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.

Mechanism and control of nonuniform phase transformation of microalloyed dual-phase steel during cooling process after hot rolling

After cooling in the hot rolling process,the metallographic structure of microalloyed dual-phase steel is nonuniform along the rolling direction,while the thickness fluctuation of microalloyed dual-phase steel with a nonuniform metallographic structure will occur during cold rolling.The mechanism of nonuniform phase transformation of microalloyed dual-phase steels was studied during the cooling process after hot rolling,and the nonuniform phase transformation of microalloyed dual-phase steel was regulated during the cooling process after hot rolling through process optimization.First,the empirical equation of phase transformation temperature was measured by a dilatometer considering thermal expansion.Then,the phase field and temperature field of laminar cooling process were calculated to provide initial boundary conditions for the finite element model.After that,the coupling finite element model of the temperature phase transformation of the strip steel in coiling transportation process was established.The simulation results show that the different thermal contact conditions of the microalloyed dual-phase steel during coil transportation lead to uneven cooling of the coil,which leads to nonuniform transformation of the coil along the rolling direction.In addition,by prolonging the time interval from coiling to unloading,the phenomenon of nonuniform phase transformation of microalloyed dual-phase steel can be effectively controlled.The simulation results are applied to industrial production.The application results show that prolonging the time interval from coiling to unloading can effectively improve the nonuniform phase transformation of microalloyed dual-phase steel in the cooling process after hot rolling.

Additive manufacturing of multi-morphology graded titanium scaffolds for bone implant applications

Porous Titanium scaffolds have attracted widespread attention as bone implants for avoiding the stress shielding effect and promoting bone-in-growth.In this study,multi-morphology graded scaffolds hy-bridized by Primitive and Gyroid structures with porosity of 50,60,and 70%were designed(denoted as PG50,PG60,and PG70,respectively)and fabricated by selective laser melting.The simulation results showed that the maximum von-Mises stress of hybridized scaffolds increased from 504.22 to 884.24 MPa with porosity.The permeability and average pore size of multi-morphology PG50,PG60,and PG70 were in the range of 3.58×10^(-9)-5.50×10^(-9) m^(2) and 568.1-758.4μm,respectively.The microstructure of multi-morphology graded scaffolds consisted of a fully martensiticα′phase.Tested permeabilities of PG50 and PG60 were 3.27×10^(-9) and 4.35×10^(-9) m^(2),respectively,which were within the range of human bone(0.01-12.1×10^(-9) m^(2)).Elastic modulus and compressive yield strength of PG50 and PG60 ranged within 5.93^(-9).86 and 180.06-257.08 MPa,respectively.Therein,the PG50 not only exhibited a similar elastic modulus compared to human cortical bone(10.1 GPa)but also had higher strength(257.08 vs 131 MPa).The results of in vitro biocompatibility assay showed that PG50 and PG60 have better cyto-compatibility than mono-morphology scaffolds with the same porosity.Taken together,PG50 is promising to be used for the restoration of bone defects due to its excellent mechanical properties,appropriate per-meability,and good cytocompatibility.

MDA-JITL model for on-line mechanical property prediction

Mechanical performance prediction is the key to the transformation and upgrading of steel enterprises to intelligent manufacturing.Due to time-varying manufacturing data,the traditional prediction model of mechanical properties of hotrolled strip may cause performance degradation or even failure in its use.An MDA-JITL model was thus proposed to handle the modeling problem of complex time-varying data.Relevant parameters were first chosen and normalized.Then,a distance measurement method combining the importance of data attributes and time characteristics was designed to select the most suitable samples for on-line local modeling.After that,using the chosen dataset,a linear local model was created to predict target sample.Finally,an uncertainty evaluation method was designed to evaluate the uncertainty of prediction results.Furthermore,the appropriate dataset partition and off-line simulation experiment scheme were created based on the peculiarities of hot-rolling production.The suggested model performs much better than the classic global model when applied to actual production data from a steel plant.The stability of its prediction accuracy is demonstrated in a simulation prediction for up to five months.Moreover,there is a high link between the uncertainty evaluation metrics and the prediction error of the model,reducing the field sampling rate by 30%in industrial applications in the latest year.

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.

Effect of post rolling stress on phase transformation behavior of microalloyed dual phase steel

The slow phase transformation of microalloyed dual phase steel makes the nonuniform stress and temperature fields during the post rolling cooling process have a significant impact on the phase transformation process.Given the relatively slow phase transformation of DP780 steel within the microalloyed dual phase steel series,the influence of stress on the phase transformation behavior of DP780 steel was investigated.To quantify the nonuniform thermal and stress conditions in the steel coil,a thermo-mechanical coupled finite element model of the hot-rolled strip cooling process was established.Based on the simulation data,DP780 steel was chosen as the research material,and Gleeble 3500 thermal simulation equipment was used for experimental validation.The thermal expansion curves were analyzed through regression to establish the dynamic model of DP780 steel phase transformation under stress.Subsequently,metallographic analysis was conducted to determine phase transformation type and grain size of DP780 steel.The results confirmed that the stress promotes the occurrence of semi-diffusion-type bainite transformation.Furthermore,an appropriate level of stress facilitates the growth of bainitic grains,while the increased stress inhibits the growth of ferritic grains.

Microstructure evolution in large billet during reduction pretreatment based on laboratory experiments

The reduction pretreatment process has been proposed to improve the center quality of large billet and reduce the rolling ratio.The microstructure evolution during the reduction pretreatment was further understood.The austenite grains were refined after the reduction pretreatment experiment,especially those at the center of the billet.The effects of strain and strain rate on the average grain size were dependent on the deformation temperature.At a strain rate of 0.01 s-1 and 1200°C,the newly formed strain-free austenite grains grew very fast as the strain continued to increase,which resulted in the coarsening of austenite grains.The calculation results of the microstructure evolution model showed that at the same deformation temperature,the evolution curves of average grain size with different strain rates had the intersection points.With the increase in temperature,the position of intersection point moved to the downward direction of strain.The simulation results showed that when the reduction amount increased to 20%,the average grain size at the center was smaller than that near the surface.It could be inferred that when the reduction amount greatly exceeded 20%,the dynamic recrystallization at the center was mostly completed,and the austenite grain growth would become the main mechanism.

Identification of FIR systems under difference-driven scheduled quantized observations

In networked system identification,how to effectively use communication resources and improve convergence speed is the focus of attention.However,there is an inherent contradiction between the two tasks.In this paper,the event-driven communication is used to save communication resources for the identification of finite impulse response systems,and the input design is carried out to meet the requirements of convergence speed.First,a difference-driven communication is proposed.Then,the performance of the communication mechanism is analyzed,and the calculation method of its communication rate is given.After that,according to the communication rate and the convergence rate of the identification algorithm,the input design problem is transformed into a constrained optimization problem,and the algorithm for finding the optimal solution is given.In addition,considering the case that the output is quantized by multiple thresholds,the way to calculate its communication rate is given and the influence of threshold number on communication rate is discussed.Finally,the effectiveness of the algorithm is verified by simulation.