【摘要】 检测铝电解槽阴极压降的异常有利于发现电解槽的异常,对提高经济效益十分有益。而铝电解槽的阴极压降带有时间属性,针对阴极压降的异常检测问题提出一种基于时间序列的异常检测算法。首先把阴极压降时间序列分割成不重叠的子序列,再基于子序列的局部密度判断异常子序列。实验结果表明,该算法能够有效地检测出铝电解槽阴极压降的异常部分。更多还原

【Abstract】 The anomaly detection for the cathode voltage of aluminum reduction cell is benefit to the discovery of the abnormality of the aluminum reduction cell,which is very beneficial to the improvement of the economic benefit. Because the cathode voltage drop of aluminum reduction cell has time attribute,an anomaly detection algorithm based on time series was proposed for the anomaly detection of the cathode voltage. Firstly,the cathode voltage time series was divided into non-overlapping sub-sequences,and then the abnormal sub-sequences were judged based on the local density of sub-sequences.The experimental results showed that the algorithm can effectively detect the abnormal part of the cathode voltage in the aluminum reduction cell.更多还原