This research study develops and validates an inverse identification algorithm framework that couples Python automation with Abaqus finite-element simulations and a Levenberg-Marquardt (LM) optimizer to optimize the material behaviour parameters (Johnson-Cook (J-C) constitutive law and the Taylor-Quinney (T-Q) heat fraction) for orthogonal cutting of PH martensitic stainless steels. The algorithm loop perturbs parameters, builds finite-difference sensitivities, updates with LM, and rewrites the input automatically, resulting in four machining output conditions across five undeformed chip thicknesses of Href = 0.10–0.25 millimetres (mm) for the chip thickness, tool-chip contact length, cutting force, and penetration force. In the absence of 15-5PH experimental machining data, validation was performed using 17-4PH numerical datasets with similar properties.