A Reverse Approach in Optimizing Pass Parameters

2010 ◽  
Vol 113-116 ◽  
pp. 1707-1711
Author(s):  
Jian Hua Hu ◽  
Yuan Hua Shuang
Keyword(s):  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element ◽  
Learning Process ◽  
Back Propagation ◽  
Fem Simulation ◽  
Steel Pipe ◽  
Good Convergence ◽  
Back Propagation Neural Networks ◽  
Element Method

A method combines a back propagation neural networks (BPNN) with the data obtained using finite element method (FEM) is introduced in this paper as an approach to solve reverse problems. This paper presents the feasibility of this approach. FEM results are used to train the BPNN. Inputs of the network are associated with dimension deviation values of the steel pipe, and outputs correspond to its pass parameters. Training of the network ensures low error and good convergence of the learning process. At last, a group of optimal pass parameters are obtained, and reliability and accuracy of the parameters are verified by FEM simulation.

Effects of Various Edge-Curve Types and Rotational Speeds of Disc Blades on Breaking Force and Energy Consumption in the Maize Stalk Chopping Process

2021 ◽  
Vol 37 (5) ◽  
pp. 951-965
Author(s):  
Peng Liu ◽  
Jin He ◽  
Hongwen Li ◽  
Qingjie Wang ◽  
Caiyun Lu ◽  
...  
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Energy Consumption ◽  
Fem Simulation ◽  
Influential Factor ◽  
List Type ◽  
Breaking Force ◽  
Field Validation ◽  
Validation Experiment ◽  
Element Method

HighlightsThe peak breaking force and energy consumption change in maize stalk were predicted by the FEM.A high SADBT reduced the PBFR and PBFS and increased the ECSC.The TRYDB had the most critical effect on the peak breaking force and energy consumption.Abstract. The mechanized retention of stalks is the primary method to avoid open burning. However, the variation in the breaking force and energy consumption in the chopping process of mechanized retention must be clarified. Therefore, based on the finite element method (FEM) and field validation experiments, the effects of various edge-curve types and rotational speeds of disc blades for maize stalk retention on the breaking force and energy consumption were examined. The test indices were the peak breaking force of the rind (PBFR) and stalk (PBFS), energy consumption of stalk chopping (ECSC), and energy transmission efficiency (ETE). The test factors were the spiral disc blade type (Archimedean, logarithmic, and sinusoidal-exponential spiral), slide-cutting angles of the disc blade tip (SADBT, 30°, 40°, 50°, and 60°), rotational speed of the Y-type blade (RSYB, 1400, 1600, 1800, 2000, 2200, and 2400 rpm), and transmission ratio between Y-type and disc blades (TRYDB, 0.25, 0.50, 0.75, and 1.0). The chopping process was divided into the cutting processes of the initial rind, rind and pith, final rind, and stalk end. The results showed that the SADBT, TRYDB, and RSYB had significant effects on the PBFR, PBFS, ECSC, and ETE. The most influential factor on all test indices was the TRYDB. The RSYB positively affected the PBFR, PBFS, and ECSC. The growth rates of the PBFR, PBFS, and ECSC increased with the TRYDB. The maximum PBFR, PBFS, and ETE values were obtained under an SADBT of 60°, and the maximum ECSC value was obtained under an SADBT of 40°. The difference in energy consumption between the field validation experiment and simulation was less than 10%, which proved the correct results of the FEM simulation. Keywords: Energy consumption, Finite element method, Maize stalk, Peak breaking force, Slide cutting.

scholarly journals Optimization of a thin-walled element geometry using a system integrating neural networks and finite element method

2017 ◽  
Vol 62 (1) ◽  
pp. 435-442 ◽  
Author(s):  
P. Golewski ◽  
J. Gajewski ◽  
T. Sadowski
Keyword(s):  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Integrated System ◽  
Multilayer Perceptrons ◽  
Optimization Of Geometry ◽  
Thin Walled ◽  
Artificial Neural ◽  
Element Method

Abstract Artificial neural networks [ANNs] are an effective method for predicting and classifying variables. This article presents the application of an integrated system based on artificial neural networks and calculations by the finite element method [FEM] for the optimization of geometry of a thin-walled element of an air structure. To ensure optimal structure, the structure’s geometry was modified by creating side holes and ribs, also with holes. The main criterion of optimization was to reduce the structure’s weight at the lowest possible deformation of the tested object. The numerical tests concerned a fragment of an elevator used in the “Bryza” aircraft. The tests were conducted for networks with radial basis functions [RBF] and multilayer perceptrons [MLP]. The calculations described in the paper are an attempt at testing the FEM - ANN system with respect to design optimization.

Springback Prediction Compensation and Optimization for Front Side Member in Sheet Metal Forming Using FEM Simulation

2013 ◽  
Vol 789 ◽  
pp. 436-442
Author(s):  
Agus Dwi Anggono ◽  
Waluyo Adi Siswanto ◽  
Omar Badrul
Keyword(s):  
Numerical Simulation ◽  
Finite Element Method ◽  
Finite Element ◽  
Sheet Metal ◽  
Sheet Metal Forming ◽  
Metal Forming ◽  
Fem Simulation ◽  
Element Size ◽  
Springback Prediction ◽  
Element Method

Numerical simulation by finite element method has become a powerful tool in predicting and preventing the unwanted effects of sheet metals technological processing. One of the most important problems in sheet metal forming is the compensation of springback. To improve the accuracy of the formed parts, the die surfaces are required to be optimized so that after springback the geometry falls at the expected shape. This paper presents and discusses numerical simulation procedure of die compensation by using the methods of Simplified Displacement Adjustment (SDA). This analysis use Benchmark 3 models of Numisheet 2011. Sensitively analysis was done by using finite element method (FEM) show that the springback values are influenced by element size, integration points and material properties.

scholarly journals Mechanical Properties and Cost-Minimized Design of 6-liter PET Bottle Using Finite Element Method

2020 ◽  
Vol 17 (6) ◽  
pp. 579-587
Author(s):  
Kunlapat THONGKAEW ◽  
Thanwit NAEMSAI
Keyword(s):  
Mechanical Properties ◽  
Finite Element Method ◽  
Finite Element ◽  
Maximum Stress ◽  
Fem Simulation ◽  
Chemical Properties ◽  
Optimal Thickness ◽  
Testing Procedures ◽  
Stress And Deformation ◽  
Element Method

Over the years, plastic water bottle manufacturing, especially PET (Polyethylene terephthalate) bottle has been steadily increasing due to its toughness, transparency, and chemical properties. However, most manufacturers have to spare time, and cost, verifying their prototypes in accordance to the Thai Industrial Standard (TIS) before any mass production can start. This paper aims to overcome some of these problems by using Finite Element Method (FEM) to study bottle mechanical properties, particularly maximum stress and deformation that can be employed to evaluate performance and optimal thickness. From simulation results the optimal thickness of a 6-liter bottle, that its maximum stress can still be kept under critical value, is 0.45 mm. The thinner and lighter bottle reduces the amount of material usage. The FEM simulation also speeds up and alleviates some necessary testing procedures in a prototype designing process.

Sign in / Sign up

Export Citation Format

Share Document