modified: src/config.py

modified:   src/dataset.py
	modified:   src/evaluate.py
	modified:   src/train.py

src/config.py

@@ -10,17 +10,21 @@ BATCH_SIZE = 256
 # Features Configuration
 INPUT_SENSOR = 'WSMS00012'
 OUTPUT_SENSORS = ['WSMS00007', 'WSMS00008', 'WSMS00009', 'WSMS00010', 'WSMS00011']
+INPUT_AXIS = 'value1'   # 底部传感器输入轴（课程要求：X轴）
+OUTPUT_AXIS = 'value3'  # 目标传感器输出轴
 
 # Model Configuration
-CHANNELS = [64, 128, 128, 256] # TCN 各层通道数
-KERNEL_SIZE = 3
+CHANNELS = [64, 64, 128, 128, 256, 256] # TCN 各层通道数
+KERNEL_SIZE = 5
 DROPOUT = 0.2
 
 # Training Configuration
-LEARNING_RATE = 1e-3
+LEARNING_RATE = 1e-4
 EPOCHS = 50
-WEIGHT_DECAY = 1e-4
+WEIGHT_DECAY = 1e-3
+ENABLE_EARLY_STOP = False
+EARLY_STOP_PATIENCE = 15
 
 # Device
 import torch
-DEVICE = 'cuda'
+DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'

src/dataset.py

@@ -7,72 +7,146 @@ from torch.utils.data import Dataset, DataLoader
 from sklearn.preprocessing import StandardScaler
 from config import *
 
+class MultiOutputStandardizer:
+    """Per-channel standardization that ignores missing labels via masks."""
+    def __init__(self, n_outputs):
+        self.n_outputs = n_outputs
+        self.mean_ = np.zeros(n_outputs, dtype=np.float32)
+        self.scale_ = np.ones(n_outputs, dtype=np.float32)
+        self.fitted = False
+
+    def fit(self, y_sequences, mask_sequences):
+        means = []
+        scales = []
+        for c in range(self.n_outputs):
+            valid_values = []
+            for y_seq, m_seq in zip(y_sequences, mask_sequences):
+                valid = m_seq[:, c] > 0.5
+                if np.any(valid):
+                    valid_values.append(y_seq[valid, c])
+            if len(valid_values) == 0:
+                means.append(0.0)
+                scales.append(1.0)
+                continue
+            vals = np.concatenate(valid_values, axis=0)
+            mean = float(np.mean(vals))
+            std = float(np.std(vals))
+            if std < 1e-6:
+                std = 1.0
+            means.append(mean)
+            scales.append(std)
+
+        self.mean_ = np.asarray(means, dtype=np.float32)
+        self.scale_ = np.asarray(scales, dtype=np.float32)
+        self.fitted = True
+
+    def transform(self, y):
+        if not self.fitted:
+            raise RuntimeError("MultiOutputStandardizer must be fitted before transform.")
+        return (y - self.mean_) / self.scale_
+
+    def inverse_transform(self, y):
+        if not self.fitted:
+            raise RuntimeError("MultiOutputStandardizer must be fitted before inverse_transform.")
+        return y * self.scale_ + self.mean_
+
+
 class BuildingDataset(Dataset):
     def __init__(self, file_paths, seq_len, step_size, scaler_X=None, scaler_Y=None, fit_scaler=False):
         self.seq_len = seq_len
         self.X_data = []
         self.Y_data = []
+        self.M_data = []
         self.scaler_X = scaler_X if scaler_X is not None else StandardScaler()
-        self.scaler_Y = scaler_Y if scaler_Y is not None else StandardScaler()
+        self.scaler_Y = scaler_Y if scaler_Y is not None else MultiOutputStandardizer(len(OUTPUT_SENSORS))
 
         raw_X = []
         raw_Y = []
+        raw_M = []
 
         for f in file_paths:
             # 读取数据
             df = pd.read_csv(f)
             # 使用长表格式: code, type, time, value1, value2, value3
             
-            # 提取 012 的 X 轴作为基准
-            df_in = df[df['code'] == INPUT_SENSOR][['time', 'value1']].rename(columns={'value1': 'input_x'})
+            # 提取 012 的输入轴作为基准
+            df_in = df[df['code'] == INPUT_SENSOR][['time', INPUT_AXIS]].rename(columns={INPUT_AXIS: 'input_signal'})
+            if len(df_in) == 0:
+                # 若无输入传感器(如自由衰减数据)，则补零
+                df_in = pd.DataFrame({'time': df['time'].unique()})
+                df_in['input_signal'] = 0.0
             
             # 提取 007~011 的 Z 轴并按时间戳逐步合并 (使用 left join 确保以 df_in 的时间为基准)
             df_merged = df_in
             for sens in OUTPUT_SENSORS:
-                df_out_sens = df[df['code'] == sens][['time', 'value3']].rename(columns={'value3': f'out_{sens}'})
+                df_out_sens = df[df['code'] == sens][['time', OUTPUT_AXIS]].rename(columns={OUTPUT_AXIS: f'out_{sens}'})
                 df_merged = pd.merge(df_merged, df_out_sens, on='time', how='left')
                 
             df_merged = df_merged.sort_values('time').reset_index(drop=True)
-            df_merged = df_merged.interpolate(method='linear').bfill().ffill().fillna(0)
             
             if len(df_merged) == 0:
                 print(f"Warning: Skipping file {f} due to no overlapping timestamps across required sensors.")
                 continue
 
-            x_seq = df_merged['input_x'].values.reshape(-1, 1)
-            # 提取所有 target 传感器的列
+            x_seq = df_merged['input_signal'].values.reshape(-1, 1).astype(np.float32)
+
+            # 提取所有 target 传感器列与可用性掩码
             out_cols = [f'out_{sens}' for sens in OUTPUT_SENSORS]
-            y_seq = df_merged[out_cols].values
+            y_seq = np.zeros((len(df_merged), len(OUTPUT_SENSORS)), dtype=np.float32)
+            m_seq = np.zeros((len(df_merged), len(OUTPUT_SENSORS)), dtype=np.float32)
+            for c, col in enumerate(out_cols):
+                series = df_merged[col]
+                observed = ~series.isna()
+                m_seq[:, c] = observed.astype(np.float32)
+                if observed.any():
+                    filled = series.interpolate(method='linear').bfill().ffill()
+                    y_seq[:, c] = filled.fillna(0.0).values.astype(np.float32)
+                else:
+                    y_seq[:, c] = 0.0
             
             raw_X.append(x_seq)
             raw_Y.append(y_seq)
+            raw_M.append(m_seq)
+
+        if len(raw_X) == 0:
+            raise ValueError("未能从文件中构造出有效序列，请检查数据路径与传感器编码配置。")
             
         # 拼接所有文件数据进行 fit
         X_all = np.vstack(raw_X)
-        Y_all = np.vstack(raw_Y)
         
         if fit_scaler:
             self.scaler_X.fit(X_all)
-            self.scaler_Y.fit(Y_all)
+            self.scaler_Y.fit(raw_Y, raw_M)
             
         # 切分窗口
-        for x_seq, y_seq in zip(raw_X, raw_Y):
+        for x_seq, y_seq, m_seq in zip(raw_X, raw_Y, raw_M):
             x_seq_scaled = self.scaler_X.transform(x_seq)
             y_seq_scaled = self.scaler_Y.transform(y_seq)
+            y_seq_scaled = np.where(m_seq > 0.5, y_seq_scaled, 0.0).astype(np.float32)
             
             for i in range(0, len(x_seq_scaled) - seq_len + 1, step_size):
-                self.X_data.append(x_seq_scaled[i:i+seq_len])
-                self.Y_data.append(y_seq_scaled[i:i+seq_len])
+                x_win = x_seq_scaled[i:i+seq_len]
+                y_win = y_seq_scaled[i:i+seq_len]
+                m_win = m_seq[i:i+seq_len]
+                if np.sum(m_win) <= 0:
+                    continue
+                self.X_data.append(x_win)
+                self.Y_data.append(y_win)
+                self.M_data.append(m_win)
                 
         self.X_data = np.array(self.X_data)
         self.Y_data = np.array(self.Y_data)
+        self.M_data = np.array(self.M_data)
 
     def __len__(self):
         return len(self.X_data)
 
     def __getitem__(self, idx):
-        return torch.tensor(self.X_data[idx], dtype=torch.float32), \
-               torch.tensor(self.Y_data[idx], dtype=torch.float32)
+        return (
+            torch.tensor(self.X_data[idx], dtype=torch.float32),
+            torch.tensor(self.Y_data[idx], dtype=torch.float32),
+            torch.tensor(self.M_data[idx], dtype=torch.float32),
+        )
 
 def get_dataloaders(condition='Non_TMD', include_free_vib=False):
     """

src/evaluate.py

@@ -7,6 +7,8 @@ from model import BuildingTCN
 
 def evaluate_model():
     _, _, test_loader, scaler_X, scaler_Y = get_dataloaders()
+    if test_loader is None:
+        raise ValueError("当前数据配置下没有可用的测试集。")
     
     model = BuildingTCN(input_size=1, output_size=5, num_channels=CHANNELS, 
                         kernel_size=KERNEL_SIZE, dropout=DROPOUT).to(DEVICE)
@@ -17,7 +19,7 @@ def evaluate_model():
     all_targets = []
     
     with torch.no_grad():
-        for inputs, targets in test_loader:
+        for inputs, targets, masks in test_loader:
             inputs = inputs.to(DEVICE)
             outputs = model(inputs)
             

src/train.py

@@ -5,11 +5,10 @@ from config import *
 from dataset import get_dataloaders
 from model import BuildingTCN
 
-def fft_loss(pred, target):
-    """计算频域损失"""
-    pred_fft = torch.fft.rfft(pred, dim=1)
-    target_fft = torch.fft.rfft(target, dim=1)
-    return nn.L1Loss()(torch.abs(pred_fft), torch.abs(target_fft))
+def masked_l1_loss(pred, target, mask):
+    diff = torch.abs(pred - target) * mask
+    denom = mask.sum().clamp(min=1.0)
+    return diff.sum() / denom
 
 def train_model():
     train_loader, val_loader, _, _, _ = get_dataloaders()
@@ -19,25 +18,24 @@ def train_model():
                         kernel_size=KERNEL_SIZE, dropout=DROPOUT).to(DEVICE)
                         
     optimizer = optim.AdamW(model.parameters(), lr=LEARNING_RATE, weight_decay=WEIGHT_DECAY)
-    scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min', patience=3, factor=0.5)
-    mse_criterion = nn.MSELoss()
+    scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min', patience=8, factor=0.5)
     
     best_val_loss = float('inf')
+    no_improve_epochs = 0
+    early_stop_patience = EARLY_STOP_PATIENCE
     
     for epoch in range(EPOCHS):
         model.train()
         train_loss = 0.0
         
-        for inputs, targets in train_loader:
-            inputs, targets = inputs.to(DEVICE), targets.to(DEVICE)
+        for inputs, targets, masks in train_loader:
+            inputs = inputs.to(DEVICE)
+            targets = targets.to(DEVICE)
+            masks = masks.to(DEVICE)
             
             optimizer.zero_grad()
             outputs = model(inputs)
-            
-            # 混合损失：时域 MSE + 频域 FFT (权重可调)
-            loss_t = mse_criterion(outputs, targets)
-            loss_f = fft_loss(outputs, targets)
-            loss = loss_t + 0.1 * loss_f
+            loss = masked_l1_loss(outputs, targets, masks)
             
             loss.backward()
             torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
@@ -49,11 +47,13 @@ def train_model():
         model.eval()
         val_loss = 0.0
         with torch.no_grad():
-            for inputs, targets in val_loader:
-                inputs, targets = inputs.to(DEVICE), targets.to(DEVICE)
+            for inputs, targets, masks in val_loader:
+                inputs = inputs.to(DEVICE)
+                targets = targets.to(DEVICE)
+                masks = masks.to(DEVICE)
                 outputs = model(inputs)
-                loss_t = mse_criterion(outputs, targets)
-                val_loss += loss_t.item()
+                loss = masked_l1_loss(outputs, targets, masks)
+                val_loss += loss.item()
                 
         train_loss /= len(train_loader)
         val_loss /= len(val_loader)
@@ -66,6 +66,12 @@ def train_model():
             best_val_loss = val_loss
             torch.save(model.state_dict(), 'best_model.pth')
             print("  --> Saved Best Model")
+            no_improve_epochs = 0
+        else:
+            no_improve_epochs += 1
+            if ENABLE_EARLY_STOP and no_improve_epochs >= early_stop_patience:
+                print(f"Early stopping at epoch {epoch+1}")
+                break
 
 if __name__ == '__main__':
     train_model()