Today, it is evident that the Internet of Things, real-time data processing, and artificial intelligence technologies are essential in industrial settings to enable early warning autonomous anomaly detection systems. Such systems can detect anomaly situations that could cause failures shortly after they occur, allowing necessary maintenance to be performed promptly. In this research, a software platform has been designed and developed to collect data from sensors placed on industrial equipment to monitor their condition using the required IoT infrastructure. The real-time data collected from this platform is analyzed using real-time data processing techniques. Here, a business process is introduced for instant anomaly detection using real-time clustering analysis methods. To validate the proposed business process architecture, a prototype software has been developed, and its ability to detect anomaly situations has been evaluated. The results show that the proposed business process architecture is effective in real-time anomaly detection and can successfully detect anomalies that can lead to industrial equipment failures.