Abstract: In view of the increasing demand for real-time monitoring of the closed state of the smart refrigerator door, and the traditional door magnetic or mechanical switch has some problems, such as complex assembly, easy failure of low-temperature condensation and high cost, etc., a door ajar detection method based on refrigerator operation big data is proposed. This method does not need to add new hardware, but uses a big data platform to build an off-line abnormal database with compressor status bit, evaporator temperature, refrigeration temperature, freezing room temperature, defrosting cycle and other related multi-source operation data as inputs, which provides a low-cost and landing detection solution for intelligent operation and maintenance of refrigerators.

Key words: Refrigerator, Door not closed tightly, Big data, Operation data, Anomaly detection