Diagnosing Faults in Wastewater Systems: A Data-Driven Approach to Handle Imbalanced Big Data

Process monitoring is essential in industrial settings to ensure system functionality, necessitating the identification and understanding of fault causes. While a substantial body of research focuses on fault detection, fault diagnosis has received significantly less attention. Typically, faults originate either from abnormal instrument behavior, indicating the need for calibration or replacement, or from process faults, signaling a malfunction within the system. A primary objective of this study is to apply the proposed fault diagnosis methodology to a benchmark that closely mirrors real-world conditions. Specifically, we introduce a fault diagnosis framework for a wastewater treatment plant (WWTP) that effectively addresses the challenges posed by imbalanced big data commonly encountered in large-scale systems. In our study, four distinct fault scenarios were investigated: fault-free conditions, process faults only, sensor faults only, and simultaneous sensor and process faults. To enhance our research, we explored various techniques and approaches to optimally address the fault diagnosis problem. Implementing an undersampling technique based on clustering and determining appropriate hyperparameters proved challenging, alongside deciding the most effective approach for undersampling. Additionally, advanced time-series models, including Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM), were employed, with particular emphasis on identifying the correct regularization factor and number of epochs being critical. When optimal model parameters are selected, each fault scenario achieves an accuracy of at least�90%, and the maximum simulation time does not exceed�15 minutes. Furthermore, we developed a Python-based GUI for this study to enable users to fully explore the capabilities of the proposed fault diagnosis algorithm.