基于GA-BP-GA优化林下三七种植红壤离散元仿真参数

doi:10.13304/j.nykjdb.2024.0188

摘要/Abstract

摘要：

为解决云南林下三七种植中农机具设计缺乏准确、可靠的离散元仿真参数的问题，以云南林下三七种植红壤为研究对象，选取EDEM中的Hertz-Mindlin with JKR cohesion模型，对相关仿真参数进行标定。在前期试验的基础上，采用Plackett-Burman试验和最陡爬坡试验筛选显著性因素及其最优值区间；以土壤仿真堆积角为响应值，分别采用响应面法（response surface methodology，RSM）和机器学习对显著性参数进行优化和对比。结果显示，采用RSM优化得到土壤JKR（Johnson-Kendall-Roberts）表面能为5.597 J·m^-2、土壤-土壤碰撞恢复系数为0.314、土壤-土壤滚动摩擦因数为0.132、土壤-65Mn钢碰撞恢复系数为0.264，测得仿真堆积角为38.16°，与实际堆积角相对误差为2.03%；采用GA-BP（genetic algorithm-back propagation）-GA模型优化的土壤JKR表面能为5.245 J·m^-2、土壤-土壤碰撞恢复系数为0.404、土壤-土壤滚动摩擦因数为0.171、土壤-65Mn钢碰撞恢复系数为0.318，仿真堆积角为36.81°，与实际堆积角相对误差为1.57%。综上表明，GA-BP-GA算法在参数优化方面优于RSM方法，获得的红壤参数标定结果可以用于离散元仿真。

关键词: 红壤, 离散元, 参数标定, 响应面, BP神经网络, 遗传算法

Abstract:

In order to solve the problem of the lack of accurate and reliable discrete element simulation parameters for the design of agricultural implements in Yunnan forest Panax pseudoginseng cultivation， the red soil of Yunnan forest Panax pseudoginseng cultivation was taken as the research object， and the Hertz-Mindlin with JKR cohesion model in EDEM was selected to calibrate the relevant simulation parameters. On the basis of the previous experiments， the Plackett-Burman test and the steepest-climbing test were used to screen the significance factors and their optimal value intervals， the soil simulation stacking angle was used as the response value， and the response surface methodology （RSM） and machine learning were used to optimize and compare the significance parameters， respectively. The results showed that the soil JKR （Johnson-Kendall-Roberts） surface energy was 5.597 J·m^-2， soil-soil collision recovery coefficient was 0.314， soil-soil rolling friction factor was 0.132， and soil-65Mn steel collision recovery coefficient was 0.264 after using RSM optimized， the simulated stacking angle was 38.16°， and the relative error with the actual stacking angle was 2.03%. While using genetic algorithm （GA）-back propagation （BP）-GA model optimized， the soil JKR surface energy was 5.245 J·m^-2， soil-soil collision recovery coefficient was 0.404， soil-soil rolling friction factor was 0.171， soil-65Mn steel collision recovery coefficient was 0.318， simulated stacking angle was 36.81°， and the relative error with the actual stacking angle was 1.57%， which was superior to that of the RSM. Above results showed that the GA-BP-GA algorithm was superior to the RSM method in parameter optimization， and the red soil parameter calibration results obtained could be used in discrete element simulation.

Key words: red soil, discrete element, parameter calibration, response surface, BP neural network, genetic algorithm

中图分类号:

S152.9

张海东, 唐志贤, 张立芸, 于淇, 宋朝君. 基于GA-BP-GA优化林下三七种植红壤离散元仿真参数[J]. 中国农业科技导报, 2025, 27(9): 120-130.

Haidong ZHANG, Zhixian TANG, Liyun ZHANG, Qi YU, Chaojun SONG. Optimization of Discrete Elemental Simulation Parameters for Forest Panax pseudoginseng Plantation Red Soil Based on GA-BP-GA[J]. Journal of Agricultural Science and Technology, 2025, 27(9): 120-130.

图/表 13

参考文献 29

[1]	张川.基于土壤重构的云南红壤复合土力学特性及影响机制研究[D].徐州:中国矿业大学,2023.
	ZHANG C. Study on the mechanical properties and mechanisms during soil reconstruction of red soil complex in Yunnan [D]. Xuzhou: China University of Mining and Technology, 2023.
[2]	邢洁洁,张锐,吴鹏,等.海南热区砖红壤颗粒离散元仿真模型参数标定[J].农业工程学报,2020,36(5):158-166.
	XING J J, ZHANG R, WU P, et al.. Parameter calibration of discrete element simulation model for latosol particles in hot areas of Hainan province [J]. Trans. Chin. Soc. Agric. Eng., 2020, 36(5): 158-166.
[3]	曾智伟,马旭,曹秀龙,等.离散元法在农业工程研究中的应用现状和展望[J].农业机械学报, 2021, 52(4):1-20.
	ZENG Z W, MA X, CAO X L, et al.. Critical review of applications of discrete element method in agricultural engineering [J]. Trans. Chin. Soc. Agric. Mach., 2021, 52(4): 1-20.
[4]	韩燕龙, 贾富国, 唐玉荣, 等.颗粒滚动摩擦系数对堆积特性的影响[J].物理学报,2014,63(17):173-179.
	HAN Y L, JIA F G, TANG Y R, et al.. Influence of granular co efficient of rolling friction on accumulation characteristics [J]. Acta Phys. Sin., 2014, 63(17): 173-179.
[5]	孙景彬,刘琪,杨福增,等.黄土高原坡地土壤与旋耕部件互作离散元仿真参数标定[J].农业机械学报,2022,53(1):63-73.
	SUN J B, LIU Q, YANG F Z, et al.. Calibration of discrete element simulation parameters of sloping soil on Loess Plateau and its interaction with rotary tillage components [J]. Trans. Chin. Soc. Agric. Mach., 2022, 53(1): 63-73.
[6]	QIU Y Q, GUO Z J, JIN X, et al.. Calibration and verification test of cinnamon soil simulation parameters based on discrete element method [J]. Agriculture, 2022, 12(8):1082-1092.
[7]	ZHU J, ZOU M, LIU Y, et al.. Measurement and calibration of DEM parameters of lunar soil simulant [J]. Acta Astronaut., 2022, 191: 169-177.
[8]	林恒矗,王琪,廖鹏,等.植烟沙壤土与触土部件相互作用的离散元仿真参数标定[J].中国农机化学报,2022,43(5):196-203.
	LIN H C, WANG Q, LIAO P, et al.. Discrete element simulation parameter calibration for the interaction between vegetated sandy loam soil and soil-touching components [J]. J. Chin. Agric. Mech., 2022, 43(5): 196-203.
[9]	宋占华,李浩,闫银发,等.桑园土壤非等径颗粒离散元仿真模型参数标定与试验[J].农业机械学报,2022,53(6):21-33.
	SONG Z H, LI H, YAN Y F, et al.. Calibration method of contact characteristic parameters of soil in mulberry field based on unequal-diameter particles DEM theory [J]. Trans. Chin. Soc. Agric. Mach., 2022, 53(6): 21-33.
[10]	向伟,吴明亮,吕江南,等.基于堆积试验的黏壤土仿真物理参数标定[J].农业工程学报,2019,35(12):116-123.
	XIANG W, WU M L, LYU J N, et al.. Calibration of simulation physical parameters of clay loam based on soil accumulation test [J]. Trans. Chin. Soc. Agric. Eng., 2019, 35(12): 116-123.
[11]	麻芳兰,黄文波,李尚平,等.广西甘蔗赤红壤离散元模型参数标定[J].农机化研究, 2023, 45(11): 18-26.
	MA F L, HUANG W B, LI S P, et al.. Parameters calibration of discrete element model for latosolic red soil of sugarcane in Guangxi autonomous region [J]. J. Agric. Mech. Res., 2023, 45(11): 18-26.
[12]	马建春,马灶亮,张昊亮,等.补阳还五汤提取工艺的响应面法和人工神经网络模型优化[J].时珍国医国药,2019,30(2):337-340.
	MA J C, MA Z L, ZHANG H L, et al.. Extraction process optimization for Buyanghuanwu decoction by response surface methodology and back propagation artificial neural network [J]. Lishizhen Med. Mater. Med. Res., 2019, 30(2): 337-340.
[13]	丁辛亭,李凯,郝伟,等.基于RSM和GA-BP-GA优化的油茶籽仿真参数标定[J].农业机械学报,2023,54(2):139-150.
	DING X T, LI K, HAO W, et al.. Calibration of simulation parameters of Camellia oleifera seeds based on RSM and GA-BP-GA optimization [J]. Trans. Chin. Soc. Agric. Mach., 2023, 54(2): 139-150.
[14]	马文鹏,尤泳,王德成,等.基于RSM和NSGA-Ⅱ的苜蓿种子离散元模型参数标定[J].农业机械学报,2020,51(8):136-144.
	MA W P, YOU Y, WANG D C, et al.. Parameter calibration of alfalfa seed discrete element model based on RSM and NSGA-Ⅱ [J]. Trans. Chin. Soc. Agric. Mach., 2020, 51(8): 136-144.
[15]	王洪波,马哲,乌兰图雅,等.采用BP神经网络和Burgers模型的细观参数标定[J].农业工程学报,2022,38(23):152-161.
	WANG H B, MA Z, Wulantuya, et al.. Calibration method of mesoscopic parameters using BP neural network and Burgers model [J]. Trans. Chin. Soc. Agric. Eng., 2022, 38(23): 152-161.
[16]	钟惟亮,丁昊,范立峰.基于BP神经网络的地聚物混凝土细观参数标定研究[J/OL].工程力学,2023:1-10 [2024-01-13]..
	ZHONG W L, DING H, FAN L F. Research on mesoscopic parameters calibration of geopolymer concrete upon BP neural network [J/OL]. Eng. Mech., 2023:1-10 [2024-01-13]. .
[17]	张海辉,张珍,张斯威,等.黄瓜初花期光合速率主要影响因素分析与模型构建[J].农业机械学报,2017,48(6):242-248.
	ZHANG H H, ZHANG Z, ZHANG S W, et al.. Analysis of main influencing factors and modeling of photosynthetic rate for cucumber at initial flowering stage [J]. Trans. Chin. Soc. Agric. Mach., 2017, 48(6): 242-248.
[18]	中华人民共和国住房和城乡建设部. 土工试验方法标准: [S].北京:中国计划出版社,2019.
[19]	刘坤宇,苏宏杰,李飞宇,等.基于响应曲面法的土壤离散元模型的参数标定研究[J].中国农机化学报,2021,42(9):143-149.
	LIU K Y, SU H J, LI F Y, et al.. Research on parameter calibration of soil discrete element model based on response surface method [J]. J. Chin. Agric. Mech., 2021, 42(9): 143-149.
[20]	石林榕,赵武云,孙伟.基于离散元的西北旱区农田土壤颗粒接触模型和参数标定[J].农业工程学报,2017,33(21):181-187.
	SHI L R, ZHAO W Y, SUN W. Parameter calibration of soil particles contact model of farmland soil in northwest arid region based on discrete element method [J]. Trans. Chin. Soc. Agric. Eng., 2017, 33(21): 181-187.
[21]	HÆRVIG J, KLEINHANS U, WIELAND C, et al.. On the adhesive JKR contact and rolling models for reduced particle stiffness discrete element simulations [J]. Powder Technol., 2017, 319: 472-482.
[22]	罗帅,袁巧霞, GOUDA Shaban,等.基于JKR粘结模型的蚯蚓粪基质离散元法参数标定[J].农业机械学报,2018,49(4):343-350.
	LUO S, YUAN Q X, GOUDA S B, et al.. Parameters calibration of vermicomposting nursery substrate with discrete element method based on JKR contact model [J]. Trans. Chin. Soc. Agric. Mach., 2018, 49(4): 343-350.
[23]	李清超,郑炫,刘进宝,等.新疆农田粉土离散元仿真参数标定[J].新疆农业科学,2022,59(8):2014-2024.
	LI Q C, ZHENG X, LIU J B, et al.. Parameter calibration of discrete element simulation of farmland silt in Xinjiang [J]. Xinjiang Agric. Sci., 2022, 59(8): 2014-2024.
[24]	薛茂远,梅益,唐方艳,等.基于GA-ELM及遗传算法的注塑件成型工艺优化[J].塑料,2022,51(1):56-61, 66.
	XUE M Y, MEI Y, TANG F Y, et al.. Optimization of injection molding process based on GA-ELM and genetic algorithm [J]. Plastics, 2022, 51(1): 56-61, 66.
[25]	BU X, XU Y, ZHAO M, et al.. Simultaneous extraction of polysaccharides and polyphenols from blackcurrant fruits: comparison between response surface methodology and artificial neural networks [J/OL]. Ind. Crops Prod., 2021, 170: 113682 [2024-01-13]. .
[26]	杨菊.基于扩展有限元法和离散元法的土壤—耕具接触研究[D].昆明:昆明理工大学,2014.
	YANG J. Analysis of soil-tool interaction using extended finite element method and discrete element method [D]. Kunming: Kunming University of Science and Technology, 2014.
[27]	GAMMOUDI N, MABROUK M, BOUHEMDA T, et al.. Modeling and optimization of capsaicin extraction from Capsicum annuum L. using response surface methodology (RSM), artificial neural network (ANN), and Simulink simulation [J/OL]. Ind. Crops Prod., 2021, 171: 113869 [2024-01-13]. .
[28]	张曦予,李锐定,莫明规,等.基于人工神经网络耦联遗传算法(BP-GA)优化干酪乳杆菌LTL1361冻干保护剂配方[J].食品工业科技,2022,43(21):175-184.
	ZHANG X Y, LI R D, MO M G, et al.. Optimization of lyophilized protective agent formulation of Lactobacillus casei LTL1361 based on artificial neural network coupled genetic algorithm (BP-GA) [J]. Sci. Technol. Food Ind., 2022, 43(21): 175-184.
[29]	李俊伟,佟金,胡斌,等.不同含水率黏重黑土与触土部件互作的离散元仿真参数标定[J].农业工程学报, 2019, 35(6): 130-140.
	LI J W, TONG J, HU B, et al.. Calibration of parameters of interaction between clayey black soil with different moisture content and soil-engaging component in NorthEast China [J]. Trans. Chin. Soc. Agric. Eng., 2019, 35(6): 130-140.

级别Grade	D：粒径Particle diameter/mm	占比Percentage/%
1	D>2.5	31.34
2	2.5≤D>2.0	8.78
3	2.0≤D>1.6	8.16
4	1.6≤D>1.0	21.47
5	1.0≤D>0.6	21.29
6	D<0.6	8.96

级别Grade	D：粒径Particle diameter/mm	占比Percentage/%
1	D>2.5	31.34
2	2.5≤D>2.0	8.78
3	2.0≤D>1.6	8.16
4	1.6≤D>1.0	21.47
5	1.0≤D>0.6	21.29
6	D<0.6	8.96

序号 Serial number	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉	X₁₀	X₁₁	堆积角 Stacking angle/（°）
1	0	0.15	1.16	0.05	0.60	0.60	0.04	1	1	1	-1	10.07
2	12	0.15	1.16	0.25	0.04	0.60	0.20	1	-1	-1	-1	67.28
3	12	0.75	1.16	0.05	0.04	0.40	0.20	-1	1	1	-1	27.25
4	12	0.75	0.44	0.25	0.60	0.60	0.04	-1	-1	1	-1	58.59
5	0	0.75	1.16	0.05	0.60	0.60	0.20	-1	-1	-1	1	3.43
6	12	0.15	0.44	0.05	0.60	0.40	0.20	1	-1	1	1	67.02
7	12	0.15	1.16	0.25	0.60	0.40	0.04	-1	1	-1	1	69.51
8	12	0.75	0.44	0.05	0.04	0.60	0.04	1	1	-1	1	31.21
9	0	0.15	0.44	0.05	0.04	0.40	0.04	-1	-1	-1	-1	4.95
10	0	0.75	1.16	0.25	0.04	0.40	0.04	1	-1	1	1	3.58
11	0	0.75	0.44	0.25	0.60	0.40	0.20	1	1	-1	-1	12.02
12	0	0.15	0.44	0.25	0.04	0.60	0.20	-1	1	1	1	30.03

序号 Serial number	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉	X₁₀	X₁₁	堆积角 Stacking angle/（°）
1	0	0.15	1.16	0.05	0.60	0.60	0.04	1	1	1	-1	10.07
2	12	0.15	1.16	0.25	0.04	0.60	0.20	1	-1	-1	-1	67.28
3	12	0.75	1.16	0.05	0.04	0.40	0.20	-1	1	1	-1	27.25
4	12	0.75	0.44	0.25	0.60	0.60	0.04	-1	-1	1	-1	58.59
5	0	0.75	1.16	0.05	0.60	0.60	0.20	-1	-1	-1	1	3.43
6	12	0.15	0.44	0.05	0.60	0.40	0.20	1	-1	1	1	67.02
7	12	0.15	1.16	0.25	0.60	0.40	0.04	-1	1	-1	1	69.51
8	12	0.75	0.44	0.05	0.04	0.60	0.04	1	1	-1	1	31.21
9	0	0.15	0.44	0.05	0.04	0.40	0.04	-1	-1	-1	-1	4.95
10	0	0.75	1.16	0.25	0.04	0.40	0.04	1	-1	1	1	3.58
11	0	0.75	0.44	0.25	0.60	0.40	0.20	1	1	-1	-1	12.02
12	0	0.15	0.44	0.25	0.04	0.60	0.20	-1	1	1	1	30.03

因素 Factor	平方和 Sum of squares	自由度 Degree of freedom	均方 Mean square	F值 F value	P值 P value
X₁	5 495.09	7	1 105.77	203.96	0.000 1^**
X₂	1 059.76	1	5 495.09	39.33	0.003 3^**
X₃	42.98	1	1 059.76	1.60	0.275 2
X₄	785.38	1	42.98	29.15	0.005 7^**
X₅	264.52	1	785.38	9.82	0.035 1^*
X₆	22.09	1	264.52	0.82	0.416 4
X₇	70.62	1	22.09	2.62	0.180 8