Tabular Regression
Keras
Joblib
English
battery
state-of-health
remaining-useful-life
time-series
regression
lstm
transformer
xgboost
lightgbm
random-forest
ensemble
Instructions to use NeerajCodz/aiBatteryLifeCycle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use NeerajCodz/aiBatteryLifeCycle with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://NeerajCodz/aiBatteryLifeCycle") - Notebooks
- Google Colab
- Kaggle
| { | |
| "version": "v1", | |
| "figures": [ | |
| { | |
| "name": "best ensemble prediction", | |
| "tags": [ | |
| "best", | |
| "ensemble", | |
| "prediction" | |
| ], | |
| "location": "best_ensemble_prediction.png" | |
| }, | |
| { | |
| "name": "capacity and rul", | |
| "tags": [ | |
| "capacity", | |
| "and", | |
| "rul" | |
| ], | |
| "location": "capacity_and_rul.png" | |
| }, | |
| { | |
| "name": "capacity distribution by temp", | |
| "tags": [ | |
| "capacity", | |
| "distribution", | |
| "by", | |
| "temp" | |
| ], | |
| "location": "capacity_distribution_by_temp.png" | |
| }, | |
| { | |
| "name": "capacity fade all batteries", | |
| "tags": [ | |
| "capacity", | |
| "fade", | |
| "all", | |
| "batteries" | |
| ], | |
| "location": "capacity_fade_all_batteries.png" | |
| }, | |
| { | |
| "name": "capacity fade by temperature", | |
| "tags": [ | |
| "capacity", | |
| "fade", | |
| "by", | |
| "temperature" | |
| ], | |
| "location": "capacity_fade_by_temperature.png" | |
| }, | |
| { | |
| "name": "ced curves", | |
| "tags": [ | |
| "ced", | |
| "curves" | |
| ], | |
| "location": "ced_curves.png" | |
| }, | |
| { | |
| "name": "classical best actual vs pred", | |
| "tags": [ | |
| "classical", | |
| "best", | |
| "actual", | |
| "vs", | |
| "pred" | |
| ], | |
| "location": "classical_best_actual_vs_pred.png" | |
| }, | |
| { | |
| "name": "classical best residuals", | |
| "tags": [ | |
| "classical", | |
| "best", | |
| "residuals" | |
| ], | |
| "location": "classical_best_residuals.png" | |
| }, | |
| { | |
| "name": "classical soh comparison", | |
| "tags": [ | |
| "classical", | |
| "soh", | |
| "comparison" | |
| ], | |
| "location": "classical_soh_comparison.png" | |
| }, | |
| { | |
| "name": "classification confusion matrices", | |
| "tags": [ | |
| "classification", | |
| "confusion", | |
| "matrices" | |
| ], | |
| "location": "classification_confusion_matrices.png" | |
| }, | |
| { | |
| "name": "degradation state distribution", | |
| "tags": [ | |
| "degradation", | |
| "state", | |
| "distribution" | |
| ], | |
| "location": "degradation_state_distribution.png" | |
| }, | |
| { | |
| "name": "dg itransformer predictions", | |
| "tags": [ | |
| "dg", | |
| "itransformer", | |
| "predictions" | |
| ], | |
| "location": "dg_itransformer_predictions.png" | |
| }, | |
| { | |
| "name": "dg itransformer training", | |
| "tags": [ | |
| "dg", | |
| "itransformer", | |
| "training" | |
| ], | |
| "location": "dg_itransformer_training.png" | |
| }, | |
| { | |
| "name": "ensemble comparison", | |
| "tags": [ | |
| "ensemble", | |
| "comparison" | |
| ], | |
| "location": "ensemble_comparison.png" | |
| }, | |
| { | |
| "name": "ensemble weights", | |
| "tags": [ | |
| "ensemble", | |
| "weights" | |
| ], | |
| "location": "ensemble_weights.png" | |
| }, | |
| { | |
| "name": "feature correlation heatmap", | |
| "tags": [ | |
| "feature", | |
| "correlation", | |
| "heatmap" | |
| ], | |
| "location": "feature_correlation_heatmap.png" | |
| }, | |
| { | |
| "name": "impedance evolution", | |
| "tags": [ | |
| "impedance", | |
| "evolution" | |
| ], | |
| "location": "impedance_evolution.png" | |
| }, | |
| { | |
| "name": "lstm actual vs predicted", | |
| "tags": [ | |
| "lstm", | |
| "actual", | |
| "vs", | |
| "predicted" | |
| ], | |
| "location": "lstm_actual_vs_predicted.png" | |
| }, | |
| { | |
| "name": "lstm training curves", | |
| "tags": [ | |
| "lstm", | |
| "training", | |
| "curves" | |
| ], | |
| "location": "lstm_training_curves.png" | |
| }, | |
| { | |
| "name": "mc dropout uncertainty lstm", | |
| "tags": [ | |
| "mc", | |
| "dropout", | |
| "uncertainty", | |
| "lstm" | |
| ], | |
| "location": "mc_dropout_uncertainty_lstm.png" | |
| }, | |
| { | |
| "name": "radar top6", | |
| "tags": [ | |
| "radar", | |
| "top6" | |
| ], | |
| "location": "radar_top6.png" | |
| }, | |
| { | |
| "name": "re vs rct scatter", | |
| "tags": [ | |
| "re", | |
| "vs", | |
| "rct", | |
| "scatter" | |
| ], | |
| "location": "re_vs_rct_scatter.png" | |
| }, | |
| { | |
| "name": "shap xgboost soh", | |
| "tags": [ | |
| "shap", | |
| "xgboost", | |
| "soh" | |
| ], | |
| "location": "shap_xgboost_soh.png" | |
| }, | |
| { | |
| "name": "soc coulomb counting demo", | |
| "tags": [ | |
| "soc", | |
| "coulomb", | |
| "counting", | |
| "demo" | |
| ], | |
| "location": "soc_coulomb_counting_demo.png" | |
| }, | |
| { | |
| "name": "soh degradation trends", | |
| "tags": [ | |
| "soh", | |
| "degradation", | |
| "trends" | |
| ], | |
| "location": "soh_degradation_trends.png" | |
| }, | |
| { | |
| "name": "soh distribution", | |
| "tags": [ | |
| "soh", | |
| "distribution" | |
| ], | |
| "location": "soh_distribution.png" | |
| }, | |
| { | |
| "name": "transformer pt training curves", | |
| "tags": [ | |
| "transformer", | |
| "pt", | |
| "training", | |
| "curves" | |
| ], | |
| "location": "transformer_pt_training_curves.png" | |
| }, | |
| { | |
| "name": "transformer tf training curves", | |
| "tags": [ | |
| "transformer", | |
| "tf", | |
| "training", | |
| "curves" | |
| ], | |
| "location": "transformer_tf_training_curves.png" | |
| }, | |
| { | |
| "name": "unified model comparison", | |
| "tags": [ | |
| "unified", | |
| "model", | |
| "comparison" | |
| ], | |
| "location": "unified_model_comparison.png" | |
| }, | |
| { | |
| "name": "vae anomaly detection", | |
| "tags": [ | |
| "vae", | |
| "anomaly", | |
| "detection" | |
| ], | |
| "location": "vae_anomaly_detection.png" | |
| }, | |
| { | |
| "name": "vae latent umap", | |
| "tags": [ | |
| "vae", | |
| "latent", | |
| "umap" | |
| ], | |
| "location": "vae_latent_umap.png" | |
| }, | |
| { | |
| "name": "vae lstm prediction", | |
| "tags": [ | |
| "vae", | |
| "lstm", | |
| "prediction" | |
| ], | |
| "location": "vae_lstm_prediction.png" | |
| }, | |
| { | |
| "name": "voltage surface 3d", | |
| "tags": [ | |
| "voltage", | |
| "surface", | |
| "3d" | |
| ], | |
| "location": "voltage_surface_3d.png" | |
| } | |
| ] | |
| } |