Predictive Analysis of a Lift Motor Using Autoregressive Integrated Moving Average (ARIMA) Model for Vibration-Based Condition Monitoring

Condition-based monitoring (CBM) has emerged as a promising technique for assessing the condition and performance of various mechanical systems, including lift motors. This paper focuses on the application of vibration signal analysis for SHM of lift motors using time series predictive model which enables the early detection of potential faults. Lift motors are subjected to various mechanical stresses, vibrations, and operational loads during their service life. In this work, velocity of the lift motor is acquired to monitor the vibration severity of the lift motor using Arduino Mega Microcontroller and Accelerometer MEMS (ADXL 345) based on the Vibration Assessment ISO chart 10816. Any vibration signal transmitted above the safety threshold will be labelled as an alert sign. It provides the maintenance team a warning signal where a further inspection is required. The acquired vibration signal is finally processed and analyzed using Autoregressive Integrated Moving Average (ARIMA) model for predictive analysis. The ARIMA model is capable of capturing the underlying patterns and trends in time series data, making it suitable for forecasting and anomaly detection in vibration signals. This paper highlights the use of ARIMA model as time-series predictive model. The time-series data is also plotted against the ISO 10816 severity chart for possible early fault detection and monitoring.