基于门控循环单元的工业设备异常检测方法及相关装置

本申请公开了一种基于门控循环单元的工业设备异常检测方法，涉及设备管理技术领域，包括：通过重构模型重构输入状态得到重构状态；输入状态包括设备的多个特征；重构模型中的编码器与解码器均包括门控循环单元；根据输入状态与重构状态计算得到重构误差，并根据重构误差确定异常分数；确定极值指标；根据重构误差与极值指标确定异常阈值；若异常分数超出异常阈值，则判定设备存在异常。该方法能够及时、高效的检测异常。本申请还公开了一种基于门控循环单元的工业设备异常检测装置、设备以及计算机可读存储介质，均具有上述技术效果。 The invention discloses an industrial equipment anomaly detection method based on a gating circulation unit, and relates to the technical field of equipment management, and the method comprises the steps: reconstructing an input state through a reconstruction model, and obtaining a reconstruction state; the input state comprises a plurality of characteristics of the equipment; an encoder and a decoder in the reconstruction model respectively comprise a gating circulation unit; calculating a reconstruction error according to the input state and the reconstruction state, and determining an abnormal score according to the reconstruction error; determining an extreme value index; determining an abnormal threshold according to the reconstruction error and the extreme va