The thermophysical properties of hydraulic oil, density, viscosity, thermal expansion, and compressibility, are pivotal factors influencing the functioning of hydraulic systems. With the multitude of hydraulic oils available for use, conducting numerous experiments to determine their specifications under different temperatures and pressures, or devising new empirical correlations, becomes a costly and time-consuming endeavour. Therefore, it becomes imperative to establish an efficient and comprehensive model based on minimal experimental data. This study adopts Physics Informed Neural Networks (PINNs) to design new correlation model to predict variations in hydraulic oil specifications using only 30 empirical data sets as a best-case scenario, enabling the prediction of 10,000 points spanning temperatures (20–100)^∘C and pressures (0–300) bar. The results derived from the PINN model exhibit favourable high accuracy, reaching up to 99.96% when compared to empirical correlations results.