating the nonlinear dynamic behavior of rotating blade with transverse crack.A novel nonlinear rotating cracked blade model(NRCBM),which contains the spinning softening,centrifugal stiffening,Coriolis force,and crack closing effects,is developed based on continuous beam theory and strain energy release rate method.The rotating blade is considered as a cantilever beam fixed on the rigid hub with high rotating speed,and the crack is deemed to be open and close continuously in a trigonometric function way with the blade vibration.It is verified by the comparison with a finite element-based contact crack model and bilinear model that the proposed NRCBM can well capture the dynamic characteristics of the rotating blade with breathing crack.The dynamic behavior of rotating cracked blade is then investigated with NRCBM,and the nonlinear damage indicator(NDI)is introduced to characterize the nonlinearity caused by blade crack.The results show that NDI is a distinguishable indicator for the severity level estimation of the crack in rotating blade.It is found that severe crack(i.e.,a closer crack position to blade root as well as larger crack depth)is expected to heavily reduce the stiffness of rotating blade and apparently result in a lower resonant frequency.Meanwhile,the super-harmonic resonances are verified to be distinguishable indicators for diagnosing the crack existence,and the third-order super-harmonic resonances can serve as an indicator for the presence of severe crack since it only distinctly appears when the crack is severe.

Multiple fault separation and detection by joint subspace learning for the health assessment of wind turbine gearboxes

The gearbox of a wind turbine （WT） has dominant failure rates and highest downtime loss among all WT subsystems. Thus, gearbox health assessment for maintenance cost reduction is of paramount importance. The concurrence of multiple faults in gearbox components is a common phenomenon due to fault induction mechanism. This problem should be considered before planning to replace the components of the WT gearbox. Therefore, the key fault patterns should be reliably identified from noisy observation data for the development of an effective maintenance strategy. However, most of the existing studies focusing on multiple fault diagnosis always suffer from inappropriate division of fault information in order to satisfy various rigorous decomposition principles or statistical assumptions, such as the smooth envelope principle of ensemble empirical mode decomposition and the mutual independence assumption of independent component analysis. Thus, this paper presents a joint subspace learning-based multiple fault detection （JSLMFD） technique to construct different subspaces adaptively for different fault pattems. Its main advantage is its capability to learn multiple fault subspaces directly from the observation signal itself. It can also sparsely concentrate the feature information into a few dominant subspace coefficients. Furthermore, it can eliminate noise by simply performing coefficient shrinkage operations. Consequently, multiple fault patterns are reliably identified by utilizing the maximum fault information criterion. The superiority of JSL-MFD in multiple fault separation and detection is comprehensively investigated and verified by the analysis of a data set of a 750 kW WT gearbox. Results show that JSL-MFD is superior to a state-of-the-art technique in detecting hidden fault patterns and enhancing detection accuracy.

Mesh relationship modeling and dynamic characteristic analysis of external spur gears with gear wear

Gear wear is one of the most common gear failures,which changes the mesh relationship of normal gear.A new mesh relationship caused by gear wear affects meshing excitations,such as mesh stiffness and transmission error,and further increases vibration and noise level.This paper aims to establish the model of mesh relationship and reveal the vibration characteristics of external spur gears with gear wear.A geometric model for a new mesh relationship with gear wear is proposed,which is utilized to evaluate the influence of gear wear on mesh stiffness and unloaded static transmission error(USTE).Based on the mesh stiffness and USTE considering gear wear,a gear dynamic model is established,and the vibration characteristics of gear wear are numerically studied.Comparison with the experimental results verifies the proposed dynamic model based on the new mesh relationship.The numerical and experimental results indicate that gear wear does not change the structure of the spectrum,but it alters the amplitude of the meshing frequencies and their sidebands.Several condition indicators,such as root-mean-square,kurtosis,and first-order meshing frequency amplitude,can be regarded as important bases for judging gear wear state.