Onur Avci

Mohammad Hesam Soleimani-Babakamali, Roksana Soleimani-Babakamali, Kourosh Nasrollahzadeh et al.

Gathering properly labelled, adequately rich, and case-specific data for successfully training a data-driven or hybrid model for structural health monitoring (SHM) applications is a challenging task. We posit that a Transfer Learning (TL) method that utilizes available data in any relevant source domain and directly applies to the target domain through domain adaptation can provide substantial remedies to address this issue. Accordingly, we present a novel TL method that differentiates between the source's no-damage and damage cases and utilizes a domain adaptation (DA) technique. The DA module transfers the accumulated knowledge in contrasting no-damage and damage cases in the source domain to the target domain, given only the target's no-damage case. High-dimensional features allow employing signal processing domain knowledge to devise a generalizable DA approach. The Generative Adversarial Network (GAN) architecture is adopted for learning since its optimization process accommodates high-dimensional inputs in a zero-shot setting. At the same time, its training objective conforms seamlessly with the case of no-damage and damage data in SHM since its discriminator network differentiates between real (no damage) and fake (possibly unseen damage) data. An extensive set of experimental results demonstrates the method's success in transferring knowledge on differences between no-damage and damage cases across three strongly heterogeneous independent target structures. The area under the Receiver Operating Characteristics curves (Area Under the Curve - AUC) is used to evaluate the differentiation between no-damage and damage cases in the target domain, reaching values as high as 0.95. With no-damage and damage cases discerned from each other, zero-shot structural damage detection is carried out. The mean F1 scores for all damages in the three independent datasets are 0.978, 0.992, and 0.975.

Serkan Kiranyaz, Ozer Can Devecioglu, Amir Alhams et al.

Continuous long-term monitoring of motor health is crucial for the early detection of abnormalities such as bearing faults (up to 51% of motor failures are attributed to bearing faults). Despite numerous methodologies proposed for bearing fault detection, most of them require normal (healthy) and abnormal (faulty) data for training. Even with the recent deep learning (DL) methodologies trained on the labeled data from the same machine, the classification accuracy significantly deteriorates when one or few conditions are altered. Furthermore, their performance suffers significantly or may entirely fail when they are tested on another machine with entirely different healthy and faulty signal patterns. To address this need, in this pilot study, we propose a zero-shot bearing fault detection method that can detect any fault on a new (target) machine regardless of the working conditions, sensor parameters, or fault characteristics. To accomplish this objective, a 1D Operational Generative Adversarial Network (Op-GAN) first characterizes the transition between normal and fault vibration signals of (a) source machine(s) under various conditions, sensor parameters, and fault types. Then for a target machine, the potential faulty signals can be generated, and over its actual healthy and synthesized faulty signals, a compact, and lightweight 1D Self-ONN fault detector can then be trained to detect the real faulty condition in real time whenever it occurs. To validate the proposed approach, a new benchmark dataset is created using two different motors working under different conditions and sensor locations. Experimental results demonstrate that this novel approach can accurately detect any bearing fault achieving an average recall rate of around 89% and 95% on two target machines regardless of its type, severity, and location.

Ozer Can Devecioglu, Serkan Kiranyaz, Zafer Yilmaz et al.

Vibration sensors are essential in acquiring seismic activity for an accurate earthquake assessment. The state-of-the-art sensors can provide the best signal quality and the highest bandwidth; however, their high cost usually hinders a wide range of applicability and coverage, which is otherwise possible with their basic and cheap counterparts. But, their poor quality and low bandwidth can significantly degrade the signal fidelity and result in an imprecise analysis. To address these drawbacks, in this study, we propose a novel, high-quality, and full bandwidth seismic signal synthesis by transforming the signal acquired from an inferior sensor. We employ 1D Operational Generative Adversarial Networks (Op-GANs) with novel loss functions to achieve this. Therefore, the study's key contributions include releasing a new dataset, addressing operational constraints in seismic monitoring, and pioneering a deep-learning transformation technique to create the first virtual seismic sensor. The proposed method is extensively evaluated over the Simulated Ground Motion (SimGM) benchmark dataset, and the results demonstrated that the proposed approach significantly improves the quality and bandwidth of seismic signals acquired from a variety of sensors, including a cheap seismic sensor, the CSN-Phidgets, and the integrated accelerometers of an Android, and iOS phone, to the same level as the state-of-the-art sensor (e.g., Kinemetrics-Episensor). The SimGM dataset, our results, and the optimized PyTorch implementation of the proposed approach are publicly shared.

Serkan Kiranyaz, Ozer Can Devecioglu, Amir Alhams et al.

Robust and real-time detection of faults on rotating machinery has become an ultimate objective for predictive maintenance in various industries. Vibration-based Deep Learning (DL) methodologies have become the de facto standard for bearing fault detection as they can produce state-of-the-art detection performances under certain conditions. Despite such particular focus on the vibration signal, the utilization of sound, on the other hand, has been neglected whilst only a few studies have been proposed during the last two decades, all of which were based on a conventional ML approach. One major reason is the lack of a benchmark dataset providing a large volume of both vibration and sound data over several working conditions for different machines and sensor locations. In this study, we address this need by presenting the new benchmark Qatar University Dual-Machine Bearing Fault Benchmark dataset (QU-DMBF), which encapsulates sound and vibration data from two different motors operating under 1080 working conditions overall. Then we draw the focus on the major limitations and drawbacks of vibration-based fault detection due to numerous installation and operational conditions. Finally, we propose the first DL approach for sound-based fault detection and perform comparative evaluations between the sound and vibration over the QU-DMBF dataset. A wide range of experimental results shows that the sound-based fault detection method is significantly more robust than its vibration-based counterpart, as it is entirely independent of the sensor location, cost-effective (requiring no sensor and sensor maintenance), and can achieve the same level of the best detection performance by its vibration-based counterpart. With this study, the QU-DMBF dataset, the optimized source codes in PyTorch, and comparative evaluations are now publicly shared.

Furkan Luleci, F. Necati Catbas, Onur Avci

The recent advances in the data science field in the last few decades have benefitted many other fields including Structural Health Monitoring (SHM). Particularly, Artificial Intelligence (AI) such as Machine Learning (ML) and Deep Learning (DL) methods for vibration-based damage diagnostics of civil structures has been utilized extensively due to the observed high performances in learning from data. Along with diagnostics, damage prognostics is also vitally important for estimating the remaining useful life of civil structures. Currently, AI-based data-driven methods used for damage diagnostics and prognostics centered on historical data of the structures and require a substantial amount of data for prediction models. Although some of these methods are generative-based models, they are used to perform ML or DL tasks such as classification, regression, clustering, etc. after learning the distribution of the data. In this study, a variant of Generative Adversarial Networks (GAN), Cycle-Consistent Wasserstein Deep Convolutional GAN with Gradient Penalty (CycleWDCGAN-GP) model is developed to investigate the "transition of structural dynamic signature from an undamaged-to-damaged state" and "if this transition can be employed for predictive damage detection". The outcomes of this study demonstrate that the proposed model can accurately generate damaged responses from undamaged responses or vice versa. In other words, it will be possible to understand the damaged condition while the structure is still in a healthy (undamaged) condition or vice versa with the proposed methodology. This will enable a more proactive approach in overseeing the life-cycle performance as well as in predicting the remaining useful life of structures.

Furkan Luleci, F. Necati Catbas, Onur Avci

There has been a major advance in the field of Data Science in the last few decades, and these have been utilized for different engineering disciplines and applications. Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) algorithms have been utilized for civil Structural Health Monitoring (SHM) especially for damage detection applications using sensor data. Although ML and DL methods show superior learning skills for complex data structures, they require plenty of data for training. However, in SHM, data collection from civil structures can be expensive and time taking; particularly getting useful data (damage associated data) can be challenging. The objective of this study is to address the data scarcity problem for damage detection applications. This paper employs 1-D Wasserstein Deep Convolutional Generative Adversarial Networks using Gradient Penalty (1-D WDCGAN-GP) for synthetic labelled acceleration data generation. Then, the generated data is augmented with varying ratios for the training dataset of a 1-D Deep Convolutional Neural Network (1-D DCNN) for damage detection application. The damage detection results show that the 1-D WDCGAN-GP can be successfully utilized to tackle data scarcity in vibration-based damage detection applications of civil structures. Keywords: Structural Health Monitoring (SHM), Structural Damage Detection, 1-D Deep Convolutional Neural Networks (1-D DCNN), 1-D Generative Adversarial Networks (1-D GAN), Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP)

Furkan Luleci, F. Necati Catbas, Onur Avci

Structural Health Monitoring (SHM) has been continuously benefiting from the advancements in the field of data science. Various types of Artificial Intelligence (AI) methods have been utilized for the assessment and evaluation of civil structures. In AI, Machine Learning (ML) and Deep Learning (DL) algorithms require plenty of datasets to train; particularly, the more data DL models are trained with, the better output it yields. Yet, in SHM applications, collecting data from civil structures through sensors is expensive and obtaining useful data (damage associated data) is challenging. In this paper, 1-D Wasserstein loss Deep Convolutional Generative Adversarial Networks using Gradient Penalty (1-D WDCGAN-GP) is utilized to generate damage associated vibration datasets that are similar to the input. For the purpose of vibration-based damage diagnostics, a 1-D Deep Convolutional Neural Network (1-D DCNN) is built, trained, and tested on both real and generated datasets. The classification results from the 1-D DCNN on both datasets resulted to be very similar to each other. The presented work in this paper shows that for the cases of insufficient data in DL or ML-based damage diagnostics, 1-D WDCGAN-GP can successfully generate data for the model to be trained on. Keywords: 1-D Generative Adversarial Networks (GAN), Deep Convolutional Generative Adversarial Networks (DCGAN), Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP), 1-D Convolutional Neural Networks (CNN), Structural Health Monitoring (SHM), Structural Damage Diagnostics, Structural Damage Detection

Furkan Luleci, F. Necati Catbas, Onur Avci

As Structural Health Monitoring (SHM) being implemented more over the years, the use of operational modal analysis of civil structures has become more significant for the assessment and evaluation of engineering structures. Machine Learning (ML) and Deep Learning (DL) algorithms have been in use for structural damage diagnostics of civil structures in the last couple of decades. While collecting vibration data from civil structures is a challenging and expensive task for both undamaged and damaged cases, in this paper, the authors are introducing Generative Adversarial Networks (GAN) that is built on the Deep Convolutional Neural Network (DCNN) and using Wasserstein Distance for generating artificial labelled data to be used for structural damage diagnostic purposes. The authors named the developed model 1D W-DCGAN and successfully generated vibration data which is very similar to the input. The methodology presented in this paper will pave the way for vibration data generation for numerous future applications in the SHM domain.

Turker Ince, Junaid Malik, Ozer Can Devecioglu et al.

Preventive maintenance of modern electric rotating machinery (RM) is critical for ensuring reliable operation, preventing unpredicted breakdowns and avoiding costly repairs. Recently many studies investigated machine learning monitoring methods especially based on Deep Learning networks focusing mostly on detecting bearing faults; however, none of them addressed bearing fault severity classification for early fault diagnosis with high enough accuracy. 1D Convolutional Neural Networks (CNNs) have indeed achieved good performance for detecting RM bearing faults from raw vibration and current signals but did not classify fault severity. Furthermore, recent studies have demonstrated the limitation in terms of learning capability of conventional CNNs attributed to the basic underlying linear neuron model. Recently, Operational Neural Networks (ONNs) were proposed to enhance the learning capability of CNN by introducing non-linear neuron models and further heterogeneity in the network configuration. In this study, we propose 1D Self-organized ONNs (Self-ONNs) with generative neurons for bearing fault severity classification and providing continuous condition monitoring. Experimental results over the benchmark NSF/IMS bearing vibration dataset using both x- and y-axis vibration signals for inner race and rolling element faults demonstrate that the proposed 1D Self-ONNs achieve significant performance gap against the state-of-the-art (1D CNNs) with similar computational complexity.

Onur Avci, Osama Abdeljaber, Serkan Kiranyaz et al.

Monitoring structural damage is extremely important for sustaining and preserving the service life of civil structures. While successful monitoring provides resolute and staunch information on the health, serviceability, integrity and safety of structures; maintaining continuous performance of a structure depends highly on monitoring the occurrence, formation and propagation of damage. Damage may accumulate on structures due to different environmental and human-induced factors. Numerous monitoring and detection approaches have been developed to provide practical means for early warning against structural damage or any type of anomaly. Considerable effort has been put into vibration-based methods, which utilize the vibration response of the monitored structure to assess its condition and identify structural damage. Meanwhile, with emerging computing power and sensing technology in the last decade, Machine Learning (ML) and especially Deep Learning (DL) algorithms have become more feasible and extensively used in vibration-based structural damage detection with elegant performance and often with rigorous accuracy. While there have been multiple review studies published on vibration-based structural damage detection, there has not been a study where the transition from traditional methods to ML and DL methods are described and discussed. This paper aims to fulfill this gap by presenting the highlights of the traditional methods and provide a comprehensive review of the most recent applications of ML and DL algorithms utilized for vibration-based structural damage detection in civil structures.

Serkan Kiranyaz, Onur Avci, Osama Abdeljaber et al.

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application-specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and motor-fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publically shared in a dedicated website.