Research on Automatic Identification and Application of Airborne Software Failure Modes Based on Artificial Intelligence

With the rapid development of technologies such as cloud computing, the Internet of Things, and artificial intelligence, the capabilities of data collection, storage, and processing have been greatly enhanced. Using traditional methods for identifying software failure modes involves a significant workload and potential errors. To address this, this paper proposes an artificial intelligence-based approach to identify and extract software failure modes, which not only improves work efficiency but also enhances the accuracy of identifying software failure modes. Firstly, we introduce the background of the big data era and the opportunities and challenges that big data brings to the identification of software failure modes. Secondly, it presents common quality characteristics and software failure modes, highlights the current bottlenecks in software failure mode identification, and clarifies the research direction. Next, by comparing traditional manual identification methods, this article introduces the research framework for failure modes. Through intelligent analysis of software failure data, the software failure characteristics are extracted. This process then proceeds to intelligent extraction of software failure features and iterative identification of software failure modes, ultimately forming an artificial intelligence-based software failure mode identification method. Finally, airborne embedded signal processing software is selected as a case study for the extraction and identification of software failure modes.