Plasma arc deposition as an additive manufacturing technology has unique advantages for producing parts with complex shapes through layer-by-layer deposition. It is critical to predict and control the temperature field during the production process due to the temperature distribution and gradients determining the properties and performance of the part. Numerical simulation approaches, such as the finite element method, which provides a large amount of data for machine learning modeling, thus reducing the overhead of experimental measurements, are widely used in machine learning. In this paper, we propose a neural network combined finite element method and process prediction workflow. A one-dimensional convolutional neural network model for predicting 2D temperature distribution is developed by training the collected data on the planar temperature field of titanium–aluminum twin-wire plasma arc additive manufacturing and the finite element method. The results show that the predicted temperature mean square error is only 0.5, with less than a 20 °C error in peak temperature and a relative error below 1%. The proposed transfer learning method achieves the same training loss and is 500 iterations faster than basic training, which improves the training speed by 25%. The current study confirms the accurate performance of the ML model and the effectiveness of the optimization method.

In this study, a pulsed laser was used as the heat source for the additive work. The Ti6Al4V/Inconel 718 alloy wire was deposited on the substrate by melting using a pulsed laser. Using the above method, single-layer and double-layer samples were printed. The sample material printed in this way is highly utilized. Compared to the complicated pre-preparation work of metal powder pre-mixing, this printing method is simple to prepare and only requires changing the wire feeding speed. The study of this paper provides a theoretical guide for the subsequent fusion deposition of heterogeneous wire materials. The samples were analyzed after molding using SEM, EDS and XRD to characterize the microstructure of the samples. The samples can be divided into three zones depending on the microstructure, the bottom columnar crystal zone, the middle mixed phase zone, and the bottom equiaxed crystal zone. From the bottom to the top of the sample, the phase microstructure changes as γ + Laves → α + β + Ti₂Ni + TiNi + Ni₃Ti → α + β. The hardness data show that the highest value in the transition zone is 951.4 HV. The hardness of the top part is second only to the transition zone due to a large number of equiaxed crystals. The bottom region is dominated by columnar crystals and is the softest of the three regions with the lowest hardness value of 701.4 HV.