There are not many high-precision, portable digital compass solutions available right now that can enhance combined navigation systems’ overall functionality. Additionally, there is a dearth of writing about these products. This is why a tunnel magnetoresistance (TMR) sensor-based high-precision portable digital compass system is designed. First, the least-squares method is used to compensate for compass inaccuracy once the ellipsoid fitting method has corrected manufacturing and installation errors in the digital compass system. Second, the digital compass’s direction angle data is utilized to offset the combined navigation system’s mistake. The final objective is to create a high-performing portable TMR digital compass system that will enhance the accuracy and stability of the combined navigation system (abbreviated as CNS). According to the experimental results, the digital compass’s azimuth accuracy was 4.1824° before error compensation and 0.4580° after it was applied. The combined navigation system’s path is now more accurate overall and is closer to the reference route than it was before the digital compass was added. Furthermore, compared to the combined navigation route without the digital compass, the combined navigation route with the digital compass included is more stable while traveling through the tunnel. It is evident that the digital compass system’s design can raise the integrated navigation system’s accuracy and stability. The integrated navigation system’s overall performance may be somewhat enhanced by this approach.

Owing to their reliance on detailed mathematical modeling, traditional control methods encounter challenges such as high control complexity and low precision when applied to high-speed flight vehicle control under strongly disturbed atmospheric conditions. To address this limitation, this study introduces a data-driven neural network mapping approach into the field of flight vehicle control. By excavating the underlying patterns in operational data and leveraging the nonlinear mapping capability of neural networks, accurate prediction and generation of control commands are achieved, thereby eliminating the dependence on precise mathematical models and offering a novel solution for complex control problems. Building on this foundation, a self-organizing map (SOM) radial basis function (RBF) neural network is proposed. Leveraging the competitive learning mechanism of SOM, it performs adaptive clustering on input samples, dynamically optimizes the number of clusters to determine the number of hidden-layer nodes in RBF, and adopts the SOM cluster centers as the centers of RBF basis functions. This design enables the one-click data-driven determination of both the number of nodes and their corresponding center vectors, significantly simplifying the network structure design process. Meanwhile, to address inherent limitations of this network, such as suboptimal output weights, unoptimized width functions, and the inherent drawbacks of the traditional Moth-Flame Optimization (MFO) algorithm, an Adaptive Enhanced Moth-Flame Optimization (AEMFO) algorithm is developed, drawing inspiration from biological swarm intelligence. By integrating strategies such as adaptive spiral update and elite opposition-based learning, it balances the global exploration and local exploitation capabilities, and performs targeted optimization of the RBF width parameters and output-layer weights. This optimization significantly enhances the accuracy of the network in mapping attitude-control commands in strongly disturbed environments, providing robust support for the stable attitude control of high-speed flight vehicles. Finally, simulation results demonstrate that the proposed method achieves high control accuracy for flight vehicle attitude control under strongly disturbed environments.