Anomaly Detection for Time Series with Difference Rate Sample Entropy and Generative Adversarial Networks

Abstract

The spontaneous combustion of residual coals in the mined-out area tends to cause an explosion, which is one kind of severe thermodynamic compound disaster of coal mines and leads to serious losses to people's lives and production safety. The prediction and early warning of coal mine thermodynamic disasters are mainly determined by the changes of the index gas concentration pattern in coal mine mined-out areas collected continuously. The time series anomaly pattern detection method is mainly used to reach the state change of gas concentration pattern. The change of gas concentration follows a certain rule as time changes. A great change in the gas concentration indicates the possibility of coal spontaneous combustion and other disasters. To emphasize the features of collected maker gas and overcome the low anomaly detection accuracy caused by the inadequate learning of the normal mode, this paper adopted a method of anomaly detection for time series with difference rate sample entropy and generative adversarial networks. Because the difference rate entropy feature of abnormal data was much larger than that of normal mode, this paper improved the calculation method of the abnormal score by giving different weights to the detection points to enhance the detection rate. To verify the effectiveness of the proposed method, this paper employed simulation models of the mined-out area and adopted coal samples from Dafosi Coal Mine to carry out experiments. Preliminary testing was performed using monitoring data from a coal mine. The experiment compared the entropy results of different time series with the detection results of generative adversarial networks and automatic encoders and showed that the method proposed in this paper had relatively high detection accuracy.

Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window

“…To address the issue, we design a kind of data reconstruction method referencing solution based on partitioned universe of discourse [26] partly which transforms original temporal data into difference sequence [27][28][29] ensuring that the model is more likely dealing with steady-state sequences and associates relative positional information of data captured in the view of whole observation time series to reduce difficulty of model learning to some extent. More than that, we choose to replace all of elements by the last one only keeping their positional information as subsidiaries to maximize timeliness of data without losing too much semantic information of temporal data.…”