Manon Dat , Hervé Plaisance , Jane Vignau-Laulhere , Sylvain Bourrigaud , Valérie Desauziers
{"title":"Modelling of pheromone release from solid matrix dispenser for integrated pest management","authors":"Manon Dat , Hervé Plaisance , Jane Vignau-Laulhere , Sylvain Bourrigaud , Valérie Desauziers","doi":"10.1016/j.biosystemseng.2024.11.013","DOIUrl":"10.1016/j.biosystemseng.2024.11.013","url":null,"abstract":"<div><div>Sex pheromones are introduced in the cultivated areas to create mating disruption and thus to protect crops from pests. This article deals with the release characteristics of a model pheromone (dodecyl acetate) encapsulated in a solid matrix developed as a passive dispenser. Released kinetics were obtained both in the field by extracting and quantifying the remaining pheromone in the dispenser over time and in laboratory by emission chamber tests under controlled conditions. Results showed that the release profiles follow pseudo-zero-order kinetics with a quasi-constant release rate of 1.53 mg day<sup>-1</sup> under field conditions for the first sixty days. Emission data showed that two key parameters, i.e., the matrix/air partition coefficient (K<sub>ma</sub>) and the convective transfer coefficient in the gas phase (h<sub>m</sub>) govern the release rate of the dispenser. Estimates of K<sub>ma</sub> varied from 1×10<sup>6</sup> to 4.55×10<sup>6</sup> and h<sub>m</sub> from 3.2×10<sup>-3</sup> to 5×10<sup>-3</sup> m s<sup>-1</sup> depending on the air velocity and temperature conditions. Temperature dependence of K<sub>ma</sub> was most significant and was addressed by estimating the enthalpy of the pheromone partitioning between the matrix dispenser and air <span><math><mrow><msub><mrow><mo>Δ</mo><mi>H</mi></mrow><mtext>ma</mtext></msub></mrow></math></span> (102 kJ mol<sup>-1</sup>). The results led to the development of a model based on K<sub>ma</sub> and h<sub>m</sub> as the main parameters describing pheromone release from the matrix dispenser. A good agreement was found between the measurements obtained in field and model predictions. This model could be an effective tool for adjusting the release rate of pheromone dispensers under practise conditions.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"249 ","pages":"Pages 18-27"},"PeriodicalIF":4.4,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaochuan Zhao , Janguo Zhao , Jiale Zhao , Zhikai Ma , Jianchang Li , Binhao Dai , Meilin An , Jiaping Wang , Jianjun Hao
{"title":"Optimisation design and experimental analysis of rotary blade reinforcing ribs using DEM-FEM techniques","authors":"Xiaochuan Zhao , Janguo Zhao , Jiale Zhao , Zhikai Ma , Jianchang Li , Binhao Dai , Meilin An , Jiaping Wang , Jianjun Hao","doi":"10.1016/j.biosystemseng.2024.11.015","DOIUrl":"10.1016/j.biosystemseng.2024.11.015","url":null,"abstract":"<div><div>This study addresses the prevalent issue of rotary blade fractures in tillage operations by designing a new type of reinforcing rib that mitigates neck force and alleviates stress concentration. Initially, utilising traditional design concepts, the side-plate reinforcing rib was segmented into units and analysed using ANSYS to develop an initial model. Evaluation indices such as specific strength structural efficiency and specific stiffness structural efficiency were employed to perform orthogonal optimisation of the rib dimensions, achieving optimal measurements of 72.9 mm in length, 15.7 mm in width, and 3.5 mm in thickness. These dimensions enhance the specific strength structural efficiency by 14.14% and the specific stiffness structural efficiency by 0.95% compared to the initial model. Further, the rib's mathematical model was refined and generalised by a curve-fitting method across different rotary blade models (IT series), followed by topological optimisation to fine-tune morphological features. This optimisation reduced the model's mass by 9.78% and improved efficiency metrics by 2.6% (strength) and 0.5% (stiffness). Comparative experiments using DEM-FEM coupled analysis were conducted on three optimised models to assess the redesigned blade's performance. The experiments evaluated key performance metrics such as neck force, maximum stress, fatigue life, and ultimate fracture stress. The results indicate that after two rounds of optimisation, the blade's neck force was reduced by 16.85%, the maximum stress decreased by 15.22%, the fatigue life increased by 76.03%, and the ultimate fracture stress improved by 20.16%. These changes align with the optimisation objectives. Subsequent control and calibration tests produced a load-strain curve that validated the simulation data with a marginal error range of 3%–10%, validating the simulation's accuracy. This research provides a robust theoretical framework for optimising the reinforcing rib and fracture resistance of rotary blades.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"249 ","pages":"Pages 1-17"},"PeriodicalIF":4.4,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xinyue Zhang , Qingjie Wang , Chao Wang , Xiuhong Wang , Zhengxin Xu , Caiyun Lu
{"title":"Guidelines for mechanical weeding: Developing weed control lines through point extraction at maize root zones","authors":"Xinyue Zhang , Qingjie Wang , Chao Wang , Xiuhong Wang , Zhengxin Xu , Caiyun Lu","doi":"10.1016/j.biosystemseng.2024.11.003","DOIUrl":"10.1016/j.biosystemseng.2024.11.003","url":null,"abstract":"<div><div>Precision agriculture advancements are epitomised by precision mechanical weeding, which contributes significantly to sustainable farming practices. Traditional leaf-recognition technologies fail to meet the stringent requirements of precision weeding because they do not adequately guide weeding tools that operate close to seedling roots, such as finger weeders, to minimise crop damage. To address this issue, a novel method is developed to delineate paths for weeding tools, thereby preventing harm to seedlings. This method employs an advanced version of YOLOv8Pose to detect weeding areas around maize seedlings by pinpointing key points on the maize seedlings. To enhance the detection accuracy, a multi-scale dilation attention (MSDA) module and a lightweight reparameterisable EfficientRep module were used. The root connection line of the maize row was obtained by sequentially connecting the key point positions. The guide line for the weeding component was then determined by correcting this root connection line using the median absolute deviation (MAD) as the threshold. The approach demonstrated a remarkable precision in guiding weeding lines with an angular error of only 0–3° and a recognition rate of 100 FPS. In actual weeding operations, the effective weeding rate was 95.6%, which was far better than the 74.2% obtained by the leaf recognition-based method. This innovative method not only enhances weeding precision but also significantly reduces crop damage risk, thereby fostering more effective and sustainable agricultural practices.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 321-336"},"PeriodicalIF":4.4,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaofang Chen , Rui Chen , Jian Wang , Hong Li , Weibin Zhang
{"title":"Evaluation of water distribution and uniformity of sprinkler irrigation based on harmonic analysis and finite element method","authors":"Xiaofang Chen , Rui Chen , Jian Wang , Hong Li , Weibin Zhang","doi":"10.1016/j.biosystemseng.2024.11.010","DOIUrl":"10.1016/j.biosystemseng.2024.11.010","url":null,"abstract":"<div><div>A model that describes the water distribution of a single fixed spray plate sprinkler (FSPS) based on the harmonic analysis was proposed. The relationship between the pressure head, nozzle diameter, mean sprinkler irrigation depth, and amplitude was established. An analytical model for evaluating the sprinkler irrigation uniformity coefficient of a multi-sprinkler combination was developed by introducing a weighting coefficient. In conjunction with the sprinkler irrigation system's finite element hydraulic calculation model, the impact of the pipe diameter, sprinkler number, and sprinkler spacing on system energy loss, pressure head, and sprinkler irrigation system uniformity was assessed. The results demonstrated that under varying pressures and nozzle diameters, the Camargo and Sentelhas coefficient (<em>c</em>) between the measured and fitted mean value of the sprinkler irrigation depth of a single FSPS was greater than 0.99, while the <em>c</em> between the measured and fitted amplitude value was approximately 0.93. Under different combinations of nozzle, pressure head, and sprinkler spacings, the measured, derived, and calculated values of 54 sprinkler irrigation uniformity combinations were basically consistent. The uniformity of the combined FSPS under a linear-move sprinkler system was significantly affected by nozzle diameter, pipe diameter, sprinkler spacing, and inlet pressure head at 0.01 level. The number of sprinklers also had a significant impact at 0.05 level. The findings of this study could serve as a theoretical foundation for the proper design of linear-move sprinkler irrigation systems.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 308-320"},"PeriodicalIF":4.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mads Kjærgaard Nielsen , Simon Klinge Nielsen , Torben Tambo
{"title":"A vibration-based machine learning approach for roller gap detection in biomass pellet production","authors":"Mads Kjærgaard Nielsen , Simon Klinge Nielsen , Torben Tambo","doi":"10.1016/j.biosystemseng.2024.11.007","DOIUrl":"10.1016/j.biosystemseng.2024.11.007","url":null,"abstract":"<div><div>This research focuses on optimising biomass pellet manufacturing processes by detecting roller gap variations in rotary ring die pelleting (RRDP) technology. Integrating experimental testing, response surface modelling (RSM), and vibration-based machine learning, this study aims to ensure optimal conditions for biomass pellet mill operation. Vibration-based machine learning techniques offer an approach for detecting roller gap variations, while RSM provides mathematical models to understand process dynamics for identifying optimisation criteria. Experimental testing explores the impact of process variables on pellet quality metrics. Results demonstrate machine learning model performance in detecting roller gap variations with F1-scores ranging from 88.1% to 100.0% across a pilot- and industrial-scaled setup. ANOVA results underscore significant relationships between roller gap, feedstock layer mass, and pelleting process metrics, while the created RSM models all have determination coefficients <span><math><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow></math></span> of <span><math><mrow><mo>≥</mo><mn>0.90</mn></mrow></math></span>. Overall, this comprehensive approach contributes valuable insights into optimising efficiency and product quality in the biomass industry through an integrated framework.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 283-296"},"PeriodicalIF":4.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Georgios T. Xanthopoulos , Samuel Paytosh , Robert S. Dungan , Nora Olsen , Rhett Spear , Gustavo Henrique de Almeida Teixeira
{"title":"Relative contributions of respiration and transpiration to the weight loss of russet-type potatoes","authors":"Georgios T. Xanthopoulos , Samuel Paytosh , Robert S. Dungan , Nora Olsen , Rhett Spear , Gustavo Henrique de Almeida Teixeira","doi":"10.1016/j.biosystemseng.2024.11.006","DOIUrl":"10.1016/j.biosystemseng.2024.11.006","url":null,"abstract":"<div><div>Potatoes are typically stored at low temperatures (5.5–8.9 °C) and high relative humidity (95–97%) to reduce water loss, the primary factor contributing to tuber weight loss. Water loss occurs mainly through transpiration from the tuber skin (97.6%), with only 2.4% through the lenticels. However, ignoring respiration as a water-loss mechanism can lead to inaccurate weight-loss determinations. This study aimed to evaluate respiration's contribution to mass loss (water loss) in russet-type potatoes. Four russet-type cultivars (Russet Burbank, Ivory Russet, Dakota Russet, and Rainier Russet) were cured at 12.8 °C and 95% relative humidity for 14 days. After curing, the temperature was gradually reduced to 5.5 °C, 7.2 °C, or 8.9 °C with 95% RH and stored for up to 9 months. Dakota Russet had the highest and Ivory Russet the lowest weight loss during storage, irrespective of temperature. The transpiration rate per unit of initial mass varied by storage temperature, from 14 ± 50.014±0.005 g kg<sup>−1</sup> h<sup>−1</sup> at 5.5 °C, 16 ± 60.016±0.006 g kg<sup>−1</sup> h<sup>−1</sup> at 7.2 °C, and 17 ± 70.017±0.007 g kg<sup>−1</sup> h<sup>−1</sup> at 8.9 °C. The transpiration rate per unit area decreased until the 4th -5th month of storage. The water vapor pressure deficit was the main factor contributing to total weight loss, with respiration rates contributing less than 10%. Further studies are needed to understand why Dakota Russet experiences significantly greater weight loss than other russet cultivars, despite the observed data on respiration rates.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 297-307"},"PeriodicalIF":4.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Meiqi Xiang, Xiaomei Gao, Gang Wang, Jiangtao Qi, Minghao Qu, Zhongyang Ma, Xuegeng Chen, Zihao Zhou, Kexin Song
{"title":"An application oriented all-round intelligent weeding machine with enhanced YOLOv5","authors":"Meiqi Xiang, Xiaomei Gao, Gang Wang, Jiangtao Qi, Minghao Qu, Zhongyang Ma, Xuegeng Chen, Zihao Zhou, Kexin Song","doi":"10.1016/j.biosystemseng.2024.11.009","DOIUrl":"10.1016/j.biosystemseng.2024.11.009","url":null,"abstract":"<div><div>Nobody would contest that physical weed removal methods offer numerous advantages over biochemical alternatives. Within the domain of intelligent mechanical weed control, comprehensive research targeting the entire intelligent weeding machine system remains relatively scarce. To expedite the practical application of intelligent weeding machines, this study explored an enhanced YOLOv5 model with one colour constancy module, which aimed at achieving higher accuracy in crop seedling detection. An innovative \"separating and closing\" strategy, which allows the machine to precisely avoid crop seedlings while effectively weeding the areas between crop seedlings was employed to facilitate intra-row weeding. By integrating this strategy with a comprehensive design of the mobile platform, inter-row weeding actuators, and harmonious control of these key components, this research successfully developed an intelligent weeding machine capable of simultaneously performing intra-row and inter-row (all-round) weeding. Compared with previous studies, this study put the emphases on complex farm lighting conditions, both inter-row and intra-row weeding functions, and weed regrowth. Field experiments conducted in lettuce (<em>Lactuca sativa</em> var. <em>ramosa</em> Hort.) fields at four different locations on three separate dates demonstrated that this intelligent weeding machine achieved average weeding rates, crop seedling damage rates, and regrowth rates of 96.87%, 1.19%, and 0.34%, respectively. The ability to perform all-round weeding simultaneously is a significant advance in mechanical weeding control. The design and methodology employed in this study have broad implications for advancing the field of precision agriculture and addressing the growing demand for sustainable farming practices.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 269-282"},"PeriodicalIF":4.4,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhouzhou Zheng , Yaohua Hu , Jianxin Dong , Pengfei Zhao , Yixue Liu , Xintong Jiang , Yichen Qiao , Shangpeng Sun , Yuxiang Huang
{"title":"Characterising vibration patterns of winter jujube trees to optimise automated fruit harvesting","authors":"Zhouzhou Zheng , Yaohua Hu , Jianxin Dong , Pengfei Zhao , Yixue Liu , Xintong Jiang , Yichen Qiao , Shangpeng Sun , Yuxiang Huang","doi":"10.1016/j.biosystemseng.2024.11.004","DOIUrl":"10.1016/j.biosystemseng.2024.11.004","url":null,"abstract":"<div><div>Understanding jujube tree dynamic characteristics is crucial for the design and invention of a catch-and-shake machine for fruit harvesting. Currently, the study of vibration characteristics based on the finite element method is the mainstream method for different types of fruit trees. However, limited by the lack of an accurate 3D tree model, there are still gaps between existing simulation analysis and actual tests to explore vibration characteristics. Specifically, the vibration mechanism of winter jujube trees is still unclear in jujube orchards. To address the issue, a multi-view 3D reconstruction technique is employed to acquire precise 3D tree models for simulation analysis. The obtained results from experiments indicate that the determination coefficient <em>R</em><sup>2</sup> of the trunks and branches diameter are 0.96 and 0.91 between reconstructed and actual measurement results. Subsequently, material properties of jujube tree are measured to conduct model analysis and harmonic response analysis to find the optimal frequency range (10–20 Hz) in which a considerable vibration response can be obtained at low vibration energies. Moreover, transient analysis and test experiments are conducted to explore the energy transfer properties under different vibration frequency. Results showed that the acceleration response gradually increased from the bottom to the top of the branch on most branches at non-resonant frequencies. The proposed method can provide informative insights on the design of high-efficiency and low-energy jujube catch-and-shake harvesters.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 255-268"},"PeriodicalIF":4.4,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuxiang Wang , Gert Kootstra , Zengling Yang , Haris Ahmad Khan
{"title":"UAV multispectral remote sensing for agriculture: A comparative study of radiometric correction methods under varying illumination conditions","authors":"Yuxiang Wang , Gert Kootstra , Zengling Yang , Haris Ahmad Khan","doi":"10.1016/j.biosystemseng.2024.11.005","DOIUrl":"10.1016/j.biosystemseng.2024.11.005","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) equipped with multispectral cameras have been widely used in precision agriculture. However, a notable challenge is the variation in ambient illumination, which affects the accuracy and reliability of UAV-based spectral-data acquisition. In this study, the aim is to evaluate and enhance the performance of existing radiometric correction techniques under varying illumination conditions, primarily concerning radiometric accuracy and homogeneity. Seven methods including three conventional methods and four new methods were employed for correcting the MicaSense Altum multispectral system which equips with a downwelling light sensor (DLS). Two specific strategies were adopted: (1) capturing reference panels at UAV flying altitudes, and (2) strategically placing multiple sets of reference panels throughout the study area. The result shows that calibrating images one time, for instance, the empirical line method (ELM), is seriously affected by the variable illumination. The commercial solution that using the DLS helps improve the uniformity of orthomosaics but lower its radiometric accuracy. Optimising the use of the DLS by capturing panels at the UAV's flight altitude can greatly improve accuracy. Additionally, when the DLS is unavailable, strategically placing multiple reference panels across the field and correcting calibration parameters for each image can effectively help mitigate the impact of varying illumination on generated reflectance orthomosaics. In conclusion, selecting suitable radiometric correction methods is crucial for UAV multi-spectral data collection when facing variable illumination conditions.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 240-254"},"PeriodicalIF":4.4,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimising maize threshing process with temporal proximity soft actor-critic deep reinforcement learning algorithm","authors":"Qiang Zhang , Xuwen Fang , Xiaodi Gao , Jinsong Zhang , Xuelin Zhao , Lulu Yu , Chunsheng Yu , Deyi Zhou , Haigen Zhou , Li Zhang , Xinling Wu","doi":"10.1016/j.biosystemseng.2024.11.001","DOIUrl":"10.1016/j.biosystemseng.2024.11.001","url":null,"abstract":"<div><div>Maize threshing is a crucial process in grain production, and optimising it is essential for reducing post-harvest losses. This study proposes a model-based temporal proximity soft actor-critic (TP-SAC) algorithm to optimise the maize threshing process in the threshing drum. The proposed approach employs an LSTM model as a real-time predictor of threshing quality, achieving an R<sup>2</sup> of 97.17% and 98.43% for damage and unthreshed rates on the validation set. In actual threshing experiments, the LSTM model demonstrates an average error of 5.45% and 3.83% for damage and unthreshed rates. The LSTM model is integrated with the TP-SAC algorithm, acting as the environment with which the TP-SAC interacts, enabling efficient training with limited real-world data. The TP-SAC algorithm addresses the temporal correlation in the threshing process by incorporating temporal proximity sampling into the SAC algorithm's experience replay mechanism. TP-SAC outperforms the standard SAC algorithm in the simulated environment, demonstrating better sample efficiency and faster convergence. When deployed in actual threshing operations, the TP-SAC algorithm reduces the damage rate by an average of 0.91% across different feed rates compared to constant control. The proposed TP-SAC algorithm offers a novel and practical approach to optimising the maize threshing process, enhancing threshing quality.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"248 ","pages":"Pages 229-239"},"PeriodicalIF":4.4,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}