<p>Synchronous control is a critical task of the dual-linear-motor-driven (DLMD) gantry. However, nonlinearities such as actuator saturation and system uncertainties, can degrade control performance, ultimately compromising machining accuracy. To address the aforementioned issues, this article proposes a high-precision adaptive synchronization control strategy based on broad learning neural networks (BLNN). First, a rotational dynamic coupling model of the gantry worktable is established to deal with the limitations of traditional modeling that neglects high-frequency rotation modes. Besides, an indirect adaptive method based on recursive least squares (RLS) is developed for real-time estimation of system model parameters, further improving the accuracy of modeling. In addition, to address the prevalent issue of actuator saturation in practical applications, a smoothing function integrated with the mean value theorem is employed, along with the design of an auxiliary feedback term to mitigate the effects of saturation. Moreover, utilizing the strong learning ability of BLNN to to further compensate for the adverse factors of saturation and the residual uncertainty of the system. Unlike traditional RBF neural networks, BLNN can autonomously add neurons, which not only eliminates the blind nature of network design but also achieves higher fitting accuracy. Finally, the stability of the closed-loop system is demonstrated using Lyapunov’s theorem, and comparative experiments are conducted using different control strategies. The experimental results confirm the superiority of the proposed control strategy.</p>