Biosystems Engineering最新文献_第3页

Establishment and correction of temperature-insensitive prediction model for soluble solid content of apples based on external parameter orthogonal algorithm 基于外部参数正交算法的苹果可溶性固形物含量温度不敏感预测模型的建立与校正

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-24 DOI: 10.1016/j.biosystemseng.2025.104367

Chang Zhou, Runze Wang, Zelin Ji, Xiyin Wang, Xingshu Li, Xiufang Xiong

Temperature changes will cause fluctuations in the visible near-infrared spectra of apples, which will affect the models’ robustness and accuracy in predicting the soluble solids content (SSC) of apples. By collecting the spectra and SSC data of apples at different temperatures, this study established common single temperature models, the mixed temperature model, and the models based on the external parameter orthogonalisation (EPO) algorithm. The results indicated that EPO algorithm can effectively eliminate the influence of temperature on the spectra, and does not affect the results of the characteristic wavelengths selection. Most of the selected characteristic wavelengths were distributed in the wavelength range of 700–900 nm. The models based on the EPO algorithm were employed to predict the samples at different temperatures. The concordance correlation coefficient (CCC) ranged between 0.865 and 0.882, and the ratio of performance of deviation (RPD) was in the range of 2.045–2.191. The models based on EPO algorithm achieved high prediction accuracy and were insensitive to temperature changes. The model established by using the spectral data in the 700–900 nm band processed by EPO algorithm had high prediction accuracy and low complexity. Finally, 60 samples were used to verify the performance of the model. It was found that there was no significant difference between the predicted values and the measured values (CCC = 0.892, RMSEP = 0.543 %, RPD = 2.173). The results of the study have practical implications for improving the economic efficiency of the apple industry, including the subsequent development of portable field testing equipment.

温度变化会引起苹果可见近红外光谱的波动，影响模型预测苹果可溶性固形物含量（SSC）的稳健性和准确性。本研究通过收集苹果在不同温度下的光谱和SSC数据，建立了常见的单一温度模型、混合温度模型和基于外部参数正交化（EPO）算法的模型。结果表明，EPO算法能有效消除温度对光谱的影响，且不影响特征波长选择的结果。选取的特征波长大部分分布在700 ~ 900 nm的波长范围内。采用基于EPO算法的模型对不同温度下的样品进行预测。一致性相关系数（CCC）在0.865 ~ 0.882之间，偏离绩效比（RPD）在2.045 ~ 2.191之间。基于EPO算法的模型预测精度高，且对温度变化不敏感。利用EPO算法处理的700 ~ 900 nm波段光谱数据建立的模型预测精度高，复杂度低。最后，用60个样本来验证模型的性能。预测值与实测值无显著性差异（CCC = 0.892, RMSEP = 0.543 %, RPD = 2.173）。研究结果对提高苹果产业的经济效益具有实际意义，包括后续便携式田间测试设备的开发。

{"title":"Establishment and correction of temperature-insensitive prediction model for soluble solid content of apples based on external parameter orthogonal algorithm","authors":"Chang Zhou, Runze Wang, Zelin Ji, Xiyin Wang, Xingshu Li, Xiufang Xiong","doi":"10.1016/j.biosystemseng.2025.104367","DOIUrl":"10.1016/j.biosystemseng.2025.104367","url":null,"abstract":"<div><div>Temperature changes will cause fluctuations in the visible near-infrared spectra of apples, which will affect the models’ robustness and accuracy in predicting the soluble solids content (SSC) of apples. By collecting the spectra and SSC data of apples at different temperatures, this study established common single temperature models, the mixed temperature model, and the models based on the external parameter orthogonalisation (EPO) algorithm. The results indicated that EPO algorithm can effectively eliminate the influence of temperature on the spectra, and does not affect the results of the characteristic wavelengths selection. Most of the selected characteristic wavelengths were distributed in the wavelength range of 700–900 nm. The models based on the EPO algorithm were employed to predict the samples at different temperatures. The concordance correlation coefficient (CCC) ranged between 0.865 and 0.882, and the ratio of performance of deviation (RPD) was in the range of 2.045–2.191. The models based on EPO algorithm achieved high prediction accuracy and were insensitive to temperature changes. The model established by using the spectral data in the 700–900 nm band processed by EPO algorithm had high prediction accuracy and low complexity. Finally, 60 samples were used to verify the performance of the model. It was found that there was no significant difference between the predicted values and the measured values (CCC = 0.892, RMSEP = 0.543 %, RPD = 2.173). The results of the study have practical implications for improving the economic efficiency of the apple industry, including the subsequent development of portable field testing equipment.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104367"},"PeriodicalIF":5.3,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837486","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}

引用次数: 0

Corrigendum to “Correlation between rheological properties and maturity of passion fruit based on machine vision” [Biosystems Engineering 250 (2025) 236–249/ 008] “基于机器视觉的百香果流变特性和成熟度之间的相关性”的勘误表[生物系统工程250 (2025)236-249 / 008]

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-24 DOI: 10.1016/j.biosystemseng.2025.104371

Fan Lin, Dengjie Chen, Caihua Lu, Jincheng He

引用次数: 0

An enhanced cow-teat-detection model for automatic teat-cup-attachment devices 一种用于自动奶杯附着装置的增强奶牛奶头检测模型

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-23 DOI: 10.1016/j.biosystemseng.2025.104374

Mengjie Li , Juan Wang , Na Li , Yaju Liu , Xue Cheng , Xinpei Fu , Sirui Li

The production mode in which a milking device is manually set on the teats of dairy cows is inefficient and labour-intensive. Automatic teat-cup-attachment technology can reduce the labour-intensive and increase milking efficient. In order to automatically attach the teat cup more accurately and quickly, an enhanced cow-teat-detection model was proposed, which was utilized in an automatic teat-cup-attachment device. Based on the YOLOv7, the Wise-IoU loss function was introduced, which enhanced the fitting ability and convergence speed of the bounding box regression. To optimize the captures pertaining to the features of cow teats in a complex background and to reduce the loss of the features from a small target, a fourth feature scale was constructed in the Neck network. To make the model focus more on the detailed information related to the target and enhance the target-recognition accuracy, a Coordinate Attention (CA) mechanism was added to the Backbone network and to the Neck network. The comparison experiment and ablation experiment were performed on the self-made dataset. The results revealed that the mAP_0.5, Precision, and Recall of the improved YOLOv7 were 98.18 %, 97.50 %, and 96.15 %, respectively, which were 1.96, 2.07, and 2.67 percentage points higher than those of the baseline YOLOv7 model, respectively. The detection performance was significantly enhanced. This study provides the technical support for the milking device to achieve accurate positioning and rapid automatic teat-cup-attachment.

在奶牛的乳头上手动设置挤奶设备的生产模式效率低下，劳动密集型。自动贴杯技术，减少劳动强度，提高挤奶效率。为了更准确、快速地自动贴贴奶杯，提出了一种增强的奶牛奶头检测模型，并将其应用于自动贴贴奶杯装置中。在YOLOv7的基础上，引入Wise-IoU损失函数，增强了边界盒回归的拟合能力和收敛速度。为了优化复杂背景下奶牛乳头特征的捕获，减少小目标特征的丢失，在颈部网络中构建了第四个特征尺度。为了使模型更加关注与目标相关的详细信息，提高目标识别的精度，在主干网络和颈部网络中加入了坐标注意（CA）机制。在自制数据集上进行了对比实验和烧蚀实验。结果表明，改进后的YOLOv7模型的mAP0.5、Precision和Recall分别为98.18%、97.50%和96.15%，分别比基线YOLOv7模型提高了1.96、2.07和2.67个百分点。检测性能显著提高。本研究为挤奶装置实现准确定位和快速自动贴杯提供了技术支持。

{"title":"An enhanced cow-teat-detection model for automatic teat-cup-attachment devices","authors":"Mengjie Li , Juan Wang , Na Li , Yaju Liu , Xue Cheng , Xinpei Fu , Sirui Li","doi":"10.1016/j.biosystemseng.2025.104374","DOIUrl":"10.1016/j.biosystemseng.2025.104374","url":null,"abstract":"<div><div>The production mode in which a milking device is manually set on the teats of dairy cows is inefficient and labour-intensive. Automatic teat-cup-attachment technology can reduce the labour-intensive and increase milking efficient. In order to automatically attach the teat cup more accurately and quickly, an enhanced cow-teat-detection model was proposed, which was utilized in an automatic teat-cup-attachment device. Based on the YOLOv7, the Wise-IoU loss function was introduced, which enhanced the fitting ability and convergence speed of the bounding box regression. To optimize the captures pertaining to the features of cow teats in a complex background and to reduce the loss of the features from a small target, a fourth feature scale was constructed in the Neck network. To make the model focus more on the detailed information related to the target and enhance the target-recognition accuracy, a Coordinate Attention (CA) mechanism was added to the Backbone network and to the Neck network. The comparison experiment and ablation experiment were performed on the self-made dataset. The results revealed that the mAP<sub>0.5</sub>, Precision, and Recall of the improved YOLOv7 were 98.18 %, 97.50 %, and 96.15 %, respectively, which were 1.96, 2.07, and 2.67 percentage points higher than those of the baseline YOLOv7 model, respectively. The detection performance was significantly enhanced. This study provides the technical support for the milking device to achieve accurate positioning and rapid automatic teat-cup-attachment.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104374"},"PeriodicalIF":5.3,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837519","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}

引用次数: 0

Coefficient of restitution considerations in the discrete element method for agricultural materials: A review 农业材料离散元法中恢复系数的考虑：综述

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-23 DOI: 10.1016/j.biosystemseng.2025.104364

Zhengpu Chen , Carl Wassgren , R.P.Kingsly Ambrose , Yuefeng Du , Zhenghe Song , Xiaoyu Li

The Discrete Element Method (DEM) has gained increasing popularity for modelling agricultural production machinery and processes. As a key DEM input parameter, the coefficient of restitution (COR) quantifies energy dissipation during particle contacts, and its accurate determination is critical for predicting realistic particle dynamics, flow patterns, and consequently the performance of agricultural machinery. Despite the importance of the COR, a comprehensive review on its determination and usage in agricultural DEM applications is currently lacking. To address this gap, this study reviewed recent literature, summarizing and evaluating COR definitions, determination approaches, influencing factors, and effects on simulation outcomes. Among different COR definitions, the velocity-based kinematic COR remains the most widely implemented in DEM software due to its computational efficiency and ease of measurement. Current measurement approaches, such as drop tests and pendulum impact tests, often require high-speed cameras, highlighting a need for simpler, more robust methods for rapid COR determination. As the COR is influenced by various factors including impact speed, impact angle, and material properties, further investigation into the value of implementing a parameter-dependent COR and its efficient incorporation into DEM simulations is needed. Research findings from previous DEM simulation studies indicate that the COR significantly influences measurements in dilute flow systems, while exerting less influence on the macroscopic flow behaviour of dense flow systems. Comprehensive sensitivity analyses of the COR in DEM simulations of agricultural production systems are lacking, limiting our understanding of its effects on simulation predictions. In summary, this study summarizes current knowledge, identifies best practices, provides guidelines for COR usage in DEM simulations, and outlines future research directions for the COR in DEM within agricultural contexts.

离散元法（DEM）在农业生产机械和过程建模方面越来越受欢迎。作为DEM的一个关键输入参数，恢复系数（COR）量化了颗粒接触过程中的能量耗散，其准确确定对于预测真实的颗粒动力学、流动模式以及农业机械的性能至关重要。尽管COR很重要，但目前缺乏对其在农业DEM应用中的确定和使用的全面审查。为了解决这一差距，本研究回顾了最近的文献，总结和评估了COR的定义、确定方法、影响因素以及对模拟结果的影响。在不同的COR定义中，基于速度的运动学COR由于其计算效率和易于测量而在DEM软件中得到了最广泛的应用。目前的测量方法，如跌落试验和摆锤冲击试验，通常需要高速摄像机，这突出表明需要更简单、更可靠的方法来快速确定COR。由于冲击速度、冲击角度和材料性能等多种因素影响着冲击响应响应，因此需要进一步研究实现参数依赖的冲击响应响应的价值，并将其有效地结合到DEM仿真中。以往的DEM模拟研究结果表明，在稀流体系中，COR对测量结果有显著影响，而对致密流体系的宏观流动行为影响较小。缺乏对农业生产系统DEM模拟中COR的综合敏感性分析，限制了我们对其对模拟预测影响的理解。总之，本研究总结了当前的知识，确定了最佳实践，为DEM模拟中COR的使用提供了指导方针，并概述了农业背景下DEM中COR的未来研究方向。

{"title":"Coefficient of restitution considerations in the discrete element method for agricultural materials: A review","authors":"Zhengpu Chen , Carl Wassgren , R.P.Kingsly Ambrose , Yuefeng Du , Zhenghe Song , Xiaoyu Li","doi":"10.1016/j.biosystemseng.2025.104364","DOIUrl":"10.1016/j.biosystemseng.2025.104364","url":null,"abstract":"<div><div>The Discrete Element Method (DEM) has gained increasing popularity for modelling agricultural production machinery and processes. As a key DEM input parameter, the coefficient of restitution (COR) quantifies energy dissipation during particle contacts, and its accurate determination is critical for predicting realistic particle dynamics, flow patterns, and consequently the performance of agricultural machinery. Despite the importance of the COR, a comprehensive review on its determination and usage in agricultural DEM applications is currently lacking. To address this gap, this study reviewed recent literature, summarizing and evaluating COR definitions, determination approaches, influencing factors, and effects on simulation outcomes. Among different COR definitions, the velocity-based kinematic COR remains the most widely implemented in DEM software due to its computational efficiency and ease of measurement. Current measurement approaches, such as drop tests and pendulum impact tests, often require high-speed cameras, highlighting a need for simpler, more robust methods for rapid COR determination. As the COR is influenced by various factors including impact speed, impact angle, and material properties, further investigation into the value of implementing a parameter-dependent COR and its efficient incorporation into DEM simulations is needed. Research findings from previous DEM simulation studies indicate that the COR significantly influences measurements in dilute flow systems, while exerting less influence on the macroscopic flow behaviour of dense flow systems. Comprehensive sensitivity analyses of the COR in DEM simulations of agricultural production systems are lacking, limiting our understanding of its effects on simulation predictions. In summary, this study summarizes current knowledge, identifies best practices, provides guidelines for COR usage in DEM simulations, and outlines future research directions for the COR in DEM within agricultural contexts.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104364"},"PeriodicalIF":5.3,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837518","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}

引用次数: 0

Discrimination of autochthonous pig breeds from meat and fat samples by FT-NIR spectra FT-NIR光谱对地方猪品种肉和脂肪样品的鉴别

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-23 DOI: 10.1016/j.biosystemseng.2025.104366

S. Parrini , C. Dadousis , F. Sirtori , M.C. Fabbri , M. Čandek-Potokar , J.M. Garcia-Casco , B. Lebret , R. Nieto , C. Aquilani , R. Bozzi

The combination of Fourier transform near-infrared spectroscopy (FT-NIRS) of meat and fat samples and principal component discriminant analysis (DAPC) has been proposed as a tool for discriminating the local production of autochthonous pig breeds. Spectral samples (n = 272) belonging to 11 local European pig breeds, Longissimus muscle, and subcutaneous fat (both intact and minced) are collected. Classification accuracy based on DAPC was applied on FT-NIRS to predict breed of origin in i) semi-external cross-validation, splitting the data into training (80 %) and testing (20 %) sets; ii) external validation, in which one breed at a time was excluded from model training and classified in one of the remaining breeds. The effect of varying sample sizes from 50 % to 100 % of the data was assessed. Almost all breeds' spectra variability was summarised into two principal components for tissue and sample preparation. In cross-validation, intact fat yielded higher classification accuracies than intact meat, with less pronounced differences in minced samples. Success assignment rates of ∼81–83 % were obtained for two breeds in intact meat samples and were higher than 83 % for five breeds in fat samples. For minced samples, correct assignments between 80 % and 100 % were possible for five breeds, both in meat and fat samples. Sample size marginally affected the results. External validation confirmed similarity among some breeds, with greater accuracy for fat samples. The assignments success provides encouraging results for discriminating local pig production, mainly based on fat, using a rapid, eco-friendly FT-NIRS method, which could serve as tool for quality assurance.

本文提出了将肉和脂肪样品的傅里叶变换近红外光谱（FT-NIRS）与主成分判别分析（DAPC）相结合，作为判别地方猪品种的工具。收集了11个欧洲当地猪品种的光谱样本（n = 272）、最长肌和皮下脂肪（完整的和切碎的）。在半外部交叉验证中，将基于DAPC的分类精度应用于FT-NIRS预测品种来源，将数据分为训练集（80%）和测试集（20%）；Ii)外部验证，即每次将一个品种排除在模型训练之外，并将其分类到剩余的品种中。评估了从50%到100%不同样本量对数据的影响。几乎所有品种的光谱变异性都归结为组织和样品制备的两个主要成分。在交叉验证中，完整的脂肪比完整的肉产生更高的分类准确性，在切碎的样品中差异不太明显。在两个品种的完整肉类样本中获得了~ 81 - 83%的成功率，在5个品种的脂肪样本中获得了高于83%的成功率。对于切碎的样本，5个品种的肉类和脂肪样本的正确分配在80%到100%之间是可能的。样本量对结果影响不大。外部验证证实了某些品种之间的相似性，脂肪样本的准确性更高。作业的成功为使用快速、环保的FT-NIRS方法区分当地生猪生产提供了令人鼓舞的结果，主要基于脂肪，该方法可以作为质量保证的工具。

{"title":"Discrimination of autochthonous pig breeds from meat and fat samples by FT-NIR spectra","authors":"S. Parrini , C. Dadousis , F. Sirtori , M.C. Fabbri , M. Čandek-Potokar , J.M. Garcia-Casco , B. Lebret , R. Nieto , C. Aquilani , R. Bozzi","doi":"10.1016/j.biosystemseng.2025.104366","DOIUrl":"10.1016/j.biosystemseng.2025.104366","url":null,"abstract":"<div><div>The combination of Fourier transform near-infrared spectroscopy (FT-NIRS) of meat and fat samples and principal component discriminant analysis (DAPC) has been proposed as a tool for discriminating the local production of autochthonous pig breeds. Spectral samples (n = 272) belonging to 11 local European pig breeds, Longissimus muscle, and subcutaneous fat (both intact and minced) are collected. Classification accuracy based on DAPC was applied on FT-NIRS to predict breed of origin in i) semi-external cross-validation, splitting the data into training (80 %) and testing (20 %) sets; ii) external validation, in which one breed at a time was excluded from model training and classified in one of the remaining breeds. The effect of varying sample sizes from 50 % to 100 % of the data was assessed. Almost all breeds' spectra variability was summarised into two principal components for tissue and sample preparation. In cross-validation, intact fat yielded higher classification accuracies than intact meat, with less pronounced differences in minced samples. Success assignment rates of ∼81–83 % were obtained for two breeds in intact meat samples and were higher than 83 % for five breeds in fat samples. For minced samples, correct assignments between 80 % and 100 % were possible for five breeds, both in meat and fat samples. Sample size marginally affected the results. External validation confirmed similarity among some breeds, with greater accuracy for fat samples. The assignments success provides encouraging results for discriminating local pig production, mainly based on fat, using a rapid, eco-friendly FT-NIRS method, which could serve as tool for quality assurance.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104366"},"PeriodicalIF":5.3,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837487","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}

引用次数: 0

Influence of angle of attack on hydrodynamic performance and its implications for designing semi-mobile aquaculture structures: A CFD study 攻角对水动力性能的影响及其对半移动式水产养殖结构设计的启示：CFD研究

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-22 DOI: 10.1016/j.biosystemseng.2025.104363

Duc Nguyen , Si Thu Paing , Sarah Wakes , Ross Vennell , Scott Rhone , Louise Kregting , Suzy Black

This study examines the influence of various angles of attack of current flow (0° to 90° with 10° intervals) on the hydrodynamic performance, surface shear stress and drag force of various designs of semi-mobile aquaculture structures. The structures were cylinder- and cone-shaped, with the porosity on the body varying from 0 % to 15 %. Computational Fluid Dynamics (CFD) was employed, and the modelled flow speed and drag force were validated with flume-based experiments on a scaled model, 2.16 m in length and 0.45 m³ in volume. It was found that when the angle of attack was 30° and 60°, flow acceleration, from 1 to 1.3

m s^{- 1}

, and low-speed zones (<0.1

m s^{- 1}

) occurred in the cylinder-shaped structure with an impermeable body (design 1A). However, flow speed was relatively uniform in the cone-shaped structure with porosity of 15 % (design 2A). When the angle of attack was 90°, flow speed in the structure increased from 0

m s^{- 1}

in design 1A to 0.4

m s^{- 1}

in design 2A. This indicated that hydrodynamics in design 2A could be more beneficial for fish welfare (increased water flow maintains dissolved oxygen) than design 1A, particularly during oblique flow conditions. However, the drag force exerted on design 2A is greater than those on design 1A. These differences in drag force increase when the flow speed increases and the volume of the structure increases, which could increase the operational costs. Overall, the findings of this work imply that designing aquaculture structures that benefit both fish and farmers is challenging, and balancing fish requirements with operational costs is crucial to select appropriate designs.

本研究考察了不同的水流攻角（0°~ 90°，间隔10°）对不同设计的半移动式水产养殖结构的水动力性能、表面剪应力和阻力的影响。结构为圆柱形和锥形，孔隙率为0% ~ 15%。采用计算流体力学（CFD）方法，在长度为2.16 m，体积为0.45 m3的比例模型上，通过基于水槽的实验验证了模型的流速和阻力。研究发现，当迎角为30°和60°时，具有不透水体的圆柱形结构（设计1A）中出现了1 ~ 1.3 ms−1的流动加速度和0.1 ms−1的低速区。而在孔隙率为15%的锥形结构中，流速相对均匀（设计2A）。当迎角为90°时，结构内的流速从设计1A的0 ms−1增加到设计2A的0.4 ms−1。这表明，与设计1A相比，设计2A中的水动力学对鱼类的福利更有利（增加水流维持溶解氧），特别是在斜流条件下。但是，设计2A的阻力大于设计1A。随着流速的增加和结构体积的增大，阻力的差异也会增大，这可能会增加操作成本。总的来说，这项工作的发现意味着设计对鱼类和农民都有利的水产养殖结构是具有挑战性的，平衡鱼类需求和运营成本对于选择适当的设计至关重要。

{"title":"Influence of angle of attack on hydrodynamic performance and its implications for designing semi-mobile aquaculture structures: A CFD study","authors":"Duc Nguyen , Si Thu Paing , Sarah Wakes , Ross Vennell , Scott Rhone , Louise Kregting , Suzy Black","doi":"10.1016/j.biosystemseng.2025.104363","DOIUrl":"10.1016/j.biosystemseng.2025.104363","url":null,"abstract":"<div><div>This study examines the influence of various angles of attack of current flow (0° to 90° with 10° intervals) on the hydrodynamic performance, surface shear stress and drag force of various designs of semi-mobile aquaculture structures. The structures were cylinder- and cone-shaped, with the porosity on the body varying from 0 % to 15 %. Computational Fluid Dynamics (CFD) was employed, and the modelled flow speed and drag force were validated with flume-based experiments on a scaled model, 2.16 m in length and 0.45 m<sup>3</sup> in volume. It was found that when the angle of attack was 30° and 60°, flow acceleration, from 1 to 1.3 <span><math><mrow><mi>m</mi><mspace></mspace><msup><mi>s</mi><mrow><mo>−</mo><mn>1</mn></mrow></msup></mrow></math></span>, and low-speed zones (<0.1 <span><math><mrow><mi>m</mi><msup><mrow><mspace></mspace><mi>s</mi></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></mrow></math></span>) occurred in the cylinder-shaped structure with an impermeable body (design 1A). However, flow speed was relatively uniform in the cone-shaped structure with porosity of 15 % (design 2A). When the angle of attack was 90°, flow speed in the structure increased from 0 <span><math><mrow><mi>m</mi><msup><mrow><mspace></mspace><mi>s</mi></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></mrow></math></span> in design 1A to 0.4 <span><math><mrow><mi>m</mi><mspace></mspace><msup><mi>s</mi><mrow><mo>−</mo><mn>1</mn></mrow></msup></mrow></math></span> in design 2A. This indicated that hydrodynamics in design 2A could be more beneficial for fish welfare (increased water flow maintains dissolved oxygen) than design 1A, particularly during oblique flow conditions. However, the drag force exerted on design 2A is greater than those on design 1A. These differences in drag force increase when the flow speed increases and the volume of the structure increases, which could increase the operational costs. Overall, the findings of this work imply that designing aquaculture structures that benefit both fish and farmers is challenging, and balancing fish requirements with operational costs is crucial to select appropriate designs.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104363"},"PeriodicalIF":5.3,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837490","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}

引用次数: 0

A quantitative method of feeding demand for M. salmoides based on multi-source information fusion 基于多源信息融合的沙棘取食需求定量方法研究

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-22 DOI: 10.1016/j.biosystemseng.2025.104372

Yaping Li , Hequn Tan , Yiren Zhang , Xuefei Liu

Accurately predicting the feed intake of fish schools during intensive aquaculture is a crucial foundation for feeding decision systems. In the pond-based captive farming process, feeding devices cannot automatically and precisely adjust feeding strategies based on the farming environment, growth information, and parameters during the feeding process. To address this, a method based on multi-source information fusion is proposed to quantify the feeding demand of M. salmoides. Firstly, a two-stage feeding experiment was conducted to collect multi-source data from the first-stage feeding, along with supplementary feed intake (feed intake in the second stage). Secondly, a feeding endpoint detection algorithm was developed for the collected audio to identify feeding audio, and correlation analysis was applied to select features extracted from the feeding audio, which were processed utilising PCA to obtain the overall feeding feature. Thirdly, the SHAP method was used to identify the sensitive features. Finally, sensitive features were selected as inputs to establish a supplementary feed intake prediction model. Experimental results showed that the GBDT achieved the best performance among six ML models (CCC = 0.96, RMSE = 226.82 g, MAE = 173.93 g); The GBDT constructed in this study achieved an CCC of 0.93, an RMSE of 226.87 g, and an MAE of 170.55 g in real aquaculture scenarios; The GBDT-based feeding strategy achieved superior performance. This study enables the conversion of multi-source data into executable decision variables for feeding devices, thereby providing a data-driven decision-making framework for intelligent feeding systems.

准确预测集约化养殖过程中鱼群的采食量是饲喂决策系统的重要基础。在基于池塘的圈养养殖过程中，饲养装置无法根据养殖环境、生长信息和饲养过程中的参数自动、精确地调整饲养策略。针对这一问题，提出了一种基于多源信息融合的沙棘取食需求量化方法。首先，进行两期饲养试验，收集第一阶段饲养和补充采食量（第二阶段采食量）的多源数据。其次，针对采集到的音频，开发了一种馈送端点检测算法，对馈送音频进行识别，并利用相关分析对馈送音频提取的特征进行选择，利用主成分分析对提取的特征进行处理，得到整体馈送特征；再次，采用SHAP方法对敏感特征进行识别。最后，选取敏感特征作为输入，建立补充采食量预测模型。实验结果表明，GBDT在6种ML模型中表现最佳（CCC = 0.96, RMSE = 226.82 g, MAE = 173.93 g）；本研究构建的GBDT在真实养殖情景下的CCC为0.93，RMSE为226.87 g， MAE为170.55 g；基于gbdt的投料策略取得了优异的性能。本研究实现了将多源数据转化为供料装置可执行的决策变量，从而为智能供料系统提供数据驱动的决策框架。

{"title":"A quantitative method of feeding demand for M. salmoides based on multi-source information fusion","authors":"Yaping Li , Hequn Tan , Yiren Zhang , Xuefei Liu","doi":"10.1016/j.biosystemseng.2025.104372","DOIUrl":"10.1016/j.biosystemseng.2025.104372","url":null,"abstract":"<div><div>Accurately predicting the feed intake of fish schools during intensive aquaculture is a crucial foundation for feeding decision systems. In the pond-based captive farming process, feeding devices cannot automatically and precisely adjust feeding strategies based on the farming environment, growth information, and parameters during the feeding process. To address this, a method based on multi-source information fusion is proposed to quantify the feeding demand of <em>M. salmoides</em>. Firstly, a two-stage feeding experiment was conducted to collect multi-source data from the first-stage feeding, along with supplementary feed intake (feed intake in the second stage). Secondly, a feeding endpoint detection algorithm was developed for the collected audio to identify feeding audio, and correlation analysis was applied to select features extracted from the feeding audio, which were processed utilising PCA to obtain the overall feeding feature. Thirdly, the SHAP method was used to identify the sensitive features. Finally, sensitive features were selected as inputs to establish a supplementary feed intake prediction model. Experimental results showed that the GBDT achieved the best performance among six ML models (CCC = 0.96, RMSE = 226.82 g, MAE = 173.93 g); The GBDT constructed in this study achieved an CCC of 0.93, an RMSE of 226.87 g, and an MAE of 170.55 g in real aquaculture scenarios; The GBDT-based feeding strategy achieved superior performance. This study enables the conversion of multi-source data into executable decision variables for feeding devices, thereby providing a data-driven decision-making framework for intelligent feeding systems.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104372"},"PeriodicalIF":5.3,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837488","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}

引用次数: 0

Erratum to “Mitigation of greenhouse gas and ammonia emissions due to livestock housing management practices: Analysis of the DATAMAN database” [Biosystems engineering (258), September 2025, 104260] “减少牲畜饲养管理实践造成的温室气体和氨排放：DATAMAN数据库的分析”[生物系统工程（258），2025年9月，104260]

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-19 DOI: 10.1016/j.biosystemseng.2025.104360

Vasileios Anestis , Wajid Umar , Federico Dragoni , Tony J. van der Weerden , Mélynda Hassouna , Alasdair Noble , Thomas Bartzanas , Barbara Amon

引用次数: 0

Toward sustainable urban agriculture: Development of a robotic end effector for hydroponic lettuce in-situ harvesting in vertical farming 面向可持续城市农业：垂直农业中水培莴苣原位收获机器人末端执行器的开发

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-19 DOI: 10.1016/j.biosystemseng.2025.104362

Tiancheng Yu , Huanyu Jiang

Vertical farming integrated with hydroponics offers sustainable urban food solutions, yet reliance on manual harvesting, which requires labour-intensive tray transport and cutting, hinders scalability. This study focuses on the design and performance testing of an end effector for automated in-situ robotic harvesting of vertically stacked hydroponic lettuce, addressing two critical advancements: mechanised harvesting and post-harvest lightweight tray logistics. Manual harvesting trials revealed that push-cutting requires only 3.154 N of force (approximately 66 % lower than pull-cutting's 9.313 N), forming the basis for an energy-efficient end effector design. A novel robotic harvesting mode based on push-cutting was proposed, incorporating five phases: inserting, gripping, cutting, transporting, and unloading. An end effector integrating gripping and cutting functions was designed and optimised. Using response surface methodology, the optimal gripper parameters were determined: rotation radius of 73 mm, rotation angle of 80°, and movable finger diameter of 25 mm. The cutting performance test revealed the optimal cutting position as 5 mm above the root-stem junction and the optimal bevel cutting angle as 15°. Through structural improvements, the end effector was enhanced with a two-finger rotation mechanism to achieve more efficient and convenient unloading. Experimental results from performance testing demonstrated a harvesting success rate of 94 % and a leaf loss rate of 3.50 %, confirming the effectiveness and feasibility of the designed end effector. This innovation establishes a logistics-minimised automation framework for vertical farms, enhancing scalability and sustainability through energy-efficient, high-precision robotics and optimised material flow.

垂直农业与水培法相结合，提供了可持续的城市食品解决方案，但依赖人工收割，这需要劳动密集型的托盘运输和切割，阻碍了可扩展性。本研究的重点是垂直堆叠水培莴苣的自动原位机器人收获的末端执行器的设计和性能测试，解决了两个关键的进步：机械化收获和收获后的轻质托盘物流。人工采集试验表明，推切只需要3.154 N的力（比拉切的9.313 N低约66%），这为节能末端执行器的设计奠定了基础。提出了一种基于推切的机器人采收模式，该模式包括插拔、夹持、切割、运输和卸载五个阶段。设计并优化了集夹持和切削功能于一体的末端执行器。采用响应面法确定了最佳夹持器参数：旋转半径为73 mm，旋转角度为80°，活动指直径为25 mm。切割性能试验表明，最佳切割位置为根茎连接处上方5 mm，最佳斜角为15°。通过结构改进，增强了末端执行器的两指旋转机构，以实现更高效和方便的卸载。性能试验结果表明，采收成功率为94%，叶片损失率为3.50%，验证了所设计末端执行器的有效性和可行性。这一创新为垂直农场建立了物流最小化的自动化框架，通过节能、高精度机器人和优化的物料流增强了可扩展性和可持续性。

{"title":"Toward sustainable urban agriculture: Development of a robotic end effector for hydroponic lettuce in-situ harvesting in vertical farming","authors":"Tiancheng Yu , Huanyu Jiang","doi":"10.1016/j.biosystemseng.2025.104362","DOIUrl":"10.1016/j.biosystemseng.2025.104362","url":null,"abstract":"<div><div>Vertical farming integrated with hydroponics offers sustainable urban food solutions, yet reliance on manual harvesting, which requires labour-intensive tray transport and cutting, hinders scalability. This study focuses on the design and performance testing of an end effector for automated in-situ robotic harvesting of vertically stacked hydroponic lettuce, addressing two critical advancements: mechanised harvesting and post-harvest lightweight tray logistics. Manual harvesting trials revealed that push-cutting requires only 3.154 N of force (approximately 66 % lower than pull-cutting's 9.313 N), forming the basis for an energy-efficient end effector design. A novel robotic harvesting mode based on push-cutting was proposed, incorporating five phases: inserting, gripping, cutting, transporting, and unloading. An end effector integrating gripping and cutting functions was designed and optimised. Using response surface methodology, the optimal gripper parameters were determined: rotation radius of 73 mm, rotation angle of 80°, and movable finger diameter of 25 mm. The cutting performance test revealed the optimal cutting position as 5 mm above the root-stem junction and the optimal bevel cutting angle as 15°. Through structural improvements, the end effector was enhanced with a two-finger rotation mechanism to achieve more efficient and convenient unloading. Experimental results from performance testing demonstrated a harvesting success rate of 94 % and a leaf loss rate of 3.50 %, confirming the effectiveness and feasibility of the designed end effector. This innovation establishes a logistics-minimised automation framework for vertical farms, enhancing scalability and sustainability through energy-efficient, high-precision robotics and optimised material flow.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104362"},"PeriodicalIF":5.3,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788841","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}

引用次数: 0

Continuous welfare assessment of dairy cows at individual level: A farmer-oriented tool based on normal daily ranges of sensor-recorded traits 奶牛个体水平的连续福利评估：基于传感器记录特征的正常每日范围的面向农民的工具

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-12-18 DOI: 10.1016/j.biosystemseng.2025.104365

Y. Gómez , N. Blasco-Andreo , A. Llabrés-Brustenga , K. Chow , J. Serra-Sagrista , G.V. Berteselli , E. Canali , X. Manteca , P. Llonch

Animal welfare on farms is currently assessed using human-evaluation protocols, which provide a single record of herd condition at a specific moment. Integrating sensor-based data and farm records, continuous information on each animal's welfare can be obtained. This study aims to create an algorithm to assess individual dairy cow welfare, contributing to the goal of building a platform to inform producers and consumers about dairy cattle welfare. It was built based on the Five Domains model of animal welfare. 221 cows from four commercial free-stall barn farms in Spain and Italy were fitted with accelerometry collars and rumen boluses and monitored for 92 days. Individual data were collected daily. Accelerometers recorded time spent ruminating, eating, lying, walking, and standing within a 24-h interval. Boluses recorded rumen pH and temperature every 10 min, averaged over 24 h. Farm records included parity, veterinary treatments, and milk conductivity. The model provides a daily global welfare index per cow, categorised into health, nutrition, and environment scores. Behaviour and mental state were not included due to a lack of relevant sensor data. Scores range from 0 to 10, indicating the likelihood of the cow experiencing welfare-compromising conditions. Normal thresholds, based on scientific literature, were set for each trait. The algorithm detected daily deviations in traits, assuming that cows with welfare issues deviate from normal behavioural and physiological patterns. When a cow's welfare index decreased, affected domains could be identified, enabling farmers to address potential welfare issues and implement corrective measures.

农场的动物福利目前使用人类评估协议进行评估，该协议提供了特定时刻畜群状况的单一记录。整合基于传感器的数据和农场记录，可以获得关于每只动物福利的连续信息。本研究旨在创建一种评估奶牛个体福利的算法，为建立一个向生产者和消费者通报奶牛福利的平台做出贡献。它是基于动物福利的五域模型建立的。对来自西班牙和意大利4个商业散养牛场的221头奶牛进行了为期92天的监测，并安装了加速计项圈和瘤胃丸。每天收集个人数据。加速度计记录了24小时间隔内反刍、进食、躺卧、行走和站立的时间。boles每10分钟记录一次瘤胃pH和温度，平均记录时间为24小时。农场记录包括胎次、兽医处理和乳传导率。该模型提供每头奶牛的每日全球福利指数，分为健康、营养和环境得分。由于缺乏相关的传感器数据，行为和精神状态未包括在内。得分范围从0到10，表示奶牛遭受福利损害的可能性。在科学文献的基础上，为每个特征设定了正常阈值。该算法检测到性状的日常偏差，假设有福利问题的奶牛偏离了正常的行为和生理模式。当奶牛的福利指数下降时，可以识别受影响的领域，使农民能够解决潜在的福利问题并实施纠正措施。

{"title":"Continuous welfare assessment of dairy cows at individual level: A farmer-oriented tool based on normal daily ranges of sensor-recorded traits","authors":"Y. Gómez , N. Blasco-Andreo , A. Llabrés-Brustenga , K. Chow , J. Serra-Sagrista , G.V. Berteselli , E. Canali , X. Manteca , P. Llonch","doi":"10.1016/j.biosystemseng.2025.104365","DOIUrl":"10.1016/j.biosystemseng.2025.104365","url":null,"abstract":"<div><div>Animal welfare on farms is currently assessed using human-evaluation protocols, which provide a single record of herd condition at a specific moment. Integrating sensor-based data and farm records, continuous information on each animal's welfare can be obtained. This study aims to create an algorithm to assess individual dairy cow welfare, contributing to the goal of building a platform to inform producers and consumers about dairy cattle welfare. It was built based on the Five Domains model of animal welfare. 221 cows from four commercial free-stall barn farms in Spain and Italy were fitted with accelerometry collars and rumen boluses and monitored for 92 days. Individual data were collected daily. Accelerometers recorded time spent ruminating, eating, lying, walking, and standing within a 24-h interval. Boluses recorded rumen pH and temperature every 10 min, averaged over 24 h. Farm records included parity, veterinary treatments, and milk conductivity. The model provides a daily global welfare index per cow, categorised into health, nutrition, and environment scores. Behaviour and mental state were not included due to a lack of relevant sensor data. Scores range from 0 to 10, indicating the likelihood of the cow experiencing welfare-compromising conditions. Normal thresholds, based on scientific literature, were set for each trait. The algorithm detected daily deviations in traits, assuming that cows with welfare issues deviate from normal behavioural and physiological patterns. When a cow's welfare index decreased, affected domains could be identified, enabling farmers to address potential welfare issues and implement corrective measures.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"262 ","pages":"Article 104365"},"PeriodicalIF":5.3,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788840","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}

引用次数: 0