Vulnerability Assessment of Asphalt Plant through Machine Learning Techniques

Abstract

Many businesses throughout the globe have recently realized the value of Supervisory Control and Data Acquisition (SCADA) systems. Many critical infrastructures, such as electricity grids, asphalt plants, and wastewater disposals, are controlled by these systems. With the introduction of Fourth Industrial Revolution, 4IR or Industry 4.0, today's SCADA systems cannot be separated from the outside world, making them more susceptible to hostile assaults. Conventional security systems including different antivirus software and firewalls are unable to safeguard SCADA systems as they are of distinct requirements. For this, different machine learning algorithms, i.e., SVM, KNN, and random forest, are tested to cover the anomaly detection along with security protection for SCADA systems. The dataset used in this research study was made locally in an asphalt plant by using different sensor data grouped in two classes: one is natural signal values, and the other one is attack class in which different sensor values are found out of range while in operation. Amongst the above-mentioned algorithms, KNN outperformed with an accuracy rate of 89% for anomaly detection and any kind of external attack can be detected and notified to the control room for on-time actions.