Yadong Ge , Junyu Tao , Zhi Wang , Lan Mu , Wei Guo , Zhanjun Cheng , Beibei Yan , Yan Shi , Hong Su , Guanyi Chen
{"title":"厌氧消化模型 No.1 号厌氧消化模型与机器学习的混合方法,用于连续厌氧消化工艺的建模和优化","authors":"Yadong Ge , Junyu Tao , Zhi Wang , Lan Mu , Wei Guo , Zhanjun Cheng , Beibei Yan , Yan Shi , Hong Su , Guanyi Chen","doi":"10.1016/j.biombioe.2024.107176","DOIUrl":null,"url":null,"abstract":"<div><p>Anaerobic digestion is a promising approach to dispose of biodegradable waste and wastewater, generating biogas as an alternative energy resource. This work proposed a so-called M-CADM1 for continuous anaerobic digestion simulation, which combined the machine learning and anaerobic digestion model No.1 (ADM1). The detailed reaction path and intermediate products in different stages of anaerobic digestion are specified in ADM1. The kinetic parameters were modified by machine learning. The characteristics (elemental composition) of feedstocks were used to predict kinetic parameters. A total of 75 biomass samples were used to establish for machine learning models. Five element contents (C, H, O, N, S), feedstock feed rate, and anaerobic digestion temperature were used as the input. The kinetic parameters were set as output. The sensitivities of 17 kinetic parameters were evaluated. 7 kinetic parameters with the highest sensitivities were selected as ADM1 model inputs by sensitivity analysis. The R<sup>2</sup> and RMSE were used as the index to evaluated the accuracy of machine learning model. The best R<sup>2</sup> and RMSE reached 0.84 and 0.196. The TIC was used as the index to evaluated the accuracy of M-CADM1. By comparing the simulated value with the experimental value, the accuracy of the overall M-CADM1 expressed by TIC of kitchen waste was 0.036. The organic acid content and pH in the reactor were considered as indicators to study the accuracy and stability of the M-CADM1. Trends in organic acids, free ammonia or hydrogen inhibition, and pH were consistent with experimental continuous anaerobic digestion results.</p></div>","PeriodicalId":253,"journal":{"name":"Biomass & Bioenergy","volume":null,"pages":null},"PeriodicalIF":5.8000,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A hybrid approach of anaerobic digestion model no. 1 and machine learning to model and optimize continuous anaerobic digestion processes\",\"authors\":\"Yadong Ge , Junyu Tao , Zhi Wang , Lan Mu , Wei Guo , Zhanjun Cheng , Beibei Yan , Yan Shi , Hong Su , Guanyi Chen\",\"doi\":\"10.1016/j.biombioe.2024.107176\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Anaerobic digestion is a promising approach to dispose of biodegradable waste and wastewater, generating biogas as an alternative energy resource. This work proposed a so-called M-CADM1 for continuous anaerobic digestion simulation, which combined the machine learning and anaerobic digestion model No.1 (ADM1). The detailed reaction path and intermediate products in different stages of anaerobic digestion are specified in ADM1. The kinetic parameters were modified by machine learning. The characteristics (elemental composition) of feedstocks were used to predict kinetic parameters. A total of 75 biomass samples were used to establish for machine learning models. Five element contents (C, H, O, N, S), feedstock feed rate, and anaerobic digestion temperature were used as the input. The kinetic parameters were set as output. The sensitivities of 17 kinetic parameters were evaluated. 7 kinetic parameters with the highest sensitivities were selected as ADM1 model inputs by sensitivity analysis. The R<sup>2</sup> and RMSE were used as the index to evaluated the accuracy of machine learning model. The best R<sup>2</sup> and RMSE reached 0.84 and 0.196. The TIC was used as the index to evaluated the accuracy of M-CADM1. By comparing the simulated value with the experimental value, the accuracy of the overall M-CADM1 expressed by TIC of kitchen waste was 0.036. The organic acid content and pH in the reactor were considered as indicators to study the accuracy and stability of the M-CADM1. Trends in organic acids, free ammonia or hydrogen inhibition, and pH were consistent with experimental continuous anaerobic digestion results.</p></div>\",\"PeriodicalId\":253,\"journal\":{\"name\":\"Biomass & Bioenergy\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.8000,\"publicationDate\":\"2024-03-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biomass & Bioenergy\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0961953424001296\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomass & Bioenergy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0961953424001296","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
A hybrid approach of anaerobic digestion model no. 1 and machine learning to model and optimize continuous anaerobic digestion processes
Anaerobic digestion is a promising approach to dispose of biodegradable waste and wastewater, generating biogas as an alternative energy resource. This work proposed a so-called M-CADM1 for continuous anaerobic digestion simulation, which combined the machine learning and anaerobic digestion model No.1 (ADM1). The detailed reaction path and intermediate products in different stages of anaerobic digestion are specified in ADM1. The kinetic parameters were modified by machine learning. The characteristics (elemental composition) of feedstocks were used to predict kinetic parameters. A total of 75 biomass samples were used to establish for machine learning models. Five element contents (C, H, O, N, S), feedstock feed rate, and anaerobic digestion temperature were used as the input. The kinetic parameters were set as output. The sensitivities of 17 kinetic parameters were evaluated. 7 kinetic parameters with the highest sensitivities were selected as ADM1 model inputs by sensitivity analysis. The R2 and RMSE were used as the index to evaluated the accuracy of machine learning model. The best R2 and RMSE reached 0.84 and 0.196. The TIC was used as the index to evaluated the accuracy of M-CADM1. By comparing the simulated value with the experimental value, the accuracy of the overall M-CADM1 expressed by TIC of kitchen waste was 0.036. The organic acid content and pH in the reactor were considered as indicators to study the accuracy and stability of the M-CADM1. Trends in organic acids, free ammonia or hydrogen inhibition, and pH were consistent with experimental continuous anaerobic digestion results.
期刊介绍:
Biomass & Bioenergy is an international journal publishing original research papers and short communications, review articles and case studies on biological resources, chemical and biological processes, and biomass products for new renewable sources of energy and materials.
The scope of the journal extends to the environmental, management and economic aspects of biomass and bioenergy.
Key areas covered by the journal:
• Biomass: sources, energy crop production processes, genetic improvements, composition. Please note that research on these biomass subjects must be linked directly to bioenergy generation.
• Biological Residues: residues/rests from agricultural production, forestry and plantations (palm, sugar etc), processing industries, and municipal sources (MSW). Papers on the use of biomass residues through innovative processes/technological novelty and/or consideration of feedstock/system sustainability (or unsustainability) are welcomed. However waste treatment processes and pollution control or mitigation which are only tangentially related to bioenergy are not in the scope of the journal, as they are more suited to publications in the environmental arena. Papers that describe conventional waste streams (ie well described in existing literature) that do not empirically address ''new'' added value from the process are not suitable for submission to the journal.
• Bioenergy Processes: fermentations, thermochemical conversions, liquid and gaseous fuels, and petrochemical substitutes
• Bioenergy Utilization: direct combustion, gasification, electricity production, chemical processes, and by-product remediation
• Biomass and the Environment: carbon cycle, the net energy efficiency of bioenergy systems, assessment of sustainability, and biodiversity issues.