Adaptive SARIMA Modeling for Continuous Chamber Temperature Tracking in Ultra-Low Temperature Freezers

Ultra-low temperature (ULT) freezers are vital for storing perishable biological materials, requiring continuous monitoring of chamber thermal conditions to ensure sample integrity. A reliable dynamic data-driven model is key for smart proactive surveillance of the ULT freezers through real-time status tracking. However, the dynamic nature of ULT freezers, influenced by external disturbances, demands adaptive models to sustain performance. Complex models thus face challenges due to time-consuming parameter updates. To ensure model prediction performance while minimising model updating time, this study proposes a Seasonal Autoregressive Integrated Moving Average (SARIMA) model-based approach for short-term ULT freezer chamber temperature prediction. This method solely relies on historical chamber temperature data, eliminating the need for additional measurements. Moreover, two adaptive duty cycle length (DCL) selection strategies and a one-step ahead DCL estimation method are developed to address auto-correlation issues caused by recurring duty cycles. Comparative analyses with reference models demonstrate that the SARIMA model, incorporating future DCL effects, excels in one-step prediction and multi-step forecast under stable and variant DCL periods. Moreover, it outperforms the reference models in auto-correlation representation, affirming its reliability in predicting future states. The proposed modelling approach promises an effective method for freezing chamber temperature prediction, enabling continuous status tracking and early fault detection. Moreover, it holds great potential for modelling other critical temperatures in refrigeration systems and facilitating flexible energy operations.