Hot Steel Strip Research Articles

EMC-YOLO: a feature enhancement and fusion based surface defect detection for hot rolled strip steel

Abstract Steel is one of the most common and widely used materials in modern industrial production, and has been widely and deeply used in the field of engineering construction. However, the manufacturing process and external factors can lead to defect problems that seriously affect the quality and appearance of the steel. Defects have the characteristics of multi-scale, weak texture, many dense and small defects, and interference in the processing environment, which are challenging for the actual location and classification of defects. The detection of these surface defects is challenging due to their multi-scale nature, weak textures, numerous small defects, and complex background interference. To address these challenges, an EMC-YOLO algorithm is proposed to detect defects accurately. First, an Enhanced Fast Feature Extraction (EFFE) module is constructed. It integrates local saliency information with global saliency information and achieves multi-depth feature fusion. The EFFE replaces the bottleneck structure of C2F, enhancing feature extraction capabilities. Secondly, to optimize multi-scale defect feature detection for small and elongated defects, a Multi-Scale Receptive Field Spatial. Pooling Fast Pyramid (MRF-SPPF) module is proposed. Finally, Cross-Reinforced Connections Across Spatial Features (CCASF) is designed to give full play to the feature representation extracted after backbone network enhancement and deeply integrate it with neck features. This closely links the enhanced backbone features with the enriched neck features. On the NEU-DET dataset, the mAP value of the proposed model is improved by 3.5%, and the accuracy of the model finally reaches 80.7%. At the same time, in another GC10-DET dataset, our model also achieved 73.5% mAP value. It achieves good accuracy while satisfying real-time performance. It has a good application prospect in the actual strip processing.

Automatic recognition of surface defects of hot rolled strip steel based on deep parallel attention convolution neural network

Automatic recognition of surface defects of hot rolled strip steel based on deep parallel attention convolution neural network

Flow characteristics of cooling nozzle for high strength after hot rolling

To further improve the cooling strength and uniformity of hot rolled strip steel after rolling and optimize the structure and process parameters of high-strength cooling equipment, this paper combined the basic structural characteristics and characteristic parameters of high-strength cooling nozzles of hot rolled strip steel, using finite element analysis software. The effect of various pressure and structural arguments on the internal flow characteristics of high-strength cooling nozzles was studied. The results show that with the increasing of the system pressure, the flow rate at the manifold outlet also increases gradually, and the fluctuation of the jet velocity increases gradually, but the flow line trend of the internal velocity is unchanged. The change in the position of the main shunt hole can affect the change in flow rate at the nozzle outlet. However, when the pressure is greater than 0.3 MPa, the fluctuation range of the flow rate at the slot outlet tends to be larger. The relevant results provide some reference for the design of high-strength cooling equipment in hot rolling.

Micro-Segregation induced strain inhomogeneity in >900 MPa UTS martensitic hot rolled advanced high strength steel

Micro-Segregation induced strain inhomogeneity in >900 MPa UTS martensitic hot rolled advanced high strength steel

Strip Surface Defect Detection Algorithm Based on YOLOv5.

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

Bending Force of Hot Rolled Strip Based on Improved Whale Optimization Algorithm and Twinning Support Vector Machine

Bending control is one of the main methods of shape control for the hot rolled plate. However, the existing bending force setting models based on traditional mathematical methods are complex and have low control accuracy, which leads to poor strip exit shapes. Aiming at the problem of complex bending force setting of the traditional algorithm, an improved whale swarm optimization algorithm and twin support vector machine-based bending force model for hot rolled strip steel (LWOA-TSVR) is proposed. Based on the hot rolling field production data of a steel plant, the research group established the bending force prediction model by using the nonlinear approximation ability of the twin support vector machine. The introduction of the Levy flight improvement algorithm improves the generalization ability, prediction accuracy, and convergence speed of the whale swarm optimization algorithm with the help of the convergence of coefficient vectors, solves the problem of a random selection of the parameters of the traditional whale swarm optimization algorithm and optimizes the ability of the whale swarm algorithm to jump out of the local optimum. Based on the actual rolling database, the hit rate of the proposed method reaches 91% (from −5 to 5 KN), which fully meets the requirements of the detection accuracy on the actual production line. The model is not only able to overcome the local search to obtain the global optimal solution, but also has the advantages of fast convergence and higher prediction accuracy. A comparison of the model with twin support vector machines and traditional whale swarm algorithms shows that the prediction accuracy is higher. The experimental results also show that this model has advantages over existing bending force prediction models in terms of improving the accuracy of the strip shape control and providing theoretical guidance for practical bending force settings.

Modeling and Monitoring for Laminar Cooling Process of Hot Steel Strip Rolling with Time–Space Nature

The laminar cooling process is an important procedure in hot steel strip rolling. The spatial distribution and the drop curve of the strip temperature are crucial for the production and the quality of the steel strip. Traditionally, lumped parameter methods are often used for the modeling of the laminar cooling process, making it difficult to consider the impact of the variation of state variables and related parameters on the system, which seriously affect the stability of the steel strip quality. In this paper, a modeling and monitoring method with a time–space nature for the laminar cooling process is proposed to monitor the spatial variation of the strip temperature. Firstly, the finite-dimensional model is obtained by time–space separation to describe the temperature variation of the steel strip. Next, a global model is constructed by using the multi-modeling integration method. Then, a residual generator is designed to monitor the strip temperature where the statistics and the threshold are calculated. Finally, the superiority and reliability of the proposed method are verified by the actual-process data of the laminar cooling process for hot steel strip rolling, and different types of faults are detected successfully.

Strip Steel Surface Defects Classification Based on Generative Adversarial Network and Attention Mechanism

In a complex industrial environment, it is difficult to obtain hot rolled strip steel surface defect images. Moreover, there is a lack of effective identification methods. In response to this, this paper implements accurate classification of strip steel surface defects based on generative adversarial network and attention mechanism. Firstly, a novel WGAN model is proposed to generate new surface defect images from random noises. By expanding the number of samples from 1360 to 3773, the generated images can be further used for training classification algorithm. Secondly, a Multi-SE-ResNet34 model integrating attention mechanism is proposed to identify defects. The accuracy rate on the test set is 99.20%, which is 6.71%, 4.56%, 1.88%, 0.54% and 1.34% higher than AlexNet, VGG16, ShuffleNet v2 1×, ResNet34, and ResNet50, respectively. Finally, a visual comparison of the features extracted by different models using Grad-CAM reveals that the proposed model is more calibrated for feature extraction. Therefore, it can be concluded that the proposed methods provide a significant reference for data augmentation and classification of strip steel surface defects.

Magnetic characterisation of strain ageing in near eutectoid drawn pearlitic wire using an electromagnetic (EM) sensor

• The electromagnetic sensors are capable of detecting strain ageing in near eutectoid pearlitic wires. • Electromagnetic sensors are a non-destructive monitoring technique, which may lead to in-situ sensors. • The development of In-situ sensors could extend service life of components. High carbon steel wires are susceptible to a detrimental ageing process, known as strain ageing. Strain ageing is responsible for the redistribution of carbon atoms within a wire microstructure. The redistribution of carbon atoms results in changes to the mechanical properties of a wire in service, which can lead to premature failure. Current methods of monitoring strain ageing are destructive, making in service monitoring challenging. Therefore, it is desirable to detect these subtle changes in a non-destructive manner. This paper reports trials of an electromagnetic (EM) sensor designed for monitoring wire samples. It is known that EM sensors are sensitive to microstructural changes in steels, and sensors are being used to monitor phase transformations during hot steel processing and strip properties in cold mills. This is the first reported use of an EM sensor for monitoring strain ageing in high carbon steel wire. Wires were tested using current standard methods (mechanical testing) alongside EM sensor measurements. An initial increase in tensile strength was observed via mechanical testing, whilst the EM sensors measured a corresponding change in real inductance. In more severe ageing conditions, mechanical properties levelled off somewhat, which was also measured in the corresponding EM sensor measurements. EM sensors are capable of detecting the subtle changes caused by strain ageing in a non-destructive manner. Therefore, the development of inline EM sensors have the potential to monitor strain ageing in a level of detail which has not been reasonably achievable with currently available testing methods.

Evaluation method for hot rolling & run out table cooling parameters

A new hot rolling & Run Out Table cooling simulator is constructed. The simulator permits continuous collation of process data including in-situ temperature measurement at numerous positions of the strip steel. Tensile properties and microstructural analysis of the hot rolled strip are correlated to the collated process data. A numerical model including phase transformation and latent heat evolution is constructed and calibrated against the experimental data. The resulting numerical model can be used to efficiently predict the optimal process parameters for manufacturing hot rolled strip steels, while the new hot rolling & Run Out Table cooling simulator can be used to efficiently validate the numerical simulation results before up-scaling to the industrial hot mill.

A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel

Hot-rolled strip steel is widely used in automotive manufacturing, chemical and home appliance industries, and its surface quality has a great impact on the quality of the final product. In the manufacturing process of strip steel, due to the rolling process and many other reasons, the surface of hot rolled strip steel will inevitably produce slag, scratches and other surface defects. These defects not only affect the quality of the product, but may even lead to broken strips in the subsequent process, seriously affecting the continuation of production. Therefore, it is important to study the surface defects of strip steel and identify the types of defects in strip steel. In this paper, a scheme based on ResNet50 with the addition of FcaNet and Convolutional Block Attention Module (CBAM) is proposed for strip defect classification and validated on the X-SDD strip defect dataset. Our solution achieves a classification accuracy of 94.11%, higher than more than a dozen other compared deep learning models. Moreover, to adress the problem of low accuracy of the algorithm in classifying individual defects, we use ensemble learning to optimize. By integrating the original solution with VGG16 and SqueezeNet, the recognition rate of oxide scale of plate system defects improved by 21.05 percentage points, and the overall defect classification accuracy improved to 94.85%.

A new dust removal technology used in hot rolling mills: Atomized spray with higher dedusting efficiency

In order to effectively remove the oxide scale dusts in the hot rolling strip steel, this study focuses on the principle of atomized spray and use it to develop a new dust removal technology used in the hot rolling mills. Through establishing a mathematic model of particle collision, 4 critical factors most affecting the dedusting efficiency are analysed: the diameter of nozzles, the diameter of water droplets, the diameter of dust particles, and the spray pressure. For further discovering the principles of the movements and concentration changes of the dust particles, a numerical model is established based on the gap space between the hot rolling mills. 2 scenarios of running the atomized dedusting or not are simulated to compute the dedusting efficiency so that the dedusting effect of the atomized spray can be confirmed for the hot rolling. The case study on the 1580 mm hot rolling line in WISCO plant demonstrates a successful dedusting efficiency of 93.50% on the R2 rough rolling mill. The spray pressure of 0.5 MPa and the nozzle diameter of 1.4 mm are appropriate to generating the proper water droplets with the diameter of 71.1 μm in order to capture the dust particles with the mean diameter of 27 μm. The study on the principles and simulations of the atomized spray facilitates more efficient dust removal for cleaner hot rolling mills. • More appropriate mathematical models are established to improve the dedusting efficiency for the hot rolling mills. • Further study discovers the influence of spray pressure and nozzle diameter on the dedusting efficiency of atomized spray. • The dedusting efficiency on the 1580 R2 rough rolling mill reaches up to 93.50% by using the atomized spray technology. • In WISCO the 0.5MPa spray pressure and the 1.4mm nozzle diameter are appropriate for effectively capturing dust particles. • The error of theoretical computation on the dedusting efficiency is only 0.03% for the 1580 R2 rough rolling mill.

Research on Surface Defect Detection Algorithm of Strip Steel Based on Improved YOLOV3

Aiming at the problems of slow detection speed and low detection accuracy in the surface defect detection of hot rolled strip steel, an improved YOLOV3 algorithm model was proposed in this paper. Firstly, the data sets is expanded by using the data enhancement algorithm to improve the robustness of the algorithm. Secondly, K-means++ with less randomness was used to perform clustering analysis on defect labels instead of K-means algorithm, and appropriate Anchor Boxes were selected as the initial candidate boxes for the improved YOLOV3 network. Finally, this study changed the detection network of YOLOV3, added a layer of prediction box and performed feature fusion to improve the detection ability of the network for small targets. The experimental results show that the improved YOLOV3 algorithm achieves 89.5% mean average precision on NEU-DET data set, which is 14.7% higher than the original YOLOV3 algorithm. Detection speed in 34 FPS at the same time, can meet the needs of industrial production.

A new multimode process monitoring method based on a hierarchical Dirichlet process—Hidden semi-Markov model with application to the hot steel strip mill process

With the expansion of modern plants and the growth of process complexities, industrial processes generally have multimodes, which are reflected in the multiple distributions and complex correlations among the process data. On the basis of single mode process monitoring methods, research on multimode process monitoring have attracted much attention. At present, most of it has been based on prior process knowledge, including the number of operating modes and the historical dataset for each mode, which are usually unavailable in many cases. This paper proposes a new multimode process monitoring method based on the hierarchical Dirichlet process (HDP) and a hidden semi-Markov model (HSMM). Firstly, HSMM is used to overcome the limitation of state durations in the traditional HMM. Then, HDP is introduced as a prior of infinite spaces solving the problem of missing mode information. Secondly, based on the HDP-HSMM framework, an automatic mode classification and identification strategy, including unknown mode identification, is established. Finally, a global–local monitoring strategy is put forward based on the Mahalanobis distance and the negative log-likelihood probability to give multimode process monitoring has been achieved. The effectiveness of the proposed method is verified on the Tennessee Eastman process and a real hot strip mill process (HSMP).

Prediction of mechanical properties of hot-rolled strip steel based on PCA-GBDT method

Improving the quality of rolled steel products is the primary task of the entire steel industry. As the main step of rolled steel production, hot rolling has received extensive attention. As far as the hot rolling process is concerned, the chemical composition of steel and related process parameters are the most direct factors affecting the quality of hot rolled steel sheets. Based on Principal Component Analysis (PCA) and Gradient Lifting Decision Tree (GBDT) methods, this paper takes the tensile strength as the research object and constructs a prediction model for the mechanical properties of hot rolled strip steel. Through principal component analysis of characteristic data, 28 variables were reduced into 8 new indicators to be used for GBDT regression analysis. 2489 pieces of data were divided into a training set and a test set at a ratio of 7:3, to be used in the training set to build a regression model, and get a root mean square error of 16.7393. The data in the test set was used to predict the tensile strength value, with the root mean square error reaching 18.2650.

Qualitative study and a novel solution to nozzle clogging problem in roll gap lubrication used in hot rolling

AbstractNozzle clogging in roll gap lubrication (RGL) is a pain area for hot strip steel rolling. Nozzle clogging severely affects lubrication affecting rolled surface quality causing prominent hot rolling defects like banding and peel‐off phenomenon in work roll. Uneven coefficient of friction leads to variable or poor lubrication, which raises the chances of cobble and tail chewing in coils, lowers roll force reductions ultimately increasing the power consumption of the mill. The present work focuses on a holistic approach where causes leading to nozzle clogging have been identified and eliminated in a stepwise manner. Gas chromatography has been employed for the first time to get an understanding about the specific carbon chains contributing towards pulp generation. Optimising the distance between mixer and spray header and using indigenously modified spray header improves the lubrication during hot rolling. roll force reduction upto 15%–16% could be achieved.

Influence of Austenitizing Parameters on the Microstructures and Mechanical Properties of 22MnB5 Hot Stamping Steel Produced by TSCR Process

Thin gauge hot strip steel can be produced by thin slab continuous casting and rolling (TSCR) process without the aid of cold rolling. However, few attempts have been made to produce hot stamping steel by using TSCR technology. As given steel, the hot stamping steel produced by the TSCR process was used to study the influence of austenitizing parameters on the final microstructures and mechanical properties. A Gleeble3500 thermal simulator was employed to heat the samples to obtain different austenite microstructures. After quenching, the Vickers hardness examination along the thickness of the sample and tensile testing were conducted. The microstructure was observed using scanning electron microscopy (SEM) and transmission electron microscopy (TEM). The results showed that on the condition of relatively lower temperature and shorter holding time, the sample exhibited better mechanical properties at the cost of microstructure uniformity along the thickness, although higher austenitizing temperature enhanced the carbide dissolution which would increase the effective carbon content in the martensite matrix. Lower heating temperature led to small prior austenite grain size and small blocks which contributed greatly to the mechanical properties.

Causes detection of unqualified bendability of hot rolled strip via improved RankBoost with multiple feature ranking algorithms

ABSTRACT In hot rolling process, mechanical properties of steel materials are important to steel quality. The bendability is one of the key parameters to evaluate the formability of the strip. When the bendability is unqualified, how to detect causes becomes a big challenge. In this paper, a model to find the causes of bendability of hot rolled strip based on improved RankBoost with multiple feature selection algorithms using historical data is built. Firstly, the related process variables and bendability results are collected. And then, seven feature ranking methods including Fisher score, Relief, Gini index, T-test, Kruskal–Wallis, mutual information entropy and minimum redundancy maximum relevance (MRMR), are used to rank the significance of features individually. Finally, to summarize the results of the seven methods, the total importance of every feature can be obtained using the improved RankBoost method to select the most important features as the major causes. The real field data set from hot rolling strip steel process is used to validate the model. The results demonstrate that the RankBoost method can give a more credible result.

Effects of Thermal Shields on Temperature of a Hot Steel Strip in Rolling Process

Effects of Thermal Shields on Temperature of a Hot Steel Strip in Rolling Process

Young Modulus at High Temperatures

The dependence of the young modulus of metals and alloys on the high temperature must be taken into account in metallurgy in the hot rolling of steel sheet on sheet-rolling mills, hot flattening of steel sheet in the sheet straightening machines, press forming forgings from hot steel sheet, hot volume stamping of metal products, and so on. For example, on the mill 5000 by SMS Siemag, the sheet-rolling of steel strips from the hot slabs at the stand Quarto (the maximum force of 120 MN) occurs at a temperature from 750 °С to 1050 °С, but the pre-flattening of hot steel strip on the five-roller sheet-straightening machine by SMS Siemag occurs usually in the temperature range from 600 °С to 760 °С. In this paper, based on the analysis of experimental data about the dependence of the young modulus for various steel alloys, the analytical dependence of the young modulus on temperature is obtained.