Common bacterial blight (CBB) is the most destructive bacterial disease affecting the production of common beans, and timely detection of CBB is crucial to limiting its spread. In this study, correlation analysis and the ReliefF algorithm were used to select vegetation indices (VIs) and texture features (TFs) that are sensitive to CBB. The CBB monitoring model based on support vector machine regression (SVR), random forest regression (RFR), and K-nearest neighbor regression (KNNR) was established using the selected the VIs, TFs, and their combinations. Then, the impact of the spatial resolution on the disease monitoring accuracy was evaluated. In addition, the early infection monitoring model was further optimised. The results show that in the early infection stage, when the spatial resolution was 0.07 m, the window size was 7 × 7, and the independent variable was a combination of VIs and TFs, the R2 of the monitoring model constructed via SVR was 0.72, which was 14.3% higher than that obtained for a 3 × 3 window (0.63). In the middle and late infection stages, the optimal spatial resolution was 0.1 m, and the monitoring model constructed using RFR and a combination of VIs and TFs performed the best, with R2 values of 0.81 and 0.88, respectively. The research results indicate that selecting an appropriate spatial resolution and window size can effectively improve the model's CBB monitoring ability and can provide a reference for accurate monitoring of large-scale CBB of common beans using airborne or spaceborne imaging spectroscopy technology.
{"title":"Evaluating the potential of airborne hyperspectral imagery in monitoring common beans with common bacterial blight at different infection stages","authors":"Binghan Jing, Jiachen Wang, Xin Zhang, Xiaoxiang Hou, Kunming Huang, Qianyu Wang, Yiwei Wang, Yaoxuan Jia, Meichen Feng, Wude Yang, Chao Wang","doi":"10.1016/j.biosystemseng.2025.02.002","DOIUrl":"10.1016/j.biosystemseng.2025.02.002","url":null,"abstract":"<div><div>Common bacterial blight (CBB) is the most destructive bacterial disease affecting the production of common beans, and timely detection of CBB is crucial to limiting its spread. In this study, correlation analysis and the ReliefF algorithm were used to select vegetation indices (VIs) and texture features (TFs) that are sensitive to CBB. The CBB monitoring model based on support vector machine regression (SVR), random forest regression (RFR), and K-nearest neighbor regression (KNNR) was established using the selected the VIs, TFs, and their combinations. Then, the impact of the spatial resolution on the disease monitoring accuracy was evaluated. In addition, the early infection monitoring model was further optimised. The results show that in the early infection stage, when the spatial resolution was 0.07 m, the window size was 7 × 7, and the independent variable was a combination of VIs and TFs, the R<sup>2</sup> of the monitoring model constructed via SVR was 0.72, which was 14.3% higher than that obtained for a 3 × 3 window (0.63). In the middle and late infection stages, the optimal spatial resolution was 0.1 m, and the monitoring model constructed using RFR and a combination of VIs and TFs performed the best, with R<sup>2</sup> values of 0.81 and 0.88, respectively. The research results indicate that selecting an appropriate spatial resolution and window size can effectively improve the model's CBB monitoring ability and can provide a reference for accurate monitoring of large-scale CBB of common beans using airborne or spaceborne imaging spectroscopy technology.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 145-158"},"PeriodicalIF":4.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428152","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}
Pub Date : 2025-02-17DOI: 10.1016/j.biosystemseng.2025.02.003
Zhulin Chen , Xuefeng Wang
Leaf nitrogen content (LNC) is crucial for the cultivation and health management of the endangered tree species Aquilaria sinensis. Although RGB imagery combined with machine learning has been effective for non-destructive LNC estimation, current models often neglect colour index texture features and face feature selection and interpretability challenges. This study introduces a framework to address these issues. Firstly, the canopy RGB imagery colour indices and the texture features of Aquilaria sinensis seedlings were collected as an initial feature set. Then, an improved hybrid feature selection algorithm combining SHapley Additive exPlanation (SHAP) with a dynamic ranking strategy was applied with a regression algorithm. This approach was tested using random forest (RF), support vector regression (SVR), and deep neural network (DNN) models. Optimal feature subsets were identified for each model, and performance comparisons determined the best LNC estimation model. Results show that texture features derived from colour indices significantly enhance LNC estimation accuracy. The dynamic SHAP ranking method outperformed RF and fixed SHAP rankings in feature selection. The optimal model, a DNN with an R2 of 0.946 and RMSE of 1.859 g kg−1 included two colour indices and five colour index texture features. While the normalised red colour index had the highest contribution, texture features contributed more overall to model accuracy. This method can be extended to other biophysical and biochemical parameter estimations.
{"title":"A novel framework for developing accurate and explainable leaf nitrogen content estimation model for aquilaria sinensis seedlings using canopy RGB imagery","authors":"Zhulin Chen , Xuefeng Wang","doi":"10.1016/j.biosystemseng.2025.02.003","DOIUrl":"10.1016/j.biosystemseng.2025.02.003","url":null,"abstract":"<div><div>Leaf nitrogen content (LNC) is crucial for the cultivation and health management of the endangered tree species <em>Aquilaria sinensis</em>. Although RGB imagery combined with machine learning has been effective for non-destructive LNC estimation, current models often neglect colour index texture features and face feature selection and interpretability challenges. This study introduces a framework to address these issues. Firstly, the canopy RGB imagery colour indices and the texture features of <em>Aquilaria sinensis</em> seedlings were collected as an initial feature set. Then, an improved hybrid feature selection algorithm combining SHapley Additive exPlanation (SHAP) with a dynamic ranking strategy was applied with a regression algorithm. This approach was tested using random forest (RF), support vector regression (SVR), and deep neural network (DNN) models. Optimal feature subsets were identified for each model, and performance comparisons determined the best LNC estimation model. Results show that texture features derived from colour indices significantly enhance LNC estimation accuracy. The dynamic SHAP ranking method outperformed RF and fixed SHAP rankings in feature selection. The optimal model, a DNN with an R<sup>2</sup> of 0.946 and RMSE of 1.859 g kg<sup>−1</sup> included two colour indices and five colour index texture features. While the normalised red colour index had the highest contribution, texture features contributed more overall to model accuracy. This method can be extended to other biophysical and biochemical parameter estimations.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 128-144"},"PeriodicalIF":4.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428153","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}
Pub Date : 2025-02-12DOI: 10.1016/j.biosystemseng.2025.01.015
Zixu Li , Zhi He , Wei Hao , Xu Wang , Xinting Ding , Yongjie Cui
This study proposes a flexible kiwifruit grasping strategy using impedance control to extend storage time, reduce picking costs, and minimise mechanical damage during harvesting. The main contribution of this strategy is integrating a fuzzy PID controller into the impedance-based kiwifruit picking system, which significantly reduces mechanical damage during the picking process. Compression tests were performed on kiwifruit to obtain viscoelastic parameters, and the Burgers model was used to describe the rheological behaviour to understand the deformation characteristics of kiwifruit under force. Subsequently, a force-based impedance control system was established using the relationship between contact force and gripper displacement to achieve precise control of the fruit-grasping process. Additionally, to enhance the performance of the impedance control system, an optimised solution was applied at the controller output. Simulation analysis shows that the optimised fuzzy PID control strategy reduced the system's settling time from 1.91 s to 1.08 s compared to traditional impedance control systems. Experimental results further validate that the new control strategy effectively reduces fruit damage, achieving flexible and high-quality kiwifruit picking. This approach also provides valuable technical references for the post-harvest automation of other soft fruits and vegetables.
{"title":"Kiwifruit harvesting impedance control and optimisation","authors":"Zixu Li , Zhi He , Wei Hao , Xu Wang , Xinting Ding , Yongjie Cui","doi":"10.1016/j.biosystemseng.2025.01.015","DOIUrl":"10.1016/j.biosystemseng.2025.01.015","url":null,"abstract":"<div><div>This study proposes a flexible kiwifruit grasping strategy using impedance control to extend storage time, reduce picking costs, and minimise mechanical damage during harvesting. The main contribution of this strategy is integrating a fuzzy PID controller into the impedance-based kiwifruit picking system, which significantly reduces mechanical damage during the picking process. Compression tests were performed on kiwifruit to obtain viscoelastic parameters, and the Burgers model was used to describe the rheological behaviour to understand the deformation characteristics of kiwifruit under force. Subsequently, a force-based impedance control system was established using the relationship between contact force and gripper displacement to achieve precise control of the fruit-grasping process. Additionally, to enhance the performance of the impedance control system, an optimised solution was applied at the controller output. Simulation analysis shows that the optimised fuzzy PID control strategy reduced the system's settling time from 1.91 s to 1.08 s compared to traditional impedance control systems. Experimental results further validate that the new control strategy effectively reduces fruit damage, achieving flexible and high-quality kiwifruit picking. This approach also provides valuable technical references for the post-harvest automation of other soft fruits and vegetables.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 101-116"},"PeriodicalIF":4.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143386942","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}
Pub Date : 2025-02-12DOI: 10.1016/j.biosystemseng.2025.01.006
Haijun Zhu , Hongling Jin , Yifan Hou , Shujie Wang , Yu Chen , Shuo Zhang , Jianhu Shen
Increasing market and labour costs arouse an urgent need to develop automatic mechanised tea picking equipment over mountainous tea plantation area. To address the poor operational stability of existing machines, this paper proposes a new design of an omnidirectional dynamic four-point levelling platform and the levelling control algorithms based on four-point levelling and central immobile levelling method. A prototype is built to test the static and dynamic levelling performance on a simulated mountainous terrain. Different from other conventional four-point levelling platforms, the rotary motion is added to this platform and the number of control units is reduced to reduce the difficulty of manoeuvring. These developments result in a damage-free feature when the rotation or inclination motion is beyond the normal manoeuvre range. The test results of the prototype showed that the inclination error of the platform was controlled at 1.1°–1.9° in 2–2.5 s during the static levelling test on a mountainous terrain with a slope of 15°. The dynamic levelling was tested on a mountainous terrain with varied slopes between 10° and 20° and the inclination error range of the platform was 1.7°–2.2°. The field tests confirmed that the levelling system can achieve omnidirectional dynamic levelling in the case of tea picking operations in mountainous areas with slopes below 20°.
{"title":"An omnidirectional dynamic levelling system with less tuning parameters for mountainous tea plantations","authors":"Haijun Zhu , Hongling Jin , Yifan Hou , Shujie Wang , Yu Chen , Shuo Zhang , Jianhu Shen","doi":"10.1016/j.biosystemseng.2025.01.006","DOIUrl":"10.1016/j.biosystemseng.2025.01.006","url":null,"abstract":"<div><div>Increasing market and labour costs arouse an urgent need to develop automatic mechanised tea picking equipment over mountainous tea plantation area. To address the poor operational stability of existing machines, this paper proposes a new design of an omnidirectional dynamic four-point levelling platform and the levelling control algorithms based on four-point levelling and central immobile levelling method. A prototype is built to test the static and dynamic levelling performance on a simulated mountainous terrain. Different from other conventional four-point levelling platforms, the rotary motion is added to this platform and the number of control units is reduced to reduce the difficulty of manoeuvring. These developments result in a damage-free feature when the rotation or inclination motion is beyond the normal manoeuvre range. The test results of the prototype showed that the inclination error of the platform was controlled at 1.1°–1.9° in 2–2.5 s during the static levelling test on a mountainous terrain with a slope of 15°. The dynamic levelling was tested on a mountainous terrain with varied slopes between 10° and 20° and the inclination error range of the platform was 1.7°–2.2°. The field tests confirmed that the levelling system can achieve omnidirectional dynamic levelling in the case of tea picking operations in mountainous areas with slopes below 20°.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 117-127"},"PeriodicalIF":4.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143386823","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}
The fine-grained management of farm animals using video analytics relies on long-term visual tracking of individual animals. When an individual is occluded or exits the camera's field of view, tracking can be lost. The problem of using visual features to re-assign identity after loss of tracking is known as re-identification. In the case of pigs, this problem is especially challenging due to the similar appearances of most individual animals within a pen.
To address this issue, an image-based pig re-identification method is developed that is invariant to pose, illumination, and camera viewpoint. This method allows pigs to be reidentified, enabling long-term monitoring. This approach uses a Vision-Transformer model (ViT) previously developed for person re-identification. The model was trained using specifically designed pig re-identification datasets with a diverse range of housing and management conditions. These datasets use overhead cameras, allowing an investigation of the effect of the detection approach on re-identification performance. Re-identification using a traditional axis-aligned pig detector was compared with a recently developed oriented pig detector that better matches the pig's pose when extracting the pig from the wider image. It was found that the use of an oriented detector led to improved performance. The proposed system achieved a peak rank-1 Cumulative Matching Characteristic (CMC) performance of 90.5%. Furthermore, it is shown that this model is capable of generalising across different farms, achieving an average rank-1 CMC 81.8% in the cross-farm setting. Finally, the proposed re-identification features can be incorporated into an existing multi-object tracking system to improve its performance at reacquiring pig identities when tracking is lost. Overall, this work demonstrates the potential of using visual re-identification features of pigs to enable individual-level animal management.
{"title":"Re-identification for long-term tracking and management of health and welfare challenges in pigs","authors":"Anicetus Odo , Niall McLaughlin , Ilias Kyriazakis","doi":"10.1016/j.biosystemseng.2025.02.001","DOIUrl":"10.1016/j.biosystemseng.2025.02.001","url":null,"abstract":"<div><div>The fine-grained management of farm animals using video analytics relies on long-term visual tracking of individual animals. When an individual is occluded or exits the camera's field of view, tracking can be lost. The problem of using visual features to re-assign identity after loss of tracking is known as re-identification. In the case of pigs, this problem is especially challenging due to the similar appearances of most individual animals within a pen.</div><div>To address this issue, an image-based pig re-identification method is developed that is invariant to pose, illumination, and camera viewpoint. This method allows pigs to be reidentified, enabling long-term monitoring. This approach uses a Vision-Transformer model (ViT) previously developed for person re-identification. The model was trained using specifically designed pig re-identification datasets with a diverse range of housing and management conditions. These datasets use overhead cameras, allowing an investigation of the effect of the detection approach on re-identification performance. Re-identification using a traditional axis-aligned pig detector was compared with a recently developed oriented pig detector that better matches the pig's pose when extracting the pig from the wider image. It was found that the use of an oriented detector led to improved performance. The proposed system achieved a peak rank-1 Cumulative Matching Characteristic (CMC) performance of 90.5%. Furthermore, it is shown that this model is capable of generalising across different farms, achieving an average rank-1 CMC 81.8% in the cross-farm setting. Finally, the proposed re-identification features can be incorporated into an existing multi-object tracking system to improve its performance at reacquiring pig identities when tracking is lost. Overall, this work demonstrates the potential of using visual re-identification features of pigs to enable individual-level animal management.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 89-100"},"PeriodicalIF":4.4,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378492","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}
Pub Date : 2025-02-09DOI: 10.1016/j.biosystemseng.2025.01.016
Xiaofen Ge , Sheng Wu , Weiliang Wen , Fei Shen , Pengliang Xiao , Xianju Lu , Haishen Liu , Minggang Zhang , Xinyu Guo
Lettuce is one of the major raw vegetables in the world, with diverse species and large differences in morphological structures. Achieving automated, high-throughput acquisition and intelligent analysis of 3D lettuce phenotypes using advanced phenotyping techniques and equipment is of great significance. Based on the high-throughput phenotyping platform MVS-PhenoV2 installed in a plant imaging room, this study constructed a method for automated analysis of 3D phenotypes of lettuce around the needs of lettuce DUS (distinctiveness, uniformity, and stability) testing and feature digitisation. Aiming at the characteristics of lettuce leaves which are mostly curved, the point cloud segmentation model SoftGroup was improved, which can realise lettuce single plant segmentation and leaf segmentation with high accuracy. Additionally based on lettuce 3D point clouds, plant orientation correction algorithm, leaf hole completion algorithm, leaf vein extraction algorithm, and leaf margin extraction algorithm were proposed. Finally, a pipelined automated analysis software tool LettuceP3D was developed for automated analysis of lettuce 3D phenotypes, which can automatically analyse 16 phenotypic indicators related to lettuce plant (e.g. plant height, plant width, and compactness) and leaf (e.g. leaf length, leaf margin perimeter, and leaf margin undulation) phenotypic characteristics. The study was validated on seven types of lettuce: Butterhead, Crisphead, Looseleaf, Oakleaf, Romaines, Stem, and Wild Relatives. Results show that the mIoU for plant and pot semantic segmentation reaches 97.2%, and the AP for leaf instance segmentation reaches 86.7%. Through comparison with measured values, the average of the algorithm exceeds 0.95. The software operates without manual interaction, processing single plant data in approximately 2s, which demonstrates a high processing efficiency. This phenotype analysis method proposed in this study is applicable for quantifying the morphological characteristics of lettuce in seven types, providing quantitative indicator data support for lettuce DUS testing, variety identification, and multi-omics studies.
{"title":"LettuceP3D: A tool for analysing 3D phenotypes of individual lettuce plants","authors":"Xiaofen Ge , Sheng Wu , Weiliang Wen , Fei Shen , Pengliang Xiao , Xianju Lu , Haishen Liu , Minggang Zhang , Xinyu Guo","doi":"10.1016/j.biosystemseng.2025.01.016","DOIUrl":"10.1016/j.biosystemseng.2025.01.016","url":null,"abstract":"<div><div>Lettuce is one of the major raw vegetables in the world, with diverse species and large differences in morphological structures. Achieving automated, high-throughput acquisition and intelligent analysis of 3D lettuce phenotypes using advanced phenotyping techniques and equipment is of great significance. Based on the high-throughput phenotyping platform MVS-PhenoV2 installed in a plant imaging room, this study constructed a method for automated analysis of 3D phenotypes of lettuce around the needs of lettuce DUS (distinctiveness, uniformity, and stability) testing and feature digitisation. Aiming at the characteristics of lettuce leaves which are mostly curved, the point cloud segmentation model SoftGroup was improved, which can realise lettuce single plant segmentation and leaf segmentation with high accuracy. Additionally based on lettuce 3D point clouds, plant orientation correction algorithm, leaf hole completion algorithm, leaf vein extraction algorithm, and leaf margin extraction algorithm were proposed. Finally, a pipelined automated analysis software tool LettuceP3D was developed for automated analysis of lettuce 3D phenotypes, which can automatically analyse 16 phenotypic indicators related to lettuce plant (e.g. plant height, plant width, and compactness) and leaf (e.g. leaf length, leaf margin perimeter, and leaf margin undulation) phenotypic characteristics. The study was validated on seven types of lettuce: Butterhead, Crisphead, Looseleaf, Oakleaf, Romaines, Stem, and Wild Relatives. Results show that the mIoU for plant and pot semantic segmentation reaches 97.2%, and the AP for leaf instance segmentation reaches 86.7%. Through comparison with measured values, the average <span><math><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow></math></span> of the algorithm exceeds 0.95. The software operates without manual interaction, processing single plant data in approximately 2s, which demonstrates a high processing efficiency. This phenotype analysis method proposed in this study is applicable for quantifying the morphological characteristics of lettuce in seven types, providing quantitative indicator data support for lettuce DUS testing, variety identification, and multi-omics studies.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 73-88"},"PeriodicalIF":4.4,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372171","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}
Pub Date : 2025-02-07DOI: 10.1016/j.biosystemseng.2025.01.018
Jun Fu , Meng Zhang , Chao Cheng , Haiming Zhao , Luquan Ren
Cleaning is a critical procedure in rice combine harvesting. Liquid films on rice stalks significantly enhance adhesion, causing sieve hole blockages in vibrating screens and production issues, reducing cleaning efficiency and increasing grain loss. In this study, a wet sticky rice stalk collision adhesion sensor was designed using polyvinylidene difluoride piezoelectric film (PVDF) as the sensitive element. A drop collision test device, combined with high-speed cameras, recorded and analysed motion patterns of rice stalks undergoing adhesion/detachment. It was shown that the liquid film produced capillary liquid bridges during collisions, and the adhesive effect of these capillary liquid bridges regulated the adhesion/detachment condition of the rice stalks. The adhesion vibration of rice stalk-PVDF piezoelectric film was modelled. The results indicated that when the drop height was 100 mm and the liquid film volume increased from 0 μL to 2.0 μL, the maximum impact voltage decreased from 1.80 V to 1.28 V, and the decay time reduced from 18.01 μs to 7.08 μs. Both the maximum impact voltage and the decay time were critical characteristic values for evaluating the collision adhesion state. The additional m2-k2-c2 vibration system acted as a power absorber, showing a significant difference in the impact voltage signal of the adhesion sensor caused by the presence or absence of a liquid film on the surface of the rice stalk. This disparity provides a basis for determining the presence of the liquid film on the rice stalk surface, helping to solve adhesion and blockage issues in rice harvesting and cleaning operations.
{"title":"Mechanism study of the effect of a surface liquid film on the collision adhesion behaviour of rice stalks","authors":"Jun Fu , Meng Zhang , Chao Cheng , Haiming Zhao , Luquan Ren","doi":"10.1016/j.biosystemseng.2025.01.018","DOIUrl":"10.1016/j.biosystemseng.2025.01.018","url":null,"abstract":"<div><div>Cleaning is a critical procedure in rice combine harvesting. Liquid films on rice stalks significantly enhance adhesion, causing sieve hole blockages in vibrating screens and production issues, reducing cleaning efficiency and increasing grain loss. In this study, a wet sticky rice stalk collision adhesion sensor was designed using polyvinylidene difluoride piezoelectric film (PVDF) as the sensitive element. A drop collision test device, combined with high-speed cameras, recorded and analysed motion patterns of rice stalks undergoing adhesion/detachment. It was shown that the liquid film produced capillary liquid bridges during collisions, and the adhesive effect of these capillary liquid bridges regulated the adhesion/detachment condition of the rice stalks. The adhesion vibration of rice stalk-PVDF piezoelectric film was modelled. The results indicated that when the drop height was 100 mm and the liquid film volume increased from 0 μL to 2.0 μL, the maximum impact voltage decreased from 1.80 V to 1.28 V, and the decay time reduced from 18.01 μs to 7.08 μs. Both the maximum impact voltage and the decay time were critical characteristic values for evaluating the collision adhesion state. The additional <em>m</em><sub>2</sub>-<em>k</em><sub>2</sub>-<em>c</em><sub>2</sub> vibration system acted as a power absorber, showing a significant difference in the impact voltage signal of the adhesion sensor caused by the presence or absence of a liquid film on the surface of the rice stalk. This disparity provides a basis for determining the presence of the liquid film on the rice stalk surface, helping to solve adhesion and blockage issues in rice harvesting and cleaning operations.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 61-72"},"PeriodicalIF":4.4,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143241287","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}
Pub Date : 2025-02-07DOI: 10.1016/j.biosystemseng.2025.01.017
Youngjoon Jeong , Sangik Lee , Jong-hyuk Lee , Won Choi
To interpret physical phenomena, traditional mesh-based methods, such as finite element method, have proven effective for engineering problems. However, as system complexity increases, whether due to larger scales, finer resolutions, or intricate geometries, these methods face significant limitations in term of computational cost and time. Complex problems, particularly those involving irregular boundaries or nonlinear behaviour, require finer meshes and greater computational power, making real-time analysis difficult. This challenge is especially relevant in agricultural systems, which are subject to high uncertainty and constantly changing environmental conditions. In this study, we proposed a method referred to as piecewise physics-informed neural networks (PINNs) to solve non-smooth problems in structural mechanics using neural networks by decomposing the computational domain. To quantitatively evaluate the performance of this method, three representative structural mechanics problems with non-smooth characteristics are employed. Results demonstrated that the piecewise PINNs provided more accurate solutions compared to conventional PINNs on these benchmark problems. Additionally, we developed a surrogate model for the non-smooth problems using piecewise PINNs without any labelled data and compared it with a model trained using deep neural networks. The proposed model outperformed the deep neural network model in cases of plane-stress problem. The results also showed that the surrogate model trained with piecewise PINNs exhibited an advantage in terms of execution time over the finite element analysis software.
{"title":"Piecewise physics-informed neural networks for surrogate modelling of non-smooth system in elasticity problems using domain decomposition","authors":"Youngjoon Jeong , Sangik Lee , Jong-hyuk Lee , Won Choi","doi":"10.1016/j.biosystemseng.2025.01.017","DOIUrl":"10.1016/j.biosystemseng.2025.01.017","url":null,"abstract":"<div><div>To interpret physical phenomena, traditional mesh-based methods, such as finite element method, have proven effective for engineering problems. However, as system complexity increases, whether due to larger scales, finer resolutions, or intricate geometries, these methods face significant limitations in term of computational cost and time. Complex problems, particularly those involving irregular boundaries or nonlinear behaviour, require finer meshes and greater computational power, making real-time analysis difficult. This challenge is especially relevant in agricultural systems, which are subject to high uncertainty and constantly changing environmental conditions. In this study, we proposed a method referred to as piecewise physics-informed neural networks (PINNs) to solve non-smooth problems in structural mechanics using neural networks by decomposing the computational domain. To quantitatively evaluate the performance of this method, three representative structural mechanics problems with non-smooth characteristics are employed. Results demonstrated that the piecewise PINNs provided more accurate solutions compared to conventional PINNs on these benchmark problems. Additionally, we developed a surrogate model for the non-smooth problems using piecewise PINNs without any labelled data and compared it with a model trained using deep neural networks. The proposed model outperformed the deep neural network model in cases of plane-stress problem. The results also showed that the surrogate model trained with piecewise PINNs exhibited an advantage in terms of execution time over the finite element analysis software.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 48-60"},"PeriodicalIF":4.4,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143241286","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}
Pub Date : 2025-02-05DOI: 10.1016/j.biosystemseng.2025.01.010
Junyu Sun , Daxi Wang , Xutong Xiao , Qiang Yu , Xuanrong Xu , Yanfei Liu , Zhande Liu , Fuxi Shi
Successful delivery and a sufficient quantity of pollen to stigmas are critical factors in improving fruit shape and weight, increasing pollination accuracy and decreasing pollen consumption, which have practical and financial benefits in large-scale agriculture. First, the adhesion structure of pollen-on-stigma was observed by cryo-scanning electron microscopy (SEM), and adhesion force was tested with atomic force microscopy (AFM). It was found that there is a natural adhesive adaptability between pollen and stigma. Then, an optimal design approach for pollinator was proposed to maximize pollen deposition fraction in targeting pollination. Computational fluid dynamics (CFD) was adopted to simulate the impact of airflow on pollen deposition; and the discrete phase model (DPM) was employed to track the particles’ trajectory and distribution on target area. The dependability of simulation was verified by experimental results obtained under identical parameters. Three airflow delivery velocities were selected with three protrusion heights, three feeding positions, and three contraction conical angles on the deposition fraction of pollen were investigated. The results indicated that the contraction conical angle of pollinator pipe has the greatest impact on targeted delivery of pollen, the best pollen distribution and the maximum deposition fraction occurring at 10°. An airflow delivery velocity of 3 m s−1 is optimal for pollination operations. Once the optimal contraction conical angle and airflow delivery velocity are determined, the protrusion height of 7 mm combined with the feeding position of 15 mm can offer better deposition efficiency. Computational and experimental results are helpful for further pollination design.
{"title":"Study of pollen deposition performance of an airflow-assisted targeted pollinating device for kiwi fruit flower","authors":"Junyu Sun , Daxi Wang , Xutong Xiao , Qiang Yu , Xuanrong Xu , Yanfei Liu , Zhande Liu , Fuxi Shi","doi":"10.1016/j.biosystemseng.2025.01.010","DOIUrl":"10.1016/j.biosystemseng.2025.01.010","url":null,"abstract":"<div><div>Successful delivery and a sufficient quantity of pollen to stigmas are critical factors in improving fruit shape and weight, increasing pollination accuracy and decreasing pollen consumption, which have practical and financial benefits in large-scale agriculture. First, the adhesion structure of pollen-on-stigma was observed by cryo-scanning electron microscopy (SEM), and adhesion force was tested with atomic force microscopy (AFM). It was found that there is a natural adhesive adaptability between pollen and stigma. Then, an optimal design approach for pollinator was proposed to maximize pollen deposition fraction in targeting pollination. Computational fluid dynamics (CFD) was adopted to simulate the impact of airflow on pollen deposition; and the discrete phase model (DPM) was employed to track the particles’ trajectory and distribution on target area. The dependability of simulation was verified by experimental results obtained under identical parameters. Three airflow delivery velocities were selected with three protrusion heights, three feeding positions, and three contraction conical angles on the deposition fraction of pollen were investigated. The results indicated that the contraction conical angle of pollinator pipe has the greatest impact on targeted delivery of pollen, the best pollen distribution and the maximum deposition fraction occurring at 10°. An airflow delivery velocity of 3 m s<sup>−1</sup> is optimal for pollination operations. Once the optimal contraction conical angle and airflow delivery velocity are determined, the protrusion height of 7 mm combined with the feeding position of 15 mm can offer better deposition efficiency. Computational and experimental results are helpful for further pollination design.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 31-47"},"PeriodicalIF":4.4,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143241285","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}
Pub Date : 2025-02-03DOI: 10.1016/j.biosystemseng.2025.01.013
Suhaiza Hanim Hanipah , Nur Farah Najia C. Hassan , Ahmad Tarmezee Talib , Mohd Afandi P Mohammed , Minato Wakisaka , Zalizawati Abdullah
Kenaf fibres are gaining traction as a promising eco-friendly material due to their renewability and impressive mechanical strength. This study explored kenaf's potential to replace traditional materials by investigating its microstructure using advanced techniques like Scanning Electron Microscopy, X-Ray Microtomography and Atomic Force Microscopy. These analyses were complimented with tensile tests to investigate the complex mechanical behaviour of kenaf fibres. The experimental results revealed the microstructure of kenaf fibres, showing no significant differences over the fibre width and longitudinal direction. Tensile tests results from tensile-cyclic and tensile-relaxation modes, suggest elasto-viscoelastic behaviour of the fibres. A finite element model to virtually represent kenaf fibres was developed using the experimental information. Model simulations under tensile, compression and shear deformations suggest that damage was more pronounced under shear and compression conditions compared to tensile mode.
{"title":"Virtual model of kenaf bast fibres based on solid mechanics and finite element study","authors":"Suhaiza Hanim Hanipah , Nur Farah Najia C. Hassan , Ahmad Tarmezee Talib , Mohd Afandi P Mohammed , Minato Wakisaka , Zalizawati Abdullah","doi":"10.1016/j.biosystemseng.2025.01.013","DOIUrl":"10.1016/j.biosystemseng.2025.01.013","url":null,"abstract":"<div><div>Kenaf fibres are gaining traction as a promising eco-friendly material due to their renewability and impressive mechanical strength. This study explored kenaf's potential to replace traditional materials by investigating its microstructure using advanced techniques like Scanning Electron Microscopy, X-Ray Microtomography and Atomic Force Microscopy. These analyses were complimented with tensile tests to investigate the complex mechanical behaviour of kenaf fibres. The experimental results revealed the microstructure of kenaf fibres, showing no significant differences over the fibre width and longitudinal direction. Tensile tests results from tensile-cyclic and tensile-relaxation modes, suggest elasto-viscoelastic behaviour of the fibres. A finite element model to virtually represent kenaf fibres was developed using the experimental information. Model simulations under tensile, compression and shear deformations suggest that damage was more pronounced under shear and compression conditions compared to tensile mode.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"251 ","pages":"Pages 20-30"},"PeriodicalIF":4.4,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158208","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号