Proceedings of the
9th International Conference of Asian Society for Precision Engineering and Nanotechnology (ASPEN2022)
15 – 18 November 2022, Singapore
doi:10.3850/978-981-18-6021-8_OR-08-0267
Cloud-based Data Analytics Framework for Real-time Lift Monitoring and Diagnostic System
1Manufacturing Execution and Control, Singapore Institute of Manufacturing Technology (SIMTech), Singapore
2SoftGridInc Pte. Ltd., Singapore
ABSTRACT
In this paper, we present an intelligent real-time lift safety monitoring system, incorporating Artificial Intelligence (AI) analytics for early fault detection and diagnosis, to improve labor productivity and benefit the society through digital transformation. We have analyzed historical data, find most frequent faults, select sensors that can give early signals that the fault can happen. To build the real time analysis, cloud architecture is used as the framework for implementation. To conduct the research, we collect data and build models in experiments of lift model and in real lift. Selected sensors are tested in lift model before being installed on site in real lift. Simulation data from lift model are collected to build initial model. Based on the functions of lift models, we simulated some experiments such as slow operation of lift, abnormal stops between floors, lift operation with weight in lift cabin. For data collected from real lift in operation, we build unsupervised machine learning model to detect slow moving and stoppage between two floors. In addition, from collected lift event data, we also can find outliers of door opening and closing behavior that can be early signal for abnormal door operation.
Keywords: Lift Monitoring, Unsupervised Learning, Artificial Intelligence (AI), Predictive Maintenance (PdM), Internet of Things (IoT)
1Manufacturing Execution and Control, Singapore Institute of Manufacturing Technology (SIMTech), Singapore
2SoftGridInc Pte. Ltd., Singapore
ABSTRACT
In this paper, we present an intelligent real-time lift safety monitoring system, incorporating Artificial Intelligence (AI) analytics for early fault detection and diagnosis, to improve labor productivity and benefit the society through digital transformation. We have analyzed historical data, find most frequent faults, select sensors that can give early signals that the fault can happen. To build the real time analysis, cloud architecture is used as the framework for implementation. To conduct the research, we collect data and build models in experiments of lift model and in real lift. Selected sensors are tested in lift model before being installed on site in real lift. Simulation data from lift model are collected to build initial model. Based on the functions of lift models, we simulated some experiments such as slow operation of lift, abnormal stops between floors, lift operation with weight in lift cabin. For data collected from real lift in operation, we build unsupervised machine learning model to detect slow moving and stoppage between two floors. In addition, from collected lift event data, we also can find outliers of door opening and closing behavior that can be early signal for abnormal door operation.
Keywords: Lift Monitoring, Unsupervised Learning, Artificial Intelligence (AI), Predictive Maintenance (PdM), Internet of Things (IoT)
