In predictive maintenance of equipment, deep learning-based time series anomaly detection has garnered significant attention; however, pure deep learning approaches often fail to achieve sufficient accuracy on real-world data. This study proposes a hybrid approach that integrates 64-dimensional time series embeddings from Granite TinyTimeMixer with 28-dimensional statistical features based on domain knowledge for HVAC equipment anomaly prediction tasks. Specifically, we combine time series embeddings extracted from a Granite TinyTimeMixer encoder fine-tuned with LoRA (Low-Rank Adaptation) and 28 types of statistical features including trend, volatility, and drawdown indicators, which are then learned using a LightGBM gradient boosting classifier. In experiments using 64 equipment units and 51,564 samples, we achieved Precision of 91--95\% and ROC-AUC of 0.995 for anomaly prediction at 30-day, 60-day, and 90-day horizons. Furthermore, we achieved production-ready performance with a false positive rate of 1.1\% or less and a detection rate of 88--94\%, demonstrating the effectiveness of the system for predictive maintenance applications. This work demonstrates that practical anomaly detection systems can be realized by leveraging the complementary strengths between deep learning's representation learning capabilities and statistical feature engineering.

翻译：在设备预测性维护领域，基于深度学习的时序异常检测方法已受到广泛关注；然而，纯深度学习方法在实际数据上往往难以达到足够的精度。本研究提出一种混合方法，将来自Granite TinyTimeMixer的64维时序嵌入与基于领域知识构建的28维统计特征相结合，用于暖通空调（HVAC）设备的异常预测任务。具体而言，我们融合了通过LoRA（低秩自适应）微调的Granite TinyTimeMixer编码器提取的时序嵌入，以及包含趋势、波动率和回撤指标在内的28类统计特征，并采用LightGBM梯度提升分类器进行学习。在使用64台设备单元和51,564个样本的实验中，我们在30天、60天和90天预测窗口上实现了91–95%的精确率与0.995的ROC-AUC值。此外，系统达到了生产就绪的性能水平，误报率不高于1.1%，检出率达到88–94%，证明了该系统在预测性维护应用中的有效性。本研究表明，通过结合深度学习表征学习能力与统计特征工程的优势，可以实现实用的异常检测系统。