The mechanization of fruit harvesting has become an essential component of modern agricultural engineering, particularly in the context of labor shortages, efficiency demands, and precision farming requirements. This study presents the construction and assessment of a terrain-level fruit picking system inspired by natural movement strategies, integrating biomimetic principles with mechanical design and computational optimization. The research aims to develop a system capable of efficiently collecting fallen fruits from ground surfaces while minimizing damage and maximizing operational efficiency.

The conceptual framework of the study is grounded in biomimicry, which emphasizes the replication of natural movement patterns observed in biological organisms. These principles are applied to design a picking mechanism that adapts to irregular terrain conditions and varying fruit distributions. The system incorporates pneumatic conveying, vibration-assisted separation, and adaptive collection modules, supported by simulation-based optimization techniques. Computational modeling approaches, including hybrid optimization algorithms and neural network-based prediction models, are utilized to enhance system performance and operational stability (Bouktif et al., 2018; Zheng et al., 2017).

The methodology involves a combination of mechanical design, computational simulation, and experimental validation. Laboratory-based simulations evaluate force transfer mechanisms under vibration excitation, while field testing assesses real-world performance in agricultural settings (Fu et al., 2017; Zhang et al., 2020). The integration of artificial intelligence frameworks enables dynamic adjustment of operational parameters, improving efficiency under varying environmental conditions.

The findings indicate that biomimetic design significantly enhances the adaptability and efficiency of terrain-level fruit picking systems. The system demonstrates improved collection rates, reduced fruit damage, and enhanced energy efficiency compared to conventional methods. However, challenges related to system complexity, cost, and scalability remain critical considerations.

This study contributes to the field of agricultural mechanization by providing a comprehensive framework for integrating biomimetic design with advanced computational techniques. The research highlights the potential of interdisciplinary approaches in addressing complex agricultural challenges and offers practical insights for the development of next-generation harvesting systems.

Biomimetic engineering, fruit harvesting system, terrain adaptation, pneumatic conveying, vibration mechanism, agricultural mechanization, neural networks, optimization algorithms

Amjady, N.; Abedinia, O. Short Term Wind Power Prediction Based on Improved Kriging Interpolation, Empirical Mode Decomposition, and Closed-Loop Forecasting Engine. Sustainability 2017, 9, 2104.

Bara, A.; Căruțașu, G.; Pîrjan, A.; Oprea, S.V.; Botha, I.; Belciu, A.; Botezatu, M.A. Intelligent System for Predicting, Analysing and Monitoring the Performance Indicators of Technological and Business Processes in the Field of Renewable Energies (SIPAMER), Issue II: Development and Implementation of the Informatics Prototype; Pro Universitaria Publisher: Bucharest, Romania, 2017; ISBN 978-606-26-0818-7.

Boroojeni, K.G.; Amini, M.H.; Bahrami, S.; Iyengar, S.S.; Sarwat, A.I.; Karabasoglu, O. A novel multi-time-scale modeling for electric power demand forecasting: From short-term to medium-term horizon. Electr. Power Syst. Res. 2017, 142, 58–73.

Bouktif, S.; Fiaz, A.; Ouni, A.; Serhani, M.M.A. Optimal Deep Learning LSTM Model for Electric Load Forecasting Using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies 2018, 11, 1636.

Caffe. Deep Learning Framework. Available online: http://caffe.berkeleyvision.org/ (accessed on 31 August 2018).

Castellani, F.; Astolfi, D.; Mana, M.; Burlando, M.; Meißner, C.; Piccioni, E. Wind Power Forecasting techniques in complex terrain: ANN vs. ANN-CFD hybrid approach. J. Phys. Conf. Ser. 2016, 753, 082002.

Cheng, L.; Zang, H.; Ding, T.; Sun, R.; Wang, M.; Wei, Z.; Sun, G. Ensemble Recurrent Neural Network Based Probabilistic Wind Speed Forecasting Approach. Energies 2018, 11, 1958.

Ding K, Zhang B C, Diao X Y, Zhang H M, Fu W, Kan Z. Optimization and experiment of vibration device shaking frequency of jujube harvester. Journal of Agricultural Mechanization Research, 2019; 41(3): 21–25, 33.

Fu W, He R, Qu J L, Sun Y, Wang L H, Kan Z. Design of self-propelled dwarf and close planting jujube harvester. Journal of Agricultural Mechanization Research, 2024; 36(4): 106–109.

Fu W, Zhang Z Y, Liu Y D, Pan J B, Cui J, Ding K, et al. Simulation experiment in lab on force transfer effect of jujube under vibration excitation. Transactions of the CSAE, 2017; 33(17): 65–72.

Gers, F.A.; Schmidhuber, J.; Cummins, F. Learning to forget: Continual prediction with LSTM. Neural Comput. 2000, 12.

Gouveia, H.T.V.; de Aquino, R.R.B.; Ferreira, A.A. Enhancing Short-Term Wind Power Forecasting through Multiresolution Analysis and Echo State Networks. Energies 2018, 11, 824.

Graves, A.; Liwicki, M.; Fernández, S.; Bertolami, R.; Bunke, H.; Schmidhuber, J. A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2009, 31.

Habisreutinger, P.; Gunderson, D.E. Real estate reuse opportunities within the regenesis project area: A case study. Int. J. Constr. Educ. Res. 2006, 2, 53–63.

Hagan, M.T.; Menhaj, M.B. Training Feedforward Networks with the Marquardt Algorithm. IEEE Trans. Neural Netw. 1994, 5, 989–993.

Hirschberg, J.; Manning, C.D. Advances in natural language processing. Science 2015, 349, 261–266.

Hochreiter, S.; Urgen Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9.

Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989, 2, 359–366.

Hoy, M.B. Alexa, Siri, Cortana, and More: An Introduction to Voice Assistants. Med. Ref. Serv. Q. 2018, 37.

Huang, C.-J.; Kuo, P.-H. A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities. Sensors 2018, 18, 2220.

Huang, Y. Advances in artificial neural networks—Methodological development and application. Algorithms 2009, 2, 973–1007.

Ibrahim, N.K.; Abdullah, R.S.A.R.; Saripan, M.I. Artificial Neural Network Approach in Radar Target Classification. J. Comput. Sci. 2009, 5, 23–32.

Kingma, D.P.; Ba, J.L. Adam: A Method for Stochastic Optimization. In Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, Portland, OR, USA, 7–11 July 2010.

Keras Documentation. Available online: https://keras.io/ (accessed on 31 August 2018).

Lange, J.; Mann, J.; Angelou, N.; Berg, J.; Sjöholm, M.; Mikkelsen, T. Variations of the Wake Height over the Bolund Escarpment Measured by a Scanning Lidar. Bound.-Layer Meteorol. 2016, 159, 147–159.

Levenberg, K. A method for the solution of certain non-linear problems in least squares. Q. J. Appl. Math. 1944, 2, 164–168.

Liu, H.; Tian, H.; Li, Y.; Zhang, L. Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions. Energy Convers. Manag. 2015, 92, 67–81.

Lippmann, R.P. An Introduction to Computing with Neural Nets. IEEE ASSP Mag. 1987, 4, 4–22.

Lubitz, W.D.; White, B.R. Wind-tunnel and field investigation of the effect of local wind direction on speed-up over hills. J. Wind Eng. Ind. Aerodyn. 2007, 95, 639–661.

Lungu, I.; Bâra, A.; Cărutasu, G.; Pîrjan, A.; Oprea, S.V. Prediction intelligent system in the field of renewable energies through neural networks. Econ. Comput. Econ. Cybern. Stud. Res. 2016, 50, 85–102.

Lungu, I.; Căruțașu, G.; Pîrjan, A.; Oprea, S.V.; Bara, A. A two-step forecasting solution and upscaling technique for small size wind farms located in hilly areas of Romania. Stud. Inform. Control 2016, 25, 77–86.

MacKay, D.J.C. Bayesian Interpolation. Neural Comput. 1992, 4, 415–447.

Mattuella, J.M.L.; Loredo-Souza, A.M.; Oliveira, M.G.K.; Petry, A.P. Wind tunnel experimental analysis of a complex terrain micrositing. Renew. Sustain. Energy Rev. 2016, 54, 110–119.

Murad, A.; Pyun, J.-Y. Deep Recurrent Neural Networks for Human Activity Recognition. Sensors 2017, 17, 2556.

Nguyen, M.-T.; Nguyen, V.-H.; Yun, S.-J.; Kim, Y.-H. Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear. Energies 2018, 11, 1202.

Niu, D.; Pu, D.; Dai, S. Ultra-Short-Term Wind-Power Forecasting Based on the Weighted Random Forest Optimized by the Niche Immune Lion Algorithm. Energies 2018, 11, 1098.

Ordóñez, F.J.; Roggen, D. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors 2016, 16, 115.

Schmidhuber, J. Deep Learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117.

Schmidhuber, J.; Wierstra, D.; Gagliolo, M.; Gomez, F. Training recurrent networks by evolino. Neural Comput. 2007, 19, 757–779.

Shen, Y.; Wang, X.; Chen, J. Wind Power Forecasting Using Multi-Objective Evolutionary Algorithms for Wavelet Neural Network-Optimized Prediction Intervals. Appl. Sci. 2018, 8, 185.

Shi G K, Li J B, Ding L P, Kan Z. Design and experiment of inertia pneumatic type cleaner system of jujube fruit. Transactions of the CSAM, 2022; 53(6): 167–176.

Sutton, R.S. Two problems with backpropagation and other steepest-descent learning procedures for networks. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Amherst, MA, USA, 15–17 August 1986.

Sutskever, I.; Martens, J.; Dahl, G.; Hinton, G. On the importance of initialization and momentum in deep learning. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 26–31 May 2013.

Tieleman, T.; Hinton, G.E.; Srivastava, N.; Swersky, K. Lecture 6.5-rmsprop: Divide the Gradient by a Running Average of its Recent Magnitude. COURSERA Neural Networks for Machine Learning. 2012. Available online: https://www.coursera.org/learn/neural-networks/lecture/YQHki/rmsprop-divide-the-gradient-by-a-running-average-of-its-recent-magnitude (accessed on 31 August 2018).

Walmsley, J.L.; Troen, I.; Lalas, D.P.; Mason, P.J. Surface-layer flow in complex terrain: Comparison of models and full-scale observations. Bound.-Layer Meteorol. 1990, 52, 259–281.

Wang, R.; Li, J.; Wang, J.; Gao, C. Research and Application of a Hybrid Wind Energy Forecasting System Based on Data Processing and an Optimized Extreme Learning Machine. Energies 2018, 11, 1712.

Wang, Y.; Liu, Y.; Li, L.; Infield, D.; Han, S. Short-Term Wind Power Forecasting Based on Clustering Pre-Calculated CFD Method. Energies 2018, 11, 854.

Welcome to Lasagne. Available online: https://lasagne.readthedocs.io/en/latest/ (accessed on 30 August 2018).

Wu, Y.; Schuster, M.; Chen, Z.; Le, Q.V.; Norouzi, M.; Macherey, W.; Krikun, M.; Cao, Y.; Gao, Q.; Macherey, K.; et al. Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. ArXiv e-Prints 2016.

Xiong, W.; Droppo, J.; Huang, X.; Seide, F.; Seltzer, M.; Stolcke, A.; Yu, D.; Zweig, G. The Microsoft 2017 conversational speech recognition system. In Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 15–20 April 2018.

Xu, X.; Niu, D.; Fu, M.; Xia, H.; Wu, H. A Multi Time Scale Wind Power Forecasting Model of a Chaotic Echo State Network Based on a Hybrid Algorithm of Particle Swarm Optimization and Tabu Search. Energies 2015, 8, 12388–12408.

Yao, Z.; Wang, C. A Hybrid Model Based on a Modified Optimization Algorithm and an Artificial Intelligence Algorithm for Short-Term Wind Speed Multi-Step Ahead Forecasting. Sustainability 2018, 10, 1443.

Yue, B.; Fu, J.; Liang, J. Residual Recurrent Neural Networks for Learning Sequential Representations. Information 2018, 9, 56.

Zhang F K, Yu F S, Li Z J, Zhang H, Lan H P, Li P, Zhang C J. Design and field testing of the air-suction machine for picking up Chinese jujube fruits. Journal of Fruit Science, 2020; 37(2): 278–285.

Zhang F K, Zhang H, Lan H P, Yu F F, Li Z J, Li P. Simulation analysis of pneumatic conveying device of air-suction jujube picker based on CFD-EDM coupling. Journal of Agricultural Science and Technology, 2021; 23(7): 107–116.

Zhang J.; Wei, Y.; Tan, Z.; Ke, W.; Tian, W. A Hybrid Method for Short-Term Wind Speed Forecasting. Sustainability 2017, 9, 596.

Zhang X J, Bai S H, Jin W, Yuan P P, Yu M J, Yan J S, et al. Development of pneumatic collecting machine of red jujube in dwarfing and close cultivation. Transactions of the CSAE, 2019; 35(12): 1–9.

Zhao S X, Feng Z. Gas flow characteristics of argon inductively coupled plasma and advections of plasma species under incompressible and compressible flows. Chinese Physics B, 2018; 27(12): 352–364. CNKI: SUN: ZGWL. 0.2018-12-050.

Zhao, H.; Zhao, H.; Guo, S. Short-Term Wind Electric Power Forecasting Using a Novel Multi-Stage Intelligent Algorithm. Sustainability 2018, 10, 881.

Zheng, D.; Shi, M.; Wang, Y.; Eseye, A.T.; Zhang, J. Day-Ahead Wind Power Forecasting Using a Two-Stage Hybrid Modeling Approach Based on SCADA and Meteorological Information, and Evaluating the Impact of Input-Data Dependency on Forecasting Accuracy. Energies 2017, 10, 1988.

Zheng, H.; Yuan, J.; Chen, L. Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation. Energies 2017, 10, 1168.