Alarm floods in industrial plants overwhelm operators by triggering numerous alarms within short time intervals, significantly complicating effective root-cause analysis. Existing causal analysis methods can support operators, but typically either neglect conditional causal relationships inherent in control loops or require manual, time-consuming extraction. This paper introduces a novel automated methodology leveraging Large Language Models (LLMs) and the logic programming language Prolog to systematically extract conditional causal relationships directly from readily available textual control narratives, textual engineering documents that describe the control system in natural language. Our logic-first approach prioritizes a thorough logical analysis of control system behavior before Prolog rule generation. Evaluations on a synthetic control system confirm accurate representation of cascade and selector control logic, demonstrating the method’s capability to reliably automate causal rule extraction and effectively support root-cause analysis during alarm floods.

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.

With rapid advances in large language model technology, more and more difficult tasks become realizable. Recent studies have shown that commercially available LLM chat tools can already solve complex engineering tasks. In this paper, we apply these LLM chat tools to the task of automated AML model generation, on the example of the Tennessee Eastman process. Besides complexity, this task also adds further challenges, as the scale of the process surpasses the LLM tool's limit for output generation. With our preliminary results, we map the requirements that model generation on this scale poses on LLM chat tools and propose solutions to new challenges derived from this task.

This paper introduces a novel alarm dataset specifically designed for the evaluation of alarm analysis methods within process plants. The complexity of industrial systems and the demands for operational safety and efficiency underscore the critical need for advanced diagnostic tools capable of handling alarm floods-situations where numerous alarms are triggered simultaneously. To bridge the gap identified in existing research regarding the availability of alarm datasets, we have developed a novel publicly available dataset derived from simulated data of a nuclear power plant. This dataset allows for a detailed analysis of alarm dynamics and enables a comprehensive evaluation of alarm analysis methods. We present a systematic methodology for generating alarm data, which involves setting alarm thresholds based on the trade-off between “false alarm rates” (FAR) and “missed alarm rates” (MAR). The dataset is employed to evaluate three existing “alarm flood classification” (AFC) methods, showcasing the practical implications and benefits of our approach. We demonstrate that AFC methods exhibit varying performances based on the implemented alarm thresholds and the quantity of available alarm data.

Simulation models are essential tools in the process industry for supporting plant operators in process optimization and predictive analysis. However, deviations often arise between simulation model output and real-world data, posing challenges to the reliability and effectiveness of these models. Identifying the causes of deviations and adjusting the simulation model accordingly is a tedious and error-prone task, requiring expertise both in the process domain and the simulation tool. Therefore, this paper introduces a model-based approach to automate root-cause identification for deviations between simulation model output and plant data, aiming to reduce manual effort, required knowledge, and susceptibility to errors. The approach builds upon an Adaptive Causal Directed Graph originating from the root-cause identification in alarm floods, presented in previous work. In this paper, the graph is extended to enable an identification of parameters to be adjusted based on detected deviations. Thus, it facilitates a cause-based simulation model adaptation in the context of model calibration and can be repurposed to assist model-based plant diagnosis tasks.