Prediction of Soil Thermal Conductivity Based on NMI-FA-DELM Model

doi:10.12141/j.issn.1000-565X.220746

Abstract

Abstract:

The thermal conductivity of soil is an important soil property, which affects the soil temperature distribution underground. It has significant practical importance in geotechnical and civil engineering design and construction. Using reasonable means to predict it can effectively solve the problems such as time-consuming and complex process. According to the characteristics of nonlinearity and timing of soil thermal conductivity data, this paper proposed a firefly algorithm (FA) optimization limit learning machine (DELM) prediction model (NMI-FA-DELM) under NMI for soil thermal conductivity prediction. The model first screened the key parameters affecting the soil thermal conductivity by NMI, and took the filtered parameters as the data set. Then the soil thermal conductivity was predicted with the FA-DELM optimized by the firefly algorithm, and the predictive results were compared with those of statistical prediction equations, random forest methods, BP neural network models, DELM models, and SVR (support vector regression) models. The results show that the NMI-FA-DELM model can effectively predict soil thermal conductivity, with corresponding root mean square error, average absolute percentage error, a10 index, and determination coefficient of 0.363, 9.667%, 0.961 and 0.92, respectively. The prediction accuracy of the NMI-FA-DELM model is better than that of other prediction models, and the content of viscous soil and sand has greater influence on the prediction results of soil thermal conductivity. This model can significantly improve the prediction accuracy of soil thermal conductivity and provides important guidance for predicting soil thermal conductivity in practical engineering applications.

Key words: soil thermal conductivity, geotechnical engineering, normalized mutual information, extreme learning machine, firefly algorithm

CLC Number:

TK448.21

LEI Yu, HUANG Yifan, LUO Xuedong, et al.. Prediction of Soil Thermal Conductivity Based on NMI-FA-DELM Model[J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 129-138.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Table 2

Fig.11

Fig.12

References 36

1	李毅，邵明安，王文焰，等．质地对土壤热性质的影响研究［J］．农业工程学报，2003，19（4）：62-65.
	LI Yi， SHAO Mingan， WANG Wenyan，et al ．Influence of soil textures on the thermal properties［J］．Transactions of the Chinese Society of Agricultural Engineering，2003，19（4）：62-65.
2	陆森，任图生．不同温度下的土壤热导率模拟［J］．农业工程学报，2009，25（7）：13-18.
	LU Sen， REN Tusheng ．Model for predicting soil thermal conductivity at various temperatures［J］．Transactions of the Chinese Society of Agricultural Engineering，2009，25（7）：13-18.
3	刘晨晖，周东，吴恒．土壤热导率的温度效应试验和预测研究［J］．岩土工程学报，2011，33（12）：1877-1886.
	LIU Chen-hui， ZHOU Dong， WU Heng ．Measurement and prediction of temperature effects of thermal conductivity of soils［J］．Chinese Journal of Geotechnical Engineering，2011，33（12）：1877-1886.
4	陆森，任图生，杨泱，等．多针热脉冲技术测定土壤热导率误差分析［J］．农业工程学报，2010，26（6）：20-25.
	LU Sen， REN Tusheng， YANG Yang，et al ．Error analysis of multi-needle heat pulse probe for soil thermal conductivity measurement［J］．Transactions of the Chinese Society of Agricultural Engineering，2010，26（6）：20-25.
5	杜宜臻，李韧，吴通华，等．土壤热导率的研究现状及其进展［J］．冰川冻土，2015，37（4）：1067-1074.
	DU Yizhen， LI Ren， WU Tonghua，et al ．Study of soil thermal conductivity：research status and advances［J］．Journal of Glaciology and Geocryology，2015，37（4）：1067-1074.
6	曾召田，范理云，莫红艳，等．土壤热导率的影响因素实验研究［J］．太阳能学报，2018，39（2）：377-384.
	ZENG Shaotian， FAN Liyun， MO Hongyan，et al ．Experimental study of influence factors of soil thermal conductivity［J］．Acta Energiae Solaris Sinica，2018，39（2）：377-384.
7	LIU Y， LI K Q， LI D A Q，et al ．Coupled thermal-hydraulic modeling of artificial ground freezing with uncertainties in pipe inclination and thermal conductivity［J］．Acta Geotechnica，2022，17（1）：257-274.
8	YU X X， ZHENG G， ZHOU H Z，et al ．Influence of geosynthetic reinforcement on the progressive failure of rigid columns under an embankment load ［J］．Acta Geotechnica，2021，16（9）：3005-3012.
9	王卫华，蔡礼良，龚一丹．土壤热导率影响因素及模型评估研究［J］．华南农业大学学报，2020，41（5）：124-132.
	WANG Weihua， CAI Liliang， GONG Yidan ．Research on influencing factors and model assessment of soil thermal conductivity［J］．Journal of South China Agricultural University，2020，41（5）：124-132.
10	WIENER O ．Abhandl math-phys Kl Konigl SachsischenGes［M］．Leipizig：Klasse．Sachs Akad．Wiss，1912：509.
11	VRIES D ．The physics of plant environments-science direct［J］．Environmental Control of Plant Growth，1963，26（4）：5-22.
12	KERSTEN M S ．Laboratory research for the determination of the thermal properties of soils［D］．Minneapolis：Minnesota University，1949.
13	CHEN S X ．Thermal conductivity of sands［J］．Heat and Mass Transfer，2008，44（10）：1241-1246.
14	RIZVI Z H， ZAIDI H H， AKHTAR S J，et al ．Soft and hard computation methods for estimation of the effective thermal conductivity of sands［J］．Heat and Mass Transfer，2020，56（6）：1947-1959.
15	ZHANG N， ZOU H F， ZHANG L M，et al ．A unified soil thermal conductivity model based on artificial neural network ［J］ International Journal of Thermal Sciences，2020，155（106414）：1-6.
16	JIANG X F， DUAN H C， LIAO J，et al ．Estimation of soil salinization by machine learning algorithms in different arid regions of northwest China ［J］．Remote Sensing，2022，14（2）：347.
17	MAES F， COLLIGNON A， VANDERMEULEN D，et al ．Multimodality image registration by maximization of mutual information ［J］．IEEE Transactions on Medical Imaging，1997，16（2）：87-98.
18	GANDOMI A H， YANG X S， ALAVI A H ．Mixed variable structural optimization using firefly algorithm ［J］．Computers & Structures，2011，89（23/24）：2325-2336.
19	GANDOMI A H， YANG X S， TALATAHARI S，et al ．Firefly algorithm with chaos ［J］．Communications in Nonlinear Science and Numerical Simulation，2013，18（1）：89-98.
20	颜学龙，马润平．基于深度极限学习机的模拟电路故障诊断［J］．计算机工程与科学，2019，41（11）：1911-1918.
	YAN Xue-long， MA Run-ping ．Fault diagnosis of analog circuits based on depth extreme learning machine［J］．Computer Engineering & Science，2019，41（11）：1911-1918.
21	商强，杨兆升，李志林，等．基于相空间重构和RELM的短时交通流量预测［J］．华南理工大学学报（自然科学版），2016，44（4）：109-114.
	SHANG Qiang， YANG Zhao-sheng， LI Zhi-lin，et al ．Short-term traffic flow prediction based on phase space reconstruction and RELM［J］．Journal of South China University of Technology（Natural Science Edition），2016，44（4）：109-114.
22	闫嘉，陈飞越，易若男，等．基于样本分布加权跨域极限学习机的电子鼻漂移补偿［J］．华南理工大学学报（自然科学版），2020，48（12）：105-113.
	YAN Jia， CHEN Feiyue， YI Ruonan，et al ．Drift compensation for electronic nose based on sample distribution weighting cross domain extreme learning machine［J］．Journal of South China University of Technology（Natural Science Edition），2020，48（12）：105-113.
23	TARNAWSKI V R， MOMOSE T， MCCOMBIE M L，et al ．Canadian field soils Ⅲ．thermal-conductivity data and modeling［J］．International Journal of Thermophysics，2015，36（1）：119-156.
24	CHEN S K ．Thermal conductivity of sands［J］．Heat and Mass Transfer，2008，44（10）：1241-1246.
25	ZHANG N， YU X， PRADHAN A，et al ．Thermal conductivity of quartz sands by thermo-time domain reflectometry probe and model prediction［J］．Journal of Materials in Civil Engineering，2015，27（12）：17-24.
26	MCCOMBIE M L， TARNAWSKI V R， BOVESECCHI G，et al ．Thermal conductivity of pyroclastic soil （pozzolana） from the environs of Rome［J］．International Journal of Thermophysics，2017，38：1-15.
27	TARNAWSKI V R， MCCOMBIE M L， MOMOSE T，et al ．Thermal conductivity of standard sands．Part Ⅲ．Full range of saturation［J］．International Journal of Thermophysics，2013，34（6）：1130-1147.
28	KARDANI N， BARDHAN A， SAMUI P，et al ．Predicting the thermal conductivity of soils using integrated approach of ANN and PSO with adaptive and time-varying acceleration coefficients［J］．International Journal of Thermal Sciences，2022，173：107427/1-15.
29	ARABGOL S， KO H S ．Application of artificial neural network and genetic algorithm to healthcarewaste prediction［J］．Journal of Artificial Intelligence & Soft Computing Research，2013，3（4）：243-250.
30	SANG Y J， LIU G， HORTON R ．Wind effects on soil thermal properties measured by the dual-probe heat pulse method ［J］．Soil Science Society of America Journal，2020，84（2）：414-424.
31	FORMAN E， PENIWATI K. Aggregating individual judgments and priorities with the analytic hierarchy process ［J］．European Journal of Operational Research，1998，108（1）：165-169.
32	YIN X， LIU Q， HUANG X，et al ．Perception model of surrounding rock geological conditions based on TBM operational big data and combined unsupervised-supervised learning［J］．Tunnelling and Underground Space Technology，2022，120：104285/1-15.
33	LIU Y ．Incomplete big data imputation mining algorithm based on BP neural network ［J］．Journal of Intelligent and Fuzzy Systems，2019，37（4）：4457-4466.
34	ZHOU J， QIU Y G， ARMAGHANI D J，et al ．Predicting TBM penetration rate in hard rock condition：A comparative study among six XGB-based metaheuristic techniques［J］．Geoscience Frontiers，2021，12（3）：1-9.
35	LEI Y， ZHOU S T， LUO X D，et al.，A comparative study of six hybrid prediction models for uniaxial compressive strength of rock based on swarm intelligence optimization algorithms［J］．Frontiers in Earth Science，2022，10（1）：1-11.
36	CIESIELKI M J， KALLA P， ASKAR S ．Taylor expansion diagrams［C］∥ Proceedings of the IEEE Computer Society PUB769．Washington，DC：IEEE，2006，55：1188-1201.

序号	岩石种类	ρ_d/（g·cm^-3）	n/%	S_r/%	m_q/%	m_s/%	m_c/%	K/（W·m^-1·K^-1）
1	淤泥质土壤	1.22	0.55	0.10	0.51	0.33	0.10	0.80
2	淤泥质土壤	1.22	0.55	0.25	0.51	0.33	0.10	1.73
3	淤泥质土壤	1.22	0.55	0.50	0.51	0.33	0.10	2.06
4	淤泥质土壤	1.22	0.55	0.70	0.51	0.33	0.10	3.00
5	沙质土壤	1.49	0.45	0.10	0.61	0.61	0.05	0.88
6	沙质土壤	1.49	0.45	0.25	0.61	0.61	0.05	2.70
7	沙质土壤	1.49	0.45	0.50	0.61	0.61	0.05	2.65
︙	︙	︙	︙	︙	︙	︙	︙	︙
256	丰浦砂	1.64	0.38	0.10	0.87	1.00	0.00	9.31
257	丰浦砂	1.59	0.40	0.10	0.87	1.00	0.00	8.56

	预测模型	E_RMSE		E_MAPE		R²		a10
	预测模型	取值	得分	取值/%	得分	取值	得分	取值	得分
训练集	NMI-FA-DELM	0.359	1.000	10.180	1.000	0.961	1.000	0.90	1.000
	统计预测方程	5.974	0.000	45.860	0.000	0.357	0.000	0.14	0.000
	极限学习机	1.789	0.745	22.789	0.646	0.807	0.745	0.34	0.263
	随机森林	1.700	0.761	17.910	0.783	0.817	0.761	0.64	0.657
	BP神经网络	2.216	0.669	39.358	0.182	0.761	0.668	0.30	0.210
	支持向量回归	1.546	0.788	20.679	0.705	0.833	0.788	0.34	0.263
测试集	NMI-FA-DELM	0.363	1.000	9.667	1.000	0.961	1.000	0.92	1.000
	统计预测方程	5.813	0.000	44.480	0.000	0.375	0.000	0.16	0.000
	极限学习机	1.795	0.737	22.714	0.625	0.807	0.737	0.38	0.289
	随机森林	1.665	0.761	15.845	0.822	0.821	0.761	0.60	0.578
	BP神经网络	2.130	0.675	31.475	0.373	0.766	0.667	0.36	0.263
	支持向量回归	1.521	0.787	20.723	0.682	0.836	0.786	0.32	0.210

[1]	TAO Wenbin, TAO Jie, HOU Junling, et al. In-Situ Stress Characteristics and Optimal Support Design of Deep Roadway#br# [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(4): 28-37.
[2]	YAN Jia, CHEN Feiyue, YI Ruonan, et al. Drift Compensation for Electronic Nose Based on Sample Distribution Weighting Cross Domain Extreme Learning Machine [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(12): 105-113.
[3]	XU Yuge LAI Chunling LUO Fei . Bagging Ensemble Fault Diagnosis Modeling with Imbalanced classification in Wastewater Treatment Plant [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(8): 107-115.
[4]	SHANG Qiang YANG Zhao-sheng LI Zhi-lin LI Lin QU Xin. Short-Term Traffic Flow Prediction Based on Phase Space Reconstruction and RELM [J]. Journal of South China University of Technology (Natural Science Edition), 2016, 44(4): 109-114.
[5]	Yu Hong-tao Gao Li-qun Han Xi-chang. Discrete Artificial Firefly Algorithm for Solving Traveling Salesman Problems [J]. Journal of South China University of Technology (Natural Science Edition), 2015, 43(1): 126-131,139.