Prediction of metadynamic softening in a multi-pass hot deformed low alloy steel using artificial neural network

The metadynamic softening behaviors in 42CrMo steel were investigated by isothermal interrupted hot compression tests. Based on the experimental results, an efficient artificial neural network (ANN) model was developed to predict the flow stress and metadynamic softening fractions. The effects of deformation parameters on metadynamic softening behaviors in the hot deformed 42CrMo steel have been investigated by the experimental and predicted results from the developed ANN model. Results show that the effects of deformation parameters, such as strain rate and deformation temperature, on the softening fractions of metadynamic recrystallization are significant. However, the strain (beyond the peak strain) has little influence. A very good correlation between experimental and predicted results indicates that the excellent capability of the developed ANN model to predict the flow stress level and metadynamic softening, the metadynamic recrystallization behaviors were well evidenced.     

Effects of strain on the workability of a high strength low alloy steel in hot compression

Based on the experimental results from the hot compression tests of 42CrMo steel, the efficiencies of power dissipation and instability parameter were evaluated. The effects of strain on the efficiency of power dissipation and instability parameter of 42CrMo steel have been discussed in detail. Processing maps were constructed by superimposition of the instability map over the power dissipation map. The dynamic recrystallization domains and instable zones were identified in the processing map. The effects of strain on microstructural evolutions were correlated with the processing maps. According to the 3D processing maps, the optimum domain of hot deformation is in the temperature range of 1050–1150 °C and strain rate range of 0.01–3 s⁻¹, with its peak efficiency of 32% at about 1140 °C and 0.23 s⁻¹, which are the optimum hot working parameters.     

Modeling of flow stress of 42CrMo steel under hot compression

The compressive deformation behavior of 42CrMo steel was investigated at temperatures from 850 °C to 1150 °C and strain rates from 0.01 s^?1 to 50 s^?1 on a Gleeble-1500 thermo-simulation machine. The results show that the true stress–true strain curves exhibit peak stresses at small strains, then the flow stresses decrease monotonically until high strains, showing a dynamic flow softening. The stress level decreases with increasing deformation temperature and decreasing strain rate, which can be represented by a Zener–Hollomon parameter in an exponent-type equation. A revised model describing the relationships of the flow stress, strain rate and temperature of the 42CrMo steel at elevated temperatures is proposed by compensation of strain. The stress–strain relations of 42CrMo steel predicted by the proposed models agree well with experimental results.     

Microstructural evolution in 42CrMo steel during compression at elevated temperatures

In order to study the workability and to optimize the processing parameters for 42CrMo steel hot forming, the hot compressive tests of 42CrMo steel were performed in the temperature range of (850-1150) °C at strain rates of (0.01-50) s^− 1 and deformation degrees of (10-60)% on Gleeble-1500 thermo-simulation machine. The effects of processing parameters, including the strain rate, forming temperature and deformation degree, on the microstructures of 42CrMo steel were investigated by metallurgical analysis. The results show that the average grain size of the deformed 42CrMo steel increases with the forming temperature and decreases with the deformation degree and strain rate. In a word, the grain size of hot compressive 42CrMo steel is dependent on the forming temperature, strain and strain rate, also on Zener-Hollomon parameter.     

Hot tensile deformation behaviors and constitutive model of 42CrMo steel

The hot tensile deformation behaviors of 42CrMo steel are studied by uniaxial tensile tests with the temperature range of 850–1100 °C and strain rate range of 0.1–0.0001 s⁻¹. The effects of hot forming process parameters (strain rate and deformation temperature) on the elongation to fracture, strain rate sensitivity and fracture characteristics are analyzed. The constitutive equation is established to predict the peak stress under elevated temperatures. It is found that the flow stress firstly increases to a peak value and then decreases, showing a dynamic flow softening. This is mainly attributed to the dynamic recrystallization and material damage during the hot tensile deformation. The deformation temperature corresponding to the maximum elongation to fracture increases with the increase of strain rate within the studied strain rate range. Under the strain rate range of 0.1–0.001 s⁻¹, the localized necking causes the final fracture of specimens. While when the strain rate is 0.0001 s⁻¹, the gage segment of specimens maintains the uniform macroscopic deformation. The damage degree induced by cavities becomes more and more serious with the increase of the deformation temperature. Additionally, the peak stresses predicted by the proposed model well agree with the measured results.     

Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25Cr–1Mo steel

Hot compression tests of modified 2.25Cr–1Mo steel were conducted on a Gleeble-3500 thermo-mechanical simulator at the temperatures ranging from 1173 to 1473 K with the strain rate of 0.01–10 s⁻¹ and the height reduction of 60%. Based on the experimental results, an artificial neural network (ANN) model and constitutive equations were developed to predict the hot deformation behavior of modified 2.25Cr–1Mo steel. A comparative evaluation of the constitutive equations and the ANN model was carried out. It was found that the relative errors based on the ANN model varied from −4.63% to 2.23% and those were in the range from −20.48% to 12.11% by using the constitutive equations, and the average root mean square errors were 0.62 MPa and 7.66 MPa corresponding to the ANN model and constitutive equations, respectively. These results showed that the well-trained ANN model was more accurate and efficient in predicting the hot deformation behavior of modified 2.25Cr–1Mo steel than the constitutive equations.     

Artificial neural network approach to predict the flow stress in the isothermal compression of as-cast TC21 titanium alloy

Isothermal compression of as-cast TC21 titanium alloy at the deformation temperatures ranging from 1000 to 1150 °C with an interval of 50 °C, the strain rates ranging from 0.01 to 10.0 s^?1 and the height reduction of 60% was conducted on a Gleeble-3500 thermo-mechanical simulator. Based on the experimental results, an artificial neural network (ANN) model with a back-propagation learning algorithm was developed to predict the flow stress in isothermal compression of as-cast TC21 titanium alloy. In the present ANN model, the strain, strain rate and deformation temperature were taken as inputs, and the flow stress as output. According to the predicted and experimental results, the maximum error and average error between the predicted flow stress and the experimental data were 4.60% and 1.58%, respectively. Comparison of the predicted results of flow stress based on the ANN model and those using the regression method, it was found that the relative error based on the ANN model varied from ?1.41% to 4.60% and that was in the range from ?13.38% to 10.33% using the regression method, and the average absolute relative error were 1.58% and 5.14% corresponding to the ANN model and regression method, respectively. These results have sufficiently indicated that the ANN model is more accurate and efficient in terms of predicting the flow stress of as-cast TC21 titanium alloy.     

Constitutive analysis to predict high temperature flow stress in 20CrMo continuous casting billet

The experimental true strain–true stress data from isothermal hot compression tests on a Gleeble-1500D thermal simulation machine, across a wide range of temperatures (1173–1373 K) and strain rates (1.5 × 10⁻³–1.5 × 10⁻² s⁻¹), were employed to study the deformation behavior and develop constitutive equations of 20CrMo alloy continuous casting billet steel. The objective was to obtain the relational expression for deformation activation energy and material constants as a function of true strain and the constitutive equation for high temperature deformation of 20CrMo based on the hyperbolic sine form model. A correlation coefficient of 0.988 and an average absolute relative error between the experimental and the calculated flow stress of 8.40% have been obtained. This indicates that the constitutive equations can be used to accurately predict the flow behavior of 20CrMo alloy steel continuous casting billet during high temperature deformation.     

Constitutive modeling for elevated temperature flow behavior of 42CrMo steel

In order to study the workability and establish the optimum hot formation processing parameters for 42CrMo steel, the compressive deformation behavior of 42CrMo steel was investigated at the temperatures from 850 to 1150 °C and strain rates from 0.01 to 50 s⁻¹ on Gleeble-1500 thermo-simulation machine. The results show that the true stress–true strain curves exhibit a peak stress at a small strain, after which the flow stresses decrease monotonically until high strains, showing a dynamic flow softening. The flow stress obtained from experiments consists of four different stage, i.e., Stage I (Work hardening stage), Stage II (Stable stage), Stage III (Softening stage) and Stage IV (Steady stage). The stress level decreases with increasing deformation temperature and decreasing strain rate, which can be represented by a Zener–Hollomon parameter in an exponent-type equation. A revised model describing the relationships of the flow stress, strain rate and temperature of 42CrMo steel at elevated temperatures is proposed by compensation of strain and strain rate. The stress–strain values of 42CrMo steel predicted by the proposed model well agree with experimental results, which confirmed that the revised deformation constitutive equation gives an accurate and precise estimate for the flow stress of 42CrMo steel.     

Constitutive equations to predict high temperature flow stress in a Ti-modified austenitic stainless steel

The experimental stress–strain data from isothermal hot compression tests, in a wide range of temperatures (1123–1523 K) and strain rates (10⁻³–10² s⁻¹), were employed to develop constitutive equations in a Ti-modified austenitic stainless steel. The effects of temperature and strain rate on deformation behaviors were represented by Zener-Holloman parameter in an exponent type equation. The influence of strain was incorporated in the constitutive analysis by considering the effect of strain on material constants. The constitutive equation (considering the compensation of strain) could precisely predict the flow stress only at 0.1 and 1 s⁻¹ strain rates. A modified constitutive equation (incorporating both the strain and strain rate compensation), on the other hand, could predict the flow stress throughout the entire temperatures and strain rates range except at 1123 K in 10 and 100 s⁻¹. The breakdown of the constitutive equation at these processing conditions is possibly due to adiabatic temperature rise during high strain rate deformation.     

An ANFIS model for the prediction of flow stress of Ti600 alloy during hot deformation process

In this paper, an adaptive network-based fuzzy inference system (ANFIS) model has been established to predict the flow stress of Ti600 alloy during hot deformation process. This network integrates the fuzzy inference system with a back-propagation learning algorithm of neural network. The experimental results were obtained from Gleeble-1500 thermal-simulator at deformation temperatures of 800–1100 °C, strain rates of 0.001–10 s^?1, and height reduction of 70%. In establishing this ANFIS model, strain rate, deformation temperature and the strain are entered as input parameters while the flow stress are used as output parameter. After the training process, the fuzzy membership functions and the weight coefficient of the network can be optimized. A comparative evaluation of the predicted and the experimental results has shown that the ANFIS model used to predict the flow stress of Ti600 titanium alloy has a high accuracy and with absolute relative error is less than 17.39%. Moreover, the predicted accuracy of flow stress during hot deformation process of Ti600 titanium alloy using ANFIS model is higher than using traditional regression method, indicating that the ANFIS model was an easy and practical method to predict flow stress for Ti600 titanium alloy.     

Constitutive analysis to predict high-temperature flow stress in modified 9Cr–1Mo (P91) steel

Constitutive analysis for hot working of modified 9Cr–1Mo (P91) ferritic steel was carried out employing experimental stress–strain data from isothermal hot compression tests, in a wide range of temperatures (1123–1373 K), strains (0.1–0.5) and strain rates (10⁻³–10² s⁻¹). The effects of temperature and strain rate on deformation behaviour were represented by Zener–Hollomon parameter in an exponent-type equation. The influence of strain was incorporated in the constitutive equation by considering the effect of strain on different material constants. Activation energy was found to vary with strain in the range 369–391 kJ mol⁻¹. The developed constitutive equation (considering the compensation of strain) could predict flow stress of modified 9Cr–1Mo steel over the specified hot working domain with very good correlation and generalization.     

Artificial neural network modeling to predict the high temperature flow behavior of an AZ81 magnesium alloy

In the present work, the capability of artificial neural network (ANN) has been evaluated to describe and to predict the high temperature flow behavior of a cast AZ81 magnesium alloy. Toward this end, a set of isothermal hot compression tests were carried out in temperature range of 250–400 °C and strain rates of 0.0001, 0.001 and 0.01 s⁻¹ up to a true strain of 0.6. The flow stress was primarily predicted by the hyperbolic laws in an Arrhenius-type of constitutive equation considering the effects of strain, strain rate and temperature. Then, a feed-forward back propagation artificial neural network with single hidden layer was established to investigate the flow behavior of the material. The neural network has been trained with an in-house database obtained from hot compression tests. The performance of the proposed models has been evaluated using a wide variety of statistical indices. The comparative assessment of the results indicates that the trained ANN model is more efficient and accurate in predicting the hot compressive behavior of cast AZ81 magnesium alloy than the constitutive equations.     

Hot deformation behavior and microstructure evolution of twin-roll-cast Mg–2.9Al–0.9Zn alloy: A study with processing map

The hot deformation behavior and microstructure evolution of twin-roll-cast of Mg–2.9Al–0.9Zn–0.4Mn (AZ31) alloy has been studied using the processing map. The tensile tests were conducted in the temperature range of 150–400 °C and the strain rate range of 0.0004–4 s⁻¹ to establish the processing map. The different efficiency domains and flow instability region corresponding to various microstructural characteristics have been identified as follows: (i) the continuous dynamic recrystallization (CDRX) domain in the range of 200–280 °C/≤0.004 s⁻¹ with fine grains which provides a potential for warm deformation such as deep drawing; (ii) the discontinuous dynamic recrystallization (DDRX) domain around 400 °C at high strain rate (0.4 s⁻¹ and above) with excellent elongation which can be utilized for forging, extrusion and rolling; (iii) the grain boundary sliding (GBS) domain at slow strain rate (below 0.004 s⁻¹) above 350 °C appears abundant of cavities, which result in fracture and reduce the ductility of the adopted material; and (iv) the flow instability region which locates at the upper left of the processing map shows the metallographic feature of flow localization.     

Prediction of compressive properties of closed-cell aluminum foam using artificial neural network

The design of artificial neural network (ANN) is motivated by analogy of highly complex, non-linear and parallel computing power of the brain. Once a neural network is significantly trained it can predict the output results in the same knowledge domain. In the present work, ANN models are developed for the simulation of compressive properties of closed-cell aluminum foam: plateau stress, Young’s modulus and energy absorption capacity. The input variables for these models are relative density, average pore diameter and cell anisotropy ratio. Database of these properties are the results of the compression tests carried out on aluminum foams at a constant strain rate of 1 × 10⁻³ s⁻¹. The prediction accuracy of all the three models is found to be satisfactory. This work has shown the excellent capability of artificial neural network approach for the simulation of the compressive properties of closed-cell aluminum foam.     

Constitutive modeling for flow stress of 55SiMnMo bainite steel at hot working conditions

The hot deformation behavior of 55SiMnMo bainite steel was studied through isothermal hot compression tests conducted using a Gleeble 3500 at 950–1100 °C, with strain rates of 0.01 s⁻¹ to 10 s⁻¹. A constitutive equation was established using the experimental results to describe the stress–strain relationship based on the dislocation density variation, considering the influence of the dynamic softening mechanism. When dynamic recovery is the only softening mechanism, a constitutive equation for flow stress was obtained from the variation of the dislocation density during hot deformation based on work hardening and dynamic recovery. When dynamic recrystallization occurs, the relationship between the dislocation density and the volume fraction of dynamic recrystallization was used to predict the flow stress after the peak. The reliability of the model was verified through a comparison between the predicted flow stress curves from the model and the experimental data.     

Analysis of high temperature deformation behavior of a high Nb containing TiAl based alloy

The effects of deformation temperature and strain rate on the hot deformation behaviors of as-cast Ti-45Al-8.5Nb-(W,B,Y) alloy were investigated. The results indicated that when deformation temperature is below 1250 °C, the flow stress decreases with the increase of deformation temperature and decrease of strain rate, once deformation temperature reaches 1250 °C, the flow stress is not sensitive to strain rate any more. A neural network model was established to predict the flow stress of this high Nb containing TiAl based alloy during hot deformation. The predicted flow stress curves are in good agreement with experimental results.     

Artificial neural network modelling to predict hot deformation behaviour of as HIPed FGH4169 superalloy

Abstract

The hot deformation behaviour of as HIPed FGH4169 superalloy was studied by single stroke compression test on MMS-200 test machine at the temperatures of 950–1050°C and the strain rates of 0·004–10 s^?1. Based on the experimental results, a back-propagation artificial neural network model and constitutive equation method were established to predict the flow stress of FGH4169 superalloy. The predictability of two different models was compared. The correlation coefficients of experimental and predicted flow stress with the trained BP ANN model and constitutive equation were 0·9995 and 0·9808 respectively. The average root mean square error (RMSE) values of the trained ANN model and constitutive equation are 0·39 and 2·21 MPa respectively. And the average absolute relative error (AARE) values of the trained ANN model and constitutive equation are 1·79 and 7·47% respectively. The results showed that the ANN model is an effective tool to predict the flow stress in comparison with constitutive equation.     

High temperature deformation behavior of a near alpha Ti600 titanium alloy

The high temperature deformation behavior of a near alpha Ti600 titanium alloy was investigated with isothermal compression tests at temperatures ranging from 800 to 1000 °C and strain rates ranging from 0.001 to 10.0 s⁻¹. The apparent activation energy of deformation was calculated to be 620.0 kJ mol⁻¹, and constitutive equation that described the flow stress as a function of the strain rate and deformation temperature was proposed for high temperature deformation of Ti600 titanium alloy in the α + β phase region. The processing map was calculated to evaluate the efficiency of the forging process in the temperatures and strain rates investigated and to recognize the instability regimes. High efficiency values of power dissipation over 55% obtained under the conditions of strain rate lower than 0.01 s⁻¹ and temperature about 920 °C was identified to represent superplastic deformation in this region. Plasticity instability was expected in the regime of strain rate higher than 1 s⁻¹ and the entire temperature range investigated.     

Numerical simulation for stress/strain distribution and microstructural evolution in 42CrMo steel during hot upsetting process

Based on experimental results, the dynamic recrystallization mathematical models of 42CrMo steel were derived. The effects of strain rates on the strain/stress distribution and microstructural evolution in 42CrMo steel during hot upsetting process were simulated by integrating the thermo-mechanical coupled finite element model. The results show that the deformation of the specimen is inhomogeneous, and the degree of the deformation inhomogeneity decreases with the increase of strain rates. The distribution of the effective stress in the specimen is also inhomogeneous, and the locus of the maximum effective stress changes with the variations of strain rates. The dynamic recrystallization volume fraction decreases with the increase of strain rates. The distribution of the dynamic recrystallization grain is inhomogeneous in the deformed specimen, and the average dynamic recrystallization grain size decreases as the strain rate is increased. A good agreement between the predicted and experimental results confirmed that the derived dynamic recrystallization mathematical models can be successfully incorporated into the finite element model to predict the microstructural evolution in the hot upsetting process for 42CrMo steel.