Application of a new feature extraction and optimization method to surface defect recognition of cold rolled strips

Considering that the surface defects of cold rolled strips are hard to be recognized by human eyes under high-speed circumstances, an automatic recognition technique was discussed. Spectrum images of defects can be got by fast Fourier transform （FFF） and sum of valid pixels （SVP）, and its optimized center region, which concentrates nearly all energies, are extracted as an original feature set. Using genetic algorithm to optimize the feature set, an optimized feature set with 51 features can be achieved. Using the optimized feature set as an input vector of neural networks, the recognition effects of LVQ neural networks have been studied. Experiment results show that the new method can get a higher classification rate and can settle the automatic recognition problem of surface defects on cold rolled strips ideally.

Research on the properties of laser welded joints of aluminum killed cold rolled steel

Aluminum killed cold rolled steel used for automobiles was welded in this paper by using CO 2 laser with wavelength 10.6μm.The experiment shows that high quality of welding can be realized at welding speed of 4 500mm/min by optimizing the parameters.The strength and hardness of laser welded joints for aluminum killed cold rolled steel increased compared to those of the base metal while the formability decreased.Forming limit diagram of joint material indicated that the laser weld seam should avoid the maximum deformation area of automobile parts during the designing period for the position of weld seam.

Online application of automatic surface quality inspection system to finishing line of cold rolled strips

An automatic surface quality inspection system installed on a finishing lineof cold rolled strips is introduced. The system is able to detect surface defects on cold rolledstrips, such as scratches, coil breaks, rusts, roll imprints, and so on. Multiple CCD area scancameras were equipped to capture images of strip surface simultaneously. Defects were detectedthrough 'Dark-field illumination' which is generated by LED illuminators. Parallel computationtechnique and fast processing algorithms were developed for real-time data processing. Theapplication to the production line shows that the system is able to detect defects effectively.

Surface Inspection System for Cold Rolled Strips Based on Image ProcessingTechnique

A new surface inspection system for cold rolled strips based on image processing is introduced. The system is equipped withtwo different illumination structures and CCD matrix cameras. The structure and image processing of the inspection system are described. Some efficient algorithms for image processing and classification are presented. The system is tested with strip samples fromcold rolling plants. The results show that the system can detect and recognize six common defects of cold rolled strips successfully.

Research on the design of cold rolled ultra high strength sheet steel

This study researches cold rolled ultra high strength martensitic steel processed by water quenching. It is found that both the quenching and overageing temperatures greatly influence the mechanical properties of martensitic steel. A tensile strength of 1500 MPa can be obtained from 0.2% C-1.8% Mn steel by soaking at 840℃,quenching at 700℃ and overageing at 200℃ for several minutes. The continuous cooling transformation （CCT） diagram reveals that full martensite can be obtained at a cooling rate of 100℃/s or higher; and at a cooling rate of 3 - 10℃/s,austenite barely decomposes at 700℃. For steel with 0.2% carbon and less manganese, austenite decomposition occurs before it is cooled to 700℃ at a cooling rate of 3 - 10℃/s, which leads to lower tensile strength. It is possible to reduce the manganese content of the 1500 MPa martensitic steel by increasing the quenching temperature. To increase the quenching temperature,the control of flatness during water quenching becomes a major concern.

Nucleation of Cold Rolled FeCo Alloy during Annealing and Its Influence on the Formation of Recrystallization Texture

The orientation distribution of recrystallization grains formed during annealing, as well as their misorientation relationship to the deformation matrix in cold rolled FeCo alloy have been investigated. It was found that most of the recrystallization nuclei were located near the boundary area with rather random orientations, and their misorientation angles to the deformation matrix were generally very high. However a few nuclei were also observed inside the deformation grains, to which they had very similar orientations. Therefore the misorientation angles between the nuclei and the deformation matrix were generally very low. The orientation and the misorientation distributions of the nuclei have very strong influence on the recrystallization process which could result in a very weak recrystallization texture. The corresponding mechanism is discussed.

Applied principle of minimum potential energy in analyzing buckle phenomenon of cold rolled strip

When solving buckling type based on minimum potential energy, it is first to make hypothesis for strip buckling type. Under the simple strain condition, buckling type and strain distribution have a certain similarity, so the hypothesis is reasonable comparatively. However, under the complicated strain condition, it is difficult to give more reasonable buckling type. Moreover, the existing algorithms usually ignore the effect which the transverse stress and the shear stress have on the buckling type. After assuming strip was only affected by shear stress for the edge wave and affected by both transverse stress and the shear stress for the center wave in the paper, the buckling form of strip under simple strain situation was calculated. It was seen from the calculating result that wave height and half wavelength were smaller than those of the existing algorithms, and the wave height and half wavelength of edge wave were all bigger than those of center wave in the same stress distribution. Secondly, a more reasonable hypothesis method of buckling type for the complicated stress distribution was put forward. After analyzing, the result showed that it was more reasonable by using the optimizing algorithm.

Effect of continuous annealing parameters on the mechanical properties and microstructures of a cold rolled dual phase steel

A cold rolled dual phase （DP） steel with the C-Si-Mn alloy system was trial-produced in the laboratory, utilizing a Gleeble-3800 thermal simulator. The effects of continuous annealing parameters on the mechanical properties and microstructures of the DP steel were investigated by mechanical testing and microstructure observation. The results show that soaking between 760 and 820℃ for more than 80 s, rapid cooling at the rate of more than 30℃/s from the quenching temperature between 620 and 680℃, and overaging lower than 300℃ are beneficial for the mechanical properties of DP steels. An appropriate proportion of the two phases is one of the key factors for the favorable properties of DP steels. If the volume fraction of martensite and, thereby, free dislocations are deficient, the tensile strength and n value of DP steels will decrease, whereas, the yield strength will increase. But if the volume fraction of martensite is excessive to make it become a dominant phase, the yield and tensile strength will increase, whereas, the elongation will decrease obviously. When rapid cooling rate is not fast enough, pearlite or cementite will appear, which will degrade the mechanical properties. Even though martensite is sufficient, if it is decomposed in high temperature tempering, the properties will he unsatisfied.

Recrystallization behavior of cold rolled Al-Zn-Mg-Cu fabricated by twin roll casting

The Al-Zn-Mg-Cu alloy strip can be successfully fabricated by twin roll casting. In order to determine the effect of thickness reduction and heat treatment temperature on the recrystallization behavior, the strips were rolled and subsequently heat treated under various conditions. As a result, a fine grained microstructure （average grain size -13 μm, average grain aspect ratio -1.7） and high mechanical properties （UTS ≥360 MPa, δ ≥20%） were obtained by cold rolling with thickness reduction of 60% and heat treatment at 500 ℃ for 1 h. Also, the effect of the microstructure on mechanical properties of the Al-Zn-Mg-Cu alloy strip was discussed. Consequently, the low cost and high strength Al-Zn-Mg-Cu alloy sheet can be fabricated by twin roll casting by proper thermo-mechanical processes.

Analysis on Width Spread of Cold Rolled Strip

Width spread is usually considered in hot rolling, nevertheless, it can be ignore in cold rolling. In order to control the crown and flatness better simultaneously and realize the decoupling of crown and flatness, the transverse displacement function of strip is defined and deduced. The factors that affects the width spread are analyzing with the function. According to the unchanged principle of volume before and after rolling, the flatness model which considers the width spread is deduced. Through the model, the transverse metal flowing of different stands and different thickness is analyzing, it is found that the width spread is biggest in cold rolling at the No. 1 stand because of the maximum thickness and reduction and the minimum deformation resistance. It gives a good foundation for the decoupling of crown and flatness.

Intelligent representation method of image flatness for cold rolled strip

Real flatness images are the bases for flatness detection based on machine vision of cold rolled strip.The characteristics of a real flatness image are analyzed,and a lightweight strip location detection(SLD)model with deep semantic segmentation networks is established.The interference areas in the real flatness image can be eliminated by the SLD model,and valid information can be retained.On this basis,the concept of image flatness is proposed for the first time.An image flatness representation(IFAR)model is established on the basis of an autoencoder with a new structure.The optimal structure of the bottleneck layer is 16×16×4,and the IFAR model exhibits a good representation effect.Moreover,interpretability analysis of the representation factors is carried out,and the difference and physical meaning of the representation factors for image flatness with different categories are analyzed.Image flatness with new defect morphologies(bilateral quarter waves and large middle waves)that are not present in the original dataset are generated by modifying the representation factors of the no wave image.Lastly,the SLD and IFAR models are used to detect and represent all the real flatness images on the test set.The average processing time for a single image is 11.42 ms,which is suitable for industrial applications.The research results provide effective methods and ideas for intelligent flatness detection technology based on machine vision.

Data-driven flatness intelligent representation method of cold rolled strip

A high-accuracy flatness prediction model is the basis for realizing flatness control.Real flatness is typically reflected as the strain distribution,which is a vector.However,it is difficult to obtain ideal results if the real flatness is directly used as the output value of the flatness intelligent prediction model.Thus,it is necessary to seek an abstract representation method of real flatness.For this reason,two new intelligent flatness representation models were proposed based on the autoencoder of unsupervised learning theory:the flatness autoencoder representation(FAR)model and the flatness stacked sparse autoencoder representation(FSSAR)model.Compared with the traditional Legendre fourth-order polynomial representation model,the representation accuracies of the FAR and FSSAR models are significantly improved,better representing the flatness defects,like the double tight edge.The optimal number of bottleneck layer neurons in the FAR and FSSAR models is 5,which means that five basic patterns can accurately represent real flatness.Compared with the FAR model,the FSSAR model has higher representation accuracy,although the flatness basic pattern is more abstract,and the physical meaning is not clear enough.Furthermore,the accuracy of the FAR model is slightly lower than that of the FSSAR model.However,it can automatically learn the flatness basic pattern with a very clear physical meaning for both the theoretical and real flatness,which is an optimal intelligent representation method for flatness.

Prediction of mechanical properties of cold rolled strip based on improved extreme random tree

Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.

Microstructure and mechanical properties of cold-rolled Ti_(50)Ni_(47)Fe_3 shape memory alloy

Mechanical and shape memory properties of a Ti50Ni47Fe3 alloy annealed at 450-750 °C for 1 h after a cold-rolled reduction of 25% were investigated by phase transformation analysis and microstructure characterization using tensile tests, Vickers hardness tests, electrical resistivity-temperature tests, SEM and TEM. From the results of the tensile, it can be inferred that the fracture stress and yield stress decreased and the fracture elongation increased as the annealing temperature increased for the rolled Ti50Ni47Fe3 alloy. They reached stead values when the temperature was above 650 °C. The change in Vickers hardness corresponded to the change in the fracture stress and yield stress. The electrical resistivity-temperature curves suggest that a two- stage martensitic transformation（B2-R-B19′） occurred during cooling and heating. The transformation temperatures decreased to lower temperatures when the annealing temperature was increased and maintained the same after the annealing temperature reached 650 °C. TEM revealed the distinct processes occurring at elevated temperatures： recovery, polygonization, and recrystallization.

Influence of Mo on Dynamic Continuous Cooling Transformation of 1000 MPa Cold Rolled Dual Phase Steel

The expanding curves of two kinds of 1000 MPa ultra-high strength cold rolled dual phase steels,which were C-Si-Mn-Cr and C-Si-Mn-Cr-Mo steel respectively,were detected on Gleeble-1500 thermal-mechanical simulator at different cooling rates.Combined with metallographic and hardness methods,the continuous cooling transformation curves (CCT) of the two steels were obtained.The results showed that Mo could raise the A r3 temperature,and strongly restrain the pearlite and bainite transformation.The reason for this was the interaction that the addition of Mo could increase the chemical driving force of ferrite transformation and the activation energy for the diffusion of carbon in austenite,which could decelerate the ferrite transformation.The hardness of the two steels was similar in the cooling rates range of this experiment and got higher with the increase of the cooling rates.When the cooling rates were above 7 ℃/s,the hardness almost kept constant because the most part of the microstructure was martensite.

Application of automatic surface inspection system in cold-rolled strip production

The detection and classification of real-time surface defects play an important role in automotive sheet inspection and production. In this paper, an automatic surface inspection system （ASIS） based on signal processing in Baosteel NO. 4 cold-rolled plant is briefly presented. We demonstrate that the strip surface defect properties such as image, type, pitch, and position can be accurately calculated and classified by the automatic surface inspection system. In the manufacturing of the high-quality cold-rolled strips, it is necessary that the real-time surface defects can be detected and transferred by the automatic surface inspection system combined with annealing lines and recoiling lines.

Fatigue Property of Hot Rolled and Cold Rolled Strips

Tension-tension fatigue properties of hot rolled and cold rolled strips with same contents and sizes were measured by using group test method at room temperature in air. The results showed that the fatigue properties of the hot rolled strips were obviously higher than those of the cold rolled strips. The hot rolled strips with similar or higher tensile strength exhibited superior fatigue property over the cold rolled strips. Fracture morphologies observed using scanning electronic microscope （SEM） showed that the hot rolled strips exhibited larger fracture areas, indicating a slightly lower plasticity, and more even fracture microstructure and stable properties. It is feasible and reliable to replace cold rolled strips with hot rolled strips.

Effect of the Heat-treatment Temperature on the Mechanical Properties and Microstructural Evolution of Cold-rolled Twinning-induced Plasticity Steel

TWIP steels with 70% cold-rolled reduction were heated at 500, 600, 700, 800, 900, 1000, and 1100 ℃. Then, the properties before and after heating were examined through tensile and hardness experiments. The microstructures were also analyzed by optical microscopy and transmission electron microscopy. The relationship between the properties and microstructure was examined as well. Finally, the evolution process of cold-rolled microstructures during heating was discussed in detail. Moreover, some conclusions can be drawn, and the heating evolution characteristics are described.

COLD ROLLING AND RECRYSTALLIZATION TEXTURE OF CROSS SHEAR ROLLED COMMERCIAL COPPER

The texture change along the normal direction to rolling plane of cross shear rolled commer- cial copper has been studied by means of two step method for ODF caleulation and computer simulation.The texture of cross shear rolling of copper is similar in primary components to that of conventional cold rolling,but the scattering degree and direction of the texture are dif- ferent,due to the residual shear strain change in different position along the normal to rolling plane.It seems that no more effect of the shear strain upon the recrystallization texture.

Tensile Mechanical Behavior of Cold Rolled Si-Mn Steel Under Different Strain Rates

Tensile mechanical behavior of cold rolled Si-Mn steel after TRIP (TRansformation Induced Plasticity) and DP (Dual Phase) treatment were investigated under different strain rates.The dynamic tensile test was carried out using the rotation disk bar-bar tensile impact apparatus.At static tension test condition,the values of total elongation for TRIP steel was approximately 2-3 times higher than DP steel because of TRIP effect;the DP steel showed a higher tensile strength because of 39.6vol% martensite in the matrix.The results of tension test at high strain rate condition were different.For the studied steel,the elongation increased with increasing strain rate due to softening of matrix caused by adiabatic heating;in addition,TRIP steel at low strain rate was always higher than that at high strain rate because progressive strain induced retained austenite was suppressed at high strain rate.