<p>Software and hardware loosely coupled systems, characterized by their critical role in various high-reliability applications, require robust fault tolerance mechanisms due to their complexity and the intertwined nature of software and hardware components. However, the tight integration of diverse functions within the system-wide computing environment, coupled with the unclear mechanism of fault propagation, presents significant challenges in enhancing system reliability. Modern avionics systems, as a prominent example, are also inherently software-hardware loosely coupled systems, and they face similar challenges in ensuring fault tolerance. In response to these challenges, this paper proposes a fault propagation analysis method that comprehensively considers both temporal and spatial dimensions. Through in-depth analysis of dependency, fault probability, and fault propagation capability, the paper constructs a fault propagation model for software and hardware loosely coupled systems, providing a precise description of fault information. In the spatial dimension, the efficiency of fault propagation analysis is enhanced using the ant colony algorithm, while in the temporal dimension, task modeling is performed using the directed acyclic graph (DAG) model to improve the adaptability of fault propagation methods to real-time task requirements. The experimental results validate the effectiveness and efficiency of the proposed fault propagation method, demonstrating that the temporal dimension of fault propagation can effectively complement the shortcomings of spatial dimension fault propagation in meeting real-time task requirements.</p>