MODELLING AN IMAGE DETECTION ALGORITHM TO EVALUATE THE DEGREE OF CORROSION

Sea water covers more than two-thirds of the surface of the earth. For a long period, seawater has been known as the most corrosive environment in nature for engineering materials, especially for many metals and alloys. Corrosion can vary to some extent depending on the geographical position, yet every seawater environment is naturally corrosive in a normal state anywhere in the world. That is why the study of corrosion of various materials is an important aspect of research. The corrosion of metal structures not only costs up to 4% of global gross domestic product annually but also poses a major threat to those who work in those areas. Predicting these risks will cause many problems to be prevented before it is too late. The integration of new technologies in the field of artificial intelligence into the chemical field makes it possible to solve the current issues. However, the lack of standardized image information, scientific research, and the number of experts aware of both fields undermine the timely integration of these fields. This study has used new algorithms for strengthening the outcome of a previous Worcester University study which used a collection of 600 photographic data in order to classify the corrosion. As a result, a model that can correctly classify corrosion with 83.5% accuracy has been taught