Intelligent Monitoring System Based on Noise-Assisted Multivariate Empirical Mode Decomposition Feature Extraction and Neural Networks.

Because of the nonlinearity and nonstationarity in the vibration signals of some rotating machinery, the analysis of these signals using conventional time- or frequency-domain methods has some drawbacks, and the results can be misleading. In this paper, a couple of features derived from multivariate empirical mode decomposition (MEMD) are introduced, which overcomes the shortcomings of the traditional features. A wind turbine gearbox and its bearings are investigated as rotating machinery. In this method, two types of feature structures are extracted from the decomposed signals resulting from the MEMD algorithm, called intrinsic mode function (IMF). The first type of feature vector element is the energy moment of effective IMFs. The other type of vector elements is amplitudes of a signal spectrum at the characteristic frequencies. A correlation factor is used to detect effective IMFs and eliminate the redundant IMFs. Since the basic MEMD algorithm is sensitive to noise, a noise-assisted extension of MEMD, NA-MEMD, is exploited to reduce the effect of noise on the output results. The capability of the proposed feature vector in health condition monitoring of the system is evaluated and compared with traditional features by using a discrimination factor. The proposed feature vector is utilized in the input layer of the classical three-layer backpropagation neural network. The results confirm that these features are appropriate for intelligent fault detection of complex rotating machinery and can diagnose the occurrence of early faults.

Simultaneous fault diagnosis of wind turbine using multichannel convolutional neural networks.

Wind turbine technology is pursuing the maturation using advanced multi-megawatt machinery equipped by powerful monitoring systems. In this work, a multichannel convolutional neural network is employed to develop an autonomous databased fault diagnosis algorithm. This algorithm has been evaluated in a 5MW wind turbine benchmark model. Several faults for various wind speeds are simulated in the benchmark model, and output data are recorded. A multichannel convolutional neural network with multiple parallel local heads is utilized in order to consider changes in every measured variable separately to identify subsystem faults. Time-domain signals obtained from the wind turbine are portrayed as images and fed independently to the proposed network. Results show that the multivariable fault diagnosis scheme diagnoses the most common wind turbine faults and achieves high accuracy.

Optimization of Taylor spatial frame half-pins diameter for bone deformity correction: Application to femur.

Using external fixtures for bone deformity correction takes advantages of less soft tissue injury, better bone alignment and enhances strain development for bone formation on cutting section, which cause shorter healing time. Among these fixtures, Taylor spatial frame is widely used and includes two rings and six adjustable struts developing 6 degrees of freedom, making them very flexible for this type of application. The current study describes a method to optimize Taylor spatial frame pin-sizes currently chosen from the surgeon's experiences. A three-dimensional model of femur was created from computed tomography images; segmentation of the medical images was made based on the Hounsfield unit (gray scale) in order to allocate adequate mechanical properties into cortical and trabecular bone sections. Both the cortical and trabecular sections were assumed to be isotropic and homogeneous. The diameter optimization of Taylor spatial frame's half-pins was carried out by coupling genetic algorithm and finite element analysis. The finite element analysis was based on a static mechanical load corresponding to a standing person's body weight. Finite element analysis results were validated with experimentally measured strains obtained from bone compression tests. A cost function, based on the developed bone stresses, was defined close to the Taylor spatial frame's half-pins. The calculated cost function showed a decrease of over 33% from the initial half-pin selection by the surgeon and the genetic algorithm optimization. Consequently, the maximum stresses experienced by the bone in the connected location of the half-pins decreased from 121.4 MPa in the surgeon's selection to 73.07 MPa as a result of the optimization process.