Scientia Agricultura Sinica ›› 2024, Vol. 57 ›› Issue (3): 584-596.doi: 10.3864/j.issn.0578-1752.2024.03.012

• FOOD SCIENCE AND ENGINEERING • Previous Articles     Next Articles

Modeling and Optimization of 3D Printing Process of Pleurotus Eryngii Powder Using Neural Network-Genetic Algorithm

SU AnXiang1(), HE AnQi2, MA GaoXing1, ZHAO LiYan2, YANG WenJian1, HU QiuHui1()   

  1. 1 Collaborative Innovation Center for Modern Grain Circulation and Safety/Jiangsu Province Engineering Research Center of Edible Fungus Preservation and Intensive Processing/College of Food Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023
    2 College of Food Science and Technology, Nanjing Agricultural University, Nanjing 210095
  • Received:2023-09-28 Accepted:2023-12-04 Online:2024-02-01 Published:2024-02-05


【Objective】Food 3D printing technology, a promising technology in the field of food, can be affected by multiple factors and thus has problems, such as difficulty in determining printing parameters and poor ability of predicting printing accuracy. This paper aimed to seek out an effective modeling method to optimize 3D printing parameters of Pleurotus eryngii powder and to determine the optimal conditions for 3D printing.【Method】Pleurotus eryngii powder and locust bean gum were adopted as 3D printing ink. Then, based on single-factor experiments, the central composite experimental design was performed to study the influence of four key process parameters - nozzle diameter, printing height, nozzle movement speed and fill density - on the accuracy of 3D printing. In order to optimize 3D printing parameters of Pleurotus eryngii powder, response surface methodology (RSM) and artificial neural network and genetic algorithm (ANN-GA) were employed to achieve different effects.【Result】The determination coefficient (R2), root mean square error (RMSE), relative error (RE), and optimal value of prediction (VOP) of RSM model were 0.8817, 0.2314, 72.73%, and 0.148, respectively; the R2, RMSE, RE, and optimal VOP of ANN-GA model were 0.9389, 0.2269, 33.85%, and 0.215, respectively. The ANN-GA model obtained higher R2, lower RMSE and RE, and was better fitting ability, and higher optimal VOP than RSM model, so ANN-GA model possessed better prediction ability. Compared with RSM, ANN-GA was more suitable for optimization of 3D printing parameters of Pleurotus eryngii powder. The optimal process parameters of 3D printing obtained by ANN-GA, with Pleurotus eryngii as printing ink, included nozzle diameter 1.2 mm, printing height 1.1 mm, nozzle movement speed 24 mm·s-1, and fill density 84%. Experimental verification suggested that the deviation of printed samples by ANN-GA was 0.325, which was superior to the actual printing deviation 0.550 by RSM.【Conclusion】ANN-GA was effective in determining the optimal process parameters of 3D printing and accurate in predicting the accuracy of food 3D printing products. Therefore, ANN-GA could serve as an effective and convenient method for optimizing personalized 3D printing parameters of agricultural products and food.

Key words: 3D food printing, Pleurotus eryngii, neural network, genetic algorithm, process optimization

Table 1

Coded and actual values of independent variables"

Nozzle diameter (mm)
Nozzle height (mm)
Moving speed of nozzle (mm∙s-1)
Fill density (%)
-2 0.8 0.8 15 60
-1 1.0 1.0 20 70
0 1.2 1.2 25 80
1 1.4 1.4 30 90
+2 1.6 1.6 35 100

Fig. 1

Effects of nozzle diameter on 3D printing performance of Pleurotus eryngii powder-Locust bean gum samples Different capital letters indicate significant difference in height (P<0.05), different lowercase letters indicate significant difference in side length (P<0.05). The same as below"

Fig. 2

Effects of nozzle height on 3D printing performance of Pleurotus eryngii powder-Locust bean gum samples"

Fig. 3

Effects of moving speed of nozzle on 3D printing performance of Pleurotus eryngii powder-Locust bean gum samples"

Fig. 4

Effects of fill density on 3D printing performance of Pleurotus eryngii powder-Locust bean gum samples"

Table 2

Central composite design and results of 3D printing parameters"

因素Factor 偏差量
Deviation (%)
Nozzle diameter (mm)
Nozzle height (mm)
Moving speed of nozzle (mm∙s-1)
Fill density (%)
1 1.00 1.00 20 70 2.60
2 1.40 1.00 20 70 1.60
3 1.00 1.40 20 70 2.20
4 1.40 1.40 20 70 1.58
5 1.00 1.00 30 70 2.69
6 1.40 1.00 30 70 2.03
7 1.00 1.40 30 70 2.21
8 1.40 1.40 30 70 1.99
9 1.00 1.00 20 90 1.54
10 1.40 1.00 20 90 0.91
11 1.00 1.40 20 90 1.95
12 1.40 1.40 20 90 0.61
13 1.00 1.00 30 90 1.60
14 1.40 1.00 30 90 1.30
15 1.00 1.40 30 90 1.73
16 1.40 1.40 30 90 1.03
17 0.80 1.20 25 80 2.00
18 1.60 1.20 25 80 2.51
19 1.20 0.80 25 80 2.51
20 1.20 1.60 25 80 1.94
21 1.20 1.20 15 80 0.47
22 1.20 1.20 35 80 1.84
23 1.20 1.20 25 60 2.56
24 1.20 1.20 25 100 0.92
25 1.20 1.20 25 80 0.12
26 1.20 1.20 25 80 0.43
27 1.20 1.20 25 80 0.86
28 1.20 1.20 25 80 0.06
29 1.20 1.20 25 80 0.19
30 1.20 1.20 25 80 0.19

Table 3

Variance analysis of regression model for printing sample deviation"

Source of variance
Sum of squares
Degree of freedom
Mean square
F value
P value
模型 Model 17.510 14 1.250 7.99 0.0001**
A喷嘴直径Nozzle diameter 0.800 1 0.800 5.10 0.0392*
B打印高度Nozzle height 0.190 1 0.190 1.22 0.2871
C移动速度Moving speed of nozzle 0.770 1 0.770 4.92 0.0424*
D填充率 Fill density 3.760 1 3.760 24.01 0.0002**
AB 0.005 1 0.005 0.03 0.8668
AC 0.190 1 0.190 1.19 0.2917
AD 0.015 1 0.015 0.10 0.7612
BC 0.007 1 0.007 0.04 0.8377
BD 0.052 1 0.052 0.33 0.5739
CD 0.006 1 0.006 0.04 0.8474
A2 5.860 1 5.860 37.45 <0.0001**
B2 5.800 1 5.800 37.04 <0.0001**
C2 1.020 1 1.020 6.48 0.0224*
D2 3.170 1 3.170 20.23 0.0004**
残差 Residual 2.350 15 0.160
失拟项Lack-of-Fit 1.900 10 0.190 2.12 0.2102
纯误差 Pure error 0.450 5 0.090
总和 Sum 19.860 29

Fig. 5

Response surface plots of effects of interaction between various factors on the comprehensive deviation of the printing samples"

Fig. 6

Simulation effect of artificial neural network"

Fig. 7

Optimization process of genetic algorithm"

Table 4

Comparison of optimization results between RSM and ANN"

The optimal value of the prediction
The result of the verification
Relative error (%)
RSM 0.8817 0.2314 0.148 0.550 72.73
ANN-GA 0.9389 0.2269 0.215 0.325 33.85
PANT A, LEE A Y, KARYAPPA R, LEE C P, AN J, HASHIMOTO M, TAN U X, WONG G, CHUA C K, ZHANG Y. 3D food printing of fresh vegetables using food hydrocolloids for dysphagic patients. Food Hydrocolloids, 2021, 114: 106546.

doi: 10.1016/j.foodhyd.2020.106546
TANG T T, ZHANG M, MUJUMDAR A S, TENG X X. 3D printed white radish/potato gel with microcapsules: Color/flavor change induced by microwave-infrared heating. Food Research International, 2022, 158: 111496.

doi: 10.1016/j.foodres.2022.111496
ZHANG J Y, PANDYA J K, MCCLEMENTS D J, LU J K, KINCHLA A J. Advancements in 3D food printing: a comprehensive overview of properties and opportunities. Critical Reviews in Food Science and Nutrition, 2022, 62(17): 4752-4768.

doi: 10.1080/10408398.2021.1878103
卢士军, 李泰, 孙君茂, 徐泽群, 戚俊, 刘鹏, 黄家章. 香菇、杏鲍菇和金针菇的氨基酸组成与蛋白质含量评价. 中国食用菌, 2022, 41(1): 45-51.
LU S J, LI T, SUN J M, XU Z Q, QI J, LIU P, HUANG J Z. Amino acid composition and protein evaluation of Lentinula edodes, Pleurotus eryngii and Flammulina velutipes. Edible Fungi of China, 2022, 41(1): 45-51. (in Chinese)
KLEFTAKI S A, SIMATI S, AMERIKANOU C, GIOXARI A, TZAVARA C, ZERVAKIS G I, KALOGEROPOULOS N, KOKKINOS A, KALIORA A C. Pleurotus eryngii improves postprandial glycaemia, hunger and fullness perception, and enhances ghrelin suppression in people with metabolically unhealthy obesity. Pharmacological Research, 2022, 175: 105979.

doi: 10.1016/j.phrs.2021.105979
ZHANG B R, LI Y Y, ZHANG F M, LINHARDT R J, ZENG G Y, ZHANG A Q. Extraction, structure and bioactivities of the polysaccharides from Pleurotus eryngii: A review. International Journal of Biological Macromolecules, 2020, 150: 1342-1347.

doi: 10.1016/j.ijbiomac.2019.10.144
PÉREZ B, NYKVIST H, BRØGGER A F, LARSEN M B, FALKEBORG M F. Impact of macronutrients printability and 3D-printer parameters on 3D-food printing: A review. Food Chemistry, 2019, 287: 249-257.

doi: S0308-8146(19)30413-3 pmid: 30857696
YANG F L, ZHANG M, BHANDARI B, LIU Y P. Investigation on lemon juice gel as food material for 3D printing and optimization of printing parameters. LWT-Food Science and Technology, 2018, 87: 67-76.

doi: 10.1016/j.lwt.2017.08.054
黄梦莎. 基于糙米凝胶的挤压式三维打印研究[D]. 无锡: 江南大学, 2019.
HUANG M S. Research on extrusion-based 3D printing based on brown rice gel[D]. Wuxi: Jiangnan University, 2019. (in Chinese)
WANG L, ZHANG M, BHANDARI B, YANG C H. Investigation on fish surimi gel as promising food material for 3D printing. Journal of Food Engineering, 2018, 220: 101-108.

doi: 10.1016/j.jfoodeng.2017.02.029
杨帆. 典型植物类重组食品挤压式三维打印成型效果及稳定性研究[D]. 无锡: 江南大学, 2018.
YANG F. Research on the modeling effect and shape retention of the extrusion-based 3D-printed typical prepared vegetarian food[D]. Wuxi: Jiangnan University, 2018. (in Chinese)
向晨曦, 李钰金, 高瑞昌, 白帆, 汪金林, 赵元晖. 打印参数对未漂洗鲟鱼糜凝胶3D打印成型效果的影响. 食品工业科技, 2022, 43(2): 1-8.
XIANG C X, LI Y J, GAO R C, BAI F, WANG J L, ZHAO Y H. Effect of printing parameters on the 3D printing molding effect of unrinsed sturgeon surimi gel. Science and Technology of Food Industry, 2022, 43(2): 1-8. (in Chinese)
CHARRIER M, OUELLET-PLAMONDON C M. Artificial neural network for the prediction of the fresh properties of cementitious materials. Cement and Concrete Research, 2022, 156: 106761.

doi: 10.1016/j.cemconres.2022.106761
PRADHAN P, TINGSANCHALI T, SHRESTHA S. Evaluation of Soil and Water Assessment Tool and Artificial Neural Network models for hydrologic simulation in different climatic regions of Asia. Science of the Total Environment, 2020, 701: 134308.

doi: 10.1016/j.scitotenv.2019.134308
张斌, 孙兰萍, 施颖, 屠康. 基于人工神经网络法优化河蚌多糖超高压提取工艺. 食品与机械, 2016, 32(11): 148-153.
ZHANG B, SUN L P, SHI Y, TU K. Optimization on ultra high pressure extraction process of mussel polysaccharide based artificial neural network. Food & Machinery, 2016, 32(11): 148-153. (in Chinese)
邹立飞, 郑鹏. 响应面法、BP神经网络优化薏仁米酒产氨基酸态氮. 食品研究与开发, 2021, 42(9): 121-130.
ZOU L F, ZHENG P. Comparative study of response surface methodology and back-propagation neural network in optimizing amino acid nitrogen production from Coix seed wine. Food Research and Development, 2021, 42(9): 121-130. (in Chinese)
MUMALI F. Artificial neural network-based decision support systems in manufacturing processes: A systematic literature review. Computers & Industrial Engineering, 2022, 165: 107964.

doi: 10.1016/j.cie.2022.107964
XING X B, CHITRAKAR B, HATI S, XIE S Y, LI H B, LI C T, LIU Z B, MO H Z. Development of black fungus-based 3D printed foods as dysphagia diet: Effect of gums incorporation. Food Hydrocolloids, 2022, 123: 107173.

doi: 10.1016/j.foodhyd.2021.107173
LIU Z B, ZHANG M, BHANDARI B, YANG C H. Impact of rheological properties of mashed potatoes on 3D printing. Journal of Food Engineering, 2018, 220: 76-82.

doi: 10.1016/j.jfoodeng.2017.04.017
李晓桐. FDM式3D打印机控制系统设计及工艺参数优化[D]. 哈尔滨: 哈尔滨理工大学, 2021.
LI X T. Control system design of FDM 3D printer and process parameter optimization[D]. Harbin: Harbin University of Science and Technology, 2021. (in Chinese)
岳阳, 封张萍, 王梦婷, 朱艳云, 陈健初, 叶兴乾. 基于BP神经网络和遗传算法的大米抗氧化肽酶解工艺优化. 食品工业, 2021, 42(8): 83-88.
YUE Y, FENG Z P, WANG M T, ZHU Y Y, CHEN J C, YE X Q. Optimization of enzymatic hydrolysis process of rice antioxidant peptides based on BP neural network and genetic algorithm. The Food Industry, 2021, 42(8): 83-88. (in Chinese)
谭永兰, 梁锐, 丁东源, 李晓君, 渠志灿, 李海波. 响应面法优化黑果腺肋花楸残渣花色苷提取工艺. 食品科技, 2020, 45(5): 246-253.
TAN Y L, LIANG R, DING D Y, LI X J, QU Z C, LI H B. Optimization of extraction process of anthocyanin from residue of Aronia melanocarpa by response surface methodology. Food Science and Technology, 2020, 45(5): 246-253. (in Chinese)
王晓彤, 古碧, 黄丽婕, 陈杰, 周雷, 覃杨华, 郑莹莹, 刘鑫. 响应面法优化制备PLA/木薯厌氧渣复合材料. 工程塑料应用, 2017, 45(2): 51-55.
WANG X T, GU B, HUANG L J, CHEN J, ZHOU L, QIN Y H, ZHENG Y Y, LIU X. Optimization of PLA/cassava residues wood plastic composites by response surface methodology. Engineering Plastics Application, 2017, 45(2): 51-55. (in Chinese)
程成鹏, 贺稚非, 唐春, 刘姝韵, 肖旭, 李洪军. 酶-碱联合工艺改善猪大肠嫩度和保水性的工艺优化. 食品与发酵工业, 2022, 48(16): 87-94.
CHENG C P, HE Z F, TANG C, LIU S Y, XIAO X, LI H J. Optimization of enzyme-alkali combined process for improving tenderness and water retention of pig large intestine. Food and Fermentation Industries, 2022, 48(16): 87-94. (in Chinese)
姬云云, 田洪磊, 詹萍, 未志胜, 王鹏, 张芳. BP神经网络结合遗传算法优化羊肉汤中香辛料的添加量. 中国食品学报, 2021, 21(3): 128-137.
JI Y Y, TIAN H L, ZHAN P, WEI Z S, WANG P, ZHANG F. Optimizing of the amount of spices in stewed mutton soup using BP neural network and genetic algorithm. Journal of Chinese Institute of Food Science and Technology, 2021, 21(3): 128-137. (in Chinese)
宋建忠, 陈盈盈, 杨婧, 李杰, 陈章浩, 常军民. 人工神经网络-遗传算法优化刺糖低聚糖提取工艺的研究. 中国食品添加剂, 2022, 33(6): 1-7.
SONG J Z, CHEN Y Y, YANG J, LI J, CHEN Z H, CHANG J M. Study on the optimization of the extraction process of polysaccharides from Saccharum alhagi by artificial neural network-genetic algorithm method. China Food Additives, 2022, 33(6): 1-7. (in Chinese)
金立明, 赵子龙, 焦熙栋, 闫博文, 范大明, 黄建联, 周文果, 赵建新, 张灏. 不同打印条件的鱼糜3D打印成型效果分析. 现代食品科技, 2020, 36(5): 214-222.
JIN L M, ZHAO Z L, JIAO X D, YAN B W, FAN D M, HUANG J L, ZHOU W G, ZHAO J X, ZHANG H. Effect of printing conditions on 3D printing of surimi. Modern Food Science and Technology, 2020, 36(5): 214-222. (in Chinese)
SEVERINI C, DEROSSI A, AZZOLLINI D. Variables affecting the printability of foods: Preliminary tests on cereal-based products. Innovative Food Science and Emerging Technologies, 2016, 38: 281-291.

doi: 10.1016/j.ifset.2016.10.001
丁易人. 基于挤出成型的食材3D打印工艺研究[D]. 杭州: 浙江大学, 2017.
DING Y R. Research on the three dimensional printing process of food materials based on extrusion molding[D]. Hangzhou: Zhejiang University, 2017. (in Chinese)
张志同, 魏正英, 任传奇, 付丽倩. 糊状食材3D打印工艺参数对成形形貌的影响研究. 机械设计与制造, 2017(S1): 74-76, 80.
ZHANG Z T, WEI Z Y, REN C Q, FU L Q. Research on the influence of paste-like ingredients 3D printing process parameters on forming morphology. Machinery Design & Manufacture, 2017(S1): 74-76, 80. (in Chinese)
LIU Y W, LIANG X, SAEED A, LAN W J, QIN W. Properties of 3D printed dough and optimization of printing parameters. Innovative Food Science & Emerging Technologies, 2019, 54: 9-18.
SMITH D M, KAPOOR Y, KLINZING G R, PROCOPIO A T. Pharmaceutical 3D printing: Design and qualification of a single step print and fill capsule. International Journal of Pharmaceutics, 2018, 544(1): 21-30.

doi: S0378-5173(18)30203-5 pmid: 29605694
GUÉNARD-LAMPRON V, MASSON M, LEICHTNAM O, BLUMENTHAL D. Impact of 3D printing and post-processing parameters on shape, texture and microstructure of carrot appetizer cake. Innovative Food Science & Emerging Technologies, 2021, 72: 102738.
VARGHESE C, WOLODKO J, CHEN L Y, DOSCHAK M, SRIVASTAV P P, ROOPESH M S. Influence of selected product and process parameters on microstructure, rheological, and textural properties of 3D printed cookies. Foods, 2020, 9(7): 907.

doi: 10.3390/foods9070907
SHAFI J, SUN Z H, JI M S, GU Z M, AHMAD W. ANN and RSM based modelling for optimization of cell dry mass of Bacillus sp. strain B67 and its antifungal activity against Botrytis cinerea. Biotechnology & Biotechnological Equipment, 2018, 32(1): 58-68.
赵峰, 姜胜兵. 基于优化的GA-BP及其在葡萄酒质量预测的应用. 哈尔滨商业大学学报(自然科学版), 2021, 37(3): 307-313.
ZHAO F, JIANG S B. Application of GA-BP based on optimization in wine quality prediction. Journal of Harbin University of Commerce (Natural Sciences Edition), 2021, 37(3): 307-313. (in Chinese)
[1] XU Qian, WANG Han, MA Sai, HU QiuHui, MA Ning, SU AnXiang, LI Chen, MA GaoXing. Inhibition and Interaction of Pleurotus eryngii Polysaccharide and Its Digestion Products on Starch Digestive Enzymes [J]. Scientia Agricultura Sinica, 2023, 56(2): 357-367.
[2] WU Jun,GUO DaQian,LI Guo,GUO Xi,ZHONG Liang,ZHU Qing,GUO JiaXin,YE YingCong. Prediction of Soil Organic Carbon Content in Jiangxi Province by Vis-NIR Spectroscopy Based on the CARS-BPNN Model [J]. Scientia Agricultura Sinica, 2022, 55(19): 3738-3750.
[3] MA YuYang,GUAN HaiXiang,YANG HaoXuan,SHAO Shuai,SHAO YiQun,LIU HuanJun. A New Method to Improve the Accuracy of Digital Elevation Model in Northeast China by Using Terrain, Soil and Crop Information [J]. Scientia Agricultura Sinica, 2021, 54(8): 1715-1727.
[4] SHAO ZeZhong,YAO Qing,TANG Jian,LI HanQiong,YANG BaoJun,LÜ Jun,CHEN Yi. Research and Development of the Intelligent Identification System of Agricultural Pests for Mobile Terminals [J]. Scientia Agricultura Sinica, 2020, 53(16): 3257-3268.
[5] ZHANG Zhuo,LONG HuiLing,WANG ChongChang,YANG GuiJun. Comparison of Hyperspectral Remote Sensing Estimation Models Based on Photosynthetic Characteristics of Winter Wheat Leaves [J]. Scientia Agricultura Sinica, 2019, 52(4): 616-628.
[6] DING YiBo,XU JiaTun,LI Liang,CAI HuanJie,SUN YaNan. Analysis of Drought Characteristics and Its Trend Change in Shaanxi Province Based on SPEI and MI [J]. Scientia Agricultura Sinica, 2019, 52(23): 4296-4308.
[7] ZHANG Biao,LIU Xuan,BI JinFeng,WU XinYe,JIN Xin,LI Xuan,LI Xiao. Suitability Evaluation of Apple for Chips-Processing Based on BP Artificial Neural Network [J]. Scientia Agricultura Sinica, 2019, 52(1): 129-142.
[8] ZHANG Fang,WEI ZhiSheng,WANG Peng,LI KaiXuan,ZHAN Ping,TIAN HongLei. Using Neural Network Coupled Genetic Algorithm to Optimize the SPME Conditions of Volatile Compounds in Korla Pear [J]. Scientia Agricultura Sinica, 2018, 51(23): 4535-4547.
[9] DU Bin, HU XiaoTao, WANG WenE, MA LiHua, ZHOU ShiWei. Stem Flow Influencing Factors Sensitivity Analysis and Stem Flow Model Applicability in Filling Stage of Alternate Furrow Irrigated Maize [J]. Scientia Agricultura Sinica, 2018, 51(2): 233-245.
[10] LIU QingFei, ZHANG HongLi, WANG YanLing. Real-Time Pixel-Wise Classification of Agricultural Images Based on Depth-Wise Separable Convolution [J]. Scientia Agricultura Sinica, 2018, 51(19): 3673-3682.
[11] ZHU YaXing, YU Lei, HONG YongSheng, ZHANG Tao, ZHU Qiang, LI SiDi, GUO Li, LIU JiaSheng. Hyperspectral Features and Wavelength Variables Selection Methods of Soil Organic Matter [J]. Scientia Agricultura Sinica, 2017, 50(22): 4325-4337.
[12] LIAO Qiu-hong, HE Shao-lan, XIE Rang-jin, QIAN Chun, HU De-yu, Lü Qiang1,YI Shi-lai, ZHENG Yong-qiang, DENG Lie. Study on Producing Area Classification of Newhall Navel Orange Based on the Near Infrared Spectroscopy [J]. Scientia Agricultura Sinica, 2015, 48(20): 4111-4119.
[13] TANG Jun-1, DENG Li-Miao-2, CHEN Hui-1, LUAN Tao-1, MA Wen-Jie-1. Research on Maize Leaf Recognition of Characteristics from Transmission Image Based on Machine Vision [J]. Scientia Agricultura Sinica, 2014, 47(3): 431-440.
[14] ZHUANG Jia-Xiang, JIANG Hai-Yan, LIU Lei-Lei, WANG Fang-Fang, TANG Liang, ZHU Yan, CAO Wei-Xing. Parameters Optimization of Rice Development Stages Model Based on Individual Advantages Genetic Algorithm [J]. Scientia Agricultura Sinica, 2013, 46(11): 2220-2231.
[15] LIANG Yi, LIU Shi-Hong. Research on the Combined Forecast Model Method Based on BP Neural Network Improved by Genetic Algorithm [J]. Scientia Agricultura Sinica, 2012, 45(23): 4924-4930.
Full text



No Suggested Reading articles found!