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

Area of Science:

• Engineering
• Computer Science
• Artificial Intelligence

Background:

• Elevators are essential urban infrastructure but prone to safety-critical failures.
• Existing data-driven diagnostics lack generalizability due to limited physical fault consideration and reliance on specific training data.

Purpose of the Study:

• To develop a reliable, real-time, and interpretable rule-based automated diagnostic framework for elevator state recognition.
• To overcome the limitations of current diagnostic methods by integrating physical fault mechanisms.

Main Methods:

• Developed a rule-based framework incorporating physically meaningful fault characteristics and dominant frequency components.
• Employed predefined expert rules derived from established standards for automated fault state classification.
• Validated the approach using real operational data from an in-service elevator.

Main Results:

• Demonstrated improved diagnostic accuracy and computational efficiency compared to manual inspection.
• The framework effectively classifies fault states in an automated manner.
• Verified the practical applicability and scalability of the proposed method.

Conclusions:

• The proposed framework offers a practical and scalable solution for intelligent elevator condition monitoring.
• It serves as a foundational technology for advanced smart maintenance and preventive safety systems.
• The integration of physical fault characteristics enhances diagnostic reliability and interpretability.