Sensors, while more widely implemented in industry, have generated a large number of high-dimension unlabeled time series data during the process of the complicated producing. If putting these data to use, we can predict and preclude malfunctions of specific industrial facilities so that there will be less pecuniary lost. In this paper, we propose a malfunction predicting algorithm based on transfer learning. We use time windows due to the periodicity of industrial data, targeting at transfer learning among pieces of equipment with different sampling rate to address the problem of learning from unlabeled data. Rationale proofs and experiments indicate the efficacy of the algorithm and the prediction accuracy reaches 97%.

传感器虽然在工业中得到了更广泛的应用，但在复杂的生产过程中产生了大量高维未标记的时间序列数据。如果使用这些数据，我们可以预测和排除特定工业设施的故障，从而减少金钱损失。在本文中，我们提出了一种基于迁移学习的故障预测算法。由于工业数据的周期性，我们使用时间窗口，针对不同采样率的设备之间的迁移学习来解决从未标记数据中学习的问题。原理证明和实验表明该算法是有效的，预测准确率达到97%。