scholarly journals Machine Learning-Based Models for the Estimation of the Energy Consumption in Metal Forming Processes

Metals ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 833
Author(s):  
Irene Mirandola ◽  
Guido A. Berti ◽  
Roberto Caracciolo ◽  
Seungro Lee ◽  
Naksoo Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Finite Element ◽  
Energy Consumption ◽  
Metal Forming ◽  
Mutual Influence ◽  
Rolling Process ◽  
Ring Rolling ◽  
Gradient Boosting ◽  
Average Error ◽  
Ring Rolling Mill

This research provides an insight on the performances of machine learning (ML)-based algorithms for the estimation of the energy consumption in metal forming processes and is applied to the radial-axial ring rolling process. To define the mutual influence between ring geometry, process settings, and ring rolling mill geometries with the resulting energy consumption, measured in terms of the force integral over the processing time (FIOT), FEM simulations have been implemented in the commercial SW Simufact Forming 15. A total of 380 finite element simulations with rings ranging from 650 mm < DF < 2000 mm have been implemented and constitute the bulk of the training and validation datasets. Both finite element simulation settings (input), as well as the FI (output), have been utilized for the training of eight machine learning models, implemented with Python scripts. The results allow defining that the Gradient Boosting (GB) method is the most reliable for the FIOT prediction in forming processes, being its maximum and average errors equal to 9.03% and 3.18%, respectively. The trained ML models have been also applied to own and literature experimental cases, showing a maximum and average error equal to 8.00% and 5.70%, respectively, thus proving once again its reliability.

scholarly journals Modeling of ring billets rolling on radial-axial ring-rolling mill

2020 ◽  
Vol 63 (8) ◽  
pp. 665-673
Author(s):  
S. A. Snitko ◽  
A. V. Yakovchenko ◽  
V. V. Pilipenko ◽  
N. I. Ivleva
Keyword(s):  
Finite Element ◽  
Flow Stress ◽  
Finite Element Modeling ◽  
Metal Flow ◽  
Rolling Process ◽  
Ring Rolling ◽  
Element Modeling ◽  
Ring Diameter ◽  
Ring Rolling Mill

On the basis of radial-axial rolling of ring billets, resource-saving technologies for metal forming have been created. Determining the rational parameters of this process is the actual scientific and technical task at development of new profiles. The method of three-dimensional finite element modeling is the most effective tool for improving the technological conditions of ring rolling process. However, as practice has shown, the finite element modeling method requires adaptation to each process of metal forming. This is the subject of the present work. The expediency of using dependency for calculating the metal flow stress for finite-element modeling of ring-rolling processes is substantiated. This dependence was developed on the basis of a theory that takes into account the chemical composition of structural carbon steel, its temperature, strain rate, accumulated deformation, and also the processes of dynamic transformation of the metal structure during hot rolling. A computer program for automated determination of dependency parameters has been developed. The analysis of the accuracy of the obtained dependence was performed in relation to the experimental data. In the course of these calculations, the method of automated determination of the metal flow stress was used by spline interpolation of the experimental data included in the computer database of digital information for a particular steel grade. The average relative error of calculated values of the metal flow stress was 8 % relative to the experimental ones. An improved method is proposed for calculating the parameters of ring billets rolling and reaching the required growth rate of the ring diameter implemented in a finite element modeling system, which is similar to the way the control system of the ring-rolling mill works in solving the same problem (reaching the required growth rate of the ring diameter) when implemented appropriate rolling in practice. When calculating the size of the compression, the iterative process and the method of half division were used. The average deviations of calculated values of the parameters of ring billets rolling from the experimental did not exceed 12.4 %, which makes it possible to apply the proposed approach to study the patterns of the rings rolling process and to improve the rolling technology.

Utilizing Data-Driven Models to Predict Brittleness in Tuscaloosa Marine Shale: A Machine Learning Approach

2021 ◽  
Author(s):  
Jamal Ahmadov
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Brittleness Index ◽  
Estimation Methods ◽  
Gradient Boosting ◽  
Average Error ◽  
Support Vector ◽  
Marine Shale ◽  
Effective Manner ◽  
Selection Of

Abstract The Tuscaloosa Marine Shale (TMS) formation is a clay- and liquid-rich emerging shale play across central Louisiana and southwest Mississippi with recoverable resources of 1.5 billion barrels of oil and 4.6 trillion cubic feet of gas. The formation poses numerous challenges due to its high average clay content (50 wt%) and rapidly changing mineralogy, making the selection of fracturing candidates a difficult task. While brittleness plays an important role in screening potential intervals for hydraulic fracturing, typical brittleness estimation methods require the use of geomechanical and mineralogical properties from costly laboratory tests. Machine Learning (ML) can be employed to generate synthetic brittleness logs and therefore, may serve as an inexpensive and fast alternative to the current techniques. In this paper, we propose the use of machine learning to predict the brittleness index of Tuscaloosa Marine Shale from conventional well logs. We trained ML models on a dataset containing conventional and brittleness index logs from 8 wells. The latter were estimated either from geomechanical logs or log-derived mineralogy. Moreover, to ensure mechanical data reliability, dynamic-to-static conversion ratios were applied to Young's modulus and Poisson's ratio. The predictor features included neutron porosity, density and compressional slowness logs to account for the petrophysical and mineralogical character of TMS. The brittleness index was predicted using algorithms such as Linear, Ridge and Lasso Regression, K-Nearest Neighbors, Support Vector Machine (SVM), Decision Tree, Random Forest, AdaBoost and Gradient Boosting. Models were shortlisted based on the Root Mean Square Error (RMSE) value and fine-tuned using the Grid Search method with a specific set of hyperparameters for each model. Overall, Gradient Boosting and Random Forest outperformed other algorithms and showed an average error reduction of 5 %, a normalized RMSE of 0.06 and a R-squared value of 0.89. The Gradient Boosting was chosen to evaluate the test set and successfully predicted the brittleness index with a normalized RMSE of 0.07 and R-squared value of 0.83. This paper presents the practical use of machine learning to evaluate brittleness in a cost and time effective manner and can further provide valuable insights into the optimization of completion in TMS. The proposed ML model can be used as a tool for initial screening of fracturing candidates and selection of fracturing intervals in other clay-rich and heterogeneous shale formations.

Effect of the Guide-Roll Positional Angle to the Stability of Radial Ring Rolling

2007 ◽  
Vol 561-565 ◽  
pp. 1875-1878 ◽  
Author(s):  
Yong Xing Hao ◽  
Lin Hua ◽  
Gui Shan Chen ◽  
Dao Ming Wang
Keyword(s):  
Position Angle ◽  
Rolling Process ◽  
Ring Rolling ◽  
Positional Angle ◽  
The Mean ◽  
The Stability ◽  
Ring Rolling Mill ◽  
Ring Rolling Process ◽  
Ring Blank ◽  
Evaluating Method

Non-stability factors affect stability of radial ring rolling process, and lead to fluctuating of ring position. This decreases rolling precision. Evaluating stability of the process is very important. A stability evaluating method is proposed. The stability can be measured with the mean square root of sequence of oscillation of ring geometrical centerline displacement. Using ABAQUS/Explicit, the stability is analyzed. It is showed that guide-roll position angle has the significant effect to the stability. If guide-roll is located at the tangential position to the ring’s fringe, the stability will vary with the angle between two planes. One passes through axes of guide roll and ring blank, and another passes through axes of drive roll and ring blank. The stability is highest when guide roll is situated at the position angle of 100˚to 130˚at exit side of ring rolling mill.

A Comparison between Isothermal and Coupled Thermo-Mechanical FE Analyses of the Ring Rolling Process

2011 ◽  
Vol 264-265 ◽  
pp. 235-240
Author(s):  
Nassir Anjami ◽  
Ali Basti
Keyword(s):  
Finite Element ◽  
Rolling Process ◽  
Ring Rolling ◽  
Continuous Change ◽  
Rigid Plastic ◽  
Mechanical And Physical Properties ◽  
Prediction And Control ◽  
3D Deformation ◽  
Ring Rolling Process ◽  
And Control

Ring rolling process, especially hot rolling is characterized by 3D deformation, continuous change of thickness and height, high nonlinearity, non-steady flow and asymmetry. It involves both mechanical and thermal behaviors. Most mechanical and physical properties and boundary conditions are temperature related. The heat flow and stress analysis cannot be analyzed separately. In this study, both isothermal and coupled thermo-mechanical (CTM) 3D rigid-plastic finite element (FE) models of the hot ring rolling (HRR) process are developed to investigate their differences in accurately and quickly predicting the process. The results show that the latter should be more advantageous to the more accurate prediction and control of microstructure and properties of the ring.

Solver for Finite Element Analysis of Ring Rolling Process

2011 ◽  
Vol 338 ◽  
pp. 251-254
Author(s):  
Xue Bin Zhang ◽  
Qiong Wan ◽  
Zhi Gang Li
Keyword(s):  
Finite Element ◽  
Control Method ◽  
Rolling Process ◽  
Ring Rolling ◽  
Metal Ring ◽  
Central Difference ◽  
Element Analysis ◽  
Explicit Finite Element ◽  
Return Algorithm ◽  
Ring Rolling Process

A dynamic explicit finite element solver is developed for numerical simulation of metal ring rolling process, which is a complex process of material nonlinearity, geometric nonlinearity and contact nonlinearity. An elastro-plastic dynamic explicit finite element equation and central difference algorithm are used. To control hourglass, a stable matrix hourglass control method is used to ensure energy balance in the simulation. Two-step method of global search and local search is used to reduce the contact judging time. In the elastic-plastic stress updating, tangent forecasting and radical return algorithm are used to eliminate the stress deviate from the yield surface. The accuracy and stability of the solver is verified by comparison of two ring rolling processes with the experimental results.

Investigation on Constant and Variable Feed Speeds Effects in Ring Rolling Process Using 3D FEM

2011 ◽  
Vol 264-265 ◽  
pp. 1776-1781 ◽  
Author(s):  
Nassir Anjami ◽  
Ali Basti
Keyword(s):  
Finite Element ◽  
Rolling Process ◽  
Ring Rolling ◽  
Outer Diameter ◽  
Fe Model ◽  
Feed Speed ◽  
3D Fem ◽  
Cold Ring Rolling ◽  
Plastic Deformation Behavior ◽  
Ring Rolling Process

Although cold ring rolling (CRR) process is largely used in the manufacturing of profiled rings like bearing races, research on this purpose has been scant. In this study, based on a validated finite element (FE) model, CRR process is simulated regarding the variable and constant feed speeds of the mandrel roll which lead to constant and variable values of the ring's diameter growth rates respectively using a 3D rigid-plastic finite element method (FEM). Major technological problems involved in the process including plastic deformation behavior, strain distribution and its uniformity, Cockcroft and Latham damage field and final outer diameter of ring are fully investigated. The results of simulations would provide a good basis for process control especially feed speed controlled mills and guiding the design and optimization of both cold and hot ring rolling process.

ENERGY SAVING TECHNOLOGIES IN POWER SUPPLY OF SMART BUILDINGS USING ARTIFICIAL INTELLIGENCE

2020 ◽  
pp. 29-37
Author(s):  
E. Yu. Shchetinin
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
Energy Consumption ◽  
Energy Saving ◽  
Commercial Buildings ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Digital Measurement ◽  
Computer Algorithms ◽  
Smart Buildings

Intelligent energy saving and energy efficiency technologies are the modern large-scale global trend in the energy systems development. The demand for smart buildings is growing not only in the world, but also in Russia, especially in the market of construction and operation of large business centers, shopping centers and other business projects. Accurate cost estimates are important for promoting energy efficiency construction projects and demonstrating their economic attractiveness. The growing number of digital measurement infrastructure, used in commercial buildings, led to increase access to high-frequency data that can be used for anomaly detection and diagnostics of equipment, heating, ventilation, and optimization of air conditioning. This led to the use of modern and efficient machine learning methods that provide promising opportunities to obtain more accurate forecasts of energy consumption of the buildings, and thus increase energy efficiency. In this paper, based on the gradient boosting model, a method of modeling and forecasting the energy consumption of buildings is proposed and computer algorithms are developed to implement it. Energy consumption dataset of 300 commercial buildings was used to assess the effectiveness of the proposed algorithms. Computer simulations showed that the use of these algorithms has increased the accuracy of the prediction of energy consumptionin more than 80 percent of cases compared to other machine learning algorithms.

Thermo-Mechanical Coupled Analysis of Heavy Shell Ring Hot Rolling Mill with Two Drive Rolls

2012 ◽  
Vol 452-453 ◽  
pp. 200-205
Author(s):  
Jian Liang Sun ◽  
Hong Min Liu ◽  
Yan Peng ◽  
Gang Liu ◽  
Yan Liu
Keyword(s):  
Hot Rolling ◽  
Rolling Mill ◽  
Rolling Process ◽  
Ring Rolling ◽  
Coupled Analysis ◽  
Test Machine ◽  
Hot Rolling Mill ◽  
Shell Ring ◽  
Ring Rolling Mill ◽  
Ring Rolling Process

The heavy shell ring rolling mill which produces the large shell ring used in nuclear power, large-scale hydrogenation reactor and coal liquefaction reactor was taken as subject investigated. Because the size of shell ring is very large and the material of shell ring is special, the double drive rolls was taken in the shell ring rolling mill. Based on the elastic-plastic FEM and MARC software platform, the three dimensional thermal-mechanical coupled model of shell ring rolling process was built in this paper. First, the heat simulation text of the shell ring material has been carried out on the Gleeble-3500 thermal simulation test machine and the material properties were obtained. Then, considering the characteristics of heavy shell ring hot rolling mill with two drive rolls, the key problems such as geometry, material and thermo-boundary conditions were solved, the thermo-mechanical coupled finite element model of heavy shell ring hot rolling has been establised. At last, based on explicit dynamic FEM, the thermo-mechanical simulation of heavy shell ring rolling process was made. The stress field, strain field and temperature field were studied, the metal plastic deformation and its influence factors were investigated. The conclusions are agreement with the real rolling process. The conclusions are significant for designing equipments of shell ring rolling mill and developing new rolling schedule.

Sign in / Sign up

Export Citation Format

Share Document