Abstract
The present study developed, evaluated and compared the prediction and simulating efficiency of both, the response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS) approaches for oil removal using a liquid-liquid hydrocyclone (LLHC) from surfactant and polymer (SP) produced water. Six parameters were involved in the process: the surfactant concentration, polymer concentration, salinity, initial oil concentration, feed flowrate and split ratio. For RSM, D-optimal design was used, while the ANFIS model was developed in term of this process with the Gaussian membership function. All models were compared statistically based on the training and testing data set by the coefficient of determination (R 2 ), root-mean-square error (RMSE), average absolute percentage error (AAPE), standard deviation (STD), minimum error, and maximum error. The R 2 for RSM and the ANFIS model for the testing set were of 0.972 and 0.999, respectively. Both models made good predictions. Trend analysis has been done to confirm the applicability of the models. From the results, it shows that the ANFIS model was more precise compared to the RSM model, which proves that the ANFIS is a powerful tool for modelling and optimizing the efficiency of the oil removal from the LLHC in the presence of SP.
Highlights
The oily wastewater produced in the petroleum and food industry, the water that falls from the board ship, among others, are hazardous to both nature and human health and it contaminates water daily
In this study, response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS) models were developed to predict the efficiency of oil removal from the surfactant and polymer (SP) produced water of the liquid-liquid hydrocyclone (LLHC)
The D-optimal design was used for the RSM and Gaussian membership function was used for the ANFIS modeling
Summary
The oily wastewater produced in the petroleum and food industry, the water that falls from the board ship, among others, are hazardous to both nature and human health and it contaminates water daily. A. Ayoub: Predicting the Efficiency of the Oil Removal From SP Produced Water by Using LLHC. The efficiency of the LLHC was governed by factors such as the initial oil concentration, temperature, and by operating parameters of the LLHC such as the feed flowrate and FIGURE 2. The efficiency of the LLHC diminishes during the implementation of the Enhanced Oil Recovery (EOR) because of a surfactant and polymer (SP) flooding, which is due to the breakthrough of the surfactant and polymer into the produced water [12]. LLHC performance can be improved fine-tuning the process, for example, by adjusting the feed flowrate and split ratio. Six parameters were involved in the process: the surfactant concentration, polymer concentration, salinity, initial oil concentration, feed flowrate, and split ratio. All models were compared statistically, based on the training and validation data set by the coefficient of determination (R2), root-mean-square error (RMSE), average absolute percentage error (AAPE), standard deviation (STD), minimum error, and maximum error
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
