Prototype Memory and Contrastive Learning Based Unsupervised Anomaly Detection for Time Series

Multivariate time series anomaly detection (MTSAD) is a critical task for real-time risk control and fault diagnosis in industrial monitoring, aerospace, and financial domains. Unsupervised MTSAD confronts three core challenges: label scarcity in practical scenarios, diverse anomaly patterns that demand adaptive modeling, and weak feature discriminability between normal and anomalous samples. To address these challenges, we propose a Prototype Memory and Contrastive Learning Based Unsupervised Anomaly Detection for Multivariate Time Series method named PC-UAD. PC-UAD comprises three core modules with hierarchical functionalities: (1) A Temporal PatchEmbedder, which adopts learnable positional encoding for dynamic temporal representation and incorporates channel projection to model adaptive cross-sensor dependencies in multivariate data; (2) A Prototype Memory Encoder, which embeds a prototype attention mechanism to explicitly memorize typical normal patterns, forming a “normal pattern dictionary” that enhances the model’s perception of normal behavioral boundaries; (3) A ContrastFusion module, which leverages contrastive learning to amplify feature distribution discrepancies between normal and anomalous data, strengthening the model’s ability to distinguish subtle anomalies. Experiments on five public multivariate time series datasets demonstrate that our method achieves superior detection accuracy compared to eight state-of-the-art approaches, with the average F1-score and ROC-AUC both ranking first.