Development of effluent removal prediction model efficiency in septic sludge treatment plant through clonal selection algorithm Sie Chun Ting a, * , A.R. Ismail b , M.A. Malek a a Department of Civil Engineering, Universiti Tenaga Nasional, IKRAM-UNITEN Road, 43000 Kajang, Selangor, Malaysia b Department of Computer Science, Kulliyyah of Information and CommunicationTechnology, International Islamic University Malaysia, P.O. Box 10, 50728 Kuala Lumpur, Malaysia article info Article history: Received 28 February 2013 Received in revised form 20 July 2013 Accepted 25 July 2013 Available online 22 August 2013 Keywords: Artificial immune system Chemical oxygen demand Prediction Septic sludge treatment plant Total suspended solids abstract This study aims at developing a novel effluent removal management tool for septic sludge treatment plants (SSTP) using a clonal selection algorithm (CSA). The proposed CSA articulates the idea of utilizing an artificial immune system (AIS) to identify the behaviour of the SSTP, that is, using a sequence batch reactor (SBR) technology for treatment processes. The novelty of this study is the development of a predictive SSTP model for effluent discharge adopting the human immune system. Septic sludge from the individual septic tanks and package plants will be desuldged and treated in SSTP before discharging the wastewater into awaterway. The Borneo Island of Sarawak is selected as the case study. Currently, there are only two SSTPs in Sarawak, namely the Matang SSTP and the Sibu SSTP, and they are both using SBR technology. Monthly effluent discharges from 2007 to 2011 in the Matang SSTP are used in this study. Cross-validation is performed using data from the Sibu SSTP from April 2011 to July 2012. Both chemical oxygen demand (COD) and total suspended solids (TSS) in the effluent were analysed in this study. The model was validated and tested before forecasting the future effluent performance. The CSA-based SSTP model was simulated using MATLAB 7.10. The rootmean square error (RMSE), mean absolute percentage error (MAPE), and correction coefficient (R) were used as performance indexes. In this study, it was found that the proposed prediction model was successful up to 84 months for the COD and 109 months for the TSS. In conclusion, the proposed CSA-based SSTP prediction model is indeed beneficial as an engineering tool to forecast the long-run performance of the SSTP and in turn, prevents infringement of future environmental balance in other towns in Sarawak. Ó 2013 Elsevier Ltd. All rights reserved. 1. Introduction Sustainability in sanitation management is not only an option; it is a necessity. Direct discharge of untreated wastewater has a negative environmental impact and poses health concerns to so- ciety. In developed countries, centralisation in the urban situation is a practice. It contributes to clean water supply and proper sani- tation. Nevertheless, the practice in developing countries is generally otherwise. However, decentralisation systems have gained popularity with the general public in both developed and developing countries (George, 2008). They have the ability of minimizing potential residual effluent removal. For instance, in Venice, Italy’s historical centre, there are more than 140 small decentralised biological wastewater treatment plants as well as a huge number of septic tanks (Tromellini, 2008; IWA, 2011). This scenario is similar to the Borneo Island of Sarawak where the major towns such as Kuching, Sibu, and Miri are still using septic tanks for treatment. Septic tanks are used to provide initial treatment by intercepting and separating solid faecal matter from the liquid. However, septic tanks must be de-sludged in four-year periods to avoid sewage overflow to waterways. This is enforced by the Local Authorities (Compulsory Desludging of Septic Tanks) By-law, 1998. The septic sludge is treated in a septic sludge treatment plant (SSTP), using a sequence batch reactor (SBR). Wastewater treatment processes are very complex, non-linear, and characterized by many uncertainties within the influent pa- rameters, the structure, and the coefficients of the model (Sergiu et al., 2007). Based on a study by Huang et al., in 2010, efficient operations of a wastewater treatment process is limited because it is affected by a variety of physical, chemical, and biological factors. SBR has been proposed in literature adapting, with the physical module, the activated sludge models (ASMs) (Henze et al., 2000). * Corresponding author. Tel.: þ60 168557057. E-mail addresses: sie_chun@hotmail.com (S.C. Ting), amelia@iium.edu.my (A.R. Ismail), marlinda@uniten.edu.my (M.A. Malek). Contents lists available at ScienceDirect Journal of Environmental Management journal homepage: www.elsevier.com/locate/jenvman 0301-4797/$ e see front matter Ó 2013 Elsevier Ltd. All rights reserved. http://dx.doi.org/10.1016/j.jenvman.2013.07.022 Journal of Environmental Management 129 (2013) 260e265