Alarm floods remain a challenge in industrial operations, potentially overwhelming human operators with excessive alarm notifications during abnormal situations. To address this, alarm flood classification (AFC) methods utilize historical data to classify recurring alarm patterns automatically. However, the practical utility of these methods may be limited by potential degradation in alarm data quality, resulting from sensor faults, communication errors, or detection delays, which can substantially compromise their classification accuracy and reliability. This paper proposes a novel methodology to systematically analyze the robustness of AFC methods against realistic alarm data quality issues. We introduce four distinct perturbations: missing alarms, false alarms, delayed alarm flood detection, and alarm reordering, to replicate real-world alarm data degradation. We evaluate our methodology using a novel alarm dataset derived from the Tennessee-Eastman process, while examining the robustness of six relevant AFC methods from the literature. The results demonstrate significant variations in robustness across different AFC methods and perturbation types, providing insights into their practical reliability under various realistic scenarios.

Maintenance of medium voltage switchgears is a complex task that requires extensive expertise. However, a substantial portion of this knowledge is often difficult for the next generation of field technicians to access and apply effectively. For instance, maintenance reports – which document system issues and corrective actions – represent a valuable knowledge source yet frequently underutilized due to their unstructured and sparse nature. In this context, recent advancements in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques have been explored to analyze historical maintenance reports and provide real-time guidance to field technicians. However, chatbot-based interactions remain constrained by the stochastic nature of responses, challenges related to domain and industry specificity, and risks of hallucination. This study introduces a novel approach that leverages LLMs to systematically extract structured, machine-readable rules – i.e., sequences of actions used to resolve specific issues – directly from maintenance reports. A human-in-the-loop approach is proposed, where a human expert validates each extracted rule, mitigating inaccuracies and enhancing quality control. These validated rules are eventually stored in a dedicated rule corpus and later deployed in a deterministic rule engine, ensuring reliability and consistency. An industrial case study evaluates the effectiveness of this approach by comparing LLM-generated rules with those manually curated by domain experts. By shifting from conventional chatbot-like interaction to a more human-centric structured rule extraction, our methodology enhances reproducibility, reliability, and accessibility in industrial maintenance knowledge management. This approach addresses hallucinations and increases robustness of LLM applications in industrial AI settings.

Alarm floods are periods of intense alarm activity that may hinder control room operators' ability to diagnose and respond to process abnormalities. In this context, a method to guide and assist operators during alarm floods would provide critical support in preventing abnormalities from escalating into serious accidents. Therefore, this study introduces a novel approach for the online classification of alarm floods based on their fault categories. Historical alarm data are used to train an ensemble of Natural Language Processing models, specifically word2vec, which learn contextual relationships between alarms under different fault conditions. As a new alarm flood appears, the models predict the most probable context alarms by exploiting the knowledge gained during training. Finally, a scoring system is proposed to reward the models that make correct predictions and eventually identify the most probable fault category. The efficacy of the method has been tested on simulated alarm data from the Tennessee Eastman Process benchmark. The results are encouraging, as the models achieved relatively high accuracy in most fault categories.