การทดสอบความไม่คงเส้นคงวาในประสิทธิภาพของแบบจำลองค่าความร้อนชีวมวลตามการวิเคราะห์แบบแยกธาตุ
Performance Inconsistencies in Biomass Higher Heating Value Models for Ultimate Analysis
Abstract
ชีวมวลเป็นหนึ่งในพลังงงานทดแทนที่สำคัญของแผนพัฒนาพลังงานทดแทนและพลังงานทางเลือกของประเทศไทยการวิเคราะห์แบบแยกธาตุบ่งบอกถึงค่าพลังงานความร้อนและคุณภาพของชีวมวล การทำนายค่าความร้อนที่มีความถูกต้องคงเส้นคงวาบนข้อมูลที่แบบจำลองไม่เคยพบเป็นสิ่งสำคัญต่อบางพื้นที่ซึ่งไม่มีข้อมูลเพียงพอที่จะให้แบบจำลองเรียนรู้ บทความใช้สามการทดลองเพื่อตรวจความไม่คงเส้นคงวาของแบบจำลองค่าความร้อน ข้อมูลที่ให้แบบจำลองเรียนรู้ คือ สิ่งทดลองส่วนผลลัพธ์ของการทดลองคือความไม่คงเส้นคงวาของแบบจำลอง บทความสร้างสถานการณ์จำลองเมื่อนำแบบจำลองค่าความร้อนมาทำนายข้อมูลอื่นที่แบบจำลองไม่เคยเรียนรู้ ผลการทดลองพบว่า แบบจำลองค่าความร้อนมีความถูกต้องที่ไม่คงเส้นคงวา บนข้อมูลที่แบบจำลองเคยพบนั้นแบบจำลองแต่ละอันให้ค่าความผิดพลาดเฉลี่ยที่ไม่ต่างกันเชิงสถิติ แต่มีโมเมนต์สูงต่างกัน ส่วนกรณีข้อมูลที่แบบจำลองไม่เคยพบนั้นการแจกแจงความความผิดพลาดจะต่างกันในทุกโมเมนต์ บนสถานการณ์จำลองแบบจำลองไม่สามารถรักษาระดับความถูกต้องอย่างที่เคยมีและไม่สามารถให้ผลการทำนายที่แม่นยำบนตัวอย่างชีวมวลของประเทศไทย ดังนั้นต้องนำข้อมูลชีวมวลในพื้นที่มาให้แบบจำลองเรียนรู้ใหม่จึงได้ผลการทำนายค่าความร้อนที่มีความแม่นยำ
Biomass is a sustainable renewable energy that can replace fossil fuels, reduce greenhouse gas emissions, and be integrated into the energy structure of Thailand. Ultimate analysis measures the Higher Heating Value (HHV) of chemical elements to determine the energy quantity of a fuel. The accuracy and consistency of the out-of-sample data for the prediction model are essential for data-poor regions like Thailand. The present study conducted three experiments to verify the consistency of the HHV models using out-of-sample data. The published datasets were the treatments, with the accuracy stabilities being the responses. Multiple situations of out-of-sample implementation were simulated. The results confirmed accuracy inconsistencies in both linear and nonlinear HHV models. The models presented statistical indifferences in the average error of the in-sample performance, while the higher moments of error distribution remained distinct. All higher moments of the residuals of the model were different in the out-of-sample data. The simulated examples indicated that previous models could not maintain the accuracy of their training sets. Additionally, they could not provide an accurate prediction of the biomass data of Thailand. Therefore, a practical dataset is necessary to retrain the HHV models before implementation to ensure accurate HHV prediction in Thailand.
Keywords
[1] R. K. P. and L. A. M. (eds. Core Writing Team), Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change, Geneva, Switzerland, 2015.
[2] S. Jenniches, “Assessing the regional economic impacts of renewable energy sources - A literature review,” Renewable Sustainable Energy Reviews, vol. 93, pp. 35–51, 2018.
[3] AEDP (Department of Alternative Energy Development and Efficiency). (2020, October). The 10-Year Alternative Energy Development Plan. Ministre of Energy. Bangkok, Thailand. [Online]. (in Thai). Available: http://www.eppo. go.th/images/Infromation_service/public_ relations/PDP2018/PDP2018Rev1.pdf
[4] A. K. Gupta and S. Kerdsuwan, “Efficient energy conversion of wastes and fuels in power systems,” KMUTNB International Journal of Applied Science Technology, vol. 7, no. 2, pp. 1–26, 2014.
[5] C. Areepak, T. Jiradechakorn, S. Chuetor, V. Champreda, and N. Laosiripojana, “Improvement of lignocellulosic pretreatment efficiency by combined chemo - Mechanical pretreatment for energy consumption reduction and biofuel production,” Renewable Energy, vol. 182, pp. 1094–1102, 2022.
[6] I. Estiati, F. B. Freire, J. T. Freire, R. Aguado, and M. Olazar, “Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass,” Fuel, vol. 180, pp. 377–383, 2016.
[7] J. Xing, K. Luo, H. Wang, Z. Gao, and J. Fan, “A comprehensive study on estimating higher heating value of biomass from proximate and ultimate analyses with machine learning approaches,” Energy, vol. 188, pp. 116077, 2019.
[8] P. Thipkhunthod, V. Meeyoo, P. Rangsunvigit, B. Kitiyanan, K. Siemanond, and T. Rirksomboon, “Predicting the heating value of sewage sludges in Thailand from proximate and ultimate analyses,” Fuel, vol. 84, no. 7–8, pp. 849–857, 2005.
[9] I. Boumanchar, K. Charafeddine, Y. Chhiti, F. E. M’hamdi Alaoui, A. Sahibed-dine, F. Bentiss, C. Jama, and M. Bensitel, “Biomass higher heating value prediction from ultimate analysis using multiple regression and genetic programming,” Biomass Conversion and Biorefinery, vol. 9, no. 3, pp. 499–509, 2019.
[10] C.-Yang Yin, “Prediction of higher heating values of biomass from proximate and ultimate analyses,” Fuel, vol. 90, no. 3, pp. 1128–1132, 2011.
[11] A. J. Callejón-Ferre, B. Velázquez-Martí, J. A. López-Martínez, and F. Manzano-Agugliaro, “Greenhouse crop residues: Energy potential and models for the prediction of their higher heating value,” Renewable and Sustainable Energy Reviews, vol. 15, no. 2, pp. 948–955, 2011.
[12] H. L. Choi, S. I. A. Sudiarto, and A. Renggaman, “Prediction of livestock manure and mixture higher heating value based on fundamental analysis,” Fuel, vol. 116, pp. 772–780, 2014.
[13] R. García, C. Pizarro, A. G. Lavín, and J. L. Bueno, “Spanish biofuels heating value estimation. Part I: Ultimate analysis data,” Fuel, vol. 117, no. PARTB, pp. 1130–1138, 2014.
[14] X. Wen, S. Jian, and J. Wang, “Prediction models of calorific value of coal based on wavelet neural networks,” Fuel, vol. 199, pp. 512–522, 2017.
[15] D. R. Nhuchhen and M. T. Afzal, “HHV predicting correlations for torrefied biomass using proximate and ultimate analyses,” Bioengineering, vol. 4, no. 1, 2017.
[16] Z. Ceylan, E. Pekel, S. Ceylan, and S. Bulkan, “Biomass higher heating value prediction analysis by ANFIS, PSO-ANFIS and GA-ANFIS,” Global Nest Journal, vol. 20, no. 3, pp. 589– 597, 2018.
[17] A. Kijkarncharoensin. (2022, January). Performance inconsistency of the Biomass Higher Heating Value (HHV) Models derived from Ultimate Analysis. [Online]. Available: https://codeocean.com/capsule/9079586/ tree/v1
[18] E. Akkaya, “ANFIS based prediction model for biomass heating value using proximate analysis components,” Fuel, vol. 180, pp. 687–693, 2016.
[19] S. B. Ghugare, S. Tiwary, V. Elangovan, and S. S. Tambe, “Prediction of higher heating value of solid biomass fuels using artificial intelligence formalisms,” Bioenergy Research, vol. 7, no. 2, pp. 681–692, 2014.
[20] A. Dashti, A. S. Noushabadi, M. Raji, A. Razmi, S. Ceylan, and A. H. Mohammadi, “Estimation of biomass higher heating value (HHV) based on the proximate analysis: Smart modeling and correlation,” Fuel, vol. 257, pp. 115931, 2019.
[21] C. Qian, Q. Li, Z. Zhang, X. Wang, J. Hu, and W. Cao, “Prediction of higher heating values of biochar from proximate and ultimate analyses,” Fuel, vol. 265, pp. 116925, 2020.
[22] C. Telmo, J. Lousada, and N. Moreira, “Proximate analysis, backwards stepwise regression between gross calorific value, ultimate and chemical analysis of wood,” Bioresource Technology, vol. 101, no. 11, pp. 3808–3815, 2010.
[23] R. A. Ibikunle, A. F. Lukman, I. F. Titiladunayo, E. A. Akeju, and S. O. Dahunsi, “Modeling and robust prediction of high heating values of municipal solid waste based on ultimate analysis,” Energy Sources, Part A: Recover Utilization Environmental Effects, 2020.
[24] M. Duan, Z. Liu, D. Yan, W. Peng, and A. Baghban, “Application of LSSVM algorithm for estimating higher heating value of biomass based on ultimate analysis,” Energy Sources, Part A: Recover Utilization Environmental Effects, vol. 40, no. 6, pp. 709–715, 2018.
[25] S. H. Samadi, B. Ghobadian, and M. Nosrati, “Prediction of higher heating value of biomass materials based on proximate analysis using gradient boosted regression trees method,” Energy Sources, Part A: Recover Utilization Environmental Effects, vol. 43, no. 6, pp. 672– 681, 2021.
[26] F. Vallejo, L. A. Díaz-Robles, R. Vega, and F. Cubillos, “A novel approach for prediction of mass yield and higher calorific value of hydrothermal carbonization by a robust multilinear model and regression trees,” Journal of the Energy Institute, vol. 93, no. 4, pp. 1755–1762, 2020.
[27] H. Qian, X. Guo, S. Fan, K. Hagos, X. Lu, C. Liu, and D. Huang, “A simple prediction model for higher heat value of biomass,” Journal of Chemical and Engineering Data, vol. 61, no. 12, pp. 4039–4045, 2016.
[28] S. V. Vassilev, D. Baxter, L. K. Andersen, and C. G. Vassileva, “An overview of the chemical composition of biomass,” Fuel, vol. 89, no. 5, pp. 913–933, 2010.
[29] A. Darvishan, H. Bakhshi, M. Madadkhani, M. Mir, and A. Bemani, “Application of MLP-ANN as a novel predictive method for prediction of the higher heating value of biomass in terms of ultimate analysis,” Energy Sources, Part A: Recover Utilization Environmental Effects, vol. 40, no. 24, pp. 2960–2966, 2018.
[30] J. O. Ighalo, A. G. Adeniyi, and G. Marques, “Application of linear regression algorithm and stochastic gradient descent in a machinelearning environment for predicting biomass higher heating value,” Biofuels, Bioproducts and Biorefining, vol. 14, no. 6, pp. 1286–1295, 2020.
[31] A. Kijkarncharoensin. (2022, January). Ultimate_Analysis. [Online]. Available: https:// data.mendeley.com/datasets/t8x96g88p3/2 (accessed Jan. 28, 2022).
[32] A. O. Balogun, O. A. Lasode, and A. G. McDonald, “Higher heating value prediction model from proximate and ultimate analysis data,” Journal of Multidisciplinary Engineering Science and Technology, vol. 7, no. 8, 2020.
[33] A. Ozyuguran, A. Akturk, and S. Yaman, “Optimal use of condensed parameters of ultimate analysis to predict the calorific value of biomass,” Fuel, vol. 214, pp. 640–646, 2018.
[34] S. Garivait, U. Chaiyo, S. Patumsawad, and J. Deakhuntod, “Physical and chemical properties of thai biomass fuels from agricultural residues,” The 2nd Joint International Conference on “Sustainable Energy and Environment (SEE 2006)” 2006, pp. 48–51.
[35] C. F. Mela and P. K. Kopalle, “The impact of collinearity on regression analysis: The asymmetric effect of negative and positive correlations,” Applied Economics, vol. 34, no. 6, pp. 667–677, 2002.
[36] S. U. Patel, B. Kumar, Y. Badhe, B. Sharma, S. Saha, S. Biswas, A. Chaudhury, S. Tambe, and B. Kulkarni, “Estimation of gross calorific value of coals using artificial neural networks,” Fuel, vol. 86, no. 3, pp. 334–344, 2007.
DOI: 10.14416/j.kmutnb.2024.03.006
ISSN: 2985-2145
Email this article 
Hide
Show all