Zhaohui Du

Compressed sensing based on dictionary learning for extracting impulse components

It is essential to extract impulse components embedded in heavy background noise in engineering applications. The methods based on wavelet have obtained huge success in removing noises, leading to state-of-the-art results. However, complying with the minimum noise principle, the shrinkage/thresholding algorithms unreasonably remove most energy of the features, and sometimes even discard some important features. Thus it is not easy to guarantee satisfactory performance in actual applications. Based on a recently proposed theory named compressed sensing, this paper presents a new scheme, Sparse Extraction of Impulse by Adaptive Dictionary (SpaEIAD), to extract impulse components. It relies on the sparse model of compressed sensing, involving the sparse dictionary learning and redundant representations over the learned dictionary. SpaEIAD learns a sparse dictionary from a whole noisy signal itself and then employs greedy algorithms to search impulse information in the learned sparse dictionary. The performance of the algorithm compares favourably with that of the mature shrinkage/thresholding methods. There are two main advantages: firstly, the learned atoms are tailored to the data being analyzed and the process of extracting impulse information is highly adaptive. Secondly, sparse level of representation coefficients is promoted largely. This algorithm is evaluated through simulations and its effectiveness of extracting impulse components is demonstrated on vibration signal of motor bearings. The advantage of SpaEIAD is further validated through detecting fault components of gearbox, which illustrates that SpaEIAD can be generalized to engineering application, such as rotating machinery signal processing.

Sparse Feature Identification Based on Union of Redundant Dictionary for Wind Turbine Gearbox Fault Diagnosis

A primary challenge in fault diagnosis is to extract multiple components entangled within a noisy observation. Therefore, this paper describes and analyzes a novel framework, based on convex optimization, for simultaneously identifying multiple features from superimposed signals. This work adequately exploits the underlying prior information that multiple faults with similar frequency spectrum have different morphological waveforms that can be sparsely represented over the union of redundant dictionaries. Within this framework, prior information is formulated into regularization terms, and a sparse optimization problem, which can be solved through the alternating direction method of multipliers (ADMM), is proposed. Meanwhile, the convergence and computational complexity of the proposed iterative framework are profoundly investigated. Moreover, sensitivity analyses and adaptive selection rules for the regularization parameters are described in detail through a set of comprehensive numerical studies. The proposed framework is validated through performing the diagnosis of multiple faults for gearbox in a wind farm. The comparison with respect to the state of the art in the field is illustrated in detail, which highlights the superiority of the proposed framework.

Crack growth sparse pursuit for wind turbine blade

One critical challenge to achieving reliable wind turbine blade structural health monitoring (SHM) is mainly caused by composite laminates with an anisotropy nature and a hard-to-access property. The typical pitch-catch PZTs approach generally detects structural damage with both measured and baseline signals. However, the accuracy of imaging or tomography by delay-and-sum approaches based on these signals requires improvement in practice. Via the model of Lamb wave propagation and the establishment of a dictionary that corresponds to scatters, a robust sparse reconstruction approach for structural health monitoring comes into view for its promising performance. This paper proposes a neighbor dictionary that identifies the first crack location through sparse reconstruction and then presents a growth sparse pursuit algorithm that can precisely pursue the extension of the crack. An experiment with the goal of diagnosing a composite wind turbine blade with an artificial crack is performed, and it validates the proposed approach. The results give competitively accurate crack detection with the correct locations and extension length.

Feature Identification With Compressive Measurements for Machine Fault Diagnosis

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.

Compressed-Sensing-Based Periodic Impulsive Feature Detection for Wind Turbine Systems

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.

Sparsity-aware tight frame learning for rotary machine fault diagnosis

It is a challenging problem to find sufficiently sparse approximation dictionaries tailed to machine vibration signals with different failure modes. Therefore, this paper describes and analyzes a novel tight frame learning scheme for machine fault diagnosis. The objective cost is evolved by integrating the tight frame constraint into the popular dictionary learning model. The resulting tight frame design strategy thus could be formulated as a nonconvex optimization problem which can be solved by alternatively implementing hard thresholding operation and singular value decomposition. Then, fault information is sparsely represented over the learned dictionary and could be effectively detected through sparse pursuit techniques. Compared with the state of the art analytic wavelet tight frame, the proposed algorithm has two main advantages: firstly, the tight frame filters are directly learned from the noisy signals and thus the sparse intrinsic structures of feature information could be profoundly captured. Secondly, sparse level of representation coefficients is promoted largely and the process of extracting fault feature information is highly adaptive. Moreover, the performance of the proposed framework is evaluated through numerical experiments and its superiority with respect to the analytic wavelet tight frame is further demonstrated through performing the diagnosis of an engineering gearbox.