Application of machine learning in anaerobic digestion: Perspectives and challenges

被引：164

作者：

Cruz, Ianny Andrade ^{[1
]}

Chuenchart, Wachiranon ^{[2
,3
]}

Long, Fei ^{[4
]}

Surendra, K. C. ^{[3
,5
]}

Andrade, Larissa Renata Santos ^{[1
]}

Bilal, Muhammad ^{[6
]}

Liu, Hong ^{[4
]}

Figueiredo, Renan Tavares ^{[1
,7
]}

Khanal, Samir Kumar ^{[2
,3
]}

Ferreira, Luiz Fernando Romanholo ^{[1
,7
]}

机构：

[1] Univ Tiradentes, Grad Program Proc Engn, Murilo Dantas,300,Farol andia, BR-49032490 Aracaju, SE, Brazil

[2] Univ Hawaii Manoa, Dept Civil & Environm Engn, 2540 Dole St, Honolulu, HI 96822 USA

[3] Univ Hawaii Manoa, Dept Mol Biosci & Bioengn, 1955 East West Rd, Honolulu, HI 96822 USA

[4] Oregon State Univ, Dept Biol & Ecol Engn, Corvallis, OR 97333 USA

[5] Global Inst Interdisciplinary Studies, Kathmandu 44600, Nepal

[6] Huaiyin Inst Technol, Sch Life Sci & Food Engn, Huaian 223003, Peoples R China

[7] Inst Technol & Res, Murilo Dantas,300,Farolandia, BR-49032490 Aracaju, SE, Brazil

来源：

BIORESOURCE TECHNOLOGY | 2022年 / 345卷

基金：

美国农业部;

关键词：

Anaerobic digestion; Process instability; Process optimization; Machine learning; Modeling; ARTIFICIAL NEURAL-NETWORK; PARTICLE SWARM OPTIMIZATION; MUNICIPAL SOLID-WASTE; BIOGAS PRODUCTION; CO-DIGESTION; PERFORMANCE PREDICTION; RELIABILITY-ANALYSIS; GENETIC ALGORITHM; MODIFIED ADM1; RANDOM FOREST;

D O I：

10.1016/j.biortech.2021.126433

中图分类号：

S2 [农业工程];

学科分类号：

0828 ;

摘要：

Anaerobic digestion (AD) is widely adopted for remediating diverse organic wastes with simultaneous production of renewable energy and nutrient-rich digestate. AD process, however, suffers from instability, thereby adversely affecting biogas production. There have been significant efforts in developing strategies to control the AD process to maintain process stability and predict AD performance. Among these strategies, machine learning (ML) has gained significant interest in recent years in AD process optimization, prediction of uncertain parameters, detection of perturbations, and real-time monitoring. ML uses inductive inference to generalize correlations between input and output data, subsequently used to make informed decisions in new circumstances. This review aims to critically examine ML as applied to the AD process and provides an in-depth assessment of important algorithms (ANN, ANFIS, SVM, RF, GA, and PSO) and their applications in AD modeling. The review also outlines some challenges and perspectives of ML, and highlights future research directions.

引用

页数：13

共 112 条

[1] Modeling and optimization of biogas production from a waste digester using artificial neural network and genetic algorithm [J].