Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
796361 | Journal of Materials Processing Technology | 2007 | 7 Pages |
The paper presents a neural network model for evaluation of the magnetic/mechanical properties and the rate of corrosive wear of the polymer matrix hard magnetic composite materials with particles of the powdered rapid quenched Nd–Fe–B strip with addition of metallic powder: iron, aluminum, CuSn10 type cast copper–tin alloy and X2CrNiMo17-12-2 high-alloy steel. Simulation approach to model the magnetic/mechanical properties in function of the chemical composition employing a neural network technique was proposed. A neural network model of corrosion wear was established based on the research results from the investigations carried out in two corrosive environments. Simulation approach to model the corrosive wear in function of the chemical composition, nature of the corrosive environment and the test duration was proposed. The obtained results indicate that the developed neural networks are able to generalize which justified using these models to the simulation of magnetic/mechanical properties and corrosive wear of hard magnetic composite materials.