Deep learning for predictive mechanical properties of hot-rolled strip in complex manufacturing systems

Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent production.It has been difficult to meet the needs of the field with the usual prediction model of mechanical properties of hotrolled strip.Insufficient data and difficult parameter adjustment limit deep learning models based on multi-layer networks in practical applications;besides,the limited discrete process parameters used make it impossible to effectively depict the actual strip processing process.In order to solve these problems,this research proposed a new sampling approach for mechanical characteristics input data of hot-rolled strip based on the multi-grained cascade forest(gcForest)framework.According to the characteristics of complex process flow and abnormal sensitivity of process path and parameters to product quality in the hot-rolled strip production,a three-dimensional continuous time series process data sampling method based on time-temperature-deformation was designed.The basic information of strip steel(chemical composition and typical process parameters)is fused with the local process information collected by multi-grained scanning,so that the next link’s input has both local and global features.Furthermore,in the multi-grained scanning structure,a sub sampling scheme with a variable window was designed,so that input data with different dimensions can get output characteristics of the same dimension after passing through the multi-grained scanning structure,allowing the cascade forest structure to be trained normally.Finally,actual production data of three steel grades was used to conduct the experimental evaluation.The results revealed that the gcForest-based mechanical property prediction model outperforms the competition in terms of comprehensive performance,ease of parameter adjustment,and ability to sustain high prediction accuracy with fewer samples.

“Quartus scale” of hot-rolled strip steels and its formation mechanism

The types and growth of various oxide scales formed during the different phases of the production of hotrolled strip steel products are reviewed. Similarities and differences between the ＂tertiary scale＂ on the surface of carbon steels at high temperatures and the oxide scale on pure iron are compared. The micro-structural features of the ＂final oxide scale＂ on the surface of strip steels at room temperature as well as the relationship between these features and the position of the steel coil （plate） and the subsequent processes of recoiling, temper rolling and trimming, etc. are summarized. The actual oxide scales retained on the commercial hot-rolled strip steels at room temperature have been proposed to define as ＂ quartus scale＂ for the first time. The micro-structural development and phase transformation of the initial ＂tertiary scale＂ during and after cooling and coiling are described. The reasons for the ＂tertiary scale＂ on carbon steels differing from the oxide scale formed on pure iron, and the major influencing factors in the formation of various types of ＂quartus scales＂ are analyzed from both thermodynamic and dynamic viewpoints. The development mechanism of ＂ quartus scales＂ is discussed and the potential effects of the ＂ quartus scale＂ state （thickness, constitution, structure and defects）, on the rusting and pickling properties of commercial hot-rolled strip steel, as well as on the mechanical properties of oxide scales are analyzed.

Hot-rolled strips of up to 19 mm in thickness and their processing to helically welded large diameter pipes of grade X80

Hot-rolled wide strip for production of large diameter,heavy gauged(up to 19 mm) helical line pipe grade X80 was a priority development over the last three years.Microstructure,texture and mechanical properties of strips have been characterised.Also the welding conditions have been simulated.The favourable microstructure is achieved by the proper selection of an appropriate chemical composition of low carbon content and increased niobium micro alloying in combination with suitable strictly controlled hot-rolling parameters.The addition of niobium in combination with the adjustment of other alloying elements increases the recrystallisation stop temperature and thus makes it possible to apply a high temperature processing(HTP) concept.The homogeneous bainitic microstructure across the strip gauge is then formed during accelerated cooling on the run-out table of the hot-rolling mill.All results indicated excellent properties of these hot strips which make it suitable for spiral pipes of grade X80 for example 18.9mm×Φ1 220 mm at dimension.

Mill scale structure and damp heat corrosion performance of four 510L hot-rolled strips

In this study, the matrix structure, state and composition of the mill scales of four typical domestically made 510L hot-rolled strips were observed and analyzed by means of optical microscopy （OM） ,scanning electron microscopy （SEM） and X-ray diffraction （XRD）. The corrosion behavior of the steels with and without mill scales were investigated by means of hot-humid corrosion tests under the condition of relative humidity （ RH ） of 95% at 50℃ and 70℃, respectively. The results show that the matrix structures, state, composition and thickness of mill scales vary in the strips. The rusting starting time of the specimens with scales is generally a bit longer than that of the specimens without scales, but their corrosion mass-gain is higher. For these two kinds of specimens ,their corrosion rate increases significantly with the increase of temperature. The rusting behavior of the 510L strips produced by various plants is different due to the variations of hot-rolling processes and designed chemical compositions. Various relevant aspects should be taken into account in the evaluation of the corrosion behavior of hot-rolled strips.

Prediction of hot-rolled strip crown based on Boruta and extremely randomized trees algorithms

The quality of hot-rolled steel strip is directly affected by the strip crown.Traditional machine learning models have shown limitations in accurately predicting the strip crown,particularly when dealing with imbalanced data.This limitation results in poor production quality and efficiency,leading to increased production costs.Thus,a novel strip crown prediction model that uses the Boruta and extremely randomized trees(Boruta-ERT)algorithms to address this issue was proposed.To improve the accuracy of our model,we utilized the synthetic minority over-sampling technique to balance the imbalance data sets.The Boruta-ERT prediction model was then used to select features and predict the strip crown.With the 2160 mm hot rolling production lines of a steel plant serving as the research object,the experimental results showed that 97.01% of prediction data have an absolute error of less than 8 lm.This level of accuracy met the control requirements for strip crown and demonstrated significant benefits for the improvement in production quality of steel strip.

A defect recognition model for cross-section profile of hot-rolled strip based on deep learning

The cross-section profile is a key signal for evaluating hot-rolled strip quality,and ignoring its defects can easily lead to a final failure.The characteristics of complex curve,significant irregular fluctuation and imperfect sample data make it a challenge of recognizing cross-section defects,and current industrial judgment methods rely excessively on human decision making.A novel stacked denoising autoencoders(SDAE)model optimized with support vector machine(SVM)theory was proposed for the recognition of cross-section defects.Firstly,interpolation filtering and principal component analysis were employed to linearly reduce the data dimensionality of the profile curve.Secondly,the deep learning algorithm SDAE was used layer by layer for greedy unsupervised feature learning,and its final layer of back-propagation neural network was replaced by SVM for supervised learning of the final features,and the final model SDAE_SVM was obtained by further optimizing the entire network parameters via error back-propagation.Finally,the curve mirroring and combination stitching methods were used as data augmentation for the training set,which dealt with the problem of sample imbalance in the original data set,and the accuracy of cross-section defect prediction was further improved.The approach was applied in a 1780-mm hot rolling line of a steel mill to achieve the automatic diagnosis and classification of defects in cross-section profile of hot-rolled strip,which helps to reduce flatness quality concerns in downstream processes.

Prediction model for mechanical properties of hot-rolled strips by deep learning

The prediction of the mechanical properties of hot-rolled strips is a very complex,highly dimensional and nonlinear problem,and the published models might lack reliability,practicability and generalization.Thus,a new model was proposed for predicting the mechanical properties of hot-rolled strips by deep learning.First,the one-dimensional numerical data were transformed into two-dimensional data for expressing the complex interaction between the influencing factors.Subsequently,a new convolutional network was proposed to establish the prediction model of tensile strength of hot-rolled strips,and an improved inception module was introduced into this network to abstract features from different scales.Many comparative experiments were carried out to find the optimal network structure and its hyperparameters.Finally,the prediction experiments were carried out on different models to evaluate the performance of the new convolutional network,which includes the stepwise regression,ridge regression,support vector machine,random forest,shallow neural network,Bayesian neural network,deep feed-forward network and improved LeNet-5 convolutional neural network.The results show that the proposed convolutional network has better prediction accuracy of the mechanical properties of hot-rolled strips compared with other models.

Correlation of morphological anisotropy and Lankford value of deep drawing sheets hot-rolled by compact strip production

Cold-rolled steel sheets in automotive applications require an excellent deep draw ability, which is characterized by the Lankford value （r-value）. In this study, a correlation was identified between r-value and pancake-shaped grain flatness which is indicated as the ratio of grain diameter in the rolling direction （RD） and normal direction （ND） of sheets （dr/dn）. A mathematical model （ r = e^0.345（dn^1/2-dr^1/2） ） was developed to calculate r-value by the microstructure of steel sheets hot-rolled by compact strip production （CSP）. It is shown that the r-value is higher, if the microstructure of steel sheet is of pancake-shaped grains elongated in the rolling direction. The calculated r-value is confirmed to fit exactly to the measured one from the large-scale production.

Influence of oxide scales on the corrosion behaviors of B510L hot-rolled steel strips

The influence of oxide scales on the corrosion behaviors of B510 L hot-rolled steel strips was investigated in this study. Focused ion beams and scanning electron microscopy were used to observe the morphologies of oxide scales on the surface and cross sections of the hot-rolled steel. Raman spectroscopy and X-ray diffraction were used for the phase analysis of the oxide scales and corrosion products. The corrosion potential and impedance were measured by anodic polarization and electrochemical impedance spectroscopy. According to the results, oxide scales on the hot-rolled strips mainly comprise iron and iron oxides. The correlation between mass gain and test time follows a power exponential rule in the damp-heat test. The corrosion products are found to be mainly composed of γ-Fe OOH, Fe3O4, ？-Fe OOH, and γ-Fe2O3. The contents of the corrosion products are different on the surfaces of the steels with and without oxide scales. The steel with oxide scales is found to show a higher corrosion resistance and lower corrosion rate.

A dual-RPA based lateral flow strip for sensitive,on-site detection of CP4-EPSPS and Cry1Ab/Ac genes in genetically modified crops

Traditional transgenic detection methods require high test conditions and struggle to be both sensitive and efficient.In this study,a one-tube dual recombinase polymerase amplification(RPA)reaction system for CP4-EPSPS and Cry1Ab/Ac was proposed and combined with a lateral flow immunochromatographic assay,named“Dual-RPA-LFD”,to visualize the dual detection of genetically modified(GM)crops.In which,the herbicide tolerance gene CP4-EPSPS and the insect resistance gene Cry1Ab/Ac were selected as targets taking into account the current status of the most widespread application of insect resistance and herbicide tolerance traits and their stacked traits.Gradient diluted plasmids,transgenic standards,and actual samples were used as templates to conduct sensitivity,specificity,and practicality assays,respectively.The constructed method achieved the visual detection of plasmid at levels as low as 100 copies,demonstrating its high sensitivity.In addition,good applicability to transgenic samples was observed,with no cross-interference between two test lines and no influence from other genes.In conclusion,this strategy achieved the expected purpose of simultaneous detection of the two popular targets in GM crops within 20 min at 37°C in a rapid,equipmentfree field manner,providing a new alternative for rapid screening for transgenic assays in the field.

Concave Cooling Control Method for Hot-rolled Strip

Hot rolled strips usually have higher strength and lower plasticity at the ends, and the mechanical properties are distributed unevenly along the length direction. Such phenomena are caused by the different cooling rates between the end and the center. The ends of the coiled strip cool down faster than the center, inducing finer grains in the sections. Furthermore, the center of the coil is kept at high temperature for longer time, which affects the precipitation of the carbides and creates the different mechanical properties from the ends. In this paper, the temperature field of the strip during cooling was simulated to discover the characteristics of the temperature change and the effect on mechanical properties. Based on the analysis, a concept of concave cooling control was introduced and implemented in the production. Results indicated that applying the concave cooling control method could significantly improve the uniformity of the properties and promote the quality of the products.

Effect of phosphorus content on interfacial heat transfer and film deposition behavior during the high-temperature simulation of strip casting

The interfacial wettability and heat transfer behavior are crucial in the strip casting of high phosphorus-containing steel.A hightemperature simulation of strip casting was conducted using the droplet solidification technique with the aims to reveal the effects of phosphorus content on interfacial wettability,deposited film,and interfacial heat transfer behavior.Results showed that when the phosphorus content increased from 0.014wt%to 0.406wt%,the mushy zone enlarged,the complete solidification temperature delayed from1518.3 to 1459.4℃,the final contact angle decreased from 118.4°to 102.8°,indicating improved interfacial contact,and the maximum heat flux increased from 6.9 to 9.2 MW/m2.Increasing the phosphorus content from 0.081wt%to 0.406wt%also accelerated the film deposition rate from 1.57 to 1.73μm per test,resulting in a thickened naturally deposited film with increased thermal resistance that advanced the transition point of heat transfer from the fifth experiment to the third experiment.

High-resolution imaging of magnetic fields of banknote anti-counterfeiting strip using fiber diamond probe

Counterfeiting of modern banknotes poses a significant challenge,prompting the use of various preventive measures.One such measure is the magnetic anti-counterfeiting strip.However,due to its inherent weak magnetic properties,visualizing its magnetic distribution has been a longstanding challenge.In this work,we introduce an innovative method by using a fiber optic diamond probe,a highly sensitive quantum sensor designed specifically for detecting extremely weak magnetic fields.We employ this probe to achieve high-resolution imaging of the magnetic fields associated with the RMB 50denomination anti-counterfeiting strip.Additionally,we conduct computer simulations by using COMSOL Multiphysics software to deduce the potential geometric characteristics and material composition of the magnetic region within the anti-counterfeiting strip.The findings and method presented in this study hold broader significance,extending the RMB 50 denomination to various denominations of the Chinese currency and other items that employ magnetic anti-counterfeiting strips.These advances have the potential to significantly improve and promote security measures in order to prevent the banknotes from being counterfeited.

Similarity evaluation model for the internal defect detection of strip steel

An internal defect meter is an instrument to detect the internal inclusion defects of cold-rolled strip steel.The detection accuracy of the equipment can be evaluated based on the similarity of the multiple detection data obtained for the same steel coil.Based on the cosine similarity model and eigenvalue matrix model,a comprehensive evaluation method to calculate the weighted average of similarity is proposed.Results show that the new method is consistent with and can even replace artificial evaluation to realize the automatic evaluation of strip defect detection results.

Application of multi-scale feature extraction to surface defect classification of hot-rolled steels

Feature extraction is essential to the classification of surface defect images. The defects of hot-rolled steels distribute in different directions. Therefore, the methods of multi-scale geometric analysis （MGA） were employed to decompose the image into several directional subba^ds at several scales. Then, the statistical features of each subband were calculated to produce a high-dimensional feature vector, which was reduced to a lower-dimensional vector by graph embedding algorithms. Finally, support vector machine （SVM） was used for defect classification. The multi-scale feature extraction method was implemented via curvelet transform and kernel locality preserving projections （KLPP）. Experiment results show that the proposed method is effective for classifying the surface defects of hot-rolled steels and the total classification rate is up to 97.33%.

Research on Retained Austenite for Advanced Aluminum-containing Hot-rolled TRIP Steel

A new type of hot-rolled transformation induced plasticity （TRIP） steel with 2.3%AI was developed to replace conventional Si-bearing TRIP steel to improve surface quality of the steel sheet. The relationship between retained austenite volume fraction and hot-rolling processing was researched by Gleeble-2000 thermo-dynamic test for the Al-bearing steel. The experimental result showed that aluminum played an important role on retaining austenite and the volume fraction increased from 4.4% to 7.5% as coiling temperature increased from 350℃ to 450℃, while coiling temperature had a stronger effect on retaining austenite than finishing rolling temoerature.

Properties,Microstructures and Precipitate Morphology of Hot-rolled Interstital-Free(IF)Steel Sheets

In order to simplify production process and to decrease production cost of thicker cold-rolled iF steel sheets for deep drawing applications, a new hot-rolled IF steel sheet is developed through hot-rolling in or region. In this paper, properties, microstructures and precipitate morphology of hot-rolled iF steel sheets are described..

Effect of Reduction on Bonding Interface of Hot-rolled Wear-resistant Steel BTW1/Q345R Cladding Plate

Wear-resistant cladding plates consisting of a substrate（Q345 R） and a clad layer（BTW1） were bonded through hot rolling at the temperature of 1 200 ℃ and a rolling speed of 0.5 m/s. The microhardness of the cladding plate was also tested after being heat treated. The microstructure evolution on the interface of BTW1/Q345 R sheets under various reduction rates was investigated with a scanning electron microscope（SEM） and EBSD. It is found that the micro-cracks and oxide films on the interface disappear when the reduction is 80%, whereas the maximum uniform diffusion distance reaches 10 μm. As a result, a wide range of metallurgical bonding layers forms, which indicates an improved combination between the BTW1 and the Q345 R. Additionally, it is discovered that the unbroken oxide films on the interface are composed of Mn, Si or Cr at the reductions of 50% and 65%. The SEM fractography of tensile specimen demonstrates that the BTW1 has significant dimple characteristics and possesses lower-sized dimples with the increment in reduction, suggesting that the toughness and bonding strength of the cladding plates would be improved by the increase of reduction. The results reveal that a high rolling reduction causes the interfacial oxide film broken and further forms a higher-sized composite metallurgical bonding interface. The peak microhardness is achieved near the interface.

Rusting behavior and preventative measures of hot-rolled steel plates for automobile applications

As one of the important categories of hot-rolled products, hot-rolled steel plates for automobile applications generally undergo uniform corrosion or localized corrosion according to different environments of manufacturing, transportation and/or storage of the plates. General corrosion often takes place on the surface of a plate in the exterior part of a package, and only reduces the thickness of the plate and slightly increases the roughness of the surface; however, localized corrosion on the surface of a plate inside the package is likely to result in the formation of pit-like defects on the substrate of the plate, which cannot be removed thoroughly by normal acid pickling or sand blasting, and affects the application of the plate. This research report analyzes the phenomena and characteristics of the rusting behavior of hot- rolled steel plates for automobile applications, and the influencing factors are summaried. The corresponding preventative measures are proposed.

An Experimental Study on Constraint Cooling Process of Hot-rolled CoilS

In order to master mechanical property, surface quality and microstructure of constraint cooling (CC) coils undervarious water cooling parameters, more than 100 coils cooling experiments were done with real production process,of which is designed a cooling experimental instrument in the end. The experiments show that high initial coolingtemperature, discontinuous cooling style, and long cooling time can improve mechanical property of cooling coilsand shorten cooling time. The CC coils experiments cover the different steel grades, so that CC process effects onhot-rolled coils may be predicted and controlled actively.