EHEryi Hu

Eryi Hu

*This is an algorithmically generated author record based on publicly available information.

Eryi Hu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Detection Method for Weak Signal Defects in SWRs Based on the Combination of Optimal Coil Sensor Design and Weak Signal Processing

    by Jiajie Xue, Yanhua Sun, Eryi Hu

    Magnetic flux leakage (MFL) detection technology is often used for the inspection of steel wire ropes. Due to the weak leakage magnetic field, weak signal defects are often difficult to detect in MFL detection. For this problem, the influencing parameters that affect the sensitivity of the coil sensor are analyzed theoretically and experimentally, and a sensor suitable for weak signal defect detection is designed. On the other hand, magnetic sensitive direction adjustment method was introduced to suppress the strand signal. Based on the finite element simulation and experimental research results, the optimal direction adjustment angle of the magnetic sensitive direction was set. Based on the above design, a combined weak signal processing method based on morphological filtering, circumferential wavelet, and morphological reconstruction was further designed. The experimental results show that the proposed method of using magnetic sensitive direction adjustment to suppress strand signals combined with weak signal filtering can effectively enhance the quality of weak signals and improve the identifiability of defects. Both multi-case and comparative experiments have proved that the proposed method has good performance and effectively improves the detection rate of weak signal defects.


  • Adaptive High-Resolution Dynamic Scanning System and Method for Deformation Monitoring of Underground Infrastructure

    by Menggang Li, Zhuoqi Li, Kun Hu, Eryi Hu, Chaoquan Tang, Gongbo Zhou

    To address critical challenges in underground infrastructure safety, this paper proposes an adaptive dynamic high-resolution scanning method employing a station-based device for deformation monitoring in coal mine sealing walls. By integrating LiDAR, inertial measurements, and encoder data, we developed a hierarchical processing framework comprising feature extraction, state estimation, and spatiotemporal registration of 3D point clouds. A penalty function-based adaptive scanning strategy was formulated to optimize point cloud density and geometric fidelity during data acquisition, which was subsequently integrated into the system. An equipment placement optimization model accounting for installation geometry and region-of-interest characteristics was established, enabling efficient and accurate capture of deformation details in sealing walls of varying dimensions. The system’s performance was evaluated using two novel metrics: point cloud acquisition temporal density (PATD) and point cloud relative area error (PRAE). An ablation study comparing scanning methods and penalty term configurations demonstrated the superiority of the proposed adaptive strategy. Calibration experiments revealed that for a 1.08 m², optimal monitoring parameters were achieved, with data completeness attained at a 1.68 m monitoring distance within 51.6 s. Field validation under simulated deformation conditions, using a 5 m² ROI, evaluated three monitoring distances. Results aligned closely with theoretical predictions, identifying 3.59 m as the optimal distance and validating the system’s capability to detect centimeter-scale displacements. This work establishes a framework for continuous infrastructure health monitoring in confined underground environments.


  • S-shaped rolling gait designed using curve transformations of a snake robot for climbing on a bifurcated pipe

    by Jingwen Lu, Chaoquan Tang, Eryi Hu, Zhipeng Li

    In this work, we focus on overcoming the challenge of a snake robot climbing on the outside of a bifurcated pipe. Inspired by the climbing postures of biological snakes, we propose an S-shaped rolling gait designed using curve transformations. For this gait, the snake robot’s body presenting an S-shaped curve is wrapped mainly around one side of the pipe, which leaves space for the fork of the pipe. To overcome the difficulty in constructing and clarifying the S-shaped curve, we present a method for establishing the transformation between a plane curve and a 3D curve on a cylindrical surface. Therefore, we can intuitively design the curve in 3D space, while analytically calculating the geometric properties of the curve in simple planar coordinate systems. The effectiveness of the proposed gait is verified by actual experiments. In successful configuration scenarios, the snake robot could stably climb on the pipe and efficiently cross or climb to the bifurcation while maintaining its target shape.


  • Open Access

    Using Deep Convolutional Neural Networks and Infrared Thermography to Identify Coal Quality and Gangue

    by Refat Mohammed Abdullah Eshaq, Eryi Hu, Hamzah A. A. M. Qaid, Yao Zhang, Tonggang Liu

    Owing to the enormous demand for and growing large-scale use of coal in the China, India, and USA, speculation has arisen about possible hazards to environmental quality and human health. The contents of fly ash and volatile matter in low-quality coal are extremely harmful to the environment. As a result, there is still much to be explored regarding known hazards and harms to the natural environment of the Earth. For the detection of high-quality coal, we propose a new method of distinguishing coal quality in terms of different “coal types” (i.e., anthracite, bituminous coal, subbituminous coal and lignite) and efficiently separating gangue and rock from the production lines of coal preparation plants (CPPs) by exploiting infrared machine vision and convolutional neural networks (CNNs) for deep learning, which can make coal use less harmful to humans and nature and/or more useful for general welfare. In this article, we conducted two experiments. First experiment is to study the reactions of coal types, gangue and rock with infrared radiation at temperatures of 50°C, 70°C, 90°C, 110°C, and 150°C. Second experiment, several common CNN models (i.e., AlexNet, DarkNet-53, GoogLeNet, NasNet_Mobileb, ResNet-18, MobileNet-v2, Inception-v3 and DenseNet-201) are trained and tested to classify coal types and distinguish gangue and rock. We achieve a remarkable classification accuracy of 100% in these training and testing processes when employing the ResNet-18 and DenseNet-201 models.


  • Feasibility study of exploiting gearbox oil temperature of wind turbine for improving a heat pump water heater in cold areas

    by Refat Mohammed Abdullah Eshaq, Eryi Hu, Ameen A Alshaba, Aiman A.M Alsenwi

    Purpose. Feasibility of completely dispensing with solar collectors (SCs) that are used in heat pump (HP) systems for hot water in cold areas. Methodology. Since the temperature of gearbox oil is relatively high, lots of heat can be exploited. Therefore, the recovery of this unutilized heat from gearbox oil temperature of a wind turbine shows a promising solution in improving heat pump (HP) efficiency for hot water especially in cold environment or the district that is located in the north of our planet where the solar energy is very low. This investigation focuses on the feasibility of direct conversion of mechanical energy harvested from the wind speed into thermal energy by exploiting only the friction phenomenon inside the gearbox of the wind turbine by completely dispensing with solar collectors (SCs) that are used in combined solar assisted heat pump (SAHP) because the SCs have various problems, such as large heat loss, low efficiency, freezing and tube-burst, which may limit their applications. Findings. Results show that the wind turbine can provide the power required for HP during the winter season due to high wind speed in Xuzhou city, Jiangsu, China particularly in January. At best, coefficient of performance (COP) may reach 4.08 without SCs, thus the suggested system ensures high COP in addition to decrease in the fuel consumption by 23.25%. Originality. Wind power driven HPs have been suggested in many pervious papers as a sustainable measure to provide heat to a house; however, to improve COP of HP system, we suggest using a wind turbine to directly drive the HP and exploit gearbox oil temperature in an assistant heat exchanger installed after the HP evaporator for providing additional thermal energy to refrigerant R12 and cooling the gearbox oil. Practical value. The coefficient of performance (COP) of HP has reached 4.08 without SCs, so the suggested system demonstrates high COP in addition to the reduced fuel consumption. Approximately 23.25% of energy could be saved using this novel system compared to a fuel water heater for DHW.

  • Open Access

    Coal/Gangue Recognition Using Convolutional Neural Networks and Thermal Images

    by Murad Saleh Alfarzaeai, Qiang Niu, Jiaqi Zhao, Refat Mohammed Abdullah Eshaq, Eryi Hu

    Recognition and separation of Coal/Gangue are important phases in the coal industries for many aspects. This paper addressed the topic of Coal/Gangue recognition and built a new model called (CGR-CNN) based on Convolutional Neural network (CNN) and using thermal images as standard images for Coal/Gangue recognition. The CGR-CNN model has been developed, augmentation principle has been applied in order to increase the dataset and the best experimental results have been achieved (99.36%) learning accuracy and (95.09%) validation accuracy, in the prediction phase (160) new images of coal and gangue (80 for both) have been tested to measure the efficiency of the work, the prediction result comes with (100%) for coal recognition accuracy and (97.5%) gangue recognition accuracy giving an overall prediction accuracy (98.75%).


  • Open Access

    Separation Between Coal and Gangue Based on Infrared Radiation and Visual Extraction of the YCbCr Color Space

    by Refat Mohammed Abdullah Eshaq, Eryi Hu, Menggang Li, Murad Saleh Alfarzaeai

    Distinguishing between coal and gangue in the production lines of mining factories based on the thermal energy and infrared radiation emission of an object is feasible. In this paper, we use an infrared camera (IC) to distinguish between coal and gangue in the industrial mining field. Additionally, this system is considered to be a binary classification system that has two classes. We analyze the infrared images of coal and gangue; then extract the appropriate texture features from the infrared images in order to develop an accurate classification system by using support vector machine (SVM). The method applied in this work essentially depends on feature extraction of images. The statistical features based on gray level information (GLI), grey-level cooccurrence matrix (GLCM) and visual features are executed. Thus, we suggest preparation steps to obtain one select feature before importing the data into the SVM classifier, and this approach is adopted as the fundamental basis for our work. We exploit only one feature of the infrared image, namely, Cb, which is extracted from the YCbCr color space, and then compute the mean value of Cb after heating and capturing the photos for the coal and gangue samples. The proposed method achieves a high classification accuracy 97.83 % by using Gaussian-SVM.