CCNorton Coil Optimizer
magnetic coil optimizer for stellarators
2 min readupdated
This standalone ONNX model solves the magnetic coil optimization problem for fusion stellarators within the Proxima Fusion CoilStellaration benchmark. The architecture combines analytical methods, a neural prior, and an iterative Levenberg-Marquardt solver (a nonlinear optimization algorithm). The model achieves an overall score of 0.9937, outperforming the standard baseline. It is useful for researchers in plasma physics and controlled nuclear fusion.
Key features
- Physics-in-the-Graph paradigm: a combination of a neural network, database search, and an analytical solver.
- Compact size of just 48.78 MB with 4.3 million parameters and zero external data files.
- Support for two tracks: fixed (fixed_shape) and variable (variable_shape) geometry.
- High accuracy with a median score of 1.0000 on official eval instances.
What you can do
- Run inference via the official CoilStellaration benchmark ONNX runner to calculate magnetic configurations.
- Integrate the model into plasma configuration design and toroidal magnet optimization pipelines.
- Explore the performance of the LM optimizer algorithm on custom tasks.
Example
The model takes plasma boundary geometry tensors as input (for example, boundary_r_cos and boundary_z_sin) along with requirement parameters, and outputs three-dimensional coil coordinates coil_x_n, coil_y_n, coil_z_n and current values currents in accordance with the leaderboard specification.
Read more
Details• Overall score: 0.9937 (+0.0135 over base baseline)
• Benchmark: Proxima Fusion CoilStellaration (v1.0)
• Format: ONNX (opset 20, IR 10, CPUExecutionProvider)
• Parameters: 48.78 MB, 4,348,180 parameters
• fixed_shape result: average score 0.9931 (latency 1.737 s)










Comments