Search

Motor fault diagnosis is imperative to enhance the reliability and security of industrial systems. However, since motors are often operated under nonstationary conditions, the high complexity of vibration signals raises notable difficulties for fault diagnosis. Therefore, considering the special physical characteristics of motor signals under nonstationary conditions, in this article, we propose a multiscale kernel based residual convolutional neural network (CNN) for motor fault diagnosis. Our contributions mainly fall into two aspects. First, we notice that each motor fault category has various patterns in vibration signals due to the changing operational conditions of the motor. To capture these patterns, a multiscale kernel algorithm is applied in the CNN architecture. Second, since the motor vibration signals are made up of many different components from different transfer paths, they are very complex and variable. To enable the architecture to extract fault features from deep and hierarchical representation spaces, sufficient depth of the network is needed, which will lead to the degradation problem. In the proposed method, residual learning is embedded into the multiscale kernel CNN to avoid performance degradation and build a deeper network. To validate the effectiveness of the proposed networks, a normal motor and five motors with different failures are tested. The results and comparisons with state-of-the-art methods highlight the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Fault diagnosis and remaining useful life (RUL) prediction are always two major issues in modern industrial systems, which are usually regarded as two separated tasks to make the problem easier but ignore the fact that there are certain information of these two tasks that can be shared to improve the performance. Therefore, to capture common features between different relative problems, a joint-loss convolutional neural network (JL-CNN) architecture is proposed in this paper, which can implement bearing fault recognition and RUL prediction in parallel by sharing the parameters and partial networks, meanwhile keeping the output layers of different tasks. The JL-CNN is constructed based on a CNN, which is a widely used deep learning method because of its powerful feature extraction ability. During optimization phase, a JL function is designed to enable the proposed approach to learn the diagnosis–prognosis features and improve generalization while reducing the overfitting risk and computation cost. Moreover, because the information behind the signals of different problems has been shared and exploited deeper, the generalization and the accuracy of results can also be improved. Finally, the effectiveness of the JL-CNN method is validated by run-to-failure dataset. Compared with support vector regression and traditional CNN, the mean-square-error of the proposed method decreases 82.7 $\%$ and 24.9 $\%$ , respectively. Therefore, results and comparisons show that the proposed method can be applied for the intercrossed applications between fault diagnosis and RUL prediction. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction has been increasingly considered in many industrial fields for the reliability and safety of their systems. As a data analysis tool of deep learning, deep convolutional neural network (CNN) shows great potential for RUL prediction. This paper proposes an intelligent RUL prediction method based on a double-CNN model architecture. Given the powerful feature extraction capability of CNN, the proposed method is fed with original vibration signals with no need to resort to any feature extractor, which can also retain the useful information in maximum. The prediction includes two stages: first, incipient fault point is identified by the first CNN model and a proposed “3/5” principle; then, the second CNN model is constructed for RUL prediction. In practice, RULs of identical components are different from each other, which poses a major challenge in RUL prediction. To overcome this problem, an intermediate reliability variable is first calculated in this paper, instead of directly predicting the RUL value. Then, a mapping algorithm is proposed to map reliability to RUL. To demonstrate the effectiveness of the proposed method, data of four tests of bearing degradation are utilized for RUL prediction. Compared with state-of-the-art methods, the proposed method shows higher prediction accuracy and robustness. The prediction results and evaluation indexes demonstrated the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Identifying impulsive features from massive amounts of dynamic signals for wind turbine systems is like finding needles in haystacks, leading to a major challenge for the Shannon-sampling-theorem-based fault detection techniques. Therefore, this paper describes and analyzes a novel impulsive feature identification technique based on compressed sensing model and convex optimization techniques. One important point of this work is to establish the prior information that periodic impulsive component is frequency compressible. On the other hand, based on a small set of nonadaptive linear measurements, a convex optimization algorithm generated from a popular algorithmic framework (alternating direction of multiplier method) is developed to recover the impulsive features. Consequently, the main highlight of this work is to enable the high-accuracy recovery of impulsive feature signals from far few measurements than the Shannon sampling theory requires. Extensive numerical studies are implemented to quantitatively evaluate the performance of the proposed technique, and its feasibility and superiority are verified simultaneously. More importantly, the validity and applicability of our impulsive feature detection technique is comprehensively investigated and confirmed based on a practical engineering dataset from a wind turbine gearbox in a wind farm. [ABSTRACT FROM PUBLISHER]

Machine fault diagnosis collects massive amounts of vibration data about complex mechanical systems. Performing feature detection from these data sets has already led to a major challenge. Compressive sensing theory is a new sampling framework that provides an alternative to the well-known Shannon sampling theory. This theory enables the recovery of sparse or compressible signals from a small set of nonadaptive linear measurements. However, it is suboptimal to recover the whole signals from the compressive measurements and then solve feature identification problems through traditional DSP techniques. Thus, a novel mechanical feature identification method is proposed in this paper. Its main advantage is that fault features are extracted directly in the compressive measurement domain without sacrificing accuracy, while a significant reduction in the dimensionality of the measurement data is achieved. Moreover, Gaussian white noises are significantly alleviated, which dramatically enhances the reliability of machine fault diagnosis. Parameter analysis is also profoundly investigated through a set of numerical experiments. Numerical simulations and experiments are further performed to prove the reliability and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

It is a challenging problem to design excellent dictionaries to sparsely represent diverse fault information and simultaneously discriminate different fault sources. Therefore, this paper describes and analyzes a novel multiple feature recognition framework which incorporates the tight frame learning technique with an adaptive subspace recognition strategy. The proposed framework consists of four stages. Firstly, by introducing the tight frame constraint into the popular dictionary learning model, the proposed tight frame learning model could be formulated as a nonconvex optimization problem which can be solved by alternatively implementing hard thresholding operation and singular value decomposition. Secondly, the noises are effectively eliminated through transform sparse coding techniques. Thirdly, the denoised signal is decoupled into discriminative feature subspaces by each tight frame filter. Finally, in guidance of elaborately designed fault related sensitive indexes, latent fault feature subspaces can be adaptively recognized and multiple faults are diagnosed simultaneously. Extensive numerical experiments are sequently implemented to investigate the sparsifying capability of the learned tight frame as well as its comprehensive denoising performance. Most importantly, the feasibility and superiority of the proposed framework is verified through performing multiple fault diagnosis of motor bearings. Compared with the state-of-the-art fault detection techniques, some important advantages have been observed: firstly, the proposed framework incorporates the physical prior with the data-driven strategy and naturally multiple fault feature with similar oscillation morphology can be adaptively decoupled. Secondly, the tight frame dictionary directly learned from the noisy observation can significantly promote the sparsity of fault features compared to analytical tight frames. Thirdly, a satisfactory complete signal space description property is guaranteed and thus weak feature leakage problem is avoided compared to typical learning methods. [ABSTRACT FROM AUTHOR]