Machine Learning-Based Performance Evaluation of a Solar-Powered Hydrogen Fuel Cell Hybrid in a Radio-Controlled Electric Vehicle

TL;DR

This study demonstrates that a small RC vehicle powered by a NiMH battery in conjunction with a PEM fuel cell achieves superior electrical performance and reliability under varied loads and environments. The authors combine a portable sensor suite with data processing, supervised throttle‑level classification, anomaly/change‑point detection, and Temporal Convolutional Networks to model and predict voltage dynamics, while also validating a solar‑powered electrolyzer for off‑grid hydrogen refueling. Key contributions include integrated sensorized data collection, ML‑driven condition monitoring, and a practical demonstration of renewable refueling, offering a scalable baseline for hydrogen‑assisted mobility. The results indicate meaningful improvements in voltage stability, reduced battery stress, and robust energy planning potential for small to larger electric vehicles, with implications for autonomous and off‑grid mobile systems.

Abstract

This paper presents an experimental investigation and performance evaluation of a hybrid electric radio-controlled car powered by a Nickel-Metal Hydride battery combined with a renewable Proton Exchange Membrane Fuel Cell system. The study evaluates the performance of the system under various load-carrying scenarios and varying environmental conditions, simulating real-world operating conditions including throttle operation. In order to build a predictive model, gather operational insights, and detect anomalies, data-driven analyses using signal processing and modern machine learning techniques were employed. Specifically, machine learning techniques were used to distinguish throttle levels with high precision based on the operational data. Anomaly and change point detection methods enhanced voltage stability, resulting in fewer critical faults in the hybrid system compared to battery-only operation. Temporal Convolutional Networks were effectively employed to predict voltage behavior, demonstrating potential for use in planning the locations of fueling or charging stations. Moreover, integration with a solar-powered electrolyzer confirmed the system's potential for off-grid, renewable hydrogen use. The results indicate that integrating a Proton Exchange Membrane Fuel Cell with Nickel-Metal Hydride batteries significantly improves electrical performance and reliability for small electric vehicles, and these findings can be a potential baseline for scaling up to larger vehicles.

Figures (6)

• Figure 1: Experimental setup for renewable hydrogen generation, including a hydrogen generator, a 30 $W$ monocrystalline silicon solar panel, a charge controller, and lead-acid batteries. This configuration enables safe and repeatable off-grid hydrogen production by using clean solar energy to electrolyze deionized water and refill hydrogen cartridges sustainably and efficiently.
• Figure 2: The Traxxas Slash 4×4 VXL 1/10-scale RC test platform used for hybrid powertrain experiments with a NiMH battery and a 30 $W$ PEM hydrogen fuel cell module.
• Figure 3: Voltage response at 100% throttle under static conditions: Figure (a) battery-only shows greater voltage drop and fluctuations; (b) The hybrid configuration consistently maintained a more stable voltage profile, as demonstrated by data smoothed using the moving average filter with the window size of 17.
• Figure 4: (a) Voltage, (b) current, and (c) power signals smoothed using SMA (window size 50) for battery-only and hybrid configurations during the 10-minute dynamic lab driving test without load. The hybrid system maintains higher voltage and smoother current and power profiles compared to the battery-only mode.
• Figure 5: Voltage anomaly and change point detection results: (a) hybrid system and (b) battery-only under a load. The hybrid setup shows enhanced voltage stability with fewer structural changes and more frequent but minor anomalies, while the battery-only configuration exhibits fewer anomalies but suffers from a steady voltage decline, indicating progressive battery depletion.