<scp>AI</scp> Driven <scp>VANET</scp> Assisted Prediction and Anomaly Detection in Active Suspension Systems: Modeling and Performance Analysis

ABSTRACT Active suspension systems provide ride comfort and vehicle stability under dynamically altering road conditions, but onboard‐only control designs are sensitive to mechanical defects, anomalous vibrations, and external disturbances. This paper suggests an AI‐driven, VANET‐assisted architecture for real‐time active suspension system prediction and anomaly detection. It uses deep learning–based anomaly detection and machine learning prediction models to monitor suspension dynamics and detect early departures from normal operational behavior. VANET‐enabled cooperative vehicle‐to‐vehicle and vehicle‐to‐infrastructure communication improves situational awareness by exchanging suspension and road‐state information. A dynamic simulation environment simulates road disruptions and communication situations during framework evaluation. Performance results show 95% anomaly detection accuracy, 26% false‐positive/false‐negative rate, 92% communication reliability, 0.2 m/s 2 RMS body acceleration for ride comfort, and 1 s suspension settling time, surpassing onboard‐only systems. We found that cooperative AI‐VANET integration enables predictive maintenance and intelligent suspension control for next‐generation connected and autonomous automobiles. Detection accuracy, false‐positive/false‐negative rates, communication reliability, RMS body acceleration, and settling time are computed by comparing predicted suspension states and detected anomalies against ground‐truth fault injections within the simulation. This comparative setup ensures that the reported improvements arise from the integration of AI‐driven anomaly prediction and cooperative VANET communication, with all results reflecting repeatable simulation outcomes under consistent baseline conditions.