A small sample size and unbalanced sample distribution are two main problems when data-driven methods are applied for fault diagnosis in practical engineering. Technically, sample generation and data augmentation have proven to be effective methods to solve this problem. The generative adversarial network (GAN) has been widely used in recent years as a representative generative model. Besides the general GAN, many variants have recently been reported to address its inherent problems such as mode collapse and slow convergence. In addition, many new techniques are being proposed to increase the sample generation quality. Therefore, a systematic review of GAN, especially its application in fault diagnosis, is necessary. In this paper, the theory and structure of GAN and variants such as ACGAN, VAEGAN, DCGAN, WGAN, et al. are presented first. Then, the literature on GANs is mainly categorized and analyzed from two aspects: improvements in GAN’s structure and loss function. Specifically, the improvements in the structure are classified into three types: information-based, input-based, and layer-based. Regarding the modification of the loss function, it is sorted into two aspects: metric-based and regularization-based. Afterwards, the evaluation metrics of the generated samples are summarized and compared. Finally, the typical applications of GAN in the bearing fault diagnosis field are listed, and the challenges for further research are also discussed.

In this work, effective methods for monitoring friction and wear of journal bearings integrated in future UltraFan^® jet engines containing a gearbox are presented. These methods are based on machine learning algorithms applied to Acoustic Emission (AE) signals. The three friction states: dry (boundary), mixed, and fluid friction of journal bearings are classified by pre-processing the AE signals with windowing and high-pass filtering, extracting separation effective features from time, frequency, and time-frequency domain using continuous wavelet transform (CWT) and a Support Vector Machine (SVM) as the classifier. Furthermore, it is shown that journal bearing friction classification is not only possible under variable rotational speed and load, but also under different oil viscosities generated by varying oil inlet temperatures. A method used to identify the location of occurring mixed friction events over the journal bearing circumference is shown in this paper. The time-based AE signal is fused with the phase shift information of an incremental encoder to achieve an AE signal based on the angle domain. The possibility of monitoring the run-in wear of journal bearings is investigated by using the extracted separation effective AE features. Validation was done by tactile roughness measurements of the surface. There is an obvious AE feature change visible with increasing run-in wear. Furthermore, these investigations show also the opportunity to determine the friction intensity. Long-term wear investigations were done by carrying out long-term wear tests under constant rotational speeds, loads, and oil inlet temperatures. Roughness and roundness measurements were done in order to calculate the wear volume for validation. The integrated AE Root Mean Square (RMS) shows a good correlation with the journal bearing wear volume.

Inertial-sensor-based attitude estimation is a crucial technology in various applications, from human motion tracking to autonomous aerial and ground vehicles. Application scenarios differ in characteristics of the performed motion, presence of disturbances, and environmental conditions. Since state-of-the-art attitude estimators do not generalize well over these characteristics, their parameters must be tuned for the individual motion characteristics and circumstances. We propose RIANN, a ready-to-use, neural network-based, parameter-free, real-time-capable inertial attitude estimator, which generalizes well across different motion dynamics, environments, and sampling rates, without the need for application-specific adaptations. We gather six publicly available datasets of which we exploit two datasets for the method development and the training, and we use four datasets for evaluation of the trained estimator in three different test scenarios with varying practical relevance. Results show that RIANN outperforms state-of-the-art attitude estimation filters in the sense that it generalizes much better across a variety of motions and conditions in different applications, with different sensor hardware and different sampling frequencies. This is true even if the filters are tuned on each individual test dataset, whereas RIANN was trained on completely separate data and has never seen any of these test datasets. RIANN can be applied directly without adaptations or training and is therefore expected to enable plug-and-play solutions in numerous applications, especially when accuracy is crucial but no ground-truth data is available for tuning or when motion and disturbance characteristics are uncertain. We made RIANN publicly available.

Convolutional Neural Network (CNN) has been widely used in bearing fault diagnosis in recent years, and many satisfying results have been reported. However, when the training dataset provided is unbalanced, such as the samples in some fault labels are very limited, the CNN’s performance reduces inevitably. To solve the dataset imbalance problem, a Generative Adversarial Network (GAN) has been preferably adopted for the data generation. In published research studies, GAN only focuses on the overall similarity of generated data to the original measurement. The similarity in the fault characteristics is ignored, which carries more information for the fault diagnosis. To bridge this gap, this paper proposes two modifications for the general GAN. Firstly, a CNN, together with a GAN, and two networks are optimized collaboratively. The GAN provides a more balanced dataset for the CNN, and the CNN outputs the fault diagnosis result as a correction term in the GAN generator’s loss function to improve the GAN’s performance. Secondly, the similarity of the envelope spectrum between the generated data and the original measurement is considered. The envelope spectrum error from the 1st to 5th order of the Fault Characteristic Frequencies (FCF) is taken as another correction in the GAN generator’s loss function. Experimental results show that the bearing fault samples generated by the optimized GAN contain more fault information than the samples produced by the general GAN. Furthermore, after the data augmentation for the unbalanced training sets, the CNN’s accuracy in the fault classification has been significantly improved.

Convolutional Neural Network (CNN) has been extensively used in bearing fault diagnosis and Remaining Useful Life (RUL) prediction. However, accompanied by CNN’s increasing performance is a deeper network structure and growing parameter size. This prevents it from being deployed in industrial applications with limited computation resources. To this end, this paper proposed a two-step method to build a cell-based light CNN by Neural Architecture Search (NAS) and weights-ranking-based model pruning. In the first step, a cell-based CNN was constructed with searched optimal cells and the number of stacking cells was limited to reduce the network size after influence analysis. To search for the optimal cells, a base CNN model with stacking cells was initially built, and Differentiable Architecture Search was adopted after continuous relaxation. In the second step, the connections in the built cell-based CNN were further reduced by weights-ranking-based pruning. Experiment data from the Case Western Reserve University was used for validation under the task of fault classification. Results showed that the CNN with only two cells achieved a test accuracy of 99.969% and kept at 99.968% even if 50% connections were removed. Furthermore, compared with base CNN, the parameter size of the 2-cells CNN was reduced from 9.677MB to 0.197MB. Finally, after minor revision, the network structure was adapted to achieve bearing RUL prediction and validated with the PRONOSTIA test data. Both tasks confirmed the feasibility and superiority of constructing a light cell-based CNN with NAS and pruning, which laid the potential to realize a light CNN in embedded systems.

Fast-switching semiconductors induce ripple currents on the high-voltage DC bus in the electric vehicle (EV). This paper describes the methods used in the project SiCWell and a new approach to investigate the influence of these overlaid ripples on the battery in EVs. The ripple current generated by the main inverter is demonstrated with a measurement obtained from an electric vehicle. A simulation model is presented which is based on an artificial reference DC bus, according to ISO 21498-2, and uses driving cycles in order to obtain current profiles relevant for battery cycling. A prototype of a battery cycling tester capable of high frequency and precise ripple current generation was developed and is used to cycle cells with superimposed ripple currents within an aging study. To investigate the impact of the frequency and the amplitude of the currents on the battery’s lifetime, these ripple parameters are varied between different test series. Cell parameters such as impedance and capacity are regularly characterized and the aging of the cells is compared to standard DC cycled reference cells. The aging study includes a total of 60 automotive-sized pouch cells. The evaluation of ripple currents and their impact on the battery can improve the state-of-health diagnosis and remaining-useful life prognosis. For the development and validation of such methods, the cycled cells are monitored with a measurement system that regularly measures current and voltage with a sampling rate of 2 MHz. The resulting dataset is suitable for the design of future ripple current aging studies as well as for the development and validation of aging models and methods for battery diagnosis.