Traditionally, system prognostics and health management (PHM) depends on sufficient prior knowledge of critical components degradation process in order to predict the remaining useful life (RUL). However, the accurate physical or expert models are not available in most cases. This paper proposes a new data-driven approach for prognostics using deep convolution neural networks (DCNN). Time window approach is employed for sample preparation in order for better feature extraction by DCNN. Raw collected data with normalization are directly used as inputs to the proposed network, and no prior expertise on prognostics and signal processing is required, that facilitates the application of the proposed method. In order to show the effectiveness of the proposed approach, experiments on the popular C-MAPSS dataset for aero-engine unit prognostics are carried out. High prognostic accuracy on the RUL estimation is achieved. The superiority of the proposed method is demonstrated by comparisons with other popular approaches and the state-of-theart results on the same dataset. The results of this study suggest that the proposed data-driven prognostic method offers a new and promising approach.
In the past years, data-driven approaches such as deep learning have been widely applied on machinery signal processing to develop intelligent fault diagnosis systems. In real-world applications, domain shift problem usually occurs where the distribution of the labeled training data, denoted as source domain, is different from that of the unlabeled testing data, known as target domain. That results in serious diagnosis performance degradation. This paper proposes a novel domain adaptation method for rolling bearing fault diagnosis based on deep learning techniques. A deep convolutional neural network is used as the main architecture. The multi-kernel maximum mean discrepancies (MMD) between the two domains in multiple layers are minimized to adapt the learned representations from supervised learning in the source domain to be applied in the target domain. The domain-invariant features can be efficiently extracted in this way, and the cross-domain testing performance can be significantly improved. Experiments on a popular rolling bearing dataset are carried out to validate the effectiveness of the domain adaptation approach, and the diagnosis performance is extensively evaluated in different scenarios. Comparisons with other approaches and related works on the same dataset demonstrate the superiority of the proposed method. The experimental results of this study suggest the proposed domain adaptation method offers a new and promising tool for intelligent fault diagnosis.
An overview of the recent development of tuned vibration absorbers (TVAs) for vibration and noise suppression is presented. The paper summarizes some popular theory for analysis and optimal tuning of these devices, discusses various design configurations, and presents some contemporary applications of passive TVAs. Furthermore, the paper also presents a brief discussion on the recent progress of adaptive and semi-active TVAs along with their on-line tuning strategies, and active and hybrid fail-safe TVAs.
The GKN (Glazman, Krein, Naimark) Theorem characterizes all self-adjoint realizations of linear symmetric (formally self-adjoint) ordinary differential equations in terms of maximal domain functions. These functions depend on the coefficients and this dependence is implicit and complicated. In the regular case an explicit characterization in terms of two-point boundary conditions can be given. In the singular case when the deficiency index d is maximal the GKN characterization can be made more explicit by replacing the maximal domain functions by a solution basis for any real or complex value of the spectral parameter λ. In the much more difficult intermediate cases, not all solutions contribute to the singular self-adjoint conditions. In 1986 Sun found a representation of the self-adjoint singular conditions in terms of certain solutions for nonreal values of λ. In this paper we give a representation in terms of certain solutions for real λ. This leads to a classification of solutions as limit-point (LP) or limit-circle (LC) in analogy with the celebrated Weyl classification in the second-order case. The LC solutions contribute to the singular boundary conditions, the LP solutions do not. The advantage of using real λ is not only because it is, in general, easier to find explicit solutions but, more importantly, it yields information about the spectrum.
An overview of the recent development of tuned vibration absorbers (TVAs) for vibration and noise suppression is presented. The paper summarizes some popular theory for analysis and optimal tuning of these devices, discusses various design configurations, and presents some contemporary applications of passive TVAs. Furthermore, the paper also presents a brief discussion on the recent progress of adaptive and semi-active TVAs along with their on-line tuning strategies, and active and hybrid fail-safe TVAs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.