WELD QUALITY INSPECTION WITH DOMAIN KNOWLEDGE INFUSED ADAPTIVE-NETWORK-BASED FUZZY INFERENCE SYSTEM

Quality of weld images in with bad lighting condition and specific image color formats add constraints to existing automated weld inspection systems. Embodiments herein provide a method and system based on Domain Knowledge Infused Adaptive-Network-based Fuzzy Inference System (DKI-ANFIS) for weld quality inspection. The DKI-ANFIS inspects the quality of weld joint using domain driven quality inspection techniques. A segmentation algorithm is used to extract the weld joint in form of fractals followed by an unsupervised technique to extract useful geometrical features from the fractals. These geometrical features are used for quality index generation. A weld inspection model comprising the DKI-ANFIS is used for determining the quality of the weld j oint. DKI-ANFIS modifies layers of ANFIS by infusing layer of domain knowledge to give better results even if there is a class imbalance in the data or the data is skewed or there is only a short corpus of data available.