Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hongji Meng has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Billet Surface Temperature Measurement Method Based on a Water Mist Dehazing Network

    by Zhenwei Hu, Wei Wei, Hongji Meng, Jian Yang

    In this paper, we present a water mist dehazing network to improve the accuracy of radiation temperature measurements of the billet surface in the secondary cooling zone of continuous casting. First, we develop a billet radiation attenuation model that accounts for the wavelength-dependent attenuation coefficient of water mist in the secondary cooling zone. Using this model and the corresponding dataset, the water mist transmittance is calculated. Furthermore, the water mist dehazing network—which is distinct from conventional dehazing networks designed for natural environments—comprises three key components: water mist feature extraction based on a combined Unet and Transformer structure; fusion of prior water mist transmittance data using an attention mechanism; and composite transmittance estimation via a multi-path dense network. The experimental results demonstrate that the proposed network effectively reduces water mist’s interference with billet surface temperature measurements in both the spatial and temporal dimensions. Compared with the standalone Unet and Unet + Transformer network architectures, the proposed network achieves a significantly improved dehazing performance, thus verifying its practical value and reliability for billet surface temperature measurement tasks.

  • Three-Dimensional Surface-Shape Measurement of Moving Billets Using Phase-Shifting Profilometry

    by Qing He, Zhuanfang Zheng, Bentao Zhang, Wei Wei, Hongji Meng

    Three-dimensional shape of the billet/slab surface is an import cue to detect the surface defects, but it is difficult for phase-shifting profilometry to handle moving objects with textured surface such as casting billets/slabs. There are two issues that need to be addressed together, including object tracking and phase error correction. We propose a method to deal with these two issues. A projection and imaging technique is introduced to track the objects covered with fringe patterns. Based on object tracking, we find that phase errors are mainly induced by rotations and translations of the measured object and we propose a model to describe the phase error distributions. The coefficients of the model are determined by actual phase error distributions, and algorithms for obtaining actual phase error distributions are developed. Phase error distributions provided by the proposed model with determined coefficients are used for phase error correction. Simulations and experiments are carried out to validate the proposed method. Via the proposed method, the three-dimensional reconstruction result of the billet surface measured in moving conditions can provide stereoscopic details as that measured in a stationary state.


  • An AttnGAN-Based Macro Image Synthesis Model for Predicting the Internal Structure of Billets

    by Hongji Meng, Yue Wang, Wenbin An, Jian Yang, Qing He

    The internal structure of casting billets directly affects the performance of steel products, but in practice, it can not be detected online. Macro images (low-magnification snapshots of the casting billet sample cross-sections) can visualize the structure, but obtaining them is lagging and costly. Numerical simulation methods are time-consuming to calculate, and only corrected for a few steel grades, making accuracy difficult to guarantee under other working conditions. Thus, we propose a model based on generative adversarial networks (GANs) to quickly predict the internal structure of billets, which can synthesize macro images from production parameters. However, the macro images are less visually varied and have small and dense features. Conventional GANs struggle to generate macro images of casting billets. Therefore, this model is based on the attentional GAN (AttnGAN) to learn different level features through the supervision of multi-resolution images. The generators apply three-branch residual blocks to predict new pixels by multi-scale information, which improves the realism of details. Additionally, considering the ordering property of continuous casting, a series model of the deep neural network and recurrent neural network is designed to encode input parameters. It is combined with image information pretraining to simplify the learning of the mapping relationship in the macro image synthesis model. After comparison with other text-to-image generation models, our model performs better in terms of evaluation metrics and visual effects. The prediction results are verified using two samples from SCM435-M steel. The obtained results have a high consistency with the real data, with the absolute error of the equiaxed crystal rate being 0.84% and 0.6%, respectively. Moreover, the inference speed of our model is fast, which is of reference value for the optimization of the continuous casting process.


  • Online Recognition of Manually Spray-Printed Ladle Numbers in Complex Dynamic Environments

    by Hongji Meng, Hancong Ma, Jian Yang, Zhenwei Hu, Jia Fan, Qing He

    During the converter process, it is crucial to automatically identify and record ladle numbers to track steel product quality and enhance automation levels. However, the steelmaking environment presents several challenges, including intricate ladle scheduling, varying lighting conditions, severe background interference, and significant disparities between manually spray-printed ladle number characteristics and publicly available datasets. The combination of these problems makes it challenging to perform accurate and real-time ladle number identification. In response, this article suggests an automatic ladle number recognition approach based on deep learning and image processing. First, a double-region object detection model based on YOLOv5 is employed to capture keyframe images of the ladle to be identified from the video stream. Then, a method that can enable the acquisition of an accurate region of ladle numbers in sophisticated industrial settings is proposed to address the distortion of numerical features caused by lighting variations and background interference in industrial environments. Last, leveraging the proprietary dataset found and a ladle number recognition model integrating CNN and multiframe image fusion is designed, developing multithreading design and image queue management to ensure real-time and accurate ladle number recognition. In this study, the video data of a steel plant is used for testing. Through testing 176 steelmaking production cycles, all ladle numbers are accurately identified prior to finishing charging molten iron, indicating the high accuracy and real-time capability of the recognition system.


  • Open Access

    A Three Dimensional Real-time Heat Transfer Model for Continuous Casting Blooms

    by Jian Yang, Zhi Xie, Hongji Meng, Zhenwei Hu, Wenhong Liu, Zhenping Ji

    Heat transfer model is the basis for control and optimization of continuous casting of steel. In this paper, a three dimensional (3D) real-time heat transfer model has been presented for continuous casting blooms, especially for the initial and final casting stages. To be real-time, an algorithm based on inheritable variable non-uniform grid and variable time steps has been developed, accelerating the 3D heat transfer model by 110~200 times. Meanwhile, the discrete parameters including grid and time step have been optimized, and the influence of central processing units (CPUs) and programming languages has also been studied. Then the relative calculation time, which is the ratio of calculation time to physical time, has been reduced to 0.62 while numerical errors are within 0.74%. Further, to reduce the uncertainty of the model, the machine-dependent parameters appearing in the thermo-physical properties and the boundary conditions have been calibrated with measurements of surface temperature by thermometer and shell-thickness by nail-shooting, then the corresponding optimization problem of minimizing the errors between calculation and measurements has been solved by particle swarm optimization algorithm. After calibration, the model's uncertainty has been obviously reduced. Finally, the calibrated model has been verified by online surface temperature measurement and it shows good agreement as the errors between calculation and measurements are less than ±10°C.


  • Open Access

    Ladle Refractory Safety Monitoring System Based on Support Vector Regression

    by Zhenwei Hu, Wei Wei, Hongji Meng

    Ladle refractories were subject to repeated chemical erosion and physical scouring by various hot fluids such as steel slag, liquid steel, argon and oxygen. Firstly, the heat transfer model of ladle wall was established, the heat transfer of ladle refractory under different corrosion conditions was analyzed. The relationship between the residual thickness of ladle lining refractory and the temperature field of the outer surface of ladle was established. Secondly, a set of infrared thermal imaging ladle outer wall temperature monitoring system was used to measure the ladle outer wall temperature, especially the slag line temperature. The changes of ladle outer surface temperature field under different corrosion conditions and different process conditions were analyzed. Finally, based on the support vector regression (SVR) model, the residual thickness prediction model of ladle refractory was designed. Combined with the ladle surface temperature and steelmaking production process conditions, the residual thickness of ladle refractory corrosion was predicted. The experiment results showed that the prediction accuracy of ladle refractory corrosion reaches 92%, which met the requirements of steelmaking plant for ladle safety monitoring in green and intelligent production.

  • Molten Steel Level Detection From Thermal Image Sequence Based on the Characteristics of Adhesive Flux

    by Qing He, Hongji Meng, Zhenwei Hu, Zhi Xie

    High-temperature medium and time-varying covering flux lead to the difficulty of molten steel level measurement. For the measurement, in our previous work, a novel principle by using temperature gradient was proposed by us, and a refractory sensor was inserted into the metallurgical container to sense the temperature gradients of the flux and the molten steel. However, sometimes liquid adhesive flux on the sensor surface disables the extraction of true temperature gradients. To fix this problem, two new models, the adhesion thickness model and the adhesion flowability model, which are inspired by the adhesion mechanism of the flux, are proposed to detect the steel-flux interface. A unified approach, sequential clustering of the shapes of the pixel gray-time curves, is introduced to conduct the detection. On this basis, the thermal image sequence with 4-D spacetime information of the sensor is used for clustering. First, gray values of each pixel in the sequence are sorted in the time dimension, and grouping of the pixels in space dimension is done. Then, the region of interest is extracted from the image sequence to remove the invalid pixels, and sequential clustering is conducted with each group. Finally, the confidence of the clustering results is measured and the clustering results with the confidence higher than the threshold are retained to detect the steel-flux interface. By utilizing the two new models, the standard deviation of the measurement errors reduces from 4.8 to 3.7 mm.