Development of Rule-Based Diagnostic Automation Technology for Elevator Fault Diagnosis

Abstract

Elevators are critical vertical transportation systems in modern urban infrastructure; however, their intricate mechanical and electrical configurations render them highly susceptible to safety-critical failures. Although various automated diagnostic techniques have been proposed, many data-driven approaches exhibit limited generalizability due to their insufficient consideration of physical fault mechanisms and strong dependence on facility-specific training data. To overcome these limitations, this study presents a rule-based automated diagnostic framework for elevator state recognition that prioritizes reliability, real-time performance, and interpretability. The proposed approach explicitly integrates physically meaningful fault characteristics and dominant frequency components into the diagnostic process, and employs predefined expert rules derived from established standards to classify fault states in an automated manner. The effectiveness of the proposed method is verified using real operational data collected from an in-service elevator, demonstrating improved diagnostic accuracy and computational efficiency compared to conventional manual inspection procedures. The proposed framework provides a practical and scalable solution for intelligent elevator condition monitoring and is expected to serve as a foundational technology for future smart maintenance and preventive safety systems.