A Hybrid P-Graph And WEKA Approach In Decision-Making: Waste Conversion Technologies Selection

Process system engineering approaches have a considerably broader reach, which is one of the benefits for decision-makers. Making a decision, however, has many drawbacks. It includes biased decisions, timeconsuming analyses, and an unpredictable future. A decision-making integration framework based on hybrid process network synthesis and machine learning was presented in this study. The municipal solid waste management case study uses to demonstrate the applicability decision-making framework. The focus of this paper is to facilitate equipment selection for municipal solid waste management. P-graph was used to generate the 160 possible structures. Then, using the WEKA software, the data from the feasible structure would be processed and evaluated using the chosen algorithm. The J48 is the best model for equipment selection using an 80:20 ratio train and test learning technique in WEKA. The kappa statistics J48 algorithm function for the training and testing dataset is 0.9722 and 1. The mean absolute error and root mean square error are 0.0042 and 0.0354. The decision-making integration framework represents by a graphical user interface in MATLAB. The focus of user interface for selection of waste conversion technologies. As a result, the model can be used to determine the best municipal solid waste conversion technology.

Automated summary

This study presents a decision-making integration framework based on hybrid process network synthesis and machine learning for equipment selection in municipal solid waste management. The P-graph is used to generate possible structures, and data from feasible structures are processed and evaluated using WEKA software. The J48 model is found to be the best for equipment selection with an 80:20 train and test learning technique. The framework is represented by a graphical user interface in MATLAB, focusing on the selection of waste conversion technologies.