TY - GEN
T1 - Monitoring the Quality of Water Production Process in Surabaya Using Max-MCUSUM Control Chart Based on Residual Deep Learning LSTM Model
AU - Aliyah, Veneza Rafa
AU - Ahsan, Muhammad
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - This study examines the water quality at the Surya Sembada water treatment plant in Surabaya, Indonesia, by analyzing turbidity, pH, permanganate index, and chlorine residual. Recognizing the inherent autocorrelation within these parameters, a Long Short-Term Memory (LSTM) neural network was implemented to model their temporal dependencies. Optimal LSTM hyperparameters were determined through rigorous experimentation using MSE, RMSE, and MAE as evaluation metrics. Residuals from the LSTM model were subsequently analyzed using a Maximum Multivariate Cumulative Sum (Max-MCUSUM) control chart. Phase I analysis indicated a statistically non-conforming process, suggesting a significant process shift. Subsequent Phase II monitoring confirmed ongoing process instability. The application of LSTM modeling and Max-MCUSUM control charting in this study provides a robust framework for early detection of anomalies and process deviations in water treatment operations, facilitating timely corrective actions and improvements in water quality controls. The Max-MCUSUM control chart demonstrated enhanced sensitivity to multivariate process shifts and the ability to identify subtle anomalies, making it an invaluable tool for maintaining and improving the consistency of water treatment processes.
AB - This study examines the water quality at the Surya Sembada water treatment plant in Surabaya, Indonesia, by analyzing turbidity, pH, permanganate index, and chlorine residual. Recognizing the inherent autocorrelation within these parameters, a Long Short-Term Memory (LSTM) neural network was implemented to model their temporal dependencies. Optimal LSTM hyperparameters were determined through rigorous experimentation using MSE, RMSE, and MAE as evaluation metrics. Residuals from the LSTM model were subsequently analyzed using a Maximum Multivariate Cumulative Sum (Max-MCUSUM) control chart. Phase I analysis indicated a statistically non-conforming process, suggesting a significant process shift. Subsequent Phase II monitoring confirmed ongoing process instability. The application of LSTM modeling and Max-MCUSUM control charting in this study provides a robust framework for early detection of anomalies and process deviations in water treatment operations, facilitating timely corrective actions and improvements in water quality controls. The Max-MCUSUM control chart demonstrated enhanced sensitivity to multivariate process shifts and the ability to identify subtle anomalies, making it an invaluable tool for maintaining and improving the consistency of water treatment processes.
KW - Control chart
KW - LSTM
KW - Max-MCUSUM
KW - Statistical quality
UR - https://www.scopus.com/pages/publications/105007542859
U2 - 10.1007/978-3-031-85926-7_15
DO - 10.1007/978-3-031-85926-7_15
M3 - Conference contribution
AN - SCOPUS:105007542859
SN - 9783031859250
T3 - Springer Proceedings in Mathematics and Statistics
SP - 211
EP - 226
BT - Mathematics for Sustainable Industry - ISMI 2024
A2 - Embong, Ahmad Fadillah
A2 - Zainuddin, Zaitul Marlizawati
A2 - Shabri, Ani
A2 - Yussof, Fatin Nadiah Mohamed
PB - Springer
T2 - 5th International Seminar on Mathematics in Industry, ISMI 2024
Y2 - 9 September 2024 through 11 September 2024
ER -