In order to solve the problem of low detection accuracy of small targets in SSD detection algorithm, a pipeline magnetic flux leakage image detection algorithm based on multi-scale SSD network is proposed. The dilated convolution and attention residual module are introduced into the SSD algorithm to fuse the low-resolution high-semantic information feature map with the high-resolution low-semantic information feature map so as to improve the resolution of the low-resolution feature map and provide detailed features for small targets. Finally, the target location and category are obtained by regression algorithm. The experimental results show that the proposed algorithm can automatically identify the location of circumferential weld, spiral weld and defect of magnetic flux leakage data. Compared with the original SSD algorithm framework, the improved algorithm has higher detection accuracy, 97.62%, 18.01% lower false detection rate, 18.36% lower false detection rate, better robustness and obvious effect on small target detection.

This paper proposes a frequency regulation strategy applied to wind turbine generators (WTGs) in an isolated grid. In order to complement active power shortage caused by load or wind speed change, an improved deloading method is proposed to improve the regulation capabilities in different speed sections and to provide WTG power reserves. Considering torque compensation may cause power fluctuation, speed reference of conventional pitch control system should be reset. Moreover, to suppress disturbances caused by load and wind speed as well as overcome dependence on system parameters, a model predictive controller (MPC) is presented to generate torque compensation for each deloaded WTG, which allows each WTG to react to the disturbance differently, depending on its generator speed and the frequency deviation. Hardware-in-the-loop simulation and experimental results show that the proposed strategy can enhance frequency response ability during load changes and smoothen power fluctuations resulting from wind speed variations.

In this paper, a novel three-degree-of-freedom piezoelectric-driven micro-positioning platform based on a lever combination compound bridge-type displacement amplification mechanism is proposed. The micro-positioning platform proposed in this paper aims to solve the current problem of the large size and small travel of the three-degree-of-freedom piezoelectric-driven micro-positioning platform. In this paper, a lever combination compound bridge-type displacement amplification mechanism combined with a new biaxial flexible hinge is proposed, the structural dimensions of the lever mechanism and the compound bridge mechanism are optimized, and the amplification multiplier is determined. The maximum output simulation analysis of the micro-positioning platform is carried out by using ANSYS, and the experimental test system is built for verification. The validation results show that the maximum errors between simulation and experiment in the z-direction, rotation direction around x, and rotation direction around y are 64 μm, 0.016°, and 0.038°, respectively, and the corresponding maximum relative errors are 5.6%, 2.4%, and 6.6%, respectively, which proves the feasibility of the theoretical design.

The magnetic tomography method (MTM) is a non-contact external inspection method for detecting metal magnetic memory signals. It has great potential for application in long-distance oil pipeline and subsea pipeline inspection. However, the spatial distribution characteristics and propagation laws of magnetic signals are not yet clear, which makes the MTM passive detection. In this study, a three-dimensional mathematical model of the magnetic field distribution of the stress concentration zone outside the pipe was established based on the boundary conditions. For the two cases in which the stress concentration zone was located at the top and bottom of the inner wall of the pipe, the model was solved by finite element analysis. The variation law of the magnetic signal outside the pipe was analyzed, and experiments were designed to verify the model. The results show that the shape of the magnetic memory signal remained unchanged after passing through the pipe wall. As the magnetic permeability of the pipe medium is much larger than that of air, the magnetic memory signal is significantly attenuated after penetrating the pipe wall. As the detection height increases, the magnetic induction outside the tube decays exponentially. The results also prove that the magnetic tomography method can detect the stress concentration zone at any position of the pipeline, and the detection accuracy is higher when it is located at the top of the pipeline.

Magnetic leakage detection technology plays an important role in the long-oil pipeline. Automatic segmentation of defecting images is crucial for the detection of magnetic flux leakage (MFL) works. At present, accurate segmentation for small defects has always been a difficult problem. In contrast to the state-of-the-art MFL detection methodologies based on convolution neural network (CNN), an optimization method is devised in our study by integrating mask region-based CNN (Mask R-CNN) and information entropy constraint (IEC). To be precise, the principal component analysis (PCA) is utilized to improve the feature learning and network segmentation ability of the convolution kernel. The similarity constraint rule of information entropy is proposed to be inserted into the convolution layer in the Mask R-CNN network. The Mask R-CNN optimizes the convolutional kernel with similar weights or higher similarity, meanwhile, the PCA network reduces the dimension of the feature image to reconstruct the original feature vector. As such, the feature extraction of MFL defects is optimized in the convolution check. The research results can be applied in the field of MFL detection.