A Brief Overview and New Knowledge Based System for Rail Direct Fastening Evaluation Using Digital Image Processing

Periodical inspection of railway track components plays an important role in railway management system. Mistakes and limitations involved in human visual inspection and lack of data acquisition, evaluation, and registration for track components’ condition necessitate applying new technologies with higher speed and precision. After a brief overview of automatic evaluation of rail components, a new knowledge-based system for evaluation of railway fastening using an automatic image system is proposed. For this purpose, imaging data were first collected. Next, using an expert system, the location of the fastening system was detected and then two indices were presented; one for evaluation of single bolts, and the other one for fastening system assessment. Experimental results show the efficiency of the proposed system in automatic judgment for railway direct fastening. This system was also proved to work quickly and successfully in the automatic evaluation of railways.