Search

Support Vector Machines (SVMs) have achieved significant success in the field of power transformer fault diagnosis. However, challenges such as determining SVM hyperparameters and their suitability for binary classification still exist. This paper proposes a novel method for power transformer fault diagnosis, called ECOC-WSO-SVM, which utilizes a White Shark Optimizer (WSO) and error correcting output codes to optimize SVMs. First, t-distributed Stochastic Neighbor Embedding (t-SNE) is employed to reduce the dimensionality of Dissolved Gas Analysis (DGA) features constructed using the correlation ratio method, from 26 dimensions. In addition, to effectively solve the hyperparameters of SVMs, a multi-strategy fusion method is proposed to improve the WSO, incorporating tent chaos initialization, elite opposite learning, and selection strategies, forming TEWSO, and its superior optimization performance is validated using IEEE CEC2021 test functions. Furthermore, to address the limitations of SVMs as a binary classifier, an error correcting output code fusion SVM is introduced, thus constructing a multi-class SVM model. Finally, the diagnostic performance of the ECOC-TEWSO-SVM model is validated using real-world data. Results demonstrate that the proposed model exhibits the best diagnostic performance compared to traditional models and those in the literature, thereby proving the significance and effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

The Mamupu skarn‐type Cu‐Au polymetallic deposit represents the first discovery of a medium deposit in the southern Yulong porphyry copper belt (YPCB), eastern Tibet. The Cu‐Au mineralization mainly occurs as chalcopyrite in breccia, within the plate‐like carbonate interlayer, being closely related to chloritization (e.g., chlorite, magnetite and epidote) and skarnization (e.g., diopside, tremolite and garnet). The ore‐related quartz syenite porphyry (QSP) and granodiorite porphyry (GP) were emplaced at 40.1 ± 0.2 Ma and 39.9 ± 0.3 Ma, respectively. The QSP of Mamupu is an alkaline‐rich intrusion, relatively enriched in LREE, LILE, depleted in HFSE, with no significant negative Eu and Ce anomalies, slightly high (87Sr/86Sr)i, low ∊Nd(t), uniform (206Pb/204Pb)i and ∊Hf(t) values, which indicates that the porphyry magma may be caused by both the mixing of metasomatized EM II enriched mantle and thickened juvenile lower crust. The QSP in the Mamupu deposit shares a similar genesis of petrology to other ore‐related porphyries within the YPCB. High oxygen fugacity and water content of the magmas are essential for the formation of porphyry and skarn Cu deposits. The QSP has similar high magmatic oxidation states and water content to the Yulong deposit, which indicates that the Mamupu has a high prospecting potential. Differences in the geological characteristics and scale of mineralization between the Mamupu and other YPCB deposits may be due to the different emplacement depths of ore‐related intrusions, as well as differences in the surrounding rocks. [ABSTRACT FROM AUTHOR]