Double-circuit transmission lines, with bipolar transmission lines of two different line-commutated converter-based high-voltage direct-current (LCC-HVDC) systems constructed on the same tower, are a new technology emerging in China to increase power transmission capacity. Double-circuit HVDC transmission lines sharing the same tower will lead to an electromagnetic coupling effect of the two circuits. According to the geometry configuration of same-tower double-circuit transmission lines in HVDC trans-mission projects, double-circuit transmission lines are unbal-anced without transposition. Therefore, the coupling effects on the healthy circuit cannot be completely eliminated. These cou-pling components will affect the sensitivity of conventional travel-ing-wave-based protection criteria. This work first develops a fault analysis for double-circuit HVDC transmission lines with various internal fault conditions, and then the linear combina-tions of four independent modal components based only on each single circuit are achieved and investigated. Finally, an integrated traveling wave-based protection scheme for double-circuit HVDC transmission lines is presented. Numerous simulation results verify that the proposed protection scheme can operate correctly in double-circuit HVDC transmission lines even for a fault with high resistance up to the maximum of 300 Ω.

High voltage direct current (HVDC) transmission systems play a critical role to optimize resource allocation and stabilize power grid operation in the current power grid thanks to their asynchronous networking and large transmission capacity. To ensure the operation reliability of the power grid and reduce the outage time, it is imperative to realize fault diagnosis of HVDC transmission systems in a short time. Based on the prior research on fault diagnosis methods of HVDC systems, this work comprehensively summarizes and analyzes the existing fault diagnosis methods from three different angles: fault type, fault influence, and fault diagnosis. Meanwhile, with the construction of the digital power grid system, the type, quantity, and complexity of power equipment have considerably increased, thus, traditional fault diagnosis methods can basically no longer meet the development needs of the new power system. Artificial intelligence (AI) techniques can effectively simplify solutions’ complexity and enhance self-learning ability, which are ideal tools to solve this problem. Therefore, this work develops a knowledge graph technology-based fault diagnosis framework for HVDC transmission systems to remedy the aforementioned drawbacks, in which the detailed principle and mechanism are introduced, as well as its technical framework for intelligent fault diagnosis decision.

Based on the four sets of faults data measured in the practical LCC-HVDC transmission project of China Southern Power Grid Tianshengqiao (Guangxi Province, China)–Guangzhou (Guangdong Province, China) HVDC transmission project, a fault diagnosis method based on the K-nearest neighbor (KNN) algorithm is proposed for an HVDC system. This method can effectively and accurately identify four different fault types, aiming to contribute to construction of a future HVDC system knowledge graph (KG). First, function and significance of fault diagnosis for KG are introduced, along with four specific fault scenarios. Then, the fault data are normalized, classified into a training set and a test set, and labeled. Based on this, the KNN fault diagnosis model is established and Euclidean distance (ED) is selected as the metric function of the KNN algorithm. Finally, the training data are conveyed to the model for training and testing, upon which the diagnosis result obtained by the KNN algorithm with a knowledge graph is compared with that of the support vector machine (SVM) algorithm and Bayesian classifier (BC). The simulation results show that the KNN algorithm can achieve the highest diagnosis accuracy, with more than 83.3% diagnostic accuracy under multiple test sets among all three diagnosis methods.

This study aims to achieve intelligent decision making in HVDC systems in the framework of knowledge graphs (KGs). First, the whole life cycle KG of an HVDC system was established by combining intelligent decision making. Then, fault diagnosis was studied as a typical case study, and an intelligent decision-making method for HVDC systems based on XGBoost that significantly improved the speed, accuracy, and robustness of fault diagnosis was designed. It is noteworthy that the dataset used in this study was extracted in the framework of KGs, and the intelligent decision making of KG and HVDC systems was accordingly combined. Four kinds of fault data extracted from KGs were firstly preprocessed, and their features were simultaneously trained. Then, sensitive weights were set, and the pre-computed sample weights were put into the XGBoost model for training. Finally, the trained test set was substituted into the XGBoost classification model after training to obtain the classification results, and the recognition accuracy was calculated by means of a comparison with the standard labels. To further verify the effectiveness of the proposed method, back propagation (BP) neural network, probabilistic neural network (PNN), and classification tree were adopted for validation on the same fault dataset. The experimental results show that the XGBoost used in this paper could achieve accuracy of over 87% in multiple groups of tests, with recognition accuracy and robustness being higher than those of its competitors. Therefore, the method proposed in this paper can effectively identify and diagnose faults in HVDC systems under different operation conditions.

Large-scale UHVDC and flexible DC projects accumulate scattered multi-modal O&M data across independent platforms, fragmenting domain knowledge and reducing the efficiency of intelligent fault diagnosis and disposal. Unstructured data typically account for more than 70% of converter-station O&M data volume, which intensifies fragmentation across SCADA, inspection media, fault recordings and documents. Distinct from prior HVDC intelligent O&M surveys, this review critically synthesizes the closed-loop knowledge construction chain via multi-modal data fusion—covering data governance, cross-modal semantic mapping, DIKW modeling, hybrid storage and knowledge graph development—and compares three fusion paradigms regarding latency, scalability and industrial deployment. It also addresses renewable-integrated O&M uncertainty, practical feature extraction, and why deep learning black-box behavior limits field practicality. Key gaps remain small-sample generalization, control-and-protection logic formalization, explainability and cross-system integration; future directions include few-shot cross-modal learning, LLM-driven knowledge evolution and digital twin coupling.

Conventional DC control and protection (C&P) systems rely on single-modal electrical data and are susceptible to false tripping and missed detection under complex operating conditions or novel fault types. In high-voltage direct current (HVDC) transmission, multi-modal data encompass time-series electrical quantities, unstructured transient waveforms, condition monitoring measurements, and environmental variables, each reflecting the system operating state from a distinct dimension with significant inter-modal complementarity. Nevertheless, fusing these heterogeneous modalities poses three key challenges: feature conflicts arising from data heterogeneity, difficulty embedding domain-specific C&P knowledge into data-driven models, and degraded model robustness under data noise and missing data conditions. This paper proposes a three-layer hierarchical fusion model that integrates multimodal data preprocessing, a C&P phase-aware rule-guided feature weighting strategy, and a dual-path decision mechanism. Experiments conducted on a dataset covering normal operation, typical fault, and complex operating scenarios demonstrate that the proposed model achieves an overall fault identification accuracy of 96.2%, which is 13.9 and 6.5 percentage points higher than a single-modal baseline and a generic multimodal model, respectively. The average decision latency of 7.2 ms satisfies the millisecond-level real-time requirement of industrial C&P systems, confirming the engineering applicability of the proposed approach.