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.

二维矩形Strip Packing问题的算法研究与改进

二维矩形Strip Packing问题的约束条件及目标函数与基本型二维矩形Packing问题类似,都是在有限的矩形容器中,有效地摆放各个矩形块,以最大化容器利用率为目标。为了解决这一NP-hard问题,该文在邓见凯、王磊提出的拟人型全局优化算法的基础上进行了深入的算法研究与改进。针对Strip Packing问题特点,提出了QHG(Quasi-Human Group)算法,其核心改进涵盖了多个方面,包括扩充初始点集合、删除和替换评价标准以及扩大邻域空间搜索范围。和单个局部极小值点的迭代相比,对局部极小值点集合进行迭代所生成布局优度更高,跳坑策略用于跳出局部极小值点,将搜索引向有希望的区域,优美度枚举有望进一步提高布局优度。通过这些措施,QHG算法更好地模拟人类决策过程,提高了全局搜索的效率。为评估QHG算法性能,对8组标准问题实例(C组、N组、NT组、CX组、NP组、ZDF组、2sp组、bwmv组)进行了大量实验。实验结果表明,QHG算法生成的布局优度优于当前国际文献中的几种较先进算法,展现了其在Strip Packing问题上的卓越性能。

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.

Mechanical properties and interfacial characteristics of 6061 Al alloy plates fabricated by hot-roll bonding

This work aims to investigate the mechanical properties and interfacial characteristics of 6061 Al alloy plates fabricated by hotroll bonding(HRB)based on friction stir welding.The results showed that ultimate tensile strength and total elongation of the hot-rolled and aged joints increased with the packaging vacuum,and the tensile specimens fractured at the matrix after exceeding 1 Pa.Non-equilibrium grain boundaries were formed at the hot-rolled interface,and a large amount of Mg_(2)Si particles were linearly precipitated along the interfacial grain boundaries(IGBs).During subsequent heat treatment,Mg_(2)Si particles dissolved back into the matrix,and Al_(2)O_(3) film remaining at the interface eventually evolved into MgO.In addition,the local IGBs underwent staged elimination during HRB,which facilitated the interface healing due to the fusion of grains at the interface.This process was achieved by the dissociation,emission,and annihilation of dislocations on the IGBs.

Soybean maize strip intercropping:A solution for maintaining food security in China

The practice of intercropping leguminous and gramineous crops is used for promoting sustainable agriculture,optimizing resource utilization,enhancing biodiversity,and reducing reliance on petroleum products.However,promoting conventional intercropping strategies in modern agriculture can prove challenging.The innovative technology of soybean maize strip intercropping(SMSI)has been proposed as a solution.This system has produced remarkable results in improving domestic soybean and maize production for both food security and sustainable agriculture.In this article,we provide an overview of SMSI and explain how it differs from traditional intercropping.We also discuss the core principles that foster higher yields and the prospects for its future development.

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.

Molecular investigation into the transformation of recalcitrant dissolved organic sulfur in refinery sour water during stripping process

Refinery sour water primarily originates from the tops of towers in various units and coker condensate,and cannot be discharged directly to a wastewater treatment plant due to high levels of chemical oxygen demand(COD)and organic sulfur contents.Even after the recovery of H_(2)S from the sour water by the stripping process,the effluent still contains a high concentration of dissolved organic sulfur(DOS),which can have a huge bad influence.While chemical composition of dissolved organic matter(DOM)in refinery wastewater has been extensively studied,the investigation of recalcitrant DOS from sour waters remains unclear.In the present study,chemical composition of sour water DOMs(especially DOS)was investigated using fluorescence spectroscopy(excitation-emission matrix,EEM)and mass spectrometry,including gas chromatography-mass spectrometry(GC-MS)and high-resolution Orbitrap MS.The GC-MS and EEM results showed that volatile and low-aromaticity compounds were effectively removed during the stripping process,while compounds with high hydrophilicity and humification degree were found to be more recalcitrant.The Orbitrap MS results showed that weak-polar oxygenated sulfur compounds were easier to be removed than oxygenated compounds.However,the effluent still contained significant amounts of sulfur-containing compounds with multiple sulfur atoms,particularly in the form of highly unsaturated and aromatic compounds.The Orbitrap MS/MS results of CHOS-containing compounds from the effluent indicate that the sulfur atoms may exist as sulfonates,disulfide bonds,thioethers.Understanding the composition and structure of sour water DOS is crucial for the development of effective treatment processes that can target polysulfide compounds and minimize their impact on the environment.

A simple route for preparation of TRIP-assisted Si-Mn steel with excellent performance using direct strip casting

The complex producing procedures and high energy-consuming limit the large-scale production and application of advanced high-strength steels(AHSSs).In this study,the direct strip casting(DSC)technology with unique sub-rapid solidification characteristics and cost advantages was applied to the production of low-alloy Si-Mn steel with the help of quenching&partitioning(Q&P)concept to address these issues.Compared this method with the conventional compact strip production(CSP)process,the initial microstructure formed under different solidification conditions and the influence of heat treatment processes on the final mechanical properties were in-vestigated.The results show that the initial structure of the DSC sample is a dual-phase structure composed of fine lath martensite and bainite,while the initial structure of the CSP sample consists of pearlite and ferrite.The volume fraction and carbon content of retained austenite(RA)in DSC samples are usually higher than those in CSP samples after the same Q&P treatment.DSC samples typically demonstrate better comprehensive mechanical properties than the CSP sample.The DSC sample partitioned at 300℃ for 300 s(DSC-Pt300)achieves the best comprehensive mechanical properties,with yield strength(YS)of 1282 MPa,ultimate tensile strength(UTS)of 1501 MPa,total elongation(TE)of 21.5%,and product of strength and elongation(PSE)as high as 32.3 GPa·%.These results indicate that the excellent mechanical properties in low-alloy Si-Mn steel can be obtained through a simple process(DSC-Q&P),which also demonstrates the superiority of DSC technology in manufacturing AHSSs.

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.

Analysis of spot defects on the surface of a cold-rolled Fe-36%Ni alloy strip

Many spot defects were found on the surface of a cold-rolled Fe-36%Ni alloy strip produced in a factory,which seriously affected the surface quality of the product.Through metallographic microscopy and scanning electron microscopy analyses,it was found that the spot defects were caused by the residual oxide layer on the surface of the cold-rolled Fe-36%Ni alloy strip after hydrogen annealing.By properly increasing the grinding amount of the blank before cold rolling to remove the oxide layer,the spot defects on the surface of the cold-rolled strip were effectively eliminated,and the surface quality of the product was ensured.

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.