מושגי ליבה
Machine learning techniques, including GWO-based and FDO-based MLP and CMLP models, can accurately classify steel plates as faulty or non-faulty, with the FDO-based models consistently achieving 100% accuracy.
תקציר
This study aimed to diagnose and predict the likelihood of steel plates developing faults using experimental text data. Various machine learning methods, such as GWO-based and FDO-based MLP and CMLP, were tested to classify steel plates as either faulty or non-faulty.
The experiments produced promising results for all models, with similar accuracy and performance. However, the FDO-based MLP and CMLP models consistently achieved the best results, with 100% accuracy in all tested datasets. The other models' outcomes varied from one experiment to another.
The findings indicate that models that employed the FDO as a learning algorithm had the potential to achieve higher accuracy with a slightly longer runtime compared to other algorithms. The study highlights the importance of early detection of faults in steel plates for maintaining safety and reliability, and the significant role that machine learning techniques can play in achieving this goal.
The researchers also discussed potential future work, such as increasing the database size, exploring alternative neural network models, and investigating novel approaches to generate more reliable and advanced models.
סטטיסטיקה
The dataset used in this study comprised 1,941 samples, with 1,553 samples allocated for training and 388 samples for testing.
The dataset had 29 variables, including Min. and Max. of X, Min. and Max of Y, Pixels Areas, X and Y Perimeter, Sum of Luminosity, Min. and Max. of Luminosity, Length of Conveyer, TypeOfSteel_A300 and A400, Steel Plate Thickness, Edges Index, Empty Index, Square Index, Outside-X Index, Edges-X Index, Edges-Y Index, Outside-Global Index, Log. of Areas, Log. X Index, Log. Y Index, Orientation Index, Luminosity Index, Sigmoid of Areas.
ציטוטים
"The findings indicate that models that employed the FDO as a learning algorithm had the potential to achieve higher accuracy with a little longer runtime compared to other algorithms."
"Early detection of faults in steel plates is critical for maintaining safety and reliability, and machine learning techniques can help predict and diagnose these faults accurately."