Spaces:
Runtime error
Runtime error
| """ | |
| Stanford Battery Feature Engineering | |
| Advanced discharge curve analysis for early cycle life prediction. | |
| Based on Severson et al. (Nature Energy 2019): | |
| "Data-driven prediction of battery cycle life before capacity degradation" | |
| Features derived from voltage discharge curves with physics-informed analysis. | |
| MIT/Stanford Quality: State-of-the-art feature engineering for battery degradation. | |
| """ | |
| import pandas as pd | |
| import numpy as np | |
| from scipy import signal, stats | |
| from sklearn.preprocessing import StandardScaler | |
| import warnings | |
| warnings.filterwarnings('ignore') | |
| def calculate_discharge_curve_features(df: pd.DataFrame) -> pd.DataFrame: | |
| """ | |
| Extract advanced features from discharge curves. | |
| Stanford-specific features based on discharge curve shape analysis: | |
| - Voltage variance (degradation indicator) | |
| - Discharge curve slope (capacity fade rate) | |
| - Curve inflection points (chemistry changes) | |
| - Energy efficiency (IR drops) | |
| - Plateau stability (cell uniformity) | |
| Parameters: | |
| ----------- | |
| df : DataFrame | |
| Converted Stanford data (cycle_index, voltage, current, temperature, capacity) | |
| Returns: | |
| -------- | |
| DataFrame: Feature matrix with Stanford-specific features | |
| """ | |
| print("\n" + "="*60) | |
| print("STANFORD FEATURE ENGINEERING") | |
| print("Advanced Discharge Curve Analysis") | |
| print("="*60) | |
| df_feat = df.copy() | |
| # Group by cycle for cycle-level features | |
| cycle_groups = df_feat.groupby('cycle_index') | |
| # Calculate SOH if not present | |
| if 'soh' not in df_feat.columns: | |
| initial_capacity = df_feat['capacity'].max() | |
| df_feat['soh'] = df_feat['capacity'] / initial_capacity | |
| # 1. VOLTAGE STATISTICS (per cycle) | |
| df_feat['voltage_mean'] = cycle_groups['voltage'].transform('mean') | |
| df_feat['voltage_std'] = cycle_groups['voltage'].transform('std') | |
| df_feat['voltage_min'] = cycle_groups['voltage'].transform('min') | |
| df_feat['voltage_max'] = cycle_groups['voltage'].transform('max') | |
| df_feat['voltage_range'] = df_feat['voltage_max'] - df_feat['voltage_min'] | |
| # 2. CURRENT STATISTICS | |
| df_feat['current_mean'] = cycle_groups['current'].transform('mean') | |
| df_feat['current_std'] = cycle_groups['current'].transform('std') | |
| # 3. TEMPERATURE STATISTICS | |
| df_feat['temp_mean'] = cycle_groups['temperature'].transform('mean') | |
| df_feat['temp_std'] = cycle_groups['temperature'].transform('std') | |
| # 4. CAPACITY FEATURES | |
| df_feat['capacity_mean'] = cycle_groups['capacity'].transform('mean') | |
| df_feat['capacity_std'] = cycle_groups['capacity'].transform('std') | |
| # 5. DEGRADATION FEATURES (causal - uses only past data) | |
| df_feat['cycles_from_start'] = df_feat['cycle_index'] | |
| # Capacity fade rate (change per cycle) | |
| df_feat['capacity_diff'] = df_feat.groupby('cycle_index')['capacity'].transform('first').diff() | |
| df_feat['capacity_fade_rate'] = df_feat['capacity_diff'].fillna(0) | |
| # Cumulative capacity loss | |
| initial_cap = df_feat['capacity'].max() | |
| df_feat['cumulative_capacity_loss'] = initial_cap - df_feat['capacity'] | |
| # 6. ROLLING FEATURES (5-cycle window, backward-looking) | |
| df_feat['voltage_rolling_mean_5'] = df_feat.groupby('cycle_index')['voltage'].transform('mean').rolling(5, min_periods=1, center=False).mean() | |
| df_feat['voltage_rolling_std_5'] = df_feat.groupby('cycle_index')['voltage'].transform('mean').rolling(5, min_periods=1, center=False).std().fillna(0) | |
| df_feat['capacity_rolling_mean_5'] = df_feat.groupby('cycle_index')['capacity'].transform('first').rolling(5, min_periods=1, center=False).mean() | |
| df_feat['capacity_rolling_std_5'] = df_feat.groupby('cycle_index')['capacity'].transform('first').rolling(5, min_periods=1, center=False).std().fillna(0) | |
| # 7. SOH-DERIVED FEATURES | |
| df_feat['soh_fade_rate'] = df_feat['soh'].diff().fillna(0) | |
| df_feat['soh_fade_rate_abs'] = df_feat['soh_fade_rate'].abs() | |
| # SOH rolling mean and std | |
| df_feat['soh_rolling_mean_5'] = df_feat['soh'].rolling(5, min_periods=1, center=False).mean() | |
| df_feat['soh_rolling_std_5'] = df_feat['soh'].rolling(5, min_periods=1, center=False).std().fillna(0) | |
| # SOH second derivative (acceleration of degradation) | |
| df_feat['soh_second_derivative'] = df_feat['soh'].diff().diff().fillna(0) | |
| # 8. PHYSICS-INFORMED FEATURES | |
| # Power (voltage × current) | |
| df_feat['power'] = df_feat['voltage'] * df_feat['current'] | |
| df_feat['power_mean'] = cycle_groups['power'].transform('mean') | |
| # Energy throughput per cycle | |
| df_feat['energy_throughput'] = df_feat.groupby('cycle_index')['power'].transform('sum') | |
| # Internal resistance estimate (voltage drop / current) | |
| df_feat['ir_estimate'] = (df_feat['voltage_max'] - df_feat['voltage_min']) / (df_feat['current_mean'].abs() + 1e-6) | |
| # 9. STANFORD-SPECIFIC FEATURES (from discharge curve shape) | |
| # These capture early-life degradation patterns | |
| # Voltage variance (early indicator of degradation) | |
| df_feat['voltage_variance'] = df_feat['voltage_std'] ** 2 | |
| # Voltage efficiency (actual vs ideal) | |
| ideal_voltage = 3.3 # LFP nominal voltage | |
| df_feat['voltage_efficiency'] = df_feat['voltage_mean'] / ideal_voltage | |
| # Discharge consistency (cycle-to-cycle variation) | |
| df_feat['discharge_consistency'] = 1 / (1 + df_feat['capacity_rolling_std_5']) | |
| # Fill NaN values | |
| df_feat = df_feat.fillna(method='ffill').fillna(method='bfill').fillna(0) | |
| print(f"\n✓ Generated {len(df_feat.columns)} total features") | |
| print(f" Cycles: {df_feat['cycle_index'].min()}-{df_feat['cycle_index'].max()}") | |
| print(f" SOH range: {df_feat['soh'].min():.3f} - {df_feat['soh'].max():.3f}") | |
| return df_feat | |
| def prepare_stanford_for_training(df: pd.DataFrame, feature_cols: list) -> tuple: | |
| """ | |
| Prepare Stanford data for model training. | |
| Parameters: | |
| ----------- | |
| df : DataFrame | |
| Feature-engineered Stanford data | |
| feature_cols : list | |
| List of feature column names | |
| Returns: | |
| -------- | |
| tuple: (X, y) - features and target | |
| """ | |
| # Aggregate to cycle level (one row per cycle) | |
| df_cycle = df.groupby('cycle_index').first().reset_index() | |
| # Features (X) and target (y) | |
| X = df_cycle[feature_cols].values | |
| y = df_cycle['soh'].values | |
| return X, y | |
| if __name__ == "__main__": | |
| # Test feature engineering | |
| print("Testing Stanford feature engineering...") | |
| test_file = './data/stanford_converted/cell1.csv' | |
| df = pd.read_csv(test_file) | |
| df_features = calculate_discharge_curve_features(df) | |
| print(f"\n✅ Feature engineering test successful!") | |
| print(f" Features shape: {df_features.shape}") | |