I&T Wish - Research and Design of a Machine Learning Based Adaptive Fault Prediction Data Analytic System for Lift Monitoring 2019-09-18
Research and Design of a Machine Learning Based Adaptive Fault Prediction Data Analytic System for Lift Monitoring
I&T Wish
Research and Design of a Machine Learning Based Adaptive Fault Prediction Data Analytic System for Lift Monitoring (REF: W-0213)
Matched I&T Solution
Trial Project
Summary and Challenges
The objective of this project is to demonstrate proof of concept (PoC) that a machine learning based data analytic system for adaptive fault prediction of lift installations based on current signals of some key components and other cost-effective sensors only is able to diagnose the healthiness of thousands of multi-brand lift installations, and give predictive maintenance alerts to maintenance agencies. The solution shall be provided without any intervention to a lift installation, and employ big data and AI-based technologies to give advanced and clear warnings for the need of corrective actions to prevent major equipment breakdowns.
Expected Outcome
Collection and processing of the retrieved sensor data (e.g., current signal) via the field measurement of lift system, analysis of the frequently encountered lift abnormal activities, and identification of the potential onset of a failure.
Development of big data analytic solutions dedicated to non-intrusive condition monitoring of lifts based on the current signals of some key components and other signals collected from other cost-effective sensors.
Software system integration, which allows multi-brand lift well-being monitoring, fault diagnosis and predictive maintenance alert.
Comprehensive demonstration of PoC, which can be continuously upgraded and further extended to address more lift fault events with more data collection.
Expected Trial Duration
6 months
Contact Information
I&T Wish Proposer
:
Electrical and Mechanical Services Department (EMSD)
