This paper explores the integration of FBG sensor technology with Machine Learning methods to provide robust and scalable methods of structural Health monitoring in real time. FBG sensors are optical sensors that operate on the principle of wavelength shift through Bragg’s grating period. Whenever any parameter such as stress, temperature, or vibration changes the Fiber grating period, it causes the shift in wavelength of the wave passing through the sensors. Wavelength shift provides the measurement of the physical parameter in real time. These are light weight scalable sensors and resistant to electromagnetic interference that can be widely used in heavy industries where SHM is crucial. For effective utilization of this modern technology, it has been combined with Machine Learning models that can handle the large and complex data received from FBG sensors. Machine Learning identifies the clusters and patterns in the datasets for the prediction of irregularities and to reduce potential failures that can create effective maintenance schedules. This paper reviews the significant work done to the combine the FBG sensor technology with the advance Machine learning models. In the end, an analysis has been conducted on integrated FBG sensor on Aluminum, epoxy and Titanium through Finite element Analysis simulation. Result have shown the wavelength shift that can be measured to determine the stress levels.