Nanoindentation test is one of the most common tests to measure the mechanical properties of materials, especially macrocomposites, which have been used since the mid-1970s. This test was carried out by a device of the same name that during this test, the tip-shaped of the device penetrates on the surface of the specimen to a size of a few nanometers, and the force-displacement curve is obtained as a direct output from this test. By postprocessing analyzes on this graph, properties such as the stiffness and hardness of the specimen are achieved. Due to the fact that the indentation of the tip is about a few nanometers in size, the roughness of the surface of the test piece affects the results of this test. This claim is readily apparent by experiments performed on different parts with different surface roughnesses. Access to this device, as well as performing this test in special circumstances, such as high-temperature nanoindentation test, is one of the instrumental limitations of this test. Also, the production of samples that have coatings is also due to the availability of the required devices, a timely process to achieve the desired mechanical properties for the user. In this study, the first issue is defining this test with a simulation model in Abaqus CAE, whose validity was proved by experimental tests. In the next step, the validity of the model obtained on the coating materials was verified. Although this simulation has taken an effective step in speeding up this process, as well as the ability to carry out this test on a wide range of materials defined by the user, this study attempts to even allow the user to not to perform simulations and also let the user to achieved the parameters like stiffness and surface hardness in a fraction of a second. This part of the research is carried out by the machine learning process. Due to the wide variety of base materials and various coatings that exist, it has been attempted, because of the conventional use of steel in the industry, the specimens like steel base materials with commercial coatings become the purpose of this research is to continue the process by using machine learning process. After all this, for achieving to the parameters like stiffness and surface hardness, The user even does not need to simulate this test on steel base materials with conventional industrial coatings, and only uses the properties that are defined to machine learning process input, and get stiffness and hardness values in fractions of a second to desired surface. Keywords Nanoindentation, Surface roughness, Coating, Stiffness, Hardness, Machine learning, High-temperature nanoindentatio