The increasing adoption of electric vehicles (EVs) has highlighted the importance of efficient battery management systems to ensure safety, reliability, and long battery life. This project presents an AI-based battery fault prediction system for electric vehicles using the LSTM (Long Short-Term Memory) algorithm implemented with TinyML on an ESP32 microcontroller. The system continuously monitors key battery parameters such as voltage, current, and temperature using appropriate sensors. These real-time values are processed through an ADC converter and fed into the ESP32 controller, where the TinyML model predicts potential battery faults based on learned patterns. The battery pack (11.1V Li-ion) is managed through a relay-based charging circuit, ensuring controlled charging and discharging operations. Additionally, important battery health indicators such as State of Charge (SOC) and State of Health (SOH) are calculated and displayed on an LCD display for user awareness. The system also integrates with the ThingSpeak cloud platform to enable remote monitoring and data visualization. In case of abnormal conditions, alerts are generated using a buzzer and cooling fan system to prevent thermal runaway and enhance safety. This intelligent system improves battery performance, enables early fault detection, reduces maintenance costs, and enhances the overall safety of electric vehicles through real-time monitoring and predictive analytics.      

Objectives:

  To design an AI-based battery fault prediction system for electric vehicles.

  To monitor battery parameters such as voltage, current, and temperature in real time.

  To implement LSTM (TinyML) on the ESP32 for early fault detection and prediction.

  To develop a relay-based charging control system for safe battery operation.

  To calculate and display State of Charge (SOC) and State of Health (SOH).

  To provide real-time data visualization on an LCD display.

  To send battery data to the ThingSpeak cloud for remote monitoring.

  To generate alerts using a buzzer and cooling fan during abnormal conditions.

  To improve battery safety, efficiency, and lifespan.      

The major building blocks of this project are:

• Regulated power supply
• ESP32 Microcontroller.
• Temperature sensor.
• Voltage sensor.
• Current sensor.
• Buzzer.
• Cooling fan.
• 11V Li-ion Battery pack
• Relay.
• Charging Circuit.
• LCD display.
• DC motor (EV).

    Software’s used:

• Embedded C programming.
• Arduino IDE programmer for dumping code into Micro controller.
• Express SCH for Circuit design.
• Thingspeak technology.

   

video: