.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "examples/plot_6kw_pmsyrm_flux_map_fem_harm.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. .. rst-class:: sphx-glr-example-title .. _sphx_glr_examples_plot_6kw_pmsyrm_flux_map_fem_harm.py: 5.6-kW PM-SyRM, train flux map, FEM data with spatial harmonics =============================================================== This example trains a GradNet flux-linkage map for a four-pole 5.6-kW PM synchronous reluctance machine (Baldor ECS101M0H7EF4) from a FEM dataset with spatial harmonics. .. GENERATED FROM PYTHON SOURCE LINES 9-26 .. code-block:: Python from pathlib import Path import motulator.drive.gradnet as gn import numpy as np from motulator.drive import utils from motulator_gradnet import ( PlotOptions, PNormGradient, get_training_data, plot_output_vs_angle, plot_surface_vs_current_and_angle, print_flux_map_errors_fem, train_gradnet, ) .. GENERATED FROM PYTHON SOURCE LINES 27-28 Compute base values based on the nominal values. .. GENERATED FROM PYTHON SOURCE LINES 28-32 .. code-block:: Python nom = utils.NominalValues(U=460, I=8.8, f=60, P=5.6e3, tau=29.7) base = utils.BaseValues.from_nominal(nom, n_p=2) .. GENERATED FROM PYTHON SOURCE LINES 33-34 Set up the paths and parameters. .. GENERATED FROM PYTHON SOURCE LINES 34-37 .. code-block:: Python p = Path(__file__).resolve().parent if "__file__" in globals() else Path.cwd() .. GENERATED FROM PYTHON SOURCE LINES 38-39 Flux map with spatial harmonics, trained on FEM data. .. GENERATED FROM PYTHON SOURCE LINES 39-46 .. code-block:: Python dataset_path = p / "datasets/baldor_fem.npz" trained_path = p / "trained_models/baldor_fem_flux_map_harm_pnorm_d48_sub10.npz" subsample = 10 k = 6 activation = PNormGradient .. GENERATED FROM PYTHON SOURCE LINES 47-48 Train the model. .. GENERATED FROM PYTHON SOURCE LINES 48-61 .. code-block:: Python if not trained_path.exists(): train_gradnet( dataset_path=dataset_path, base=base, save_model_path=trained_path, is_flux_map=True, k=k, embed_dim=48, epochs=1000, subsample=subsample, activation=activation, ) .. GENERATED FROM PYTHON SOURCE LINES 62-63 Load the dataset for visualization comparison. .. GENERATED FROM PYTHON SOURCE LINES 63-69 .. code-block:: Python # Get the training and validation data (complement) from the helper function trn_data, val_data = get_training_data( str(dataset_path), base=base, subsample=subsample, other_keys=["theta_m", "tau_m"] ) .. GENERATED FROM PYTHON SOURCE LINES 70-71 Load the GradNet model and create its callable. .. GENERATED FROM PYTHON SOURCE LINES 71-75 .. code-block:: Python model = gn.load_gradnet(trained_path) harm_map = gn.FluxMapWithHarmonics(model, k=k) .. GENERATED FROM PYTHON SOURCE LINES 76-77 Evaluate the model at single point. .. GENERATED FROM PYTHON SOURCE LINES 77-86 .. code-block:: Python i_s_dq_mtpa = -9 + 9j # Approximately the rated MTPA current theta_m = np.deg2rad(30) psi_s_dq, tau_m = harm_map(i_s_dq_mtpa, np.exp(1j * theta_m)) print(f"Current: {i_s_dq_mtpa:.2f} A") print(f"Angle: {np.rad2deg(theta_m):.2f} deg") print(f"Flux linkage: {psi_s_dq:.2f} Vs") print(f"Torque per pole pair: {tau_m:.2f} Nm") .. rst-class:: sphx-glr-script-out .. code-block:: none Current: -9.00+9.00j A Angle: 30.00 deg Flux linkage: 0.29+0.82j Vs Torque per pole pair: 13.64 Nm .. GENERATED FROM PYTHON SOURCE LINES 87-88 Plot torque surface. .. GENERATED FROM PYTHON SOURCE LINES 88-111 .. code-block:: Python # Define ranges for visualization i_q_range = np.linspace(0, 2 * base.i, 50) theta_m_range = np.linspace(0, 2 * np.pi / k, 50) # Plot torque as a function of i_q and theta_m at fixed i_d plot_surface_vs_current_and_angle( current_range=i_q_range, fixed_value=i_s_dq_mtpa.real, theta_m_range=theta_m_range, map_fcn=harm_map, input="i_q", output="tau_m", val_data=val_data, trn_data=trn_data, opts=PlotOptions( base=base, lims={"x": (0, 2), "y": (0, 60), "z": (0, 1.5)}, ticks={"x": [0, 1, 2], "y": [0, 30, 60], "z": [0, 0.5, 1.0, 1.5]}, loci_levels_source="val", ), ) .. image-sg:: /examples/images/sphx_glr_plot_6kw_pmsyrm_flux_map_fem_harm_001.png :alt: plot 6kw pmsyrm flux map fem harm :srcset: /examples/images/sphx_glr_plot_6kw_pmsyrm_flux_map_fem_harm_001.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 112-113 Plot torque vs angle. .. GENERATED FROM PYTHON SOURCE LINES 113-128 .. code-block:: Python theta_m_range = np.linspace(0, 2 * np.pi / k, 120) plot_output_vs_angle( fixed_value=i_s_dq_mtpa, theta_m_range=theta_m_range, map_fcn=harm_map, val_data=val_data, trn_data=trn_data, opts=PlotOptions( base=base, lims={"x": (0, 60), "y": (0, 1)}, ticks={"x": [0, 15, 30, 45, 60], "y": [0, 0.2, 0.4, 0.6, 0.8, 1.0]}, ), ) .. image-sg:: /examples/images/sphx_glr_plot_6kw_pmsyrm_flux_map_fem_harm_002.png :alt: plot 6kw pmsyrm flux map fem harm :srcset: /examples/images/sphx_glr_plot_6kw_pmsyrm_flux_map_fem_harm_002.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 129-130 Print statistical error metrics on validation data. .. GENERATED FROM PYTHON SOURCE LINES 130-133 .. code-block:: Python val_dict = dict(zip(["psi_s_dq", "i_s_dq", "theta_m", "tau_m"], val_data, strict=True)) print_flux_map_errors_fem(map_fcn=harm_map, raw_data=val_dict, base=base) .. rst-class:: sphx-glr-script-out .. code-block:: none Error metrics: Flux linkage: rmse=0.018 p.u., max=0.071 p.u., std=0.009 p.u. Torque: rmse=0.031 p.u., max=0.211 p.u., std=0.021 p.u. .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 1.013 seconds) .. _sphx_glr_download_examples_plot_6kw_pmsyrm_flux_map_fem_harm.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_6kw_pmsyrm_flux_map_fem_harm.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_6kw_pmsyrm_flux_map_fem_harm.py ` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: plot_6kw_pmsyrm_flux_map_fem_harm.zip ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_