Add PyTorch/ONNX prediction models with physics fallback

- Train 3 MLP networks (acid speed 14→1, tension 4→10, quality 6→2)
  on 12,000 synthetic samples generated from physics models + noise
- Export pre-trained ONNX models to pt_models/ directory
- Rewrite prediction.py: ONNX inference first, physics fallback if unavailable
- Add onnxruntime + numpy to requirements.txt (Aliyun mirror for Docker)
- Use Tsinghua mirror in Dockerfile for pip installs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.12-slim
 WORKDIR /app
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
 COPY . .
 CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]