Monitoring of key parameters of modern vehicles
is essential for their safe operation, reliable functionality, and
optimal performance. Unusual situations like overheating, high
power consumption, and motor overload may cause equipment
failure, inefficiency, and other faults. Conventional methods of
monitoring do not include real-time monitoring, remote accessibility,
and fault predictions.
The present paper considers a Smart Vehicle Health Monitoring
System based on the IoT and ML technologies. The
system is designed on the basis of the ESP32 microcontroller,
LM35 temperature sensor, ACS712 current sensor, BO motor,
alerting buzzer, and Blynk cloud server for monitoring and fault
detection. Data from sensors are collected in real-time mode by
ESP32 microcontroller and analyzed in terms of classification
of vehicle operation as NORMAL, WARNING, and CRITICAL
modes. In order to increase the predictive maintenance potential,
several machine learning techniques like Logistic Regression,
Decision Tree, Random Forest, Support Vector Machine, and
K-Nearest Neighbor have been used by employing the acquired
data set. According to experimental results, the Random Forest
technique proved to be the most accurate classification technique,
which was 87.3
The processed data as well as system status can be transferred
to the Blynk cloud platform via WiFi. The buzzer alerting system
can be triggered under the abnormal operating conditions like
overheating and overload of the vehicle. Thus, the developed
system provides a low cost and intelligent solution for real-time
diagnostics and maintenance of the vehicles.

IoT, ESP32, Vehicle Health Monitoring, LM35 Sensor, ACS712 Current Sensor, Blynk Cloud, Embedded Systems, Real-Time Monitoring, Fault Detection, Predictive Maintenance, Smart Vehicles, Cloud Monitoring, Edge Computing, Automotive Diagnostics, Wireless Sen