In the rapidly evolving landscape of artificial intelligence, large language models (LLMs) have emerged as powerful tools with the potential to transform various industries. A recent article published in Engineering titled “Can large language models solve complex engineering issues? Practical applications in reliability systems engineering” explores the integration of LLMs within the realm of reliability systems engineering (RSE), shedding light on both the opportunities and challenges this presents.

Reliability systems engineering is a sophisticated discipline that focuses on the entire product life-cycle, aiming to reduce failure rates, enhance system reliability, and extend product lifespans. The introduction of LLMs into this field has the potential to significantly boost industrial production efficiency and flexibility. The study conducted by a team of researchers from Beihang University, Jiangsu University of Technology, and the University of Alberta provides a comprehensive overview of the current development of LLMs in RSE, analyzing key application scenarios and technologies, and identifying existing challenges.

The research team systematically collected literature from the Web of Science database, using keywords related to LLMs and RSE. Their analysis revealed that LLMs can be applied across various dimensions of the RSE V-model, including requirements, design, manufacturing, verification, and maintenance. These models are capable of supporting traditional tasks such as design modeling and requirements analysis, as well as more advanced applications like perceptual enhancement and intelligent manufacturing. For instance, fine-tuning LLMs with domain-specific data has shown high accuracy in detecting vulnerabilities in Ethereum smart contracts and improving fault diagnosis accuracy in bridge cranes.

However, the integration of LLMs into RSE is not without its challenges. One significant issue is the systemic deficiencies in domain data. Complex engineering tasks often involve imbalanced and incomplete data, particularly regarding failures, which can lead to biases in failure prediction. This not only hampers the summarization of design experiences but also limits the training effectiveness and inference capabilities of LLMs. Additionally, the complexity of RSE analysis, characterized by the phased and diverse structure of the V-model, requires LLMs to integrate physical laws, statistical patterns, and domain-specific knowledge. The “black-box” nature of LLMs further complicates matters, as their probabilistic inference outputs often lack transparency and explainability, making it difficult to meet the high standards of complex engineering tasks.

Looking ahead, the article suggests several future development directions for LLMs in RSE. One key area is the exploration of pre-trained industrial LLMs capable of addressing complex engineering issues. This involves optimizing knowledge extraction and retrieval methods, integrating expert knowledge, and generating high-quality datasets to enhance training effectiveness. Another direction is improving the adaptability of LLMs for solving complex analysis processes by integrating them with probabilistic models, Bayesian inference, and reinforcement learning. This would enable LLMs to better manage uncertainty and make decisions in real-world scenarios. Finally, the organic integration of human, machine, and intelligence is seen as crucial for coordinated development, especially in safety-critical domains like aerospace and healthcare.

The integration of LLMs into reliability systems engineering holds significant promise, yet several critical areas require further development. Despite the unique advantages LLMs offer in knowledge extraction and application within RSE, they still face limitations in data resources, performance, and explainability. Future efforts should focus on exploring more practical engineering application scenarios, promoting collaborative interaction with other intelligent models, and developing systematic engineering frameworks. By doing so, LLMs can enhance the intelligence of design and production processes, ultimately empowering RSE with greater efficiency and reliability.

The paper “Can large language models solve complex engineering issues? Practical applications in reliability systems engineering,” is authored by Yue Zhang, Yanjie Song, Yi Ren, Lining Xing, Qiang Feng, Ruifeng Xiang, Zili Wang, Witold Pedrycz. Full text of the open access paper: https://doi.org/10.1016/j.eng.2025.07.037. For more information about Engineering, visit the website at https://www.sciencedirect.com/journal/engineering.