In wastewater treatment process (WWTP), abnormal data seriously reduce data quality rendering the application techniques impractical. The implementation of abnormal data detection is challenging due to the nonlinear nature of WWTP. Typically, constructing an accurate anomaly detector requires large amounts of labeled data, which is difficult in practice. Thus, a self-supervised memory enhanced deep clustering method (SMEL) is proposed to detect abnormal data without using any labels. First, a self-supervised deep clustering network, combining stacked autoencoders and the clustering algorithm, leverages unlabeled data to extract nonlinear features and capture the normal pattern. Second, an adaptive weight objective function, jointly optimizing the reconstruct error and clustering error, is designed to obtain a robust clustering structure. Third, double memory enhanced modules, consisting of a centroid memory and a score memory, are presented to enhance training stability and detection accuracy. Finally, experiments on three WWTP datasets show that SMEL achieves the highest detection accuracy.

Missing values frequently appearing in the wastewater treatment process are automatically replaced by zero to ensure the implementation of downstream applications. These meaningless zero values bias data distribution and decrease data quality. However, the existing imputation methods treat all values equally without considering the existence of meaningless zero values, affecting the performances of imputation and downstream models. Thus, an attention-guided position-sensitive multiple imputation (APMI) method is proposed. First, a position-sensitive localization attention module selectively focuses on the most informative values, enhancing the ability for observed data utilization. Second, a masked attention multiple imputation module focuses on the observed values and fuses multiple candidate estimations as the final result to improve imputation performance. Third, a joint optimization objective function is designed to ensure the consistency of localization and imputation tasks. The extensive experimental results show that the proposed APMI outperforms existing method imputation performance under different missing rates.