Data mining models are used to analyze large amounts of data in order to identify patterns and relationships that can be used for decision making. In the context of surface inspection and identification of accurate defects in steel sheets, data mining models can be used to analyze images of the steel sheets and identify defects such as cracks, scratches, and other surface imperfections.
One type of data mining model that can be used for this purpose is called a "convolutional neural network" (CNN). This type of model is able to analyze images and identify patterns within them, making it well-suited for identifying defects in steel sheet images.
Another type of data mining model that can be used is called "Support Vector Machine" (SVM). It is an algorithm that can be used to classify the steel sheets into defective or non-defective based on the features extracted from the images of the steel sheets.
Additionally, other data mining models like Random Forest, Decision Trees, K-Nearest Neighbors, and Naive Bayes can also be used to classify and identify the defects in steel sheets.
Overall, data mining models can be an effective way to analyze images of steel sheets and identify defects. These models can be trained using large amounts of data and can be used to classify the steel sheets into defective or non-defective with high accuracy.
Steel is one of the high demanded industrial material. It has a crucial role in increasing the per capita income of the country. It also acts as the primary material in many industries like construction, infrastructure, making pieces of machinery. Steel is the
material found in common demand worldwide. Therefore, quality assurance of the material is considered as the most essential attribute. Due to increased competition in product
supply makes, the manufacturer task to find a suitable market for his/her product challenging.
However, an ever-ending requirement for the quality of industrial products in the market. Hence, it
is becoming unavoidable to have an eye on the perfection of the product to meet up the
international standards. This helps the steel industries to compete globally .
Efficiency in steel production must be maximised, and inspection in the quality has to
be enhanced. In the present scenario, the quality check is done visually by employing
human resources. This process is time-consuming, and the efficiency of the work is not
entirely reliable to meet the global standards. Hence it has laid a path to automate
the defect detection and classify the defected products to reduce the defects in the finished
products.
Surface defects detection technique is widely applied in industrial scenarios. The
surface quality inspection of steel plate has passed through three stages of
development, including manual visual inspection, traditional non-destructive testing, and machine
vision detection. Artificial visual inspection commonly uses the stroboscopic method.
