Jun 2026· Safety Science and Technology· 0 citations· 36 references
TL;DR
The viability of integrating LLM‐assisted fault detection into specific industrial scenarios is investigated and an improvement in fault detection accuracy over conventional methods is demonstrated in this work.
Abstract
In industrial processes, the infrequent and unpredictable faults often lead to small sample sizes and a limited amount of labeled fault data. Traditional data‐driven methods struggle under these conditions, as they typically rely on large volumes of labeled fault data for effective training. To overcome these limitations, an exploratory fault detection method based on the pre‐trained large language model (LLM) is proposed. The pre‐trained LLM is utilized to extract fault features from small, imbalanced datasets without the explicit labels. Additionally, a stepwise tuple‐based validation process is introduced to ensure logical consistency in fault analysis and to mitigate the effects of potential LLM hallucinations. The proposed method is validated using a case study involving a sudden feedstock (coal) shortage fault in a circulating fluidized bed boiler. The results demonstrate an improvement in fault detection accuracy over conventional methods in this case study (achieving an accuracy of 0.948 and an F1‐score of 0.926), confirming the feasibility of the proposed approach. The viability of integrating LLM‐assisted fault detection into specific industrial scenarios is investigated in this work.
These findings endorse the viability of LLMs as a feasible alternative for data error detection; nonetheless, challenges such as hallucination and cost aspects remain, especially regarding the resources necessary for the effective implementation of these models in practical applications.
LLM-Detector is proposed, a framework that utilizes the in-context learning capacity of LLMs for structured, prompt-conditioned scoring synthesis, enabling LLMs to derive anomaly detection logic from structured normal-state knowledge.
This study presents a novel, AI-assisted approach to industrial reliability analysis that integrates Failure Modes, Effects and Criticality Analysis (FMECA) and the Failure Reporting, Analysis, and Corrective Action System (FRACAS) with Natural Language Processing (NLP). We developed an algorithm that automates and streamlines the analysis of equipment field-failure reports and other unstructured maintenance records. The proposed framework combines unsupervised clustering to identify recurring equipment failure modes with a supervised Support Vector Machine (SVM) classifier with a Radial Basis Function (RBF) kernel to categorize equipment field reliability reports by failure mode and underlying mechanism at scale. Using an train–test split, the proposed model achieved accuracy on the test dataset, indicating effective generalization to unseen maintenance reports. The Confusion Matrix metrics across all classes showed true positive rate (TPR) (or sensitivity) of 0.91, indicating the model’s strong ability to correctly identify positive samples. The false positive rate (FPR) averaged 0.03 across all classes, demonstrating excellent specificity (true negative rate, TNR of 0.97). Operationally, the methodology reduces the resource-intensive manual work required to prepare, interpret, and process FRACAS reports, thus enabling timelier, data-driven equipment reliability analysis. Overall, the study demonstrates the feasibility and benefits of using AI-assisted reliability tools that balance automation with human expertise through a human-in-the-loop approach.
Esther Yu, Guangjiang Cao, Y. Khalil et al.· Journal of Research in Engin...· 0 citations
Neural networks are increasingly used to support decision-making. To verify their reliability and adaptability, researchers and practitioners have proposed a variety of tools and methods for tasks such as NN code verification, refactoring, and migration. These tools play a crucial role in guaranteeing both the correctness and maintainability of neural network architectures, helping to prevent implementation errors, simplify model updates, and ensure that complex networks can be reliably extended and reused. Yet, assessing their effectiveness remains challenging due to the lack of publicly available diverse datasets of neural networks that would allow systematic evaluation. To address this gap, we leverage large language models (LLMs) to automatically generate a dataset of neural networks that can serve as a benchmark for validation. The dataset is designed to cover diverse layer types and to handle multiple input data types and tasks. In total, 608 samples are generated, each conforming to a set of precise design choices. To further ensure their consistency, we validate the correctness of the generated networks using static analysis and symbolic tracing. We make the dataset publicly available to support the community in advancing research on neural network reliability and adaptability.
Large language models (LLMs) are built on the classic Transformer architecture and have become a core driving force for the rapid development of modern artificial intelligence. This paper presents a systematic review of LLMs, elaborating on their fundamental working principles, mainstream open-source models, effective lightweight optimization methods, retrieval-augmented generation frameworks and key human-value-aligned technologies. Nowadays, LLMs have been widely applied in practice. Typical scenarios include intelligent text generation, professional knowledge-based question answering and automated code generation, delivering remarkable value to both industries and academia. However, their large-scale industrial application is still restricted by multiple challenges. The major issues involve content hallucination, poor model interpretability, excessive computing resource consumption, potential ethical risks and unsatisfactory multimodal integration capability. This paper also forecasts the future development directions of LLMs, such as lightweight deployment on edge devices, safety-focused human value alignment, in-depth cross-modal fusion and customized large models for vertical industries. Additionally, it collects a number of representative cases, which can offer solid references and practical guidance for relevant researchers and engineering practitioners to carry out further studies.
Label noise, which is frequently encountered in real-world data, is a critical problem that can directly degrade model performance. In this study, we systematically investigated the impact of label noise on intent classification by comparing the in-context learning (ICL) approach of large language models (LLMs) with fine-tuned transformer models. In the experiments conducted on the Banking77 dataset, we evaluated four LLMs and two transformer models under three different noise types and three different noise levels. We also tested the LLMs with different prompting strategies to examine the effect of taking precautions against potential noise on different LLMs. Our findings show that strong LLMs experience less than 2 percent loss in accuracy and F1 score even under the heaviest noise conditions, whereas in fine-tuned transformer models and relatively weaker LLMs, the drop can reach the 15-20 percent range.
Yusuf Sali· Signal Processing and Commun...· 0 citations