Abstract: With the increasing push toward mechanization and digital intelligence in modern agriculture, agricultural motors have become vital components, underpinning productivity by powering various essential equipment. As the sector advances toward greener, smarter, and more efficient operations, the demand for reliable motor performance becomes ever more critical. However, faults in these motors can lead to significant setbacks, disrupting crucial agricultural timelines, inflicting economic losses, and posing potential safety risks. Traditional diagnostic methods, including machine learning and deep learning approaches, though effective, often face challenges in interpretability, scalability, and adaptability to the specific requirements of agricultural systems. These limitations hinder their widespread application in real-world agricultural environments, where conditions can vary greatly, and system transparency is paramount for effective troubleshooting. To address these gaps, this study proposes a novel, knowledge-driven approach by constructing a dedicated knowledge graph tailored for agricultural motor fault diagnosis. The knowledge graph framework integrates information from multiple heterogeneous data sources, such as maintenance logs, technical manuals, and fault records, transforming unstructured textual data into structured, semantically rich, and queryable knowledge. This is achieved through the deployment of advanced natural language processing techniques, specifically leveraging the BERT-BiLSTM-CRF model for entity recognition, which allows the accurate extraction of key fault-related entities, such as components, fault types, and causes, even from complex and technical descriptions. In addition, relationship extraction between entities is accomplished through a combination of pattern matching and regular expression techniques, capturing the intricate relationships between components and fault causes in a manner that enhances the coherence and utility of the knowledge graph. This structured approach facilitates a more comprehensive understanding of fault mechanisms, supporting improved fault classification and prediction capabilities. A notable feature of this diagnostic system is the integration of an intelligent question-answering (QA) module powered by the GPT model, which enhances the accessibility and usability of the knowledge graph for end-users. Through natural language processing, the QA module interprets and processes user queries, translating them into structured Cypher queries that the Neo4j graph database can execute. This allows users, even those without technical expertise, to interactively query the knowledge graph, retrieving relevant diagnostic insights with ease and precision. The system's interpretability and ease of use are further augmented by the Neo4j database’s visualization capabilities, providing an intuitive graphical representation of complex fault relationships and enabling efficient navigation of diagnostic pathways. The proposed knowledge graph-based diagnostic system offers a series of advantages over traditional machine learning methods. It reduces data dependence and operational costs, ensures high diagnostic accuracy, and supports real-time updates, making it suitable for dynamically evolving fault scenarios in agricultural settings. Furthermore, by combining semantic richness with structural flexibility, the system enhances fault traceability and interpretability, empowering users to make informed maintenance decisions and preemptively address potential failures. This study demonstrates the potential of knowledge graphs as an innovative tool for fault diagnosis in agriculture, providing a scalable, accurate, and interpretable diagnostic framework that bridges the gap between complex data structures and practical diagnostic needs. The findings underscore the value of integrating advanced natural language models with graph-based storage and retrieval mechanisms, paving the way for broader applications in agricultural machinery management and intelligent maintenance systems.