Research on confirmation of basic technological parameters of tension levellers based on neural network and genetic algorithm

Confirmation of basic technological parameters of tension levellers is the most important factor of leveling strip. Up to now, most factories have used experts’ experience to decide these parameters, without any established rule to follow. For better quality of strip, a valid method is needed to decide technological parameters precisely and reasonably. In this paper, a method is used based on neural network and genetic algorithm. Neural network has a good ability to extract rules from work process of tension levellers. Then using neural network, which has learned from a lot of working samples, to be the evaluation of fitness, genetic algorithm could easily find the best or better technological parameters. At the end of this paper, examinations are given to show the effect of this method.

Enhancing corrosion resistance of ZK60 magnesium alloys via Ca microalloying: The impact of nanoscale precipitates

Enhancing corrosion resistance of Mg-Zn alloys with high strength and low cost was critical for broadening their large-scale practical applications. Here we prepared solutionized, peak-and over-aged ZK60 alloys with and without microalloying Ca(0.26 wt.%) to explore the effects of nanoscale precipitates on their corrosion behavior in detail via experimental analyses and theoretical calculations. The results suggested the peak-aged ZK60 alloy with Ca addition showed improved corrosion resistance in comparison with the alloys without Ca,owing to the contribution of Ca on the refinement of precipitates and increase in their number density. Although the precipitates and Mg matrix formed micro-galvanic couples leading to dissolution, the fine and dense precipitates could generate “in-situ pinning” effect on the corrosion products, forming a spider-web-like structure and improving the corrosion inhibition ability accordingly. The pinning effect was closely related to the size and number density of precipitates. This study provided important insight into the design and development of advanced corrosion resistant Mg alloys.

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.

Mechanism of high-energy pulsed current-assisted rolling of 08AL carbon steel ultra-thin strip

To improve the plastic deformation performance of a 08AL carbon steel ultra-thin strip,a pulsed electric field was integrated into the plastic processing of the ultra-thin strip,and the effects of high-energy current on its deformation ability were investigated.Current-assisted tensile tests were employed,and the results clarified that the pulsed current could reduce the activation energy of faults and promoted dislocation slip within grains and at grain boundaries,leading to a decrease in the deformation resistance of the metal and an increase in its plastic properties.Under the current density of 2.0 A/mm2,the yield strength,tensile strength,and elongation of the rolled sample reached 425 MPa,467 MPa,and 12.5%,respectively.During the rolling process,it was found that the pulsed current promoted the dynamic recrystallization of the ultra-thin strip,reduced its dislocation density and deformation resistance,and promoted the coordinated deformation of the metal.

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.

Processing map of as-cast 7075 aluminum alloy for hot working

The true stress-strain curves of as-cast 7075 aluminum alloy have been obtained by isothermal compression tests at temperatures of 300 500 ~C and strain rates of 0.01 10 s i. The plastic flow instability map is established based on Gegel B and Murthy instability criteria because the deformed compression samples suggest that the combination of the above two instability criteria has more comprehensive crack prediction ability. And the processing map based on Dynamic Mate- rial Model （DMM） of as-cast 7075 aluminum alloy has been developed through a superposition of the established instability map and power dissipation map. In terms of microstructure of the deformed samples and whether plastic flow is stable or not, the processing map can be divided into five areas： stable area with as-cast grain, stable area with homogeneous grain resulting from dynamic recovery, instability area with as-cast grain, instability area with the second phase and instability area with mixed grains. In consideration of microstructure characteristics in the above five areas of the processing map, the stable area with homogeneous grain resulting from dynamic recovery, namely the temperatures at 425465 ℃ and the strain rates at 0.01^-1 s^-1, is suggested to be suitable processing window for the as-cast 7075 aluminum alloy.

Preparation and Microstructure of ZrO_2-MoSi_2 Composite Powder and Compound Coating

In order to improve the lifetime of continuous casting,ZrO_2-MoSi_2 composite powder used for plasmaspraying was prepared via spray drying and vacuum sintering.The microstructure and characteristics of the powder were investigated by particle size analysis,scanning electron microscopy and X-ray diffraction,respectively.The results show that the average viscosity and settlement rate are 60.43 mPas and 1.86%,respectively,when adding ammonium polyacrylate as a dispersant and polyvinyl alcohol as a binder.The powder obtained at the solid content of 70 wt.%,the dispersant amount of 1wt.%,the binder of 10 wt.%,and the sintering temperature of 1200 "C has the spherical agglomerate and a moderate size,which can be melted on the composite coating surface with a good compactness via plasma-spraying.

Effect of hot rolling and cooling process on microstructure and properties of 2205/Q235 clad plate

The 2205/Q235 clad plate was fabricated by vacuum hot rolling with symmetrical assembling pattern of Q235/2205/2205/ Q235.The flow stress behavior and processing map of 2205 duplex stainless steel (DSS)were investigated by hot compressive tests on a Gleeble-3800 simulator.Then,thermal-mechanical coupled nonlinear finite element models of vacuum hot rolling and subsequent cooling process were established.From the simulation results,the influence of rolling reduction and rolling speed on hot deformation state of 2205 DSS in the assembled slab was disclosed and the optimal rolling parameters were presented.Meanwhile,the cooling rate of 2205 DSS under different cooling conditions and thicknesses of the clad plate was obtained.According to the numerical simulation results,pilot experiments were successfully carried out on a laboratory scale.The material universal testing machine,optical microscope,scanning electron microscope and energy-dispersive spectrometer were used to evaluate the mechanical properties and microstructure of bonding interface and 2205 DSS matrix for different rolling reduction and cooling processes.The results showed that with symmetrical assembling pattern,the approximate thermodynamic conditions can be established for 2205 DSS to avoid cracks in hot rolling process.When the rolling reduction increased from 10 to 40%,the shear strength of the bonding interface is increased from 120 to 530 MPa,and the uniform two-phase microstructure of 2205 DSS and satisfactory' mechanical properties can be obtained with cooling rate higher than 10℃/s between 1050 and 500℃ after rolling.