MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611101023 A) filed by Madan Mohan Malaviya University Of Technology on August 20, 2026, for An Embedded Intelligent Device For Electric Vehicle Battery Health Monitoring And Early Fault Diagnosis.
Inventors include Dr. Anukriti Sharma; and Dr. Navdeep Singh.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: The present invention relates to an embedded artificial intelligence (AI) enabled battery fault monitoring device and diagnosis system for continuous real-time health assessment and early fault detection in electric vehicle (EV) battery systems. The proposed invention is configured to acquire and continuously monitor multi-sensor battery operational data, including battery voltage, current, motor speed, battery temperature, vibration, ambient temperature, and humidity, through an integrated sensing network embedded within the electric vehicle. The proposed diagnostic framework employs a Convolutional Neural Network (CNN) for automatic feature learning and battery health classification. The dataset is categorized into a healthy state and 3 fault severity levels (Level-1, Level-2, and Level-3). The dataset is divided into 70% training data and 30% testing data to develop a deep learning model. Before CNN training, the acquired multi-sensor signals undergo comprehensive feature extraction in both the time and frequency domains using Fast FFT analysis to capture statistical, spectral, and frequency characteristics associated with battery degradation and fault evolution. Furthermore, PCA and t-SNE are employed for feature visualization and to examine the separation between different fault condition. The performance of the proposed intelligent fault detection and classification framework is evaluated shows an overall accuracy is 98.55%. The obtain result indicate effectiveness, robustness, and reliability of the proposed embedded AI-based battery monitoring device for multi-sensor data processing and early fault diagnosis.
Disclaimer: Curated by HT Syndication.
