Dataset for Electrical Line Fault Detection & Classification

<p dir="ltr">The dataset consists of four cases (TL-1 to TL-4), each representing a distinct configuration of a three-phase distributed transmission line system simulated for both fault detection and fault classification.</p><p dir="ltr"><b>Transmission Line Configurations</b></p><ul><li><b>TL-1:</b><br>Comprised of one generating unit and one RLC load representing a distributed high-voltage transmission line (200 km) with faults at the load end.</li><li><b>TL-2:</b><br>Comprised of one generating unit and one RLC load representing a short-distance transmission line, used to study behavior under reduced propagation delay and impedance effects.</li><li><b>TL-3:</b><br>Comprised of two generating units and three RLC loads, representing a distributed high-voltage long transmission line (200 km) with faults at the load end.</li><li><b>TL-4:</b><br>Comprised of two generating units and three RLC loads, representing a distributed high-voltage long transmission line (200 km) with faults at the source end.</li></ul><p dir="ltr">Each case includes three-phase voltage and current waveform<b>s</b> under normal and faulted operating conditions.</p><p dir="ltr"><b>Fault Detection Label</b></p><p dir="ltr">To indicate whether the system is under a fault condition:</p><ul><li><code>1</code> → <b>No Fault</b></li><li><code>2</code> → <b>Fault Present</b></li></ul><h4><b>Fault Classification Labels</b></h4><p dir="ltr">The detailed fault types correspond to the following numeric codes :</p><table><tr><th><p dir="ltr">Code</p></th><th><p dir="ltr">Fault Type</p></th><th><p dir="ltr">Description</p></th></tr><tr><td><p>1</p></td><td><p dir="ltr">NF</p></td><td><p dir="ltr">No Fault</p></td></tr><tr><td><p>2</p></td><td><p dir="ltr">ABC</p></td><td><p dir="ltr">Three-phase fault</p></td></tr><tr><td><p>3</p></td><td><p dir="ltr">ABG</p></td><td><p dir="ltr">Double line-to-ground fault (A-B-Ground)</p></td></tr><tr><td><p>4</p></td><td><p dir="ltr">BCG</p></td><td><p dir="ltr">Double line-to-ground fault (B-C-Ground)</p></td></tr><tr><td><p>5</p></td><td><p dir="ltr">ACG</p></td><td><p dir="ltr">Double line-to-ground fault (A-C-Ground)</p></td></tr><tr><td><p>6</p></td><td><p dir="ltr">AB</p></td><td><p dir="ltr">Line-to-line fault (A-B)</p></td></tr><tr><td><p>7</p></td><td><p dir="ltr">BC</p></td><td><p dir="ltr">Line-to-line fault (B-C)</p></td></tr><tr><td><p>8</p></td><td><p dir="ltr">CA</p></td><td><p dir="ltr">Line-to-line fault (C-A)</p></td></tr><tr><td><p>9</p></td><td><p dir="ltr">AG</p></td><td><p dir="ltr">Single line-to-ground fault (A-Ground)</p></td></tr><tr><td><p>10</p></td><td><p dir="ltr">BG</p></td><td><p dir="ltr">Single line-to-ground fault (B-Ground)</p></td></tr><tr><td><p>11</p></td><td><p dir="ltr">CG</p></td><td><p dir="ltr">Single line-to-ground fault (C-Ground)</p></td></tr></table><h4><b>Structure</b></h4><p dir="ltr">Each CSV file (e.g., <code>TL_1_fault_detection.csv</code>, <code>TL_2_fault_classification.csv</code>) contains:</p><ul><li>Time-series data of three-phase voltages and currents.</li><li>A target column indicating fault detection (1 / 2) or fault classification (1 – 11).</li></ul><p dir="ltr">Together, these datasets provide a comprehensive basis for machine learning and deep learning studies on:</p><ul><li>Fault detection (binary classification).</li><li>Fault type identification (multi-class classification).</li><li>Fault location analysis in long vs. short, and source- vs. load-end fault scenarios.</li></ul><p></p>