Physics informed neural network (PINN) method is proposed to alleviate problems in many science and engineering scenarios when data-collection is difficult, or traditional numerical calculations are lack of convenience because more time-consuming numerical calculations are required whenever one or more parameters of the process is changed. However, for advanced manufacturing processes like laser melting (LM), a basis of laser metal additive manufacturing, involve many complex physical phenomena (e.g. melting, convection, solidification, vaporization and interface evolution), the full equations of which are too complex to be solved by current PINN. This paper proposes a reality-augmented adaptive physics informed machine learning (RAA-PIML) method to meet the objectives of precise and fast predictive LM. It applies adaptive function, integrating heat transfer law and boundary condition equations to loss function, which has fast convergence and strong physics-based constraints. The reality-augmented data are acquired by few experiments and an accurate 3D heat transfer model covering turbulence. The conducted experimental results demonstrate that the developed solution exhibits higher efficiency than simulation, and superior performance than state-of-the-art methods, which shows outstanding potential in industry applications.