Image of Burden Point Cloud Based on Kmeans-Bayesian Segmentation with Energy Estimation

Obtaining a high-precision 3-D burden surface (BS) shape of a blast furnace (BF) is of significance for improving energy efficiency in the ironmaking process, and for stabilizing the operation of the BF. However, existing methods used for detecting the BS cannot provide precise data to guide the burden distribution operation of the BF effectively, because they cannot overcome the harsh environment inside the BF. Therefore, to obtain a reliable BS shape under a high-temperature, high-pressure, high-dust, and low-light environment, a 3-D high-temperature industrial endoscope with a large depth of field and wide field of view is proposed in this article. First, image-forming optical system indices are obtained by analyzing the environmental factors and geometry of the BF. Based on these indices, an optical system with a large depth of field, wide field of view, and low-light imaging capacity is designed. Next, a 3-D depth calculation method based on a virtual and real twin binocular optical system is used to obtain 3-D depth of feature points on the burden distribution ring. Furthermore, a functional relationship model between the image defocusing degree and depth of the BS is established, based on the 3-D depth. Finally, a monocular vision 3-D reconstruction method based on the depth from defocus parameter is used to realize the 3-D reconstruction of the BS. Experimental industrial applications of the proposed device demonstrate that it can provide data support for the BF burden distribution operation and has a significant industrial application value.

Numerical investigation of burden distribution in ironmaking blast furnace

At blast furnace B at Salzgitter Flachstahl a series of innovative measuring techniques are installed to monitor the processes at the blast furnace top, making this furnace one of the best equipped furnaces in Europe. These techniques comprise full 2D measurement of the temperature profile of the top gas shortly above the burden surface, 3D radar scan of the whole burden surface and online measurement of the dust concentration in the top gas. After more than 5 years’ experience with most of these techniques, they enable to better understand the complex chemical and physical interrelations occurring in the BF stack between the ascending process gas and the descending solid burden. A couple of examples of incidents that were monitored are presented in this article, including influences of charging programmes on top gas temperature profiles and influences of disturbed gas solids interaction on the BF working state. The new measuring techniques with tailor-made data processing enable the operators to gain a better picture of the processes currently occurring in the blast furnace, consequently supporting them in keeping the blast furnace operation as stable and efficient as possible.

Accurate measurement of the position and shape of the blast furnace (BF) burden surface (BS) is crucial for automated and intelligent BF control. The detection method based on key points of BS can improve the accuracy of radar BS detection in challenging environments with strong interference, ensuring long-term detection accuracy stability across long maintenance intervals. However, transferring a successfully applied detection model from the original BF to a new target BF requires sufficient sample collection in the target BF and model retraining. In practical scenario, data collection is often constrained by plenty of factors like time, space, and personnel. Thus, reducing the number of samples needed for retraining, or implementing model transfer based on small samples, can significantly boost BS detection efficiency. This paper proposes a Conv-Adapter Transfer Net (CATNet) designed for the transfer problem of key point detection models in BFBS and small sample scenarios. The CATNet adopts a newly designed parallel Conv-Adapter transfer module, a small-scale deep learning network with a minimal parameter quantity. Compared to fine-tuning the entire backbone model with a large number of parameters, retraining this transfer module requires far less training data. Therefore, CATNet is more suitable for model transfer in small sample scenarios. The experimental results demonstrate that the CATNet can exhibit strong transfer capability and higher prediction accuracy than the commonly used pretrain-finetune method in small sample scenarios, thereby enhancing the efficiency of model transfer across different BFs.

The top gas temperature is an apparent indicator of the distribution state of gas flow, and it is an important parameter to judge the furnace condition. It is related to the top equipment in addition to the charge characteristics and bottom-up generation and distribution. Therefore, the fluid-solid heat transfer model from burden surface -chute-rising ducts is established in this paper. The finite element method is used to calculate the flow and heat transfer of the gas at the top of the blast furnace, and the influence of the chute on the top gas temperature is analyzed. The accuracy of the model is verified by the actual blast furnace top temperature. The results show that the chute has a guiding effect on the gas flow. As the chute rotates, the top gas temperature fluctuates. This research is helpful for actual blast furnace operators to understand the top temperature and make the condition judgment more accurate.

Real-time and accurate measurement of blast furnace (BF) stockline is important for charging control and BF safety. However, traditional non-contact methods for stockline detection face many challenges such as low accuracy, poor anti-interference ability, and stability in harsh BF environments. The high-temperature novel industrial endoscope (NIE), a visible light detection equipment for BF burden surface (BBS), has captured real-time and continuous video streams of BBS, which provides a brand-new means and ideas for non-contact stockline detection. Based on this, a novel non-contact stockline detection method based on real-time burden surface video streams is proposed. First, an edge detection network based on bootstrap sampling and eigenvector coding clustering (ECC) is established to extract accurate edge distribution of burden surface video streams. Then, an actual imaging region model of the NIE is developed by the latitude circle method to quantify the relationship between the actual imaging region and the BF stockline. Finally, the edge of burden surface video streams is correlated with the corresponding actual imaging region through the NIE imaging model, and the non-contact stockline detection model is derived to realize the BF stockline detection based on video streams. Experiments and industrial applications show that the proposed method is superior to the traditional non-contact stockline detection methods in terms of detection accuracy, stability, and real-time performance.

An ironmaking blast furnace (BF) is a complex high-temperature moving bed reactor involving counter-, co- and cross-current flows of gas, liquid and solid, coupled with heat and mass exchange and chemical reactions. Two-dimensional (2D) models were widely used for understanding its internal state in the past. In this paper, a three-dimensional (3D) CFX-based mathematical model is developed for describing the internal state of a BF in terms of multiphase flow and the related thermochemical behavior, as well as process indicators. This model considers the intense interactions between gas, solid and liquid phases, and also their competition for the space. The model is applied to a BF covering from the burden surface at the top to the liquid surface in the hearth, where the raceway cavity is considered explicitly. The results show that the key in-furnace phenomena such as flow/temperature patterns and component distributions of solid, gas and liquid phases can be described and characterized in different regions inside the BF, including the gas and liquids flow circumferentially over the 3D raceway surface. The in-furnace distributions of key performance indicators such as reduction degree and gas utilization can also be predicted. This model offers a cost-effective tool to understand and control the complex BF flow and performance.

Radar technology is performed to obtain the position and morphology of burden surface in blast furnace, which is conducive to the optimal process of decision-making over burden distribution. Considering the imaging of the of echo spectrum, includes the characteristics of local highlighting and low signal-to-noise ratio, the adaptive gray-scale compensation algorithm combined with multi-scale Retinex image enhancement is adopted for high-quality brightness adjustment and color correction. Then, in order to make the target burden surface prominent and distinguishable, the improved hot metal coding method is applied to conduct pseudo-color processing of the enhanced image as obtained previously. In the meantime, the guided image filtering algorithm is introduced to maintain the target boundary of the burden surface while ensuring the effective removal of noise. Finally, the fractal interpolation algorithm is employed in line with the principle of SAR imaging to reconstruct the radar image of burden surface in blast furnace. Moreover, a qualitative analysis is conducted during production of the major characteristics of burden surface.

Model of burden distribution in operating blast furnaces

Information of unordered point cloud is limited because of no direct topologic relation between points or triangular facets. So it will be difficult to obtain the feature points of 3D point cloud data. In this article, we use the geometry properties, such as normal, curvature and density of the points' information to detect features of the 3D point cloud data and propose a curvature and density based feature point detection method for unordered 3D point cloud data. Firstly, we define a feature parameter of 3D point cloud data, which includes the distance with its neighboring points, the sum of the normal angle between the point and neighboring points, and point cloud data curvature. Secondly, the density of data points is calculated by using Octree and is used as the features of points by a threshold of their feature parameter. The experimental results show that our new approach might detect feature points accurately for the given 3D point cloud data.

As buildings have almost come to a saturation point in most developed countries, the management and maintenance of existing buildings have become the major problem of the field. Building Information Modeling (BIM) is the underlying technology to solve this problem. It is a 3D semantic representation of building construction and facilities that contributes to not only the design phase but also the construction and maintenance phases, such as life-cycle management and building energy performance measurement. This study aims at the processes of creating as-built BIM models, which are constructed after the design phase. Point cloud, a set of points in 3D space, is an intermediate product of as-built BIM models that is often acquired by 3D laser scanning and photogrammetry. A raw point cloud typically requires further procedures, e.g. registration, segmentation, classification, etc. In terms of segmentation and classification, machine learning methodologies are trending due to the enhanced speed of computation. However, supervised machine learning methodologies require labelling the training point clouds in advance, which is time-consuming and often leads to inevitable errors. And due to the complexity and uncertainty of real-world environments, the attributes of one point vary from the attributes of others. These situations make it difficult to analyze how one single attribute contributes to the result of segmentation and classification. This study developed a method of producing point clouds from a fast-generating 3D virtual indoor environment using procedural modeling. This research focused on two attributes of simulated point clouds, point density and the level of random errors. According to Silverman (1986), point density is associated with the point features around each output raster cell. The number of points within a neighborhood divided the area of the neighborhood is the point density. However, in this study, there was a little different. The point density was defined as the number of points on a surface divided by the surface area. And the unit is points per square meters (pts/m2). This research compared the performances of a machine learning segmentation and classification algorithm on ten different point cloud datasets. The mean loss and accuracy of segmentation and classification were analyzed and evaluated to show how the point density and level of random errors affect the performance of the segmentation and classification models. Moreover, the real-world point cloud data were used as additional data to evaluate the applicability of produced models.

Classification model for blast furnace status based on multi-source information

The distribution of burden layers in an ironmaking blast furnace strongly influences the conditions in the upper part of the process. The bed permeability largely depends on the distribution of ore and coke in the lumpy zone, which affects the radial gas flow distribution in the shaft. Along with the continuous advancement of technology, more information about the internal conditions of the blast furnace can be obtained through advanced measurement equipment, including 2D profiles and 3D surface maps of the top burden surface. However, the change of layer structure along with the burden descent cannot be directly measured. A mathematical model predicting the burden distribution and the internal layer structure during the descending process is established in this paper. The accuracy of the burden distribution model is verified by a comparison with experimental results. A sensitivity study was undertaken to clarify the role of some factors on the arising layer distribution, including the descent-rate distribution, the initial burden surface profile, and the charging direction through the charging matrix. The findings can be used as a theoretical basis to guide plant operations for optimizing the charging.

Data and knowledge driven approach for burden surface optimization in blast furnace

The variation in point cloud density is driven by many different factors. This variation is expected to affect the quality of the information extracted from the point clouds, however, the extent to which these variations impact the ability to accurately extract and assess geometric features of highways from point cloud data are unknown. This paper investigates the impacts of point density reduction on the extraction and assessment of four critical geometric features. The density of light detection and ranging (LiDAR) data was first reduced and the different features were extracted at varying levels of point density and on a selection of different highway segments in Alberta, Canada. The information obtained at lower point density was then compared to what was obtained at 100% point density. It was found that clearance assessments and sight distance assessments had low sensitivity to reductions in point density (i.e., reducing the point density to as low as 10% of the original data (30 ppm2 on the pavement surface) yielded results comparable to what was obtained at 100% density (300 ppm2) In contrast, for cross section slope estimation and curve attribute estimation higher sensitivity to point density was observed. These findings are critical for transportation agencies considering the adoption of LiDAR technology to manage elements of their infrastructure and for researchers developing data processing tools and algorithms for the semantic segmentation of transportation features from remotely sensed point clouds.