Image denoising under low signal‐to‐noise ratio (SNR) and non‐Gaussian noise is still a challenging problem in image processing. In this study, the authors prose a kind of improved convolution neural network auto‐encoders for image denoising. Different from other priors based methods, the denoising auto‐encoders (DAEs) can learn end‐to‐end mappings from noisy images to the target ones. This study research statistical features of image residual between the restored images and target images. According to the maximum entropy principle, the training loss function of the ordinary DAEs was modified with residual statistics as the constraint condition, and an improved training algorithm was proposed based on augmented Lagrange function method. Thus, the quality of restored image can be improved through removing image information from residual more efficiently. Experiments show not only the denoising effects of improved DAEs is superior to the original mean‐square‐error loss function DAEs in both peak SNR and Riesz feature similarity metric indexes, but also has the ability to suppress the different types of noises with different levels through a single model.

No abstract

In order to realize the nondestructive testing (NDT) of the internal leakage fault of hydraulic spool valves, the internal leakage rate must be predicted by AE (acoustic emission) technology. An AE experimental platform of internal leakage of hydraulic spool valves is built to study the characteristics of AE signals of internal leakage and the relationship between AE signals and leakage rates. The research results show the AE signals present a wideband characteristic. The main frequencies are concentrated in 30~50 kHz and the peak frequency is around 40 kHz. When the leakage rate is large, there are significant signal characteristics appearing in the high frequency band of 75~100 kHz. The exponent of the root mean square(RMS) of AE signals is positively correlated with the exponent of the leakage rate only if the leakage rate is greater than 2~3 mL/min. This find could be used to predict the internal leakage rate of hydraulic spool valves.

A method of robust control combined with compensation of feed-forward load force and feedback friction is presented to reduce the motion vibration of 6-DOF six degree-of -freedom hydraulic parallel robot. A mathematic model for the asymmetric hydraulic actuator controlled by symmetric valve is established and a Lugre friction observer is designed. The observed friction and ideal load force computed through the inverse dynamics of 6-DOF parallel robot are dynamically compensated. According to the mixedsensitivity theory, a robust controller about the asymmetric hydraulic actuator system is developed. Simulation results show that the proposed method effectively reduces the system vibration which is caused by the parameter uncertainties and nonlinear friction during platform's reverse motion and enhances the motion precision of the system.

No abstract