Scholarly record

EXPERIMENTAL AND PREDICTION OF POROSITY IN SOME SINTERED IRON-BASED POWDER METALLURGY MATERIALS BY USING ARTIFICIAL NEURAL NETWORKS

Mihaela MARIN

Abstract

The goal of the work reported in this paper is to describe and develop an artificial neural network (ANN) to evaluate the effect of processing parameters such as density, pressing and sintering time on microstructural characteristics including porosity and microstructure of some iron-based powder metallurgy (PM) materials. There are various methods for generating models to predict the the effect of processing parameters. The materials used in this study are prealloyed iron-based powders. The particle size of the powders is ranging from 45 to 150 ?m. In the first step, the analyzed powders were mixed for 30 minutes with zinc stearate 1%. Zn- stearate was added as a lubricant. In the next step, the mixed powders were pressed. The studied powders were single pressed in a die at two different pressures: 400 and 600 MPa. By pressing is obtaining cylindrical green compacts with 8 mm diameter and 6 mm height. After pressing, the green compacts were subject to sintering. In case of the analyzed specimens, the sintering was carried out in a laboratory furnace at a temperature of 1150? C with different two times: 90 and 120 minutes. The results presented in this paper demonstrate thet the ANN model predictions have been successfully validated by experimental measurements.

Publication Impact Profile

• Captures
• Mendeley - Readers: 5

PLUMX see details

DOI resolver: doi.org/10.5593/sgem2018/6.1/s24.028

Publication details

Back to publication list