This study presents a novel approach to managing the air-fuel ratio in internal combustion engines (ICEs) by integrating an artificial neural network (ANN) with sliding mode control (SMC) to enhance system robustness against sensor failures. Accurate air-fuel ratio control is crucial for optimizing engine performance, fuel efficiency, and emissions. However, sensor malfunctions can significantly disrupt the control process, leading to poor engine operation and increased emissions. This research proposes a hybrid control strategy that employs ANN for precise estimation of the optimal air-fuel ratio and SMC to ensure stability and robustness in the presence of sensor faults. The ANN is trained on a comprehensive dataset representing various operating conditions of the engine, enabling it to adaptively predict the required air-fuel ratio. Meanwhile, the SMC design effectively mitigates the impact of sensor failures by maintaining control system performance through variable gains and robust feedback mechanisms. Simulation results demonstrate that the proposed method significantly improves air-fuel ratio control accuracy and system resilience compared to traditional control strategies. This research contributes to the advancement of intelligent control systems for internal combustion engines, paving the way for enhanced performance and reduced environmental impact in automotive applications.