SPIF Quality Prediction Based on Experimental Study Using Neural Networks Approaches
- PDF / 1,367,119 Bytes
- 14 Pages / 612 x 792 pts (letter) Page_size
- 32 Downloads / 152 Views
Quality Prediction Based on Experimental Study Using Neural Networks Approaches S. Akrichi1,*, S. Abid2,**, H. Bouzaien3,***, and N. Ben Yahia1,**** 1Research
Unit in Structural Solid, Mechanics and Technological Development (University of Tunis, Tunisia), Avril, 1938-1007 Tunisia 2 Laboratory of Signal, Image Processing and Energy Control (SIME, University of Tunis, Tunisia), Avril, 1938-1007 Tunisia 3 Laboratory of Higher Institute of Technological Studies of Kef, Campus Universitaire, Boulifa, Le Kef, 7100 Tunisia *e-mail: [email protected] **e-mail: [email protected] ***e-mail: [email protected] ****e-mail: [email protected] Received June 4, 2018; revised March 30, 2019; accepted September 18, 2019
Abstract—This paper deals with the quality prediction of the Single Point Incremental forming (SPIF) process. The quality prediction can be evaluated through five parameters: Roughness surface, thickness, springback, circularity and position errors. Despite the contribution of many researchers on the development of sheet metal forming process, the geometric accuracy of the formed part remains less developed and analyzed. Several parameters are relevant to this inaccuracy namely the complexity of the part geometry, the Elasto-Plastic Material Behavior and tool path strategy. The present work proposes an experimental study for a complex geometry part (double truncated cone) obtained by SPIF. To product a truncated cone, two different trajectories were used: single and alternating directions. While in literature three quality parameters are generally used (roughness surface, thickness and springback) we propose in the paper to predict moreover two other quality parameters which are the circularity and the position errors. To deal with the nonlinearity of the problem we proposed to use an ANN and benefit of its generalization capacities to generate new and unpredictable situations through different input parameters: Strategy tool path, incremental step size, spindle speed, feed rate, and the forming angle. To improve the generalization accuracy of the neural network the modified back propagation algorithm was used in the learning phase of one hidden multilayer neural network. Experimental results show that the new proposed prediction model allows to reach an accurate prediction more than 96.74% with respect to all the quality parameters. Keywords: SPIF, Quality Part, ANN approach DOI: 10.3103/S0025654420010033
NOMENCLATURE SPIF
Single-point incremental forming
ANN
Artificial neurons network
Ra
Arithmetic mean surface roughness
TH
Variation thickness
SB
Springback
CE
Circularity (roundness) error
PE
Position tolerance error
E TPS
Initial sheet thickness Tool path strategy 138
SPIF QUALITY PREDICTION α
Forming angle
f
Feed rate
N
Spindle rate
Δz
Vertical increment
MSE
Mean square error
MRE
Mean relative error
R2
139
Correlation coefficient
1. INTRODUCTION Single-point incremental forming (SPIF) is a promising process for the production of small series par
Data Loading...
