The Path Planning and Location Method of Inspection Robot in a Large Storage Tank Bottom.

With the development of robot technology, inspection robots have been applied to the defect detection of large tanks. However, the existing path planning algorithm of the tank bottom detection robot is easy to fall into the local minimum, and the path is not smooth. Besides, the positioning of the tank bottom detection robot is not accurate. This article proposes a path planning and location algorithm for the large tank bottom detection robot. Specifically, we design a preset spiral path according to the shape of the tank bottom, and a rotating potential field (RPF) near the obstacle is added to avoid the problem of path planning falling into a local minimum. We obtained accurate and smooth planning results. Compared with the state-of-the-art, the RPF method reduced the average RMSE by 9.49%. In addition, by measuring the acoustic emission distance, the three-point positioning algorithm can be used to achieve the calculation of the robot position detection in the proposed method, and the average positioning error on the spiral path is only 0.0748 ± 0.0032.

Combined CNN and Pixel Feature Image for Fatty Liver Ultrasound Image Classification.

Recent revolutionary results of deep learning indicate the advent of reliable classifiers to perform difficult tasks in medical diagnosis. Fatty liver is a common liver disease, and it is also one of the major challenges people face in disease prevention. It will cause many complications, which need to be found and treated in time. In the field of automatic diagnosis of fatty liver ultrasound images, there are problems of less data amount, and the pathological images of different severity are similar. Therefore, this paper proposes a classification method through combining convolutional neural network with the differential image patches based on pixel-level features for fatty liver ultrasonic images. It can automatically diagnose the ultrasonic images of normal liver, low-grade fatty liver, moderate grade fatty liver, and severe fatty liver. The proposed method not only solves the problem of less data amount but also improves the accuracy of classification. Compared with other deep learning methods and traditional methods, the experimental results show that our method has better accuracy than other classification methods.

Oxygen vacancies engineering in electrocatalysts nitrogen reduction reaction.

Ammonia is important, both as a fertilizer and as a carrier of clean energy, mainly produced by the Haber-Bosch process, which consumes hydrogen and emits large amounts of carbon dioxide. The ENRR (Electronchemical Nitrogen Reduction Reaction) is considered a promising method for nitrogen fixation owing to their low energy consumption, green and mild. However, the ammonia yield and Faraday efficiency of the ENRR catalysts are low due to the competitive reaction between HER and NRR, the weak adsorption of N2 andthe strong N≡N triple bond. Oxygen vacancy engineering is the most important method to improve NRR performance, not only for fast electron transport but also for effective breaking of the N≡N bond by capturing metastable electrons in the antibonding orbitals of nitrogen molecules. In this review, the recent progress of OVs (oxygen vacancies) in ENRR has been summarized. First, the mechanism of NRR is briefly introduced, and then the generation methods of OVs and their applicationin NRR are discussed, including vacuum annealing, hydrothermal method, hydrogen reduction, wet chemical reduction, plasma treatment and heterogeneous ion doping. Finally, the development and challenges of OVs in the field of electrochemical nitrogen fixation are presented. This review shows the important areas of development of catalysts to achieve industrially viable NRR.

Monocular Depth Estimation: Lightweight Convolutional and Matrix Capsule Feature-Fusion Network.

This paper reports a study that aims to solve the problem of the weak adaptability to angle transformation of current monocular depth estimation algorithms. These algorithms are based on convolutional neural networks (CNNs) but produce results lacking in estimation accuracy and robustness. The paper proposes a lightweight network based on convolution and capsule feature fusion (CNNapsule). First, the paper introduces a fusion block module that integrates CNN features and matrix capsule features to improve the adaptability of the network to perspective transformations. The fusion and deconvolution features are fused through skip connections to generate a depth image. In addition, the corresponding loss function is designed according to the long-tail distribution, gradient similarity, and structural similarity of the datasets. Finally, the results are compared with the methods applied to the NYU Depth V2 and KITTI datasets and show that our proposed method has better accuracy on the C1 and C2 indices and a better visual effect than traditional methods and deep learning methods without transfer learning. The number of trainable parameters required by this method is 65% lower than that required by methods presented in the literature. The generalization of this method is verified via the comparative testing of the data collected from the internet and mobile phones.

Monocular vision-based low-frequency vibration calibration method with correction of the guideway bending in a long-stroke shaker.

Calibration is required to maximize the sensitivity and measurement accuracy of vibration sensors. In this study, a low-frequency vibration calibration method is proposed that is based on the concept of monocular vision. In this method, we employ a high-accuracy edge extraction method to extract the edges of sequential images so as to obtain the high calibration accuracy. However, the proposed method must rely on a long-stroke shaker to provide vibration excitation to the sensor, and the bending in the guideway caused by the mechanical processing reduces the calibration accuracy, especially at very low frequencies. The proposed setting compensates for the bending using an additional monocular vision technique to significantly improve the calibration accuracy. To validate the calibration accuracy of the proposed method, a comparison was conducted between results obtained via the laser interferometry, the Earth's gravitation method, and the proposed method when applied to calibrate the sensitivity of a tri-axial acceleration sensor at frequencies between 0.04 and 8 Hz. The results of the comparison showed the proposed method calibrated the sensor sensitivity with high accuracy and was able to accurately account for the bending when the frequency was lower than 0.3 Hz. In contrast, the calibration accuracy of the laser interferometry decreased because of the bending.

Bandpass-sampling-based heterodyne interferometer signal acquisition for vibration measurements in primary vibration calibration.

Heterodyne interferometers have been widely used for primary vibration calibration in recent years. Primary vibration calibration performance depends on the precision and real-time nature of vibration measurements, factors determined by the acquisition and demodulation of the heterodyne interferometer signal. This signal is commonly collected using the Nyquist sampling method, requiring devices with high sampling rates and large memories, or a sampling method using a mixer and low-pass filter-analog devices which may create time delays. This study proposes a novel bandpass sampling method that reduces sampling rate and storage capacity without generating time delays. To improve vibration measurement precision, an optimal sampling rate is designed to collect the heterodyne interferometer signal, and the collected signal is demodulated using the phase-unwrapping sine approximation method. The proposed method is compared with existing methods through simulated and experimental data. Experimental results show that the proposed method avoids time delays and high sampling rates, while providing high-precision vibration measurements.

A Fast Synthetic Aperture Radar Raw Data Simulation Using Cloud Computing.

Synthetic Aperture Radar (SAR) raw data simulation is a fundamental problem in radar system design and imaging algorithm research. The growth of surveying swath and resolution results in a significant increase in data volume and simulation period, which can be considered to be a comprehensive data intensive and computing intensive issue. Although several high performance computing (HPC) methods have demonstrated their potential for accelerating simulation, the input/output (I/O) bottleneck of huge raw data has not been eased. In this paper, we propose a cloud computing based SAR raw data simulation algorithm, which employs the MapReduce model to accelerate the raw data computing and the Hadoop distributed file system (HDFS) for fast I/O access. The MapReduce model is designed for the irregular parallel accumulation of raw data simulation, which greatly reduces the parallel efficiency of graphics processing unit (GPU) based simulation methods. In addition, three kinds of optimization strategies are put forward from the aspects of programming model, HDFS configuration and scheduling. The experimental results show that the cloud computing based algorithm achieves 4_ speedup over the baseline serial approach in an 8-node cloud environment, and each optimization strategy can improve about 20%. This work proves that the proposed cloud algorithm is capable of solving the computing intensive and data intensive issues in SAR raw data simulation, and is easily extended to large scale computing to achieve higher acceleration.

3D reconstruction of ultrasound scanned data for tissue mimicking material sample.

This paper investigates a 3D reconstruction based on the ultrasonic scanned data for tissue mimicking material (TMM) sample. A two-step varied window filter is developed to smooth ultrasound backscatter signals at first. Next, the anisotropic diffusion filter with a triangular window is presented to reduce the noise of the 2D images by aligning one-dimensional signals. Finally, the 3D structure of the object embedded in the TMM sample is reconstructed using the detected edges images. The performance of the proposed method is analyzed and validated through a number of experiments in both 2D imaging and 3D reconstruction.