ARCHIVES

In current times, aircraft safety and reliability are important attributes aviation since minor flaws in the performance of any system can result in serious problems. The proposed system involves fault detection and preventive maintenance of the aircraft using IoT Machine Learning techniques. With this regard, temperature sensors, pH sensors, MQ sensors, and ADXL sensor play roles in the monitoring of temperature, contamination of fuel, leakage of gases, and vibration of an aircraft, respectively. Furthermore, sensors are linked with the ESP32 microcontroller to preprocess data. In the addition, data are transmitted to the cloudbased platform for analysis. Fault detection and classification are performed using Machine Learning through the application of random forest classifier method. This method achieved the accuracy classification of 93.8%. Firstly, the proposed framework ensures greater safety of flights through early fault detection, eliminates any unpredicted downtimes, and streamlines the process of maintenance. Furthermore, this framework is scalable and can be applied other use cases in the aviation industry. Through the application of this study in developing an intelligent predictive maintenance system, there has been a significant contribution to the advancement of predictive maintenance.