Predictive gearbox oil temperature using Machine Learning techniques 2020-01-0731
Gearbox failure is the most common failure, which is being detected in vehicles, turbines and other applications. It is not possible to detect every fault manually because gearbox failure depends on various factors like gearbox oil temperature, uncertain driving patterns, engine components and other various gearbox parameters. In recent decades, a lot of research has been done in detecting gearbox failure and various methods and techniques have been proposed to predict failure and also to reduce maintenance and failure costs. To predict the behaviour of the gearbox, robust and efficient algorithms are required. In this work, an effective and accurate algorithm to predict gearbox failure after analysing various symptoms arising on gearbox oil temperature is proposed. Gearbox oil temperature variations are caused by different factors like viscosity, water saturation, dielectric constant and conductivity. Diverse machine learning models such as Support Vector Machine, Random forest and Logistic Regression algorithms from the dataset obtained from gearbox real-time observations are leveraged in this analysis. This paper aims to use sensor data for monitoring oil temperature for fault detection. Data consists of missing data from sensors, correct and invalid data. Collected data is filtered out and analyzed to predict the behaviour using different algorithms. Then we determine the classifier which provides better accuracy and the root cause of gearbox failure. This will help us in taking corrective and important preventive safety measures to minimize failure. Finally, a bench marking is done to derive effectiveness of predictive maintenance achieved in terms of downtime and production quality improvement for OEM’s and Tier’s.