<p class="wp-block-paragraph"><strong>Project Identity:</strong><em> Shinar of Clark</em><br><strong>Author:</strong><em> Yi Zeng</em><br><strong>Framework:</strong><em> Spatio-Temporal Fault Contagion Tracking and Predictive Asset Management</em><br>Manuscript PDF:<em> </em><a href="https://github.com/Shinar-of-Clark/Clark-Paradigm-Initiative/blob/main/papers/paper-3-fault-correlation/Spatio-Temporal%20Fault%20Contagion%20Tracking%20and%20Predictive%20Asset%20Management%20for%20Offshore%20Wind%20Farms%20Based%20on%20Multi-Terminal%20Harmonic%20Fingerprints.pdf" target="_blank" rel="noreferrer noopener">Read the Full Paper Here</a><br><strong>DOI:</strong><em> </em><a href="https://doi.org/10.5281/zenodo.20306854" target="_blank" rel="noreferrer noopener">https://doi.org/10.5281/zenodo.20306854</a><br><strong>github</strong><em>:</em><a href="https://github.com/Shinar-of-Clark/Clark-Paradigm-Initiative" target="_blank" rel="noreferrer noopener">https://github.com/Shinar-of-Clark/Clark-Paradigm-Initiative</a><br><strong>Email:</strong><em>Clark@ShinarOfClark.com</em></p>
<p class="wp-block-paragraph">With the continuous expansion of offshore wind farm installed capacity, ensuring the reliable operation of critical electrical assets has become a primary challenge. Targeting the ”5-Level 7-Node” multi-terminal harmonic characteristics of offshore wind systems, this paper proposes a predictive asset management framework focusing on cross-terminal fault contagion tracking and early warning. Specifically, we investigate the spatiotemporal propagation rules of sub-health abnormal states across different structural levels (e.g., wind turbine generator, converter, step-up transformer, submarine cable, and grid connection point).</p>
<p class="wp-block-paragraph"><br>To achieve efficient and precise prediction, this paper proposes a two-stage hybrid deep learning architecture based on the synergy of CNN and Transformer: the CNN acts as a Trigger, precisely capturing fault precursors by identifying the spatial features of harmonic envelopes; subsequently, the Transformer takes over to analyze the evolutionary path of cross-terminal faults and predict their occurrence time. By demonstrating the ability to predict anomaly propagation and estimate contagion time delays, this paper validates the feasibility of proactive fault prediction. Although precise absolute delay times still require long-term field validation, the proposed method successfully lays the foundation for predictive maintenance, ensuring that incipient faults are detected and intervened in a timely manner before evolving into catastrophic failures.</p>
<div data-wp-interactive="core/file" class="wp-block-file"><object data-wp-bind--hidden="!state.hasPdfPreview" hidden class="wp-block-file__embed" data="https://shinarofclark.com/wp-content/uploads/2026/06/Spatio-Temporal-Fault-Contagion-Tracking-and-Predictive-Asset-Management-for-Offshore-Wind-Farms-Based-on-Multi-Terminal-Harmonic-Fingerprints-1.pdf" type="application/pdf" style="width:100%;height:800px" aria-label="嵌入 Spatio-Temporal Fault Contagion Tracking and Predictive Asset Management for Offshore Wind Farms Based on Multi-Terminal Harmonic Fingerprints"></object><a id="wp-block-file--media-de8c8f18-1ec3-4865-88b8-1ed526243246" href="https://shinarofclark.com/wp-content/uploads/2026/06/Spatio-Temporal-Fault-Contagion-Tracking-and-Predictive-Asset-Management-for-Offshore-Wind-Farms-Based-on-Multi-Terminal-Harmonic-Fingerprints-1.pdf">Spatio-Temporal Fault Contagion Tracking and Predictive Asset Management for Offshore Wind Farms Based on Multi-Terminal Harmonic Fingerprints</a><a href="https://shinarofclark.com/wp-content/uploads/2026/06/Spatio-Temporal-Fault-Contagion-Tracking-and-Predictive-Asset-Management-for-Offshore-Wind-Farms-Based-on-Multi-Terminal-Harmonic-Fingerprints-1.pdf" class="wp-block-file__button wp-element-button" download aria-describedby="wp-block-file--media-de8c8f18-1ec3-4865-88b8-1ed526243246">Download</a></div>
Project Identity: Shinar of Clark
Author: Yi Zeng
Framework: Spatio-Temporal Fault Contagion Tracking and Predictive Asset Management
Manuscript PDF: Read the Full Paper Here
DOI: https://doi.org/10.5281/zenodo.20306854
github:https://github.com/Shinar-of-Clark/Clark-Paradigm-Initiative
Email:Clark@ShinarOfClark.com
With the continuous expansion of offshore wind farm installed capacity, ensuring the reliable operation of critical electrical assets has become a primary challenge. Targeting the ”5-Level 7-Node” multi-terminal harmonic characteristics of offshore wind systems, this paper proposes a predictive asset management framework focusing on cross-terminal fault contagion tracking and early warning. Specifically, we investigate the spatiotemporal propagation rules of sub-health abnormal states across different structural levels (e.g., wind turbine generator, converter, step-up transformer, submarine cable, and grid connection point).
To achieve efficient and precise prediction, this paper proposes a two-stage hybrid deep learning architecture based on the synergy of CNN and Transformer: the CNN acts as a Trigger, precisely capturing fault precursors by identifying the spatial features of harmonic envelopes; subsequently, the Transformer takes over to analyze the evolutionary path of cross-terminal faults and predict their occurrence time. By demonstrating the ability to predict anomaly propagation and estimate contagion time delays, this paper validates the feasibility of proactive fault prediction. Although precise absolute delay times still require long-term field validation, the proposed method successfully lays the foundation for predictive maintenance, ensuring that incipient faults are detected and intervened in a timely manner before evolving into catastrophic failures.
