scholarly journals Motor Load Balancing with Roll Force Prediction for a Cold-Rolling Setup with Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 1367
Author(s):  
Sangho Lee ◽  
Youngdoo Son
Keyword(s):  
Load Balancing ◽  
Cold Rolling ◽  
Rolling Process ◽  
Machine Learning Algorithms ◽  
Data Set ◽  
Hot Rolling Process ◽  
Major Trend ◽  
Motor Load ◽  
Set Up ◽  
Available Information

The use of machine learning algorithms to improve productivity and quality and to maximize efficiency in the steel industry has recently become a major trend. In this paper, we propose an algorithm that automates the setup in the cold-rolling process and maximizes productivity by predicting the roll forces and motor loads with multi-layer perceptron networks in addition to balancing the motor loads to increase production speed. The proposed method first constructs multilayer perceptron models with all available information from the components, the hot-rolling process, and the cold-rolling process. Then, the cold-rolling variables related to the normal part set-up are adjusted to balance the motor loads among the rolling stands. To validate the proposed method, we used a data set with 70,533 instances of 128 types of steels with 78 variables, extracted from the actual manufacturing process. The proposed method was found to be superior to the physical prediction model currently used for setups with regard to the prediction accuracy, motor load balancing, and production speed.

Mechanics Analysis and Numerical Simulation on the Precise Forming Process of Spline Cold Rolling

2008 ◽  
Vol 575-578 ◽  
pp. 416-421 ◽  
Author(s):  
Yong Tang Li ◽  
Jian Li Song ◽  
Da Wei Zhang ◽  
Quan Gang Zheng
Keyword(s):  
Numerical Simulation ◽  
Cold Rolling ◽  
Theoretical Basis ◽  
Rolling Force ◽  
Rolling Process ◽  
Average Pressure ◽  
Forming Process ◽  
Mechanics Analysis ◽  
Simulation And Experiment ◽  
Set Up

The forming process of spline cold rolling was analyzed. The unit average pressure, contact area and rolling force in the cold rolling precision forming process were analyzed and solved. The mechanical and mathematical model has been set up on the basis of the analysis. The numerical simulation of spline cold rolling process was carried out. The results obtained by comparison of theoretical analysis, numerical simulation and experiment provide a theoretical basis for the study and application of spline cold rolling process.

Effect of Ferritic Hot Rolling Process on Microstructure and Properties of IF Steel

2020 ◽  
Vol 993 ◽  
pp. 505-512
Author(s):  
Wen Gao Chang ◽  
Wei Yu ◽  
Huan Yang ◽  
Zeng Qiang Man ◽  
Yun Fei Cao
Keyword(s):  
Cold Rolling ◽  
Hot Rolling ◽  
Rolling Texture ◽  
Rolling Process ◽  
Continuous Annealing ◽  
If Steel ◽  
Coiling Temperature ◽  
Microstructure And Properties ◽  
Hot Rolling Process ◽  
Cold Rolling And Annealing

The effect of ferritic hot rolling process on microstructure and properties of Ti microalloyed IF steel was investigated. The hot rolling-coiling, cold rolling and continuous annealing processes of ferritic zone were physically simulated. The influence of thermal deformation (finishing rolling temperature, coiling temperature) on the structure, texture and forming properties of Ti-If steel was studied through tensile test, EBSD, XRD and other analytical methods. The results showed that the recrystallization occurred after hot rolling and coiling in the ferritic region. Weak α-fiber and weak γ-fiber were obtained in the central layer of hot rolling plates, and the strength of γ-fiber was higher when finished rolling at low temperature. α-fiber and weak γ-fiber were strengthened after cold rolling. After annealing, the α-fiber was weakened and the γ-fiber was strengthened, and the γ-fiber became the main texture. The larger and more uniform grain size and better mechanical properties were obtained by IF steel finished rolling and coiling at high temperature and after continuous annealing, reaching yield strength of 106 MPa, tensile strength of 297 MPa, elongation rate of 52%, n value of 0.26 and r value of 2.3. The hot rolling texture is hereditary. If the more γ-fiber is formed after hot rolling, the more γ-fiber recrystallization texture is formed after cold rolling and annealing.

scholarly journals Advances in Machine Learning Detecting Changeover Processes in Cyber Physical Production Systems

2020 ◽  
Vol 4 (4) ◽  
pp. 108
Author(s):  
Bastian Engelmann ◽  
Simon Schmitt ◽  
Eddi Miller ◽  
Volker Bräutigam ◽  
Jan Schmitt
Keyword(s):  
Machine Learning ◽  
Production Control ◽  
Production Systems ◽  
Heterogeneous Data ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Medium Size ◽  
Data Set ◽  
Set Up ◽  
Cyber Physical Production Systems

The performance indicator, Overall Equipment Effectiveness (OEE), is one of the most important ones for production control, as it merges information of equipment usage, process yield, and product quality. The determination of the OEE is oftentimes not transparent in companies, due to the heterogeneous data sources and manual interference. Furthermore, there is a difference in present guidelines to calculate the OEE. Due to a big amount of sensor data in Cyber Physical Production Systems, Machine Learning methods can be used in order to detect several elements of the OEE by a trained model. Changeover time is one crucial aspect influencing the OEE, as it adds no value to the product. Furthermore, changeover processes are fulfilled manually and vary from worker to worker. They always have their own procedure to conduct a changeover of a machine for a new product or production lot. Hence, the changeover time as well as the process itself vary. Thus, a new Machine Learning based concept for identification and characterization of machine set-up actions is presented. Here, the issue to be dealt with is the necessity of human and machine interaction to fulfill the entire machine set-up process. Because of this, the paper shows the use case in a real production scenario of a small to medium size company (SME), the derived data set, promising Machine Learning algorithms, as well as the results of the implemented Machine Learning model to classify machine set-up actions.

Recent Development in Process Control for Aluminum Cold Rolling: Features of the Fata Hunter’s hSystem®

1999 ◽  
Author(s):  
Pier Michele Cattelino ◽  
Corrado Licata ◽  
Luigi Rèpaci
Keyword(s):  
Cold Rolling ◽  
Process Simulation ◽  
Rolling Process ◽  
Simulation Techniques ◽  
Adaptive Capabilities ◽  
Simulation And Control ◽  
Set Up ◽  
And Control ◽  
Fine Tune ◽  
Level 2

Abstract Aim of the present paper is to highlight Fata Hunter’s hSystem®, emphasizing its self adaptive capabilities, process simulation and control together with simulation techniques which allowed the system developers to set up and fine tune the whole automation package. In the framework of the implementation of the automation package, and especially of level 2, particular attention has been put upon cold rolling process modelization. To this aspect the second part of this paper has been dedicated.

Microstructural Evolution in Al-Sc and Al-Sc-Zr Alloys

2007 ◽  
Vol 546-549 ◽  
pp. 629-632 ◽  
Author(s):  
Zhi Guo Chen ◽  
Simon P. Ringer ◽  
Zi Qiao Zheng ◽  
Jue Zhong
Keyword(s):  
Cold Rolling ◽  
Microstructural Evolution ◽  
Hot Rolling ◽  
Rolling Process ◽  
Small Particles ◽  
The Core ◽  
Hot Rolling Process ◽  
Zr Alloys

The microstructures of Al-0.2Sc and Al-0.2Sc-0.12Zr alloys have been investigated.The results show that Al3Sc and Al3(Sc1-xZrx) dispersoids exist in as-rolled Al-0.2Sc and Al-0.2Sc-0.12Zr alloy respectively, and their orientation is (001)α║(001)dispersoid, [010]α║[010]dispersoid.The Al3Sc particles in as-rolled Al-0.2Sc were precipitated from hot rolling process, while the larger Al3(Sc1-xZrx) particles in as-rolled Al-0.2Sc-0.12Zr from the solidification, and the small particles also from hot rolling process. There is segregation of Sc and Zr in the Al3(Sc1-xZrx) dispersoid, and Sc is rich in the outside shell while Zr rich in the core of the particles. It is believed that the grain and subgrain boundaries can be pinned by the Al3Sc particles when annealed after cold-rolling, and this may lead to restricting the recrystallization of the Sc-containing alloys.And it’s not until the dissolution of Al3Sc that the recrystallization can happen in this kind of alloys.

Research on the Influence of Hot Strip Shape to Ribbing Defect

2014 ◽  
Vol 494-495 ◽  
pp. 377-382
Author(s):  
Zeng Shuai Qiu ◽  
An Rui He ◽  
Chao Chao Chen ◽  
Jun Ming Peng ◽  
Xiao Yong Tang
Keyword(s):  
Cold Rolling ◽  
Hot Rolling ◽  
Rolling Process ◽  
Hot Rolling Process ◽  
Strip Shape ◽  
Hot Strip ◽  
Uneven Wear

Aim at solving the problem of ribbing defect is found on cold rolling strips which is caused by bad hot strip shape, analyze the reason from the hot rolling process, and study out that there are some reasons such as uneven wear of rolls can lead to ribbing defect. Roll contour, roll shifting model, rolling plan were optimized and got a geart effect: the hot strip shape being better, the production being more stable, the ratio of ribbing defect decreasing obviously (from 2.2% to 0.3%). The quality of their product has been improved a lot.

Identify Compounds' Target Against Alzheimer's Disease Based on In-Silico Approach

2019 ◽  
Vol 16 (3) ◽  
pp. 193-208 ◽  
Author(s):  
Yan Hu ◽  
Guangya Zhou ◽  
Chi Zhang ◽  
Mengying Zhang ◽  
Qin Chen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Small Molecule ◽  
Characteristic Curve ◽  
Machine Learning Algorithms ◽  
Learner Model ◽  
Mao B ◽  
Number Of Patients ◽  
Sar Model ◽  
Set Up

Background: Alzheimer's disease swept every corner of the globe and the number of patients worldwide has been rising. At present, there are as many as 30 million people with Alzheimer's disease in the world, and it is expected to exceed 80 million people by 2050. Consequently, the study of Alzheimer’s drugs has become one of the most popular medical topics. Methods: In this study, in order to build a predicting model for Alzheimer’s drugs and targets, the attribute discriminators CfsSubsetEval, ConsistencySubsetEval and FilteredSubsetEval are combined with search methods such as BestFirst, GeneticSearch and Greedystepwise to filter the molecular descriptors. Then the machine learning algorithms such as BayesNet, SVM, KNN and C4.5 are used to construct the 2D-Structure Activity Relationship(2D-SAR) model. Its modeling results are utilized for Receiver Operating Characteristic curve(ROC) analysis. Results: The prediction rates of correctness using Randomforest for AChE, BChE, MAO-B, BACE1, Tau protein and Non-inhibitor are 77.0%, 79.1%, 100.0%, 94.2%, 93.2% and 94.9%, respectively, which are overwhelming as compared to those of BayesNet, BP, SVM, KNN, AdaBoost and C4.5. Conclusion: In this paper, we conclude that Random Forest is the best learner model for the prediction of Alzheimer’s drugs and targets. Besides, we set up an online server to predict whether a small molecule is the inhibitor of Alzheimer's target at http://47.106.158.30:8080/AD/. Furthermore, it can distinguish the target protein of a small molecule.

Hot Rolling Process Simulation: Application to UIC-60 Rail Rolling

2010 ◽  
Vol 3 (1) ◽  
pp. 65-71
Author(s):  
Armindo Guerrero ◽  
Javier Belzunce ◽  
Covadonga Betegon ◽  
Julio Jorge ◽  
Francisco J. Vigil
Keyword(s):  
Hot Rolling ◽  
Process Simulation ◽  
Rolling Process ◽  
Hot Rolling Process

Risk Factor Identification, Classification and Prediction Summary of Chronic Kidney Disease

2020 ◽  
Vol 13 ◽  
Author(s):  
Pramila Arulanthu ◽  
Eswaran Perumal
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Disease Diagnosis ◽  
Medical Data ◽  
Machine Learning Algorithms ◽  
World Health ◽  
Medical Field ◽  
Data Set ◽  
Medical Issues ◽  
Health Organization

: The medical data has an enormous quantity of information. This data set requires effective classification for accurate prediction. Predicting medical issues is an extremely difficult task in which Chronic Kidney Disease (CKD) is one of the major unpredictable diseases in medical field. Perhaps certain medical experts do not have identical awareness and skill to solve the issues of their patients. Most of the medical experts may have underprivileged results on disease diagnosis of their patients. Sometimes patients may lose their life in nature. As per the Global Burden of Disease (GBD-2015) study, death by CKD was ranked 17th place and GBD-2010 report 27th among the causes of death globally. Death by CKD is constituted 2·9% of all death between the year 2010 and 2013 among people from 15 to 69 age. As per World Health Organization (WHO-2005) report, 58 million people expired by CKD. Hence, this article presents the state of art review on Chronic Kidney Disease (CKD) classification and prediction. Normally, advanced data mining techniques, fuzzy and machine learning algorithms are used to classify medical data and disease diagnosis. This study reviews and summarizes many classification techniques and disease diagnosis methods presented earlier. The main intention of this review is to point out and address some of the issues and complications of the existing methods. It is also attempts to discuss the limitations and accuracy level of the existing CKD classification and disease diagnosis methods.

Sign in / Sign up

Export Citation Format

Share Document