Abstract

Specimens of DIN 100MnCrW4 steel (type O1 tool steel) have been cut and prepared for performing a duplex surface treatment involving nitriding and low temperature vanadium thermo-reactive deposition and diffusion (TRD) technique. The TRD process was performed in a molten salt bath at different temperatures of 575, 650 and 725°C for 1–30h. The treatment formed a vanadium carbonitride coating with the thickness up to 10.5μm on a hardened diffusion zone. Characterizations by means of an optical microscope (OM), scanning electron microscope equipped with energy dispersive X-ray spectrometer (SEM–EDS) and X-ray diffraction analysis (XRD) indicated that the compact and dense coating mainly consisted of V(C,N) and V2(C,N) phases. All the growth processes of the formed vanadium carbonitride layer obtained by TRD followed a parabolic kinetics while the calculated activation energy (Q) for the treatment was 181.1kJ/mol. An artificial neural network (ANN) based model for predicting the layer thickness of ceramic coatings was presented. Constructing the model, training, validating and testing of experimental results from 72 different specimens were conducted. The data used as inputs in the proposed model were arranged in a format of five parameters that comprised of “pre-nitriding time”, “ferro-vanadium particle size”, “ferro-vanadium weight percent”, “salt bath temperature” and “coating time”. Accordingly, the thickness of duplex coating in each specimen was estimated accurately. Finally, the proposed ANN-based model showed a strong potential for predicting the layer thickness of duplex ceramic coating performed by the TRD technique on the substrate of cold work tool steel.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call