As a crucial component within the power industry, the hydraulic turbine speed control system significantly plays a vital role in the safe and stable operation of hydropower stations. The intelligent operation and maintenance of this system is a vital means to ensure the safety, stability, and economy of the unit. The hydropower plant has accumulated extensive fault text data related to the hydraulic turbine speed control system over the years, which has yet to be effectively mined and utilized. To address these issues, this paper proposes a novel method using BERTWWM-BiLSTM-MHA-CRF for constructing a fault knowledge graph of hydraulic turbine speed control system. Initially, the knowledge graph schema is designed, followed by an analysis of the recording characteristics of the hydraulic turbine speed control system fault text. This is accompanied by the cleaning and labeling of unstructured text. Subsequently, an entity extraction model utilizing the BERTWWM-BiLSTM-MHA-CRF framework is developed to facilitate the intelligent extraction of entities and relationships. Finally, the triples, consisting of entities and relationships, are stored in the Neo4j graph database to finalize the construction and visualization of the fault knowledge graph, along with the proposed application process for auxiliary decision-making. The data processing methodology outlined in this paper, based on the graph schema design, effectively produces high-quality datasets. Furthermore, compared to the traditional model and mainstream large language models, the BERTWWM-BiLSTM-MHA-CRF model demonstrates superior entity extraction performance. Finally, combining fault instance validation, it demonstrates that the knowledge graph provides effective support for fault diagnosis in the hydraulic turbine speed control system.

The trace water content in industrial oil critically affects the operational stability and service life of industrial equipment and serves as a key indicator for evaluating oil quality. Therefore, the rapid, sensitive, and visual detection of trace water in oil is of great engineering significance for equipment condition monitoring and early fault warning. Existing detection methods predominantly rely on precision instruments; although they enable quantitative analysis, their operational procedures are complicated and time-consuming, which are unsuitable for on-site real-time monitoring. Consequently, there is an urgent need for a novel trace water detection sensor that offers high sensitivity, visualization, and adaptability to oil-phase environments. Herein, a coplanar electrode alternating current electroluminescent (ACEL) sensor is developed for the visual detection of trace water in oil. The ACEL sensor features a multilayer structure comprising a substrate layer, a coplanar electrode layer, and a humidity-sensitive luminescent layer. The humidity-sensitive luminescent layer consists of humidity-sensitive hydrogel and ZnS: Cu electroluminescent powder, forming a loose and porous film that enables high-sensitivity humidity sensing and simultaneously electroluminescent visual signal output. The sensing mechanism study reveals that variations in trace water content modulate the dielectric properties of the humidity-sensitive layer, which further affect the electroluminescent intensity of the ACEL sensor. In addition, the ACEL sensor enables the rapid, naked-eye recognition of humidity changes under trace water conditions without the need for precision instruments, achieving a rapid response time of 3 s and a detection limit as low as 60 ppm, all making it applicable for different types of industrial oils. Thus, this ACEL sensor features a novel detection mechanism, excellent universality, fast response, and ease of operation, offering a new visual sensing strategy for trace water detection in industrial oil and holding broad prospects for practical applications.