Production Of Steel Strip Research Articles

A Lightweight Strip Steel Surface Defect Detection Network Based on Improved YOLOv8

Strip steel surface defect detection has become a crucial step in ensuring the quality of strip steel production. To address the issues of low detection accuracy and long detection times in strip steel surface defect detection algorithms caused by varying defect sizes and blurred images during acquisition, this paper proposes a lightweight strip steel surface defect detection network, YOLO-SDS, based on an improved YOLOv8. Firstly, StarNet is utilized to replace the backbone network of YOLOv8, achieving lightweight optimization while maintaining accuracy. Secondly, a lightweight module DWR is introduced into the neck and combined with the C2f feature extraction module to enhance the model’s multi-scale feature extraction capability. Finally, an occlusion-aware attention mechanism SEAM is incorporated into the detection head, enabling the model to better capture and process features of occluded objects, thus improving performance in complex scenarios. Experimental results on the open-source NEU-DET dataset show that the improved model reduces parameters by 34.4% compared with the original YOLOv8 algorithm while increasing average detection accuracy by 1.5%. And it shows good generalization performance on the deepPCB dataset. Compared with other defect detection models, YOLO-SDS offers significant advantages in terms of parameter count and detection speed. Additionally, ablation experiments validate the effectiveness of each module.

TAFENet: A Two-Stage Attention-Based Feature-Enhancement Network for Strip Steel Surface Defect Detection

Strip steel serves as a crucial raw material in numerous industries, including aircraft and automobile manufacturing. Surface defects in strip steel can degrade the performance, quality, and appearance of industrial steel products. Detecting surface defects in steel strip products is challenging due to the low contrast between defects and background, small defect targets, as well as significant variations in defect sizes. To address these challenges, a two-stage attention-based feature-enhancement network (TAFENet) is proposed, wherein the first-stage feature-enhancement procedure utilizes an attentional convolutional fusion module with convolution to combine all four-level features and then strengthens the features of different levels via a residual spatial-channel attention connection module (RSC). The second-stage feature-enhancement procedure combines three-level features using an attentional self-attention fusion module and then strengthens the features using a RSC attention module. Experiments on the NEU-DET and GC10-DET datasets demonstrated that the proposed method significantly improved detection accuracy, thereby confirming the effectiveness and generalization capability of the proposed method.

A Survey of Vision-Based Methods for Surface Defects’ Detection and Classification in Steel Products

In the competitive landscape of steel-strip production, ensuring the high quality of steel surfaces is paramount. Traditionally, human visual inspection has been the primary method for detecting defects, but it suffers from limitations such as reliability, cost, processing time, and accuracy. Visual inspection technologies, particularly automation techniques, have been introduced to address these shortcomings. This paper conducts a thorough survey examining vision-based methodologies related to detecting and classifying surface defects on steel products. These methodologies encompass statistical, spectral, texture segmentation based methods, and machine learning-driven approaches. Furthermore, various classification algorithms, categorized into supervised, semi-supervised, and unsupervised techniques, are discussed. Additionally, the paper outlines the future direction of research focus.

Life cycle assessment of carbon footprint in dual-phase automotive strip steel production.

As the demand for automotive materials grows more stringent in environmental considerations, it becomes imperative to conduct thorough environmental impact assessments of dual-phase automotive strip steel (DP steel). However, the absence of detailed and comparable studies has left the carbon footprint of DP steel and its sources largely unknown. This study addresses this gap by establishing a cradle-to-gate life cycle model for DP steel, encompassing on-site production, energy systems, and upstream processes. The analysis identifies and scrutinizes key factors influencing the carbon footprint, with a focus on upstream mining, transportation, and on-site production processes. The results indicate that the carbon footprint of DP steel is 2.721 kgCO2-eq/kgDP, with on-site processes contributing significantly at 88.1%. Sensitivity analysis is employed to assess the impact of changes in resource structure, on-site energy, CO2 emission factors, and byproduct recovery on the carbon footprint. Proposals for mitigating carbon emissions in DP steel production include enhancing process gas recovery, transitioning to cleaner energy sources, and reducing the hot metal-to-steel ratio. These findings offer valuable insights for steering steel production towards environmentally sustainable practices.

Process-based life cycle inventory framework for assessing the carbon footprint of products from complex production paths: Case of dual-phase automotive strip steel

The production paths of industrial products are usually complex, leading to difficulties and a large workload when conducting traditional process-based life cycle assessment (P-LCA). Existing studies on reducing LCA workload have focused mainly on simplifying the process or combining LCA with correlation methods. For complex production paths that cannot be simplified or changed, the methods have weak generality. To fill in these research gaps, a process-based life cycle inventory (P-LCI) framework for complex production paths is proposed. P-LCI contains accurate classification and definition methods for input, output and unit processes, and an interconnection model for calculating process coefficients according to the complexity of the linkages among processes is proposed. Based on the proposed framework, a case study of the dual-phase automotive strip steel (DP) production process is performed. The results show that the production of 1 kg of DP steel consumes 0.679 kg of molten steel from a basic oxygen furnace plant and 0.557 kg from the another. Coke plants produce the largest carbon footprint (CF) per unit of coke, which is 0.889–1.231 kgCO2e/kg-coke. For the cradle-to-gate lifecycle of DP steels, the BFP has the largest CF at 0.614 kgCO2e/kg-DP, accounting for 26.32%. Through the proposed P-LCI framework, unit processes can be clearly defined, and the interconnection model can be used as the basis for environmental impact analysis. When the production path changes, the model can be flexibly adjusted, and the workload of repeated model construction can be reduced.

Evaluation of a Combined Casting and Deformation Process in the Production of a Three-Layer Steel Strip

Evaluation of a Combined Casting and Deformation Process in the Production of a Three-Layer Steel Strip

Tailoring Strength and Ductility of an Fe–Mn–Al–C Low‐Density Duplex Steel by Controlling the Cooling Path after Hot Rolling

The low‐density duplex steels provide a potential for the industrial application owing to their good strength‐ductility match and reduced density. In the present work, the microstructure of an Fe–8.03Mn–6.10Al–0.4C (wt%) low‐density duplex steel was adjusted by controlling the cooling path after hot rolling, which is a conventional process during the production of steel sheets and strips. A microstructure of ferrite and austenite has been achieved by annealing the air‐cooled samples, and the microstructure of furnace‐cooled annealed samples consists of banded ferrite, austenite, and martensite. This is mainly due to the fact that the austenite is more stable by refining the grain size via embedding the needle‐like α‐ferrite. The existing of martensite and the banded microstructure in furnace‐cooled annealed samples induces the occurrence of cracks during deformation, resulting in an abrupt fracture at a relatively lower strain level. However, for air‐cooled annealed samples, a good ductility of duplex microstructure ensures that the deformation can be sustained up to a much higher strain level, and the transformation induced plasticity effect plays a positive role at the later deformation stage; this contributes to the occurrence of an extra work hardening rate recovery during deformation and thus to a good strength‐ductility match.

Cross-Domain Transfer Learning for Galvanized Steel Strips Defect Detection and Recognition

Abstract Defect detection is a crucial direction of deep learning, which is suitable for industrial inspection of product quality in strip steel. As the strip steel production line continuously outputs products, it is necessary to take corresponding measures for the type of defect, once a subtle quality problem is found on steel strips. We propose a new defect area detection and classification method for automation strip steel defect detection. In order to eliminate the way of insufficient data in industrial production line scenarios, we design a transfer learning scheme to support the training of defect region detection. Subsequently, in order to achieve a more accurate classification of defect categories, we designed a deep learning model that integrated the detection results of defect regions and defects feature extraction. After applying our method to the test set and production line, we can achieve extremely high accuracy, reaching 87.11%, while meeting the production speed of the production line compared with other methods. The accuracy and speed of the model realize automatic quality monitoring in the manufacturing process of strip steel.

A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill

Width-related defects are a common occurrence in the Hot Strip Mill process which can lead to extra processing, concessions, or scrapping. The detection and Root Cause Analysis of these defects is a largely manual process and is vulnerable to several negative factors including human error, late feedback, and knock-on effects in successive steel strip products. Automated tools which utilize Artificial Intelligence and Machine Learning for defect detection and Root Cause Analysis in hot rolling have not yet been adopted outside of surface defect detection and roller force optimization. In this paper, we propose an automated tool for the detection and Root Cause Analysis of width-related defects in the hot rolling process which utilizes a combination of expert knowledge and several Machine Learning models. Through this, we aim to increase the scope, and encourage further development, of Machine Learning applications within the Hot Strip Mill process. Both classical algorithms and Computer Vision methods were used for the Machine Learning component of the tool, namely, classification trees and pre-trained convolutional neural networks. The tool is trained and validated using data from an existing hot rolling mill and thus the challenges of collecting and processing real-world legacy data are highlighted and discussed. The Machine Learning models used are shown to perform optimally by validation performance metrics. The tool is found to be suitable for the specified purpose and would be further improved with more training data.

Effect of Preheating on the Mechanical Workability Improvement of High-Strength Electrical Steels during Tandem Cold Rolling

Cold-rolled silicon steel strip products are widely used as the main soft magnetic components in cores of electrical motors, generators, and transformers. In the case of rotating electrical machines, the so-called non-oriented electro-technical steels are normally applied. They are characterized by a similar behaviour to the induced magnetic field found in all sheet plane directions. The kind of soft magnetic alloys that defined herein not only possess an isotropy of electromagnetic properties, but also high mechanical strength; such alloys are called high-strength electro-technical (HSET) steels. These commercially produced HSET steels contain a high silicon content in the range of 3–4 wt.%. However, if the silicon content exceeds 3%, the machinability of Fe–Si alloys is dramatically reduced and they become much more brittle as a consequence. According to this, regular hot band brittle damage occurs during cold deformation at a high-speed tandem rolling mill. In accordance with these reasons, the production of thin high-strength silicon steel grades using the traditional methods of cold rolling deformation is extremely problematic and it is characterised by a high degree of steel sheet mechanical damage. In this scientific work, the effect of preheating hot-rolled strips on their mechanical workability improvement during tandem cold rolling was investigated. The results of this study indicate that the cold rolling of hot bands at elevated temperatures increases their resistance to brittle failure and mechanical plasticity. Moreover, the mathematical simulation clearly demonstrates that residual stress is distributed relatively homogeneously across the thickness of samples, which were cold rolled at 100 °C in contrast to the same ones deformed at room temperature.

Determination of the wear of the surfaces of barrels of work rolls in a continuous finishing group of stands of a wide-strip hot rolling mill

Compensate for elastic and thermal deformations of the work rolls, as well as to ensure the possibility of rolling a flat strip, the surface of the barrel of the work rolls is profiled. During the production of steel strips on a continuous mill, the initial grinding profiles of the barrel surfaces change due to their wear. According to a number of studies, the shape of the worn surface will be determined by a number of factors: by sliding the rolled metal along the roll in the deformation zone, which depends, among other things, on the length of the produced strip; temperature conditions in the deformation zone; the presence of a movable intermediate layer between the roll and the strip, for example, mill scale during hot rolling or cutting fluid during cold rolling; chemical composition of the rolled steel; quality of rolling rolls; applied steel strip reduction modes in the mill stands; uneven heating of the rolled metal over the section, as well as some other parameters. A study was carried out on the basis of experimental data on evaluating the profile of the barrel of work rolls after they were dumped and cooled from the rolling stands. It was found that the main parameter affecting the wear of the surface is the length of the strip rolled in a given stand. It has been confirmed that wear along the length of the roll barrel is uneven. A method for calculating the wear of the surfaces of the barrels of the work rolls of a wide-strip mill along their length, based on the operating mode, is proposed. The results of the study can be used to improve the shape of the grinding profiling curve of the work roll barrels and it can be used in models for controlling the shape of a strip, and calculate technological rolling conditions

Increase of durability of railway wheels at JSC “Aktyubinsk ferroalloys plant”

Compensate for elastic and thermal deformations of the work rolls, as well as to ensure the possibility of rolling a flat strip, the surface of the barrel of the work rolls is profiled. During the production of steel strips on a continuous mill, the initial grinding profiles of the barrel surfaces change due to their wear. According to a number of studies, the shape of the worn surface will be determined by a number of factors: by sliding the rolled metal along the roll in the deformation zone, which depends, among other things, on the length of the produced strip; temperature conditions in the deformation zone; the presence of a movable intermediate layer between the roll and the strip, for example, mill scale during hot rolling or cutting fluid during cold rolling; chemical composition of the rolled steel; quality of rolling rolls; applied steel strip reduction modes in the mill stands; uneven heating of the rolled metal over the section, as well as some other parameters. A study was carried out on the basis of experimental data on evaluating the profile of the barrel of work rolls after they were dumped and cooled from the rolling stands. It was found that the main parameter affecting the wear of the surface is the length of the strip rolled in a given stand. It has been confirmed that wear along the length of the roll barrel is uneven. A method for calculating the wear of the surfaces of the barrels of the work rolls of a wide-strip mill along their length, based on the operating mode, is proposed. The results of the study can be used to improve the shape of the grinding profiling curve of the work roll barrels and it can be used in models for controlling the shape of a strip, and calculate technological rolling conditions

A real-time cost optimization of two-section oven system with discrete gradient extremum seeking control: An experimental study in iron and steel industry

The heavy industry plants are focused on finding ways to minimize energy costs, which is one of the most significant costs of production. In this paper, a case study on a real oven system used in a steel strip production line is performed. Oven systems consume different types of energy simultaneously. Therefore, energy cost optimization is a good case study for the oven systems. The real oven system studied in the present study consists of two sections with eight heating zones. A natural gas burner and a recirculation fan with a power of 45 kW are installed in each zone for continuous heating of steel strips. We improved Discrete Gradient Extremum Seeking Control (DGESC) in the oven system without changing the oven structure and its built-in burner controller and optimized the fan speeds so that the total cost of the heating process is minimized. The improved DGESC was evaluated during steel strip production with the constraints related to the oven safety, measurement device characteristics, and delays for stabilization. The measure of energy consumption was obtained from the oven automated software and compared with the consumption when using the oven manufacturer’s recommended settings. At the end of the production, the improved DGESC strategy showed that the same output can be produced with less cost at different operating speeds of the fans. In particular, the total cost of the electrical energy and natural gas was reduced by 3.44% when using 78% of fan speed instead of using 70% recommended by the manufacturer. The promising results of the improved DGESC can be further enhanced by upgrading the oven system for individual measurements.

Faster Metallic Surface Defect Detection Using Deep Learning with燙hannel燬huffling

Deep learning has been constantly improving in recent years, and a significant number of researchers have devoted themselves to the research of defect detection algorithms. Detection and recognition of small and complex targets is still a problem that needs to be solved. The authors of this research would like to present an improved defect detection model for detecting small and complex defect targets in steel surfaces. During steel strip production, mechanical forces and environmental factors cause surface defects of the steel strip. Therefore, the detection of such defects is key to the production of high-quality products. Moreover, surface defects of the steel strip cause great economic losses to the high-tech industry. So far, few studies have explored methods of identifying the defects, and most of the currently available algorithms are not sufficiently effective. Therefore, this study presents an improved real-time metallic surface defect detection model based on You Only Look Once (YOLOv5) specially designed for small networks. For the smaller features of the target, the conventional part is replaced with a depth-wise convolution and channel shuffle mechanism. Then assigning weights to Feature Pyramid Networks (FPN) output features and fusing them, increases feature propagation and the network’s characterization ability. The experimental results reveal that the improved proposed model outperforms other comparable models in terms of accuracy and detection time. The precision of the proposed model achieved by mAP@0.5 is 77.5% on the Northeastern University, Dataset (NEU-DET) and 70.18% on the GC10-DET datasets.

Dynamic operation optimization based on improved dynamic multi-objective dragonfly algorithm in continuous annealing process

The continuous annealing production process is the strip iron heat treatment process. Considering the numerous disturbance parameters and frequent environmental changes in the production process, dynamic multi-objective optimization is studied. (1)To anticipate whether the environment will change, this paper proposed dynamic detection based on Long-Short Term Memory (LSTM) prediction mechanism. A single-step prediction method is adopted to predict the strip hardness at the next moment which is compared with the value at the previous moment. (2)To track the dynamic Pareto frontier, the Information Fusion (IF) strategy in Dynamic Multi-Objective Dragonfly Algorithm (DMODA) is proposed. The population is updated by integrating the environmental offset with the evolution information. Computational experiments show the proposed strategy is effective when dealing with dynamic problems and it has been well applied in the continuous annealing process. The strip steel quality and production capacity can remain stable during the dynamic production process.

DCAM-Net: A Rapid Detection Network for Strip Steel Surface Defects Based on Deformable Convolution and Attention Mechanism

Strip steel surface defect detection is a critical step in the production field of the steel industry and a vital guarantee to improve the quality of strip steel production. However, due to the poor contrast of the strip steel surface defect images, the diversity of defect types, scales, texture structures, and the irregular distribution of defects, it is difficult to achieve rapid and accurate detection of strip steel surface defects with the existing methods. In this article, a rapid detection network for strip steel surface defects based on deformable convolution and attention mechanism (DCAM-Net) is proposed. First, we introduce contrast limited adaptive histogram equalization (CLAHE) as a data augmentation method to improve the contrast of the defect image and highlight the defect feature on the strip steel surface images. Second, we propose a novel enhanced deformation-feature extraction block (EDE-block) for various complex and irregularly distributed strip steel defects. By fusing deformable convolution, the receptive field of the defect feature extraction network is expanded to capture complete and comprehensive defect texture features. Finally, we introduce the coordination attention (CA) module to replace the backbone network’s spatial pyramid pooling (SPP) structure, which further factorizes the pooling operation and effectively improves the network’s ability to locate defects. The experimental results on the NEU-DET dataset showed that the mean Average Precision (mAP@IoU <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$=0.5$ </tex-math></inline-formula> ) of the proposed algorithm is 82.6%, which is 7.3% higher than the baseline network, and the detection speed is up to 100.2 fps, which effectively improves the detection efficiency of surface defects of strip steel.

Optimization of Rolling Schedule for Single-Stand Reversible Cold Rolling Mill Based on Multiobjective Artificial Fish Swarm Algorithm

The single-stand reversible cold rolling mill is important equipment in the production of steel strips. The rolling schedule is the core technological content in the strip production of the single-stand reversible cold rolling mill. The scientific rolling schedule is the fundamental guarantee for the production capacity of the rolling mill, product quality, accuracy, shape quality, energy saving, and consumption reduction. This paper takes the dynamic rolling process of single-stand cold rolling as the research object, the purposes of increasing production capacity, saving energy, and reducing consumption are achieved by optimizing the rolling schedule. Based on the study of the mechanism model and the analysis of a large number of field measured data, a slice of mathematical models of the rolling process suitable for engineering calculation are proposed, and a few objective functions suitable for the single-stand reversible cold rolling process are designed. On this basis, the artificial fish swarm algorithm is improved into a multiobjective optimization algorithm for the optimization of rolling schedule, and the optimal rolling load distribution scheme is obtained. Finally, the optimization method of rolling schedule proposed in this paper is applied to the actual rolling production. The results show that the proposed method can improve productivity and save energy compared with the empirical rolling schedule, and the feasibility and validity of the proposed algorithm are verified.

Surface defect detection of steel strips based on improved YOLOv4

During the production and processing of steel strips, the production process and external factors lead to surface defects that negatively impact the strips’ integrity and functionality. However, traditional manual defect detection algorithms cannot meet modern accuracy requirements. Therefore, we propose a steel strip surface defect detection method based on the improved you-only-look-once version 4 (YOLOv4) algorithm. The attention mechanism is embedded in the backbone network structure, and the path aggregation network is modified into a customised receptive field block structure, which strengthens the feature extraction functionality of the network model. From the final experimental results, relative to the original YOLOv4 algorithm, the proposed algorithm's mean average precision values in the detection of four types of steel strip defects is improved by 3.87%, reaching 85.41%, thereby providing a new detection method for daily steel strip surface defects.

Comprehensive evaluation about the quality of steel strip based on combination weighting

Abstract In order to solve the problem that the quality of steel strip products is rough by manual evaluation, this paper will combine expert knowledge with quality data and establish four evaluation grades by taking surface quality, mechanical properties and dimensional accuracy as evaluation indicators. Analytic hierarchy process (AHP) and entropy weight method are used to confirm the weight of each evaluation indicator. The mechanical properties and dimensional accuracy indicators are confirmed by statistical method to find out the optimal range of indicator parameters, and the indicator deterioration degree is calculated. The deterioration degree of surface quality indicator is confirmed by fuzzy language quantization. The membership degree of each indicator parameter is calculated according to the membership degree function of ridge distribution, and then the fuzzy comprehensive evaluation result matrix of strip quality is obtained by synthesizing each indicator parameter step by step. Finally, the comprehensive score of strip steel quality is obtained by quantizing and summing the evaluation result matrix. The experimental results show that the evaluation result of the model is consistent with the actual data, so it has certain practicability.

Effect of combined machining on structure and properties of electrospark coatings on low-carbon Steel by self-fluxing special electrode

The methods of surface-plastic deformation are considered. The process of production and processing of steel strip from low-carbon steel is considered. The results of a study of the effect of combined processing on the structure and physical and mechanical properties of electrophysical coatings deposited on low-carbon steel after burnishing with a specially designed tool and devices are presented. The optimal burnishing mode for mineral ceramics VOK-60 is determined. The number of pores in the coating was determined by the eddy current method.