Materials under advanced characterization methods demands the ever-increasing data collection and storage capacities and pose a challenge in the modern materials science which were understood to behave in a typical way. In contrary, the damage in any composites cause rejection during the materials screening for the destined applications. Any kind of micro damages which are insensitive to bare observation could be the reason for catastrophic failures. Many composites, be it sandwich type or any other needs to be free from any micro flaws. Thus it is inevitable for the material designers to develop sandwich materials free from any kind of damages. Thus the damage/crack detection plays an important attribute in the development of sandwich composites. The damage detection requires all new procedures for rapid interpreting and analyzing the data collected for the damage and helps to obtain a best materials discovery for the needy purpose.The work presented herein endeavours to solve the issues with current crack detection and classification practices of sandwich composites, and it is developed for achieving high performance. In this work authors leverage different machine learning algorithms for classifying the damages and non-damaged composites. And in which deep learning is significantly yield good accuracy.