Despite the impressive process of current domain adaptation-based fault diagnosis approaches, access to source data and source model parameters is a sine qua non, resulting in obvious limitations when deploying to real industry, particularly considering the data storage, transmission, and privacy issues. In light of this, an interesting and challenging diagnosis scenario is studied in this article, i.e., source-free black-box adaptation diagnosis (SBAD), where only the model output information from the source domain is available for target tasks. To address this issue, a novel diagnosis framework named knowledge transfer from distillation to adaptation (KTDA) is proposed accordingly. Without source data and source model details, KTDA first develops a decoupled self-distillation mechanism to distill source domain knowledge from the black-box model's outputs to the target model, in which the noisy knowledge is simultaneously dealt with by the global and local self-regularization. In addition, a self-adaptation strategy is presented to further adjust the model, where the unlabeled target data is treated differently to reduce the intradomain divergence for improving the fit to the target task. Note that, the target model is not restricted to be the same as the source model in KTDA, thus having more flexibility and versatility in realistic industrial applications. We conduct a variety of fault diagnosis tasks for performance verification, empirical evidence shows the effectiveness and prospect of our method.

Despite the remarkable success of end-to-end intelligent diagnosis methods, the shortage of available training data remains one of the most challenging issues in real industrial scenarios. In light of this, a wide variety of deep generative models are developed for data volume expansion. Notably, the denoising diffusion probabilistic model (DDPM) has recently shown impressive sample quality and diversity in various tasks. However, DDPM typically operates in the original pixel space, resulting in an expensive computational cost and restricting its applicability in industrial applications. In tackling the above issues, we develop an interpretable vector quantization-guided latent denoising diffusion probability model (IVQ-LDM) in this work. In IVQ-LDM, the vector quantized-variational autoencoder is introduced to compress the data to a lower dimensional space, where the kernels with physical meaning are then designed in the first layer to enhance the density of latent information and improve model interpretability. After that, a conditional DDPM is built in this latent space to learn the low-dimensional representation for data augmentation. Compared with existing methods, the IVQ-LDM achieves enhancements in sample quality, computational efficiency, and interpretability. Extensive experiments on three mechanical systems corroborate the effectiveness and superiority of the proposed method.

Cyclic spectral coherence (CSCoh) is an effective tool to reveal the cyclostationarity of the fault-induced components (FICs). Integrating CSCoh over the domain of the spectral frequency or decomposing CSCoh by matrix factorization methods can provide an enhanced diagnosis spectrum. However, for compound faults, the integration-based strategy or the factorization-based method will fail once the features of different faults are coupled with each other in the informative frequency band. In light of this, we present a novel harmonic sparse structured nonnegative matrix factorization (HSSNMF) framework, enabling us to learn a part-based representation of CSCoh with the desired harmonic sparse structures (HSSs) of FICs. Specifically, the proposed method is formulated as an optimization problem with explicit HSS constraints in the objective function, where an iterative solving algorithm and an initialization way for the optimization problem are provided. Moreover, the convergence and complexity of HSSNMF are analyzed theoretically and empirically. Extensive comparisons in both the synthetic and experimental data are conducted to verify the advantages. The qualitative results show that HSSNMF not only can isolate the FICs from the noisy data but can also separate the different FICs from each other, and the quantitative results demonstrate that the performance of the proposed algorithm is improved by at least 10%.

To cater to fault diagnosis of rotating machinery under complex working conditions, unsupervised domain adaptation technology has been widely explored and applied. Existing methods mainly reduce domain bias in two ways, including metric learning and discriminator-based adversarial learning. Different from these technologies, in this work, we only resort to entropy optimization strategies and develop a novel entropy-oriented domain adaptation (EODA) model for intelligent diagnosis of rotating machinery. Specifically, a convolutional network with a cosine-distance classifier is introduced to construct the model framework, which can reduce intraclass variation and make the output more confident. In addition, negentropy-guided prediction diversity optimization and minimax entropy game-guided prototype-feature alignment are co-designed to realize domain adaptation. Extensive experiments based on two different mechanical systems are used to validate our method. Comprehensive results and discussions demonstrate that our EODA can achieve compelling performance.

Domain adaptation technology has been intensively studied in machine fault diagnosis for more reliable diagnosis performance. Nonetheless, most approaches rely on the availability of source data, which is always unattainable in many practical industrial scenarios due to the costs of expensive data storage and transmission as well as privacy protection. As a consequence, there is an urgent need to design an adaptation method that is independent of source data. This technology is also more in line with the requirements for lightweight and timely diagnosis. Given this, in this article, we develop a novel source-free adaptation diagnosis (SFAD) method. In SFAD, a robust self-training mechanism and a target prediction matrix constraint are presented, achieving model adaption with only unlabeled target data. Extensive experiments on our own and public datasets demonstrate the effectiveness and superiority of the proposed method.

Domain adaptation technologies have been extensively explored and successfully applied to machine fault diagnosis, aiming to address problems that target data are unlabeled and have a certain distribution bias with source data. Nonetheless, existing fault diagnosis methods mainly explore feature-level alignment strategies to reduce domain discrepancies, which not only fails to directly ascertain the relationship between the target output and domain deviation, but also cannot guarantee accurate diagnosis results (i.e., learning class-discriminative features) when only relying on feature adaptation. In light of these issues, a more intuitive and effective domain adaptation method is developed for intelligent diagnosis of machinery in this article, in which the minimum class confusion and maximum nuclear norm-based target prediction constraints are simultaneously designed to promote learning reliable domain-invariant and discriminative features for accurate fault diagnosis. We conduct extensive experiments based on two different mechanical systems to evaluate the proposed method. Comprehensive results and discussions demonstrate the promising performance of our approach.

Deep networks based mechanical intelligent diagnosis has been recently attracting considerable attentions with the development of Industry 4.0. Unfortunately, a more practical diagnostic scenario, i.e., unsupervised partial transfer diagnosis, has not yet been well addressed. In view of this, a novel unsupervised intelligent diagnosis framework named classifier inconsistency-based domain adaptation network is proposed in this article. In this approach, two discriminative one-dimensional convolutional networks are designed as the basic architecture. The source samples of the same categories as the target domain are then identified and emphasized to boost positive network training. Meanwhile, the classifier inconsistency is introduced to guide the model to learn discriminative and domain-invariant representations for the correct classification of unlabeled target data. Extensive experiments on two datasets are conducted to evaluate the proposed method. Additionally, five popular methods are selected for comparison. The comprehensive results validate the effectiveness and superiority of the proposed approach.

As the requirements on powertrain efficiency of electric vehicles (EVs) are increasing, integrated motor-transmission (IMT) powertrain systems for EVs are becoming a promising solution. For the integration of IMT powertrain systems, the system state information and the actuator status are usually required for the closed-loop controller design or the on-board fault diagnosis. Embracing the demands, an observer for simultaneous estimation of input and system state of an IMT powertrain system is studied in this paper. It is well-known that controller area network (CAN) has been dominant in the vehicle network, which is used to communicate among controllers, sensors, and actuators. However, the CAN bus always induces time-varying delays when there are a number of communication nodes on the bus. The CAN-bus induced delay would result in vibrations in the vehicle powertrain or even deterioration of the entire closed-loop system. To deal with the CAN-bus induced delay in the estimation work for IMT powertrain systems, the potential random delays are considered in a three-state nonlinear model which represents the behavior of an IMT system. To estimate the input and state simultaneously, an adaptive unscented Kalman filter (AUKF) is adopted. As we know, the adopted AUKF has the benefits of dealing with system nonlinearities and calculating the noise covariance matrix automatically. Simulations and comparisons are carried out. We can see from the results that the proposed observer estimates the input and system state well. Moreover, the resulting estimation error is smaller comparing with the estimation error of the observer based on extended Kalman filter algorithm.

In the era of big data, a huge amount of monitoring and manufacturing data is generated every hour. As these data are typically measured from different machines and under different working regimes, prior information and domain knowledge are highly required in order to properly analyze and utilize these data. In view of this limitation, a data-driven self-comparison approach is proposed for the monitoring of rotating machinery. In this approach, comb filtering is introduced to extract the concerned signals from multisource background noise. A Gini-guided residual singular value decomposition is then proposed to enhance local anomalies induced by early defects. Finally, an iterative Mahalanobis distance is constructed to measure the statistical deviation of monitored component from a normal state. With the proposed method, health monitoring of rotating machinery could be achieved without prior information and domain knowledge, thereby providing an automatic data processing and condition monitoring tool in big data context.

Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.

High resolution and accurate location are the crucial goals associated with the application of guided waves for nondestructive testing purposes. In this paper, through experimental studies, the influences of the frequency-dependent amplitude to the testing resolution of guided wave methods are investigated. Firstly, the factors which result in frequency dependency to the amplitude characteristic of guided wave modes are investigated. Then, the influences of the frequency-dependent amplitude to the spectrum of guided wave mode propagating in the structure are analyzed. The results show that it brings amplitude modulation to guided wave modes, resulting in peak frequency shifting and bandwidth variation in their spectra. This spectrum distortion affects the wave form of the received wave packet (i.e., time duration), and further the testing resolution of guided wave modes. Ultimately, two simple and universal experimental cases are introduced to verify and illustrate these effects. The results show that because of the frequency-dependent amplitude, the testing resolution of guided wave modes is still limited even when either time reversal technique or dispersion compensation is applied.

Remaining useful life (RUL) prediction allows for predictive maintenance of machinery, thus reducing costly unscheduled maintenance. Therefore, RUL prediction of machinery appears to be a hot issue attracting more and more attention as well as being of great challenge. This paper proposes a model-based method for predicting RUL of machinery. The method includes two modules, i.e., indicator construction and RUL prediction. In the first module, a new health indicator named weighted minimum quantization error is constructed, which fuses mutual information from multiple features and properly correlates to the degradation processes of machinery. In the second module, model parameters are initialized using the maximum-likelihood estimation algorithm and RUL is predicted using a particle filtering-based algorithm. The proposed method is demonstrated using vibration signals from accelerated degradation tests of rolling element bearings. The prediction result identifies the effectiveness of the proposed method in predicting RUL of machinery.