Prediction of gas yield generated by energy recovery from municipal solid waste using deep neural network and moth-flame optimization algorithm. (15th August 2021)

• Record Type: Journal Article
• Authors: Yang, Libing; Nguyen, Hoang; Bui, Xuan-Nam; Nguyen-Thoi, Trung; Zhou, Jian; Huang, Jianing
• Is Part Of: Journal of cleaner production. Volume 311(2021)
• Publication Date: 2021-08-15
• Subjects: Energy recovery -- Municipal solid waste -- Cleaner production -- Moth-flame optimization -- Deep neural network; Factory and trade waste -- Management -- Periodicals; Manufactures -- Environmental aspects -- Periodicals; Déchets industriels -- Gestion -- Périodiques; Usines -- Aspect de l'environnement -- Périodiques; 628.5
• DOI: 10.1016/j.jclepro.2021.127672
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: In recent years, the strong development of urban areas and rapid population growth have contributed significantly to environmental pollution issues, especially SW. Of those, municipal solid waste (MSW) is considered a major concern of waste treatment plants. Nowadays, with the development of science and technology, MSW has been treated and recycled to recover energy. However, the issue of energy recovery and optimization from MSW remains a challenge for waste treatment plants. Therefore, a novel artificial intelligence approach was proposed in this study for predicting the gas yield (GY) generated by energy recovery from MSW with high accuracy. Accordingly, a deep neural network (DNN) was developed to predict GY from MSW. Subsequently, the Moth-Flame optimization (MFO) algorithm was applied to optimize the DNN model and improve its accuracy, called MFO-DNN model. The findings revealed that both the DNN and MFO-DNN models predicted GY very well. Of those, the proposed MFO-DNN model provided dominant performance than the DNN model. Based on the proposed MFO-DNN model, the toxic gases can be thoroughly controlled and optimized to recover the gas field from MSW for waste treatment plants, minimizing negative impacts on the surrounding environment. Highlights: Gas yield generated by energy recovery from municipal solid waste was investigated. Deep neural network (DNN) was applied to predict gas yield recovered from MSW. Moth-flame optimization was applied to improve the DNN's accuracy. The MFO-DNN was proposed as a robust intelligent model for predicting gas yield.