Search for: All records

Abstract Direct inverse analysis of faults in machinery systems such as gears using first principle is intrinsically difficult, owing to the multiple time- and length-scales involved in vibration modeling. As such, data-driven approaches have been the mainstream, whereas supervised trainings are deemed effective. Nevertheless, existing techniques often fall short in their ability to generalize from discrete data labels to the continuous spectrum of possible faults, which is further compounded by various uncertainties. This research proposes an interpretability-enhanced deep learning framework that incorporates Bayesian principles, effectively transforming convolutional neural networks (CNNs) into dynamic predictive models and significantly amplifying their generalizability with more accessible insights of the model's reasoning processes. Our approach is distinguished by a novel implementation of Bayesian inference, enabling the navigation of the probabilistic nuances of gear fault severities. By integrating variational inference into the deep learning architecture, we present a methodology that excels in leveraging limited data labels to reveal insights into both observed and unobserved fault conditions. This approach improves the model's capacity for uncertainty estimation and probabilistic generalization. Experimental validation on a lab-scale gear setup demonstrated the framework's superior performance, achieving nearly 100% accuracy in classifying known fault conditions, even in the presence of significant noise, and maintaining 96.15% accuracy when dealing with unseen fault severities. These results underscore the method's capability in discovering implicit relations between known and unseen faults, facilitating extended fault diagnosis, and effectively managing large degrees of measurement uncertainties. 

Abstract Timely and accurate bearing fault detection plays an important role in various industries. Data-driven deep learning methods have recently become a prevailing approach for bearing fault detection. Despite the success of deep learning, fault diagnosis performance is hinged upon the size of labeled data, the acquisition of which oftentimes is expensive in actual practice. Unlabeled data, on the other hand, are inexpensive. To fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance, in this research, we develop a semi-supervised learning method built upon the autoencoder. In this method, a joint loss is established to account for the effects of both the labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other benchmark models. 

Abstract The fault diagnosis of bearing in machinery system plays a vital role in ensuring the normal operating performance of system. Machine learning-based fault diagnosis using vibration measurement recently has become a prevailing approach, which aims at identifying the fault through exploring the correlation between the measurement and respective fault. Nevertheless, such correlation will become very complex for the practical scenario where the system is operated under time-varying conditions. To fulfill the reliable bearing fault diagnosis under time-varying condition, this study presents a tailored deep learning model, so called deep long short-term memory (LSTM) network. By fully exploiting the strength of this model in characterizing the temporal dependence of time-series vibration measurement, the negative consequence of time-varying conditions can be minimized, thereby improving the diagnosis performance. The published bearing dataset with various time-varying operating speeds is utilized in case illustrations to validate the effectiveness of proposed methodology. 

This dataset is collected from a laboratory scale floating offshore wind turbine with mooring systems. The wave data as well as the 6DoF platform motion data are collected by the wave gauges and Qualisys motion capture system, respectively.  Three wave conditions are considered.  More details please refer to the PDF documentation. 

This dataset is collected from a lab scale gear system.  The experiments are conducted across 9 different fault conditions and three load conditions with 6 different sensor locations.  More details can be found in the word documentation. 

This paper introduces a simulation framework and a corresponding Robust Optimal Control (ROC) for docking Unmanned Underwater Vehicles (UUVs) that leverages Marine Renewable Energy (MRE) for improved autonomy in docking and charging operations. The proposed simulation framework integrates the dynamics of the Wave Energy Converter (WEC), docking station, and UUV within a unified system. Utilizing the WEC-Sim for the hydrodynamic modeling and MoorDyn for mooring dynamics, and in-house UUV dynamics in Simulink, the simulation effectively accounts for complex interactions under dynamic ocean conditions. The ROC docking controller, consisting of a Linear Quadratic Regulator (LQR) and a Sliding Mode Control (SMC), is designed to enhance robustness against environmental disturbances and system uncertainties. This controller utilizes input-output linearization to transform the nonlinear dynamics into a manageable linear form, optimizing docking performance while compensating for disturbances and uncertainties. The combined simulation and control approach is validated under various ocean conditions, demonstrating effective docking precision and energy efficiency. This work lays a foundational platform for future advancements in autonomous marine operations for UUV docking systems integrated with WEC. In addition, this work also demonstrates the feasibility of using MRE to significantly extend the operational duration of UUVs; such a platform will be leveraged for further development of structural health monitoring and fault diagnosis techniques for offshore structures such as WECs and Floating Offshore Wind Turbines. 

Rolling bearing is a critical component of machinery that has been widely applied in manufacturing, transportation, aerospace, and power and energy industries. The timely and accurate bearing fault detection thus is of vital importance. Computational data-driven deep learning has recently become a prevailing approach for bearing fault detection. Despite the progress of the deep learning approach, the deep learning performance is hinged upon the size of labeled data, the acquisition of which is expensive in actual implementation. Unlabeled data, on the other hand, are inexpensive. In this research, we develop a new semi-supervised learning method built upon the autoencoder to fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance. Compared with the state-of-the-art semi-supervised learning methods, this proposed method can be more conveniently implemented with fewer hyperparameters to be tuned. In this method, a joint loss is established to account for the effects of labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other well-established baseline methods. Specifically, nearly all emulation runs using the proposed methodology can lead to around 2%–5% accuracy increase, indicating its robustness in performance enhancement.