In spacecraft attitude control, conventional proportional-integral-derivative Control (PID) methods are widely adopted for their simplicity and stability, yet suffer from inefficiencies in manual parameter tuning and limited adaptability to dynamic uncertainties. To address these challenges, a novel hybrid control framework integrating PID control with a whale optimization algorithm (WOA)-enhanced backpropagation (BP) neural network is proposed in this paper. The BP neural network dynamically adjusts PID parameters through error backpropagation, while WOA optimizes the network’s learning rate and momentum coefficient via global search, effectively avoiding local optima and accelerating convergence. Simulations under disturbance torques demonstrate that the proposed method achieves precise Euler angle tracking with reduced overshoot and steady-state error. This work offers a robust solution for spacecraft systems requiring high-precision attitude regulation in uncertain environments.