Authors: Om A. Chougule, Vikas A. Patil
Abstract: Stone crusher sites commonly depend on manual supervision, physical registers and reactive security measures, which can lead to theft of equipment or raw material, delayed response to unauthorized movement, incomplete operational records and avoidable downtime. The Automation of Stone Crusher Management System (ASCMS) presented in the attached study is an intelligent automation framework designed to address these problems through integrated IoT sensing, AI-enabled surveillance, real-time dashboards and centralized software control. This professional research paper reorganizes the supplied work into a structured manuscript and presents the system objective, methodology, architecture, implementation process and reported results in a clear academic format. The system uses multiple input sources, including surveillance cameras, RFID and motion sensors, and manual operational inputs. These inputs are processed through a centralized software layer that performs data integration, analytics, machine-learning-based anomaly detection, decision support and alert generation. The output layer provides live dashboards, automated notifications, reports and optimization recommendations. The source results indicate that ASCMS improves security, reduces unauthorized incidents, automates operational logging, supports real-time monitoring and remains scalable for broader industrial applications. The incident comparison reported in the source shows a reduction from 18 theft or intrusion events before implementation to 4 events after ASCMS deployment. Overall, the work demonstrates that a layered AI-IoT architecture can improve safety, accountability and operational efficiency in stone crusher management when it is supported by careful hardware integration, software validation, security testing and continuous feedback-based optimization.
