<p class="wp-block-paragraph"><strong>Low-Voltage Distribution Network Physical Fingerprint and AI Expert Diagnostic Platform</strong><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#harmonisense-lv"></a></p>
<blockquote class="wp-block-quote has-small-font-size is-layout-flow wp-block-quote-is-layout-flow">
<figure class="wp-block-image"><a href="https://www.python.org/"><img src="https://camo.githubusercontent.com/324d45e6f6b77e85e34b513ddaee855acd83146e10e7316bd93c9b01eedd233e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f707974686f6e2d332e382532422d626c75652e737667" alt="Python Version"/></a></figure>
<figure class="wp-block-image is-resized"><a href="https://creativecommons.org/licenses/by-nc-sa/4.0/"><img src="https://camo.githubusercontent.com/ed6dc0db32f838ac999b25896dd6f9508f4646667358b4bb7d07e723ad38da7b/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d434325323042592d2d4e432d2d5341253230342e302d6c69676874677265792e737667" alt="License: CC BY-NC-SA 4.0" style="width:158px;height:auto"/></a></figure>
<figure class="wp-block-image"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main"><img src="https://camo.githubusercontent.com/c27a457659b89ee4f1f80f7995c559dd37f2051bde7167ad25791e5c5c92cc8e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6275696c642d70617373696e672d627269676874677265656e2e737667" alt="Build Status"/></a></figure>
<figure class="wp-block-image"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main"><img src="https://camo.githubusercontent.com/8aba8ed638454f14489c43c9280483d0cfe8c11a18cef0b62d4c48ae69d0932c/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f456e67696e652d506879736963616c25323041492d6f72616e67652e737667" alt="Engine"/></a></figure>
<figure class="wp-block-image"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main"><img src="https://camo.githubusercontent.com/e347aca7ea9d7512263eef61bfa85181ce4c34ba9bb5e7e4fa86bca457ebb688/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f506c6174666f726d2d57696e2532302537432532304c696e75782532302537432532304d61632d3737372e737667" alt="Platform"/></a></figure>
<figure class="wp-block-image"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main/Images/sys_overview.png" target="_blank" rel="noreferrer noopener"><img src="https://github.com/Shinar-of-Clark/HarmoniSense-LV/raw/main/Images/sys_overview.png" alt="HarmoniSense-LV System Dashboard Mastery"/></a></figure>
<p class="wp-block-paragraph">HarmoniSense-LV is an AI-driven diagnostic system for low-voltage grids based on high-order physical harmonic fingerprints. It enables automatic topology reconstruction of the physical distribution network via AI algorithms, performs multi-dimensional fingerprint identification of connected loads, and quickly locates electricity theft, unregistered users, and unauthorized connections of new energy equipment.</p>
<h2 class="wp-block-heading has-medium-font-size">📖 Auxiliary Documentation</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#-auxiliary-documentation"></a></p>
<p class="wp-block-paragraph">To facilitate developers and users, the project provides detailed Markdown documentation:</p>
<ul class="wp-block-list">
<li>📄 <a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main/Product%20Specification.md"><strong>Product Specification</strong></a>: Contains detailed algorithm methodology, technical advantages, and system screenshot descriptions.</li>
<li>📘 <a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main/User%20Manual.md"><strong>User Manual</strong></a>: Provides step-by-step guidance on how to run the system, import data, and interpret reports.</li>
<li>🍄 <a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/blob/main/HarmoniSense_Core%20Functions%20and%20Principles%20White%20Paper.md"><strong>White Paper</strong></a>: Core functions and principles documentation.</li>
<li>💡<strong><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV/releases/tag/v1.0.0">release</a></strong>: v1.0.0: Initial Release.</li>
<li>🔓<a href="http://168.138.32.72:8053" data-type="link" data-id="http://168.138.32.72:8053">demo address</a>:<a href="http://168.138.32.72:8053/" target="_blank" rel="noreferrer noopener">168.138.32.72:8053/</a></li>
</ul>
<hr class="wp-block-separator has-alpha-channel-opacity"/>
<h2 class="wp-block-heading has-medium-font-size">🚀 Core Features</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#-core-features"></a></p>
<ul class="wp-block-list">
<li><strong>AI Topology Reconstruction</strong>: Based on the Pearson correlation coefficient algorithm, it automatically reconstructs the physical phase and link structure of the substation area without manual record entry.</li>
<li><strong>Load Fingerprint Identification</strong>: Deep feature extraction technology accurately identifies specific electricity consumption patterns such as EV charging, distributed photovoltaics, cryptocurrency mining machines, and high-power heat pumps.</li>
<li><strong>Unauthorized Node Detection</strong>: Through physical energy conservation residual analysis, it locks onto unauthorized connection (electricity theft/unregistered user) nodes in seconds.</li>
<li><strong>Multi-language Interaction</strong>: Built-in dynamic switching between Chinese and English, providing an industrial-grade real-time interactive dashboard.</li>
</ul>
<h2 class="wp-block-heading has-medium-font-size">🛠️ Technical Architecture</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#%EF%B8%8F-technical-architecture"></a></p>
<p class="wp-block-paragraph">The project adopts a modular design with a clear code structure:</p>
<ul class="wp-block-list">
<li><code>dashboard_app.py</code>: <strong>Main program entry point</strong>. Built on Dash (Plotly), responsible for global state management and callback logic.</li>
<li><code>app_logic.py</code>: <strong>AI core algorithm center</strong>. Contains data cleaning, simulation engine, phase identification, and anomaly analysis logic.</li>
<li><code>app_viz.py</code>: <strong>Topology graph rendering engine</strong>. Responsible for NetworkX spatial computation and Plotly dynamic topology visualization.</li>
<li><code>app_components.py</code>: <strong>UI component library</strong>. Encapsulates sidebar, cards, expert report box, and accordion components.</li>
<li><code>app_translations.py</code>: <strong>Internationalization dictionary</strong>. Supports full business terminology mapping between Chinese and English.</li>
</ul>
<h2 class="wp-block-heading has-medium-font-size">🚦 Quick Start</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#-quick-start"></a></p>
<h3 class="wp-block-heading has-medium-font-size">1. Environment Setup</h3>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#1-environment-setup"></a></p>
<p class="wp-block-paragraph">Ensure your Python environment supports the following libraries:</p>
<pre class="wp-block-preformatted">pip install dash dash-bootstrap-components pandas networkx numpy scipy openpyxl</pre>
<h3 class="wp-block-heading has-medium-font-size">2. Launch the System</h3>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#2-launch-the-system"></a></p>
<p class="wp-block-paragraph">Run the main script to start the Flask/Dash service:</p>
<pre class="wp-block-preformatted">python dashboard_app.py</pre>
<p class="wp-block-paragraph">After launching, visit: <code>http://127.0.0.1:8053</code></p>
<h2 class="wp-block-heading has-medium-font-size">📚 Theoretical Foundation & Acknowledgements</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#-theoretical-foundation--acknowledgements"></a></p>
<p class="wp-block-paragraph">The algorithm design philosophy and physical mapping logic of this platform are deeply inspired by the following academic achievements:</p>
<ul class="wp-block-list">
<li><strong>Paper Title</strong>: <em>Utilising Smart-Meter Harmonic Data for Low-Voltage Network Topology Identification</em></li>
<li><strong>Core Team</strong>: Ali Othman, Neville R. Watson, Andrew Lapthorn (University of Canterbury); Radnya Mukhedkar (EPECentre).</li>
<li><strong>Published Journal</strong>: <em>Energies</em> 2025, 18(13), 3333.</li>
<li><strong>Paper Link</strong>: <a href="https://doi.org/10.3390/en18133333">https://doi.org/10.3390/en18133333</a></li>
</ul>
<p class="wp-block-paragraph"><strong>Acknowledgements</strong>: Special thanks to the research team at the University of Canterbury for their pioneering work in the field of harmonic analysis for low-voltage distribution networks.</p>
<hr class="wp-block-separator has-alpha-channel-opacity"/>
<h2 class="wp-block-heading has-medium-font-size">⚖️ License</h2>
<p class="wp-block-paragraph"><a href="https://github.com/Shinar-of-Clark/HarmoniSense-LV#%EF%B8%8F-license"></a></p>
<p class="wp-block-paragraph">This project is licensed under the <strong><a href="https://creativecommons.org/licenses/by-nc-sa/4.0/">Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)</a></strong>.</p>
<ul class="wp-block-list">
<li><strong>You are free to</strong>: Share (copy and redistribute) and Adapt (remix, transform, and build upon) the material.</li>
<li><strong>Under the following terms</strong>:
<ul class="wp-block-list">
<li><strong>Attribution</strong>: You must give appropriate credit and provide a link to the license.</li>
<li><strong>Non-Commercial</strong>: <strong>You may not use the material for commercial purposes.</strong></li>
<li><strong>Share-Alike</strong>: If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.</li>
</ul>
</li>
</ul>
<hr class="wp-block-separator has-alpha-channel-opacity"/>
<blockquote class="wp-block-quote is-layout-flow wp-block-quote-is-layout-flow">
<p class="wp-block-paragraph"><strong>© Designed & Developed by Clark</strong> | I have obtained the key to Babel, and I shall raise countless towers in Shinar</p>
</blockquote>
</blockquote>
Low-Voltage Distribution Network Physical Fingerprint and AI Expert Diagnostic Platform
HarmoniSense-LV is an AI-driven diagnostic system for low-voltage grids based on high-order physical harmonic fingerprints. It enables automatic topology reconstruction of the physical distribution network via AI algorithms, performs multi-dimensional fingerprint identification of connected loads, and quickly locates electricity theft, unregistered users, and unauthorized connections of new energy equipment.
📖 Auxiliary Documentation
To facilitate developers and users, the project provides detailed Markdown documentation:
🚀 Core Features
AI Topology Reconstruction : Based on the Pearson correlation coefficient algorithm, it automatically reconstructs the physical phase and link structure of the substation area without manual record entry.
Load Fingerprint Identification : Deep feature extraction technology accurately identifies specific electricity consumption patterns such as EV charging, distributed photovoltaics, cryptocurrency mining machines, and high-power heat pumps.
Unauthorized Node Detection : Through physical energy conservation residual analysis, it locks onto unauthorized connection (electricity theft/unregistered user) nodes in seconds.
Multi-language Interaction : Built-in dynamic switching between Chinese and English, providing an industrial-grade real-time interactive dashboard.
🛠️ Technical Architecture
The project adopts a modular design with a clear code structure:
dashboard_app.py: Main program entry point . Built on Dash (Plotly), responsible for global state management and callback logic.
app_logic.py: AI core algorithm center . Contains data cleaning, simulation engine, phase identification, and anomaly analysis logic.
app_viz.py: Topology graph rendering engine . Responsible for NetworkX spatial computation and Plotly dynamic topology visualization.
app_components.py: UI component library . Encapsulates sidebar, cards, expert report box, and accordion components.
app_translations.py: Internationalization dictionary . Supports full business terminology mapping between Chinese and English.
🚦 Quick Start
1. Environment Setup
Ensure your Python environment supports the following libraries:
pip install dash dash-bootstrap-components pandas networkx numpy scipy openpyxl
2. Launch the System
Run the main script to start the Flask/Dash service:
python dashboard_app.py
After launching, visit: http://127.0.0.1:8053
📚 Theoretical Foundation & Acknowledgements
The algorithm design philosophy and physical mapping logic of this platform are deeply inspired by the following academic achievements:
Paper Title : Utilising Smart-Meter Harmonic Data for Low-Voltage Network Topology Identification
Core Team : Ali Othman, Neville R. Watson, Andrew Lapthorn (University of Canterbury); Radnya Mukhedkar (EPECentre).
Published Journal : Energies 2025, 18(13), 3333.
Paper Link : https://doi.org/10.3390/en18133333
Acknowledgements : Special thanks to the research team at the University of Canterbury for their pioneering work in the field of harmonic analysis for low-voltage distribution networks.
⚖️ License
This project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) .
You are free to : Share (copy and redistribute) and Adapt (remix, transform, and build upon) the material.
Under the following terms :
Attribution : You must give appropriate credit and provide a link to the license.
Non-Commercial : You may not use the material for commercial purposes.
Share-Alike : If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
© Designed & Developed by Clark | I have obtained the key to Babel, and I shall raise countless towers in Shinar