An Intelligent Quadrotor Fault Diagnosis Method Based on Novel Deep Residual Shrinkage Network

In this paper, a fault diagnosis algorithm named improved one-dimensional deep residual shrinkage network with a wide convolutional layer (1D-WIDRSN) is proposed for quadrotor propellers with minor damage, which can effectively identify the fault classes of quadrotor under interference information, and without additional denoising procedures. In a word, that fault diagnosis algorithm can locate and diagnose the early minor faults of the quadrotor based on the flight data, so that the quadrotor can be repaired before serious faults occur, so as to prolong the service life of quadrotor. First, the sliding window method is used to expand the number of samples. Then, a novel progressive semi-soft threshold is proposed to replace the soft threshold in the deep residual shrinkage network (DRSN), so the noise of signal features can be eliminated more effectively. Finally, based on the deep residual shrinkage network, the wide convolution layer and DroupBlock method are introduced to further enhance the anti-noise and over-fitting ability of the model, thus the model can effectively extract fault features and classify faults. Experimental results show that 1D-WIDRSN applied to the minimal fault diagnosis model of quadrotor propellers can accurately identify the fault category in the interference information, and the diagnosis accuracy is over 98%.

An improved denoise method based on EEMD and optimal wavelet threshold for model building of OPAX

To improve the accuracy of Operational Path Analysis with Exogeneous Inputs (OPAX) model by excluding the noise interference sufficiently in the vehicle operating condition data (time-domain vibration signal), the combined noise reduction method of Ensemble Empirical Mode Decomposition (EEMD) and wavelet threshold was used. Since the noise content of each noisy intrinsic mode functions (IMFs) decomposed by EEMD is uncertain, the effective signal element in the less noisy IMFs affects the accuracy of the first-layer wavelet coefficients to estimate the noise variance, the EEMD and wavelet particle swarm optimization sample entropy threshold denoising (EEMD-WPSE) method is presented in terms of information entropy. In this method, the sample entropy of the eliminated noise is used as the information cost function, together with the particle swarm optimization algorithm to find the optimal wavelet threshold of each high-frequency noisy IMFs. After denoising the simulation signal, it is found that the combination of EEMD-WPSE threshold with hard threshold function, soft threshold function and half-soft threshold function identifying higher SNR and lower RMSE, are given to demonstrate the higher universality of the proposed method. The method is applied to the noise reduction processing of the automobile operating condition data for constructing the OPAX model, and the degree of similarity between the synthesized responses of the care-target point obtained by the OPAX model and the measured responses under the second order operational condition are observed, as it turned out, the calculation results of SNR and RMSE indicated that EEMD-WPSE can better promote the accuracy of OPAX model in terms of noise reduction.

On next to soft threshold corrections to DIS and SIA processes

We study the perturbative structure of threshold enhanced logarithms in the coefficient functions of deep inelastic scattering (DIS) and semi-inclusive e+e− annihilation (SIA) processes and setup a framework to sum them up to all orders in perturbation theory. Threshold logarithms show up as the distributions ((1−z)−1 logi(1−z))+ from the soft plus virtual (SV) and as logarithms logi(1−z) from next to SV (NSV) contributions. We use the Sudakov differential and the renormalisation group equations along with the factorisation properties of parton level cross sections to obtain the resummed result which predicts SV as well as next to SV contributions to all orders in strong coupling constant. In Mellin N space, we resum the large logarithms of the form logi(N) keeping 1/N corrections. In particular, the towers of logarithms, each of the form $$ {a}_s^n/{N}^{\alpha }{\log}^{2n-\alpha }(N),{a}_s^n/{N}^{\alpha }{\log}^{2n-1-\alpha }(N)\cdots $$ a s n / N α log 2 n − α N , a s n / N α log 2 n − 1 − α N ⋯ etc for α = 0, 1, are summed to all orders in as.

X-ray image denoising based on wavelet transform and median filter

This paper mainly proposed and researched based on wavelet transform, and then used the X-map denoising technique of value filter. In other words, the value image was filtered in the spatial domain, and the value filtering was used as the standard pulse (salt) noise, also used as in the wavelet domain. After the filtered image was decomposed by biorthogonal double wavelet transform, a wavelet coefficient matrix was generated, and a soft threshold quantisation process was performed on the wavelet coefficients to produce a new wavelet coefficient matrix. In the end, they used a new wavelet coefficient matrix for image reconstruction. The processing resulted that the denoising method proposed in this paper showed that the X image can be denoised, which not only reduced the X-picture-like noise but also preserved the X-picture-like details as much as possible. It also helped to enhance diagnostic accuracy and reduced the difference in reading.