Quality of machined components and products has an overwhelming dependence on the integrity of cutting inserts, among several other factors. Dynamics of machining processes plays an important role in this tool integrity and determine the quality of machined parts. Monitoring of tool condition to further predict and control the machined part quality during any machining process is a challenging task and the topic has been of great research interest in the past four decades. However, despite all research and development efforts so far, a reliable method of generic nature which can be implemented across the board and is scalable beyond requirement of specific environment, is still missing. The challenge here is in the complexity of interaction among process parameters, machine tool and the material being machined. A single measure of cutting force, vibration response, process sound pressure, acoustic emission, optical data or process temperature does not provide a full insight on the process and thus the condition of the cutting tool and machined parts. Fusion of process data from sources and sensors has been proposed in the past as an approach to get a more comprehensive picture of the process and thus a feasible way to develop more robust solutions for quality monitoring & control. This either has not succeeded so far to any wide spread implementation in the industrial environment due to complexity and cost in the design and implementation of such a system. Recent developments especially in miniature and wireless sensors, powerful and easy to use data acquisition and analysis platforms and big data analysis algorithms to exploit machine learning are highly feasible enablers to developing more robust and reliable process monitoring and control systems. This project will explore this opportunity in a scientific and systemic manner with the objective of developing a process monitoring and control methodology exploiting machining data fusion approach in combination with AI. The current project work research scope: • The statistical features-based surface quality prediction using various regression algorithms (decision tree regression, KNN regression, SVR and so on) and data engineering methods (dimensionality reduction, models selection and comparison) • Study on which signal processing method is most suitable for surface quality prediction • Deep study on data fusion technologies based on multi-sensor data for the improvement of quality prediction robustness