Biosystems Engineering最新文献

Divergent drivers of long-term trends vs. acute outbreaks in harmful algal blooms 长期趋势的不同驱动因素vs.有害藻华的急性爆发

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-31 DOI: 10.1016/j.biosystemseng.2026.104402

Xianglong Dai , Siyuan Zhang , Yinglan A , Guoqiang Wang , Jin Wu , Guangwen Ma , Kaiji Li , Shuyu Zeng

Harmful algal blooms (HABs) have become an environmental issue of global concern due to their wide distribution and sudden outbreak. The existing research mainly focuses on the attribution of the long-term trend of algal blooms, in which eutrophication has been considered as the main driving factor. However, this trend-based analysis framework does not reliably predict the occurrence of specific water blooms, largely due to insufficient explanation of the interaction mechanism between persistent drivers and event triggers. In this study, Hulun Lake was taken as an example to distinguish the red tide driving factors at annual, monthly and daily scales to clarify the interaction between persistence maintenance factors and short-term meteorological trigger factors. On an annual scale, HABs have shifted from localised, low-frequency events to widespread, high-frequency outbreaks, peaking in 2022. Water blooms mainly occurred in July–August, concentrated in the semi-enclosed southwest and northern bays. Total nitrogen and precipitation are key long-term predictors, reflecting the role of eutrophication and hydrological variability. On the monthly scale, HABs were divided into four types according to frequency and severity. This classification shows that meteorological activation and nutrient structure together determine the bloom pattern. HABs are more likely to occur under ' warm, humid, calm and nutrient-rich ' conditions. The key thresholds are: air temperature >19.7 °C (Interquartile coefficient of variation, IQRCV = 9 %), relative humidity >61 %(IQRCV = 21 %), wind speed <3.2 m/s(IQRCV = 37 %). On the daily scale, the formation of HABs is driven by cumulative meteorological effects. When 7-day air temperature >103 °C (IQRCV = 77 %), relative humidity >380 % (IQRCV = 77 %), wind speed <3.0 m/s (IQRCV = 77 %), the risk is further increased. These findings support a multi-scale strategy that combines watershed nutrient control with real-time meteorological monitoring.

有害藻华因其分布广泛、爆发突发性强，已成为全球关注的环境问题。现有的研究主要集中在藻华长期趋势的归因上，其中富营养化被认为是主要驱动因素。然而，这种基于趋势的分析框架并不能可靠地预测特定水华的发生，很大程度上是由于对持续驱动因素和事件触发因素之间的相互作用机制解释不足。本研究以呼伦湖为例，在年、月、日尺度上区分赤潮驱动因子，阐明持续维持因子与短期气象触发因子之间的相互作用。从年度规模来看，赤潮已经从局部的低频率事件转变为广泛的高频率爆发，并在2022年达到峰值。水华主要发生在7 - 8月，集中在半封闭的西南和北部海湾。总氮和降水是关键的长期预测因子，反映了富营养化和水文变率的作用。在月量表上，根据频率和严重程度将有害藻华分为四种类型。这种分类表明，气象激活和营养结构共同决定了水华模式。有害藻华更可能发生在“温暖、潮湿、平静和营养丰富”的条件下。关键阈值为：气温19.7℃（四分位变异系数IQRCV = 9%）、相对湿度61% （IQRCV = 21%）、风速3.2 m/s（IQRCV = 37%）。在日尺度上，赤潮的形成是由累积的气象效应驱动的。当7天气温103℃（IQRCV = 77%）、相对湿度380% （IQRCV = 77%）、风速3.0 m/s （IQRCV = 77%）时，危险性进一步增加。这些发现支持将流域养分控制与实时气象监测相结合的多尺度战略。

{"title":"Divergent drivers of long-term trends vs. acute outbreaks in harmful algal blooms","authors":"Xianglong Dai , Siyuan Zhang , Yinglan A , Guoqiang Wang , Jin Wu , Guangwen Ma , Kaiji Li , Shuyu Zeng","doi":"10.1016/j.biosystemseng.2026.104402","DOIUrl":"10.1016/j.biosystemseng.2026.104402","url":null,"abstract":"<div><div>Harmful algal blooms (HABs) have become an environmental issue of global concern due to their wide distribution and sudden outbreak. The existing research mainly focuses on the attribution of the long-term trend of algal blooms, in which eutrophication has been considered as the main driving factor. However, this trend-based analysis framework does not reliably predict the occurrence of specific water blooms, largely due to insufficient explanation of the interaction mechanism between persistent drivers and event triggers. In this study, Hulun Lake was taken as an example to distinguish the red tide driving factors at annual, monthly and daily scales to clarify the interaction between persistence maintenance factors and short-term meteorological trigger factors. On an annual scale, HABs have shifted from localised, low-frequency events to widespread, high-frequency outbreaks, peaking in 2022. Water blooms mainly occurred in July–August, concentrated in the semi-enclosed southwest and northern bays. Total nitrogen and precipitation are key long-term predictors, reflecting the role of eutrophication and hydrological variability. On the monthly scale, HABs were divided into four types according to frequency and severity. This classification shows that meteorological activation and nutrient structure together determine the bloom pattern. HABs are more likely to occur under ' warm, humid, calm and nutrient-rich ' conditions. The key thresholds are: air temperature >19.7 °C (Interquartile coefficient of variation, IQRCV = 9 %), relative humidity >61 %(IQRCV = 21 %), wind speed <3.2 m/s(IQRCV = 37 %). On the daily scale, the formation of HABs is driven by cumulative meteorological effects. When 7-day air temperature >103 °C (IQRCV = 77 %), relative humidity >380 % (IQRCV = 77 %), wind speed <3.0 m/s (IQRCV = 77 %), the risk is further increased. These findings support a multi-scale strategy that combines watershed nutrient control with real-time meteorological monitoring.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104402"},"PeriodicalIF":5.3,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146076945","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

Computer vision and IoT based plant phenotyping and growth monitoring with 3D point clouds 基于计算机视觉和物联网的植物表型和生长监测与3D点云

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-30 DOI: 10.1016/j.biosystemseng.2026.104398

Akash Ajagekar , Yu Jiang , Fengqi You

Computer vision and Internet of Things (IoT) technologies offer robust solutions for plant phenotyping, but traditional mainstream segmentation methods often fail in high-density plantings with overlapping foliage. This study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions. While recent agricultural applications have shown limited success and required domain-specific adaptations, Segment Anything Model (SAM) and FastSAM were demonstrated to achieve exceptional zero-shot segmentation performance for individual lettuce plants in high-density arrangements without additional training. This capability effectively addresses the traditional challenges of species-specific parameter tuning and extensive training data requirements and fine-tuning. By mapping 2D segmentation masks to corresponding 3D point clouds, the system accurately extracted key phenotypic traits, namely plant height, length, and width, from which area and volume were subsequently estimated, showing strong correlations with manual measurements for Rex and Rouxai lettuce cultivars. This high-temporal, non-destructive monitoring provided unique insights into plant growth dynamics. The study highlights distinct growth patterns among these cultivars, underscoring the importance of tailored phenotyping approaches to optimise crop management strategies. By addressing the limitations of existing phenotyping methods, this work advances precision agriculture technologies, offering a cost-effective and efficient solution for monitoring dynamic crop growth with potential applications across various crops and growing conditions.

计算机视觉和物联网（IoT）技术为植物表型分析提供了强大的解决方案，但传统的主流分割方法在叶子重叠的高密度种植中往往失败。本研究介绍了一种集成的表型系统，该系统结合了自动化数据捕获和高时间RGB-D成像，使用现成的硬件（英特尔RealSense D435和树莓派）在受控温室条件下生成生菜的3D点云。虽然最近的农业应用显示出有限的成功，并且需要特定领域的适应，但片段任意模型（SAM）和FastSAM被证明可以在高密度排列的单个生菜植株上实现出色的零射击分割性能，而无需额外的培训。这种能力有效地解决了物种特定参数调优和广泛的训练数据需求和微调的传统挑战。通过将2D分割掩模映射到相应的3D点云，该系统准确提取出植株高度、长度和宽度等关键表型性状，并由此估算出面积和体积，与人工测量的Rex和Rouxai生菜品种具有很强的相关性。这种高时间、非破坏性的监测提供了对植物生长动态的独特见解。该研究强调了这些品种之间不同的生长模式，强调了定制表型方法对优化作物管理策略的重要性。通过解决现有表型分析方法的局限性，本工作推进了精准农业技术，为监测作物动态生长提供了一种具有成本效益和效率的解决方案，具有潜在的应用于各种作物和生长条件。

{"title":"Computer vision and IoT based plant phenotyping and growth monitoring with 3D point clouds","authors":"Akash Ajagekar , Yu Jiang , Fengqi You","doi":"10.1016/j.biosystemseng.2026.104398","DOIUrl":"10.1016/j.biosystemseng.2026.104398","url":null,"abstract":"<div><div>Computer vision and Internet of Things (IoT) technologies offer robust solutions for plant phenotyping, but traditional mainstream segmentation methods often fail in high-density plantings with overlapping foliage. This study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions. While recent agricultural applications have shown limited success and required domain-specific adaptations, Segment Anything Model (SAM) and FastSAM were demonstrated to achieve exceptional zero-shot segmentation performance for individual lettuce plants in high-density arrangements without additional training. This capability effectively addresses the traditional challenges of species-specific parameter tuning and extensive training data requirements and fine-tuning. By mapping 2D segmentation masks to corresponding 3D point clouds, the system accurately extracted key phenotypic traits, namely plant height, length, and width, from which area and volume were subsequently estimated, showing strong correlations with manual measurements for Rex and Rouxai lettuce cultivars. This high-temporal, non-destructive monitoring provided unique insights into plant growth dynamics. The study highlights distinct growth patterns among these cultivars, underscoring the importance of tailored phenotyping approaches to optimise crop management strategies. By addressing the limitations of existing phenotyping methods, this work advances precision agriculture technologies, offering a cost-effective and efficient solution for monitoring dynamic crop growth with potential applications across various crops and growing conditions.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104398"},"PeriodicalIF":5.3,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071124","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

Adaptive synchronous sliding mode levelling system for combine harvester considering track circumference: Co-simulation and experimental verification 考虑履带周长的联合收割机自适应同步滑模调平系统：联合仿真与实验验证

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-29 DOI: 10.1016/j.biosystemseng.2026.104396

Jinpeng Hu , Maolin Shi , Tianle Ma , Peng Liu , Xiaoyu Chai , Guangqiao Cao , Lizhang Xu

To address variable track tension, poor cylinder synchronisation, and suboptimal chassis levelling in tracked combine harvesters in hilly terrain, a sliding mode synchronisation levelling control strategy is proposed that integrates theoretical track circumference (TTC) constraints with adaptive cylinder synchronisation control. The hydraulic circuit and operating principle of the four-point levelling chassis are analysed, and a mathematical model is developed to describe TTC variation during levelling. Particle Swarm Optimisation–Backpropagation (PSO-BP) surrogate models are established to capture the relationships among cylinder displacement, tension pulley position, levelling angles, and TTC. Based on these surrogates, the tension pulley position and cylinder extensions are optimised by formulating a constrained objective function and solving it with the Grey Wolf Optimiser (GWO). An adaptive synchronisation sliding mode controller (ASSMC) is then proposed, in which a disturbance observer estimates disturbances in the nonlinear hydraulic system and the synchronisation error is incorporated as a compensation term to improve tracking accuracy. Co-simulation results showed that the proposed strategy reduced levelling time to 1.8 s on a 5° lateral slope and 2.1 s on a 5° longitudinal slope. The cylinder synchronisation error remained below 0.52 mm, with negligible overshoot in cylinder displacement, outperforming conventional PID control. Meanwhile, TTC was maintained within 4580–4600 mm under all tested scenarios. Field tests further confirmed fast and accurate levelling, with body inclination maintained within ±0.2° and track tension satisfying the TTC constraint throughout, validating the effectiveness of the proposed system.

针对丘陵地形履带式联合收割机履带张力变化、汽缸同步性差以及底盘调平不理想等问题，提出了一种将理论履带周长约束与自适应汽缸同步控制相结合的滑模同步调平控制策略。分析了四点调平底盘的液压回路和工作原理，建立了调平过程中TTC变化的数学模型。建立了粒子群优化-反向传播（PSO-BP）替代模型，以捕获气缸位移、张力轮位置、调平角度和TTC之间的关系。在此基础上，通过构造约束目标函数，利用灰狼优化器（GWO）对约束目标函数进行优化。然后提出了一种自适应同步滑模控制器（ASSMC），其中扰动观测器估计非线性液压系统中的扰动，并将同步误差作为补偿项以提高跟踪精度。联合仿真结果表明，该策略可将5°侧坡的调平时间缩短至1.8 s，将5°纵坡的调平时间缩短至2.1 s。气缸同步误差保持在0.52 mm以下，气缸位移超调可以忽略不计，优于传统的PID控制。同时，在所有测试场景下，TTC都保持在4580-4600 mm之间。现场测试进一步证实了快速准确的调平，车身倾角保持在±0.2°，履带张力始终满足TTC约束，验证了所提出系统的有效性。

{"title":"Adaptive synchronous sliding mode levelling system for combine harvester considering track circumference: Co-simulation and experimental verification","authors":"Jinpeng Hu , Maolin Shi , Tianle Ma , Peng Liu , Xiaoyu Chai , Guangqiao Cao , Lizhang Xu","doi":"10.1016/j.biosystemseng.2026.104396","DOIUrl":"10.1016/j.biosystemseng.2026.104396","url":null,"abstract":"<div><div>To address variable track tension, poor cylinder synchronisation, and suboptimal chassis levelling in tracked combine harvesters in hilly terrain, a sliding mode synchronisation levelling control strategy is proposed that integrates theoretical track circumference (TTC) constraints with adaptive cylinder synchronisation control. The hydraulic circuit and operating principle of the four-point levelling chassis are analysed, and a mathematical model is developed to describe TTC variation during levelling. Particle Swarm Optimisation–Backpropagation (PSO-BP) surrogate models are established to capture the relationships among cylinder displacement, tension pulley position, levelling angles, and TTC. Based on these surrogates, the tension pulley position and cylinder extensions are optimised by formulating a constrained objective function and solving it with the Grey Wolf Optimiser (GWO). An adaptive synchronisation sliding mode controller (ASSMC) is then proposed, in which a disturbance observer estimates disturbances in the nonlinear hydraulic system and the synchronisation error is incorporated as a compensation term to improve tracking accuracy. Co-simulation results showed that the proposed strategy reduced levelling time to 1.8 s on a 5° lateral slope and 2.1 s on a 5° longitudinal slope. The cylinder synchronisation error remained below 0.52 mm, with negligible overshoot in cylinder displacement, outperforming conventional PID control. Meanwhile, TTC was maintained within 4580–4600 mm under all tested scenarios. Field tests further confirmed fast and accurate levelling, with body inclination maintained within ±0.2° and track tension satisfying the TTC constraint throughout, validating the effectiveness of the proposed system.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104396"},"PeriodicalIF":5.3,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071123","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

Dynamic analysis of the infection process of cucumber powdery mildew based on instance segmentation 基于实例分割的黄瓜白粉病感染过程动态分析

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-23 DOI: 10.1016/j.biosystemseng.2026.104395

Zonghuan Han , Chen Qiao , Yiding Zhang , Lingxian Zhang , Yong Wang , Wei Gao , Yaqi Li

Powdery mildew represents a significant threat to cucumber yield, with its infection process encompassing stages such as “attachment, colonisation, and dispersal.” With the advancement of deep learning, computer vision techniques are increasingly applied to study powdery mildew infection patterns. However, existing biological methods are low-throughput, subjective, and struggle to capture the dynamic characteristics of pathogen infection throughout the entire process. Current microscopic image analysis methods also fail to simultaneously recognise and segment various infection structures across different stages of infection, making it difficult to reveal the evolving infection patterns over time. To overcome these limitations, this paper proposes an integrated SR-QC-TA framework for modelling the infection behaviour of cucumber powdery mildew. First, a time-series dataset of microscopic images covering all stages of infection was constructed, systematically documenting the evolution of key infection structures from attachment to dispersal. Second, an instance segmentation algorithm, FS-YOLOv8s, was developed to achieve high-precision, multi-class recognition of pathogen structures in complex backgrounds. Additionally, a multi-dimensional quantitative characterisation method for pathogen infection features was designed, describing infection characteristics in terms of quantity, morphology, and location. Finally, based on these recognition and characterisation results, a temporal analysis framework was established to quantify dynamic changes in infection and reveal the stages of infection behaviour. Experimental results demonstrate that FS-YOLOv8s achieved mAP^box@0.5 and mAP^mask@0.5 scores of 91.8 % and 92.3 %, respectively, enabling high-precision segmentation across all infection stages. This research advances intelligent monitoring and control of cucumber powdery mildew and drives disease monitoring in horticultural crops toward bioengineering systems.

白粉病对黄瓜产量构成重大威胁，其感染过程包括“附着、定植和扩散”等阶段。随着深度学习技术的发展，计算机视觉技术越来越多地应用于研究白粉病的感染模式。然而，现有的生物学方法是低通量的，主观的，并且难以捕捉整个过程中病原体感染的动态特征。目前的显微图像分析方法也不能同时识别和分割感染不同阶段的各种感染结构，这使得很难揭示随着时间的推移而演变的感染模式。为了克服这些限制，本文提出了一个集成的SR-QC-TA框架来模拟黄瓜白粉病的感染行为。首先，构建了覆盖感染所有阶段的显微图像时间序列数据集，系统地记录了关键感染结构从附着到扩散的演变过程。其次，开发了一种实例分割算法FS-YOLOv8s，实现了复杂背景下病原体结构的高精度、多类识别。此外，设计了一种病原体感染特征的多维定量表征方法，从数量、形态和位置等方面描述了感染特征。最后，基于这些识别和表征结果，建立了一个时间分析框架，以量化感染的动态变化并揭示感染行为的阶段。实验结果表明，FS-YOLOv8s的mAPbox@0.5和mAPmask@0.5得分分别为91.8%和92.3%，能够在所有感染阶段进行高精度分割。本研究推进了黄瓜白粉病的智能监测与控制，推动了园艺作物病害监测向生物工程方向发展。

{"title":"Dynamic analysis of the infection process of cucumber powdery mildew based on instance segmentation","authors":"Zonghuan Han , Chen Qiao , Yiding Zhang , Lingxian Zhang , Yong Wang , Wei Gao , Yaqi Li","doi":"10.1016/j.biosystemseng.2026.104395","DOIUrl":"10.1016/j.biosystemseng.2026.104395","url":null,"abstract":"<div><div>Powdery mildew represents a significant threat to cucumber yield, with its infection process encompassing stages such as “attachment, colonisation, and dispersal.” With the advancement of deep learning, computer vision techniques are increasingly applied to study powdery mildew infection patterns. However, existing biological methods are low-throughput, subjective, and struggle to capture the dynamic characteristics of pathogen infection throughout the entire process. Current microscopic image analysis methods also fail to simultaneously recognise and segment various infection structures across different stages of infection, making it difficult to reveal the evolving infection patterns over time. To overcome these limitations, this paper proposes an integrated SR-QC-TA framework for modelling the infection behaviour of cucumber powdery mildew. First, a time-series dataset of microscopic images covering all stages of infection was constructed, systematically documenting the evolution of key infection structures from attachment to dispersal. Second, an instance segmentation algorithm, FS-YOLOv8s, was developed to achieve high-precision, multi-class recognition of pathogen structures in complex backgrounds. Additionally, a multi-dimensional quantitative characterisation method for pathogen infection features was designed, describing infection characteristics in terms of quantity, morphology, and location. Finally, based on these recognition and characterisation results, a temporal analysis framework was established to quantify dynamic changes in infection and reveal the stages of infection behaviour. Experimental results demonstrate that FS-YOLOv8s achieved mAP<sup>box</sup>@0.5 and mAP<sup>mask</sup>@0.5 scores of 91.8 % and 92.3 %, respectively, enabling high-precision segmentation across all infection stages. This research advances intelligent monitoring and control of cucumber powdery mildew and drives disease monitoring in horticultural crops toward bioengineering systems.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104395"},"PeriodicalIF":5.3,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023374","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

Design and optimisation of differentiated UAV-based fertiliser applicator 差异化无人机施肥机的设计与优化

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-22 DOI: 10.1016/j.biosystemseng.2026.104399

Jingang Han , Guobin Wang , Xinyu Xue , Cancan Song , Yubin Lan

As an emerging precision agriculture technology, UAV fertiliser application technology has been rapidly developed in recent years. However, existing UAV-based fertiliser applicators (UFAs) lack differentiated variable performance design for different discharge port outlets. To address this limitation, this study designed an UAV fertiliser applicator with adjustable fertiliser discharge. This UFA mainly consists of a flow-regulating fan and an adjustment module. The flow-regulating fan is installed at the bottom of the fertiliser tank to adjust fertiliser discharge rate. The regulating unit is installed at the bottom of the flow-regulating fan to adjust the differentiated fertiliser amount at the outlets. The motion model of fertiliser particles was established based on DEM, and used to analyse the influence of parameters such as the feeding angle, flow-regulating fan angle, and outlet angle on the effect pattern on the variation of fertiliser application rate at different outlets. Bench tests were conducted to verify the overall discharge performance and the differences among various outlets under different discharge rates and combinations of the regulating units. Simulation results showed that when the feeding angle is 70°, the flow-regulating fan angle is 15°, and the outlet angle is 15°, the coefficient of variation (CV) of the five outlets is 66.63 %, demonstrating that the UFA can achieve significant differentiation in fertiliser discharge among outlets. Bench tests showed that the average proportion of fertiliser discharged from individual outlets ranged from approximately 8.59 %–61.38 %, confirming substantial variability. This study can provide a reference for the research on variable UFAs with different outlets to change the amount of fertiliser applied.

无人机施肥技术作为一种新兴的精准农业技术，近年来得到了迅速发展。然而，现有的基于无人机的化肥施用器（ufa）缺乏针对不同排放口的差异化可变性能设计。为了解决这一限制，本研究设计了一种可调节肥料排放量的无人机施肥器。该UFA主要由调节风机和调节模块组成。在肥槽底部安装流量调节风机，调节肥料排出量。调节单元安装在流量调节风机的底部，用于调节各出口的差别化肥料量。基于DEM建立了肥料颗粒的运动模型，分析了进料角、调流风机角、出口角等参数对不同出口施肥量变化的影响规律。通过台架试验，验证了不同流量和调节机组组合下各出口的整体放电性能差异。仿真结果表明，当进料角为70°、调流风机角为15°、出口角为15°时，5个出口的变异系数（CV）为66.63%，表明UFA能实现不同出口间肥料排放的显著差异。台架试验表明，各个排水口排放的化肥平均比例约为8.59% - 61.38%，证实了大量的变化。本研究可为不同出口的可变ufa变化施肥量的研究提供参考。

{"title":"Design and optimisation of differentiated UAV-based fertiliser applicator","authors":"Jingang Han , Guobin Wang , Xinyu Xue , Cancan Song , Yubin Lan","doi":"10.1016/j.biosystemseng.2026.104399","DOIUrl":"10.1016/j.biosystemseng.2026.104399","url":null,"abstract":"<div><div>As an emerging precision agriculture technology, UAV fertiliser application technology has been rapidly developed in recent years. However, existing UAV-based fertiliser applicators (UFAs) lack differentiated variable performance design for different discharge port outlets. To address this limitation, this study designed an UAV fertiliser applicator with adjustable fertiliser discharge. This UFA mainly consists of a flow-regulating fan and an adjustment module. The flow-regulating fan is installed at the bottom of the fertiliser tank to adjust fertiliser discharge rate. The regulating unit is installed at the bottom of the flow-regulating fan to adjust the differentiated fertiliser amount at the outlets. The motion model of fertiliser particles was established based on DEM, and used to analyse the influence of parameters such as the feeding angle, flow-regulating fan angle, and outlet angle on the effect pattern on the variation of fertiliser application rate at different outlets. Bench tests were conducted to verify the overall discharge performance and the differences among various outlets under different discharge rates and combinations of the regulating units. Simulation results showed that when the feeding angle is 70°, the flow-regulating fan angle is 15°, and the outlet angle is 15°, the coefficient of variation (CV) of the five outlets is 66.63 %, demonstrating that the UFA can achieve significant differentiation in fertiliser discharge among outlets. Bench tests showed that the average proportion of fertiliser discharged from individual outlets ranged from approximately 8.59 %–61.38 %, confirming substantial variability. This study can provide a reference for the research on variable UFAs with different outlets to change the amount of fertiliser applied.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104399"},"PeriodicalIF":5.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146022869","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

Binocular vision-based method for fruit motion and force parameter acquisition 基于双目视觉的水果运动与力参数获取方法

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-21 DOI: 10.1016/j.biosystemseng.2026.104397

Yang Zhang , Linyun Xu , Yancheng Zhu , Yanyan Wang , Hongping Zhou , Aiqi Zhang

With the rapid development of the forestry and fruit industries, vibration harvesting has become an efficient method for fruit detachment, making accurate acquisition of motion and dynamic force parameters essential. This study proposes a non-contact binocular vision method to estimate precisely the 3D motion and force parameters of fruits under vibratory excitation. Fruit motion is decomposed into translation, swing, and rotation modes based on the captured 3D coordinates of surface feature points. A multi-coordinate transformation model is constructed to calculate pose parameters, and a differentiated force analysis method is introduced based on pedicel mechanical properties. A simulated fruit model was developed and validated through experiments: one group used a custom test bench to excite detached pecans, while another employed a vibration motor to excite a ginkgo tree. High-speed cameras recorded the entire process. Comparative analysis of theoretical, simulated, and experimental results showed that, under zero feature-point deviation, average relative errors for motion and force parameters were in the 10⁻⁴–10⁻⁵ range. With experimental feature-point deviations averaging 2.08 ± 0.32 mm, simulations using 2 mm deviations kept maximum errors within 6 %, confirming high accuracy. For long-pedicel fruits, pedicel state (tensioned vs. relaxed) had a dynamic impact on binding forces: peak forces in the tensioned state were up to three times higher, validating theoretical assumptions. The non-contact approach avoids errors from added sensor mass and provides theoretical support for analysing fruit motion and detachment in vibration harvesting. This research offers practical value for improving harvesting precision and equipment performance.

随着林业和果业的快速发展，振动采收已成为果品剥离的一种有效方法，准确获取果品运动和动力参数至关重要。提出了一种非接触式双目视觉方法来精确估计振动激励下水果的三维运动和受力参数。基于捕获的表面特征点三维坐标，将水果运动分解为平移、摆动和旋转三种模式。建立了多坐标变换模型计算位姿参数，引入了基于椎弓根力学特性的微分力分析方法。我们建立了一个模拟水果模型，并通过实验进行了验证：一组使用定制的试验台来刺激分离的山核桃，另一组使用振动电机来刺激银杏树。高速摄像机记录下了整个过程。理论、仿真和实验结果对比分析表明，在零特征点偏差情况下，运动和力参数的平均相对误差在10−4 ~ 10−5之间。实验特征点偏差平均为2.08±0.32 mm，采用2 mm偏差进行模拟，最大误差控制在6%以内，精度较高。对于长花梗水果，花梗状态（紧张与放松）对结合力有动态影响：紧张状态下的峰值力高达三倍，验证了理论假设。非接触方法避免了传感器质量增加带来的误差，为振动采集中果实运动和分离分析提供了理论支持。该研究对提高采集精度和设备性能具有一定的实用价值。

{"title":"Binocular vision-based method for fruit motion and force parameter acquisition","authors":"Yang Zhang , Linyun Xu , Yancheng Zhu , Yanyan Wang , Hongping Zhou , Aiqi Zhang","doi":"10.1016/j.biosystemseng.2026.104397","DOIUrl":"10.1016/j.biosystemseng.2026.104397","url":null,"abstract":"<div><div>With the rapid development of the forestry and fruit industries, vibration harvesting has become an efficient method for fruit detachment, making accurate acquisition of motion and dynamic force parameters essential. This study proposes a non-contact binocular vision method to estimate precisely the 3D motion and force parameters of fruits under vibratory excitation. Fruit motion is decomposed into translation, swing, and rotation modes based on the captured 3D coordinates of surface feature points. A multi-coordinate transformation model is constructed to calculate pose parameters, and a differentiated force analysis method is introduced based on pedicel mechanical properties. A simulated fruit model was developed and validated through experiments: one group used a custom test bench to excite detached pecans, while another employed a vibration motor to excite a ginkgo tree. High-speed cameras recorded the entire process. Comparative analysis of theoretical, simulated, and experimental results showed that, under zero feature-point deviation, average relative errors for motion and force parameters were in the 10<sup>−4</sup>–10<sup>−5</sup> range. With experimental feature-point deviations averaging 2.08 ± 0.32 mm, simulations using 2 mm deviations kept maximum errors within 6 %, confirming high accuracy. For long-pedicel fruits, pedicel state (tensioned vs. relaxed) had a dynamic impact on binding forces: peak forces in the tensioned state were up to three times higher, validating theoretical assumptions. The non-contact approach avoids errors from added sensor mass and provides theoretical support for analysing fruit motion and detachment in vibration harvesting. This research offers practical value for improving harvesting precision and equipment performance.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104397"},"PeriodicalIF":5.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146022868","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

Design and experiment of air-assisted spiral seed-supply device for high-speed narrow-row dense planting of maize 玉米高速窄行密植气助螺旋送种装置的设计与试验

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-19 DOI: 10.1016/j.biosystemseng.2025.104358

Wensheng Sun , Shujuan Yi , Hailong Qi , Yifei Li , Zhibo Dai , Yupeng Zhang , Song Wang , Yunxiao Liu

To solve the problem of large seeding volume of the planter under the dense planting mode of maize, and the high requirements on the seed-supplying capacity of the seed-supplying device during high-speed operation, an air-assisted spiral seed-supply device is designed. The combination of spiral seed relocation and airflow seed delivery is used for efficient seed supply. The coupling of discrete element method and computational fluid dynamics (DEM-CFD) was used to investigate the influence of different pipe lengths, sleeve axial openings, and spiral shaft guides on the device's ability to seed-supply. A quadratic regression model was fitted between pipe lengths, sleeve axial openings, and spiral shaft guides, and seed-supply performance indexes, to obtain the optimal parameter combinations of the device. The effects of different types of seeds and the rotational speed of the spiral shaft on the performance of the device were investigated through bench tests. The results show that the optimal combination of structural parameters of the device is 44.153 mm of sleeve axial opening, 56.228 mm of spiral shaft guide, and 644.998 mm of pipe length, and the seed supply rate, the coefficient of variation of seed supply rate stability, and the seed breakage rate under the simulation validation are 24.72 g s⁻¹, 2.04 %, and 1.66 % respectively, and the deviation of the bench validation results from the simulation validation results is 0.15 g s⁻¹, 0.08 %, and 0.2 % respectively, which verifies the validity of the optimisation results of the simulation test parameters.

为解决玉米密集种植模式下播种机播种量大，高速运行时对供种装置供种能力要求高的问题，设计了一种气助式螺旋供种装置。采用螺旋送种和气流送种相结合的方式，实现高效送种。采用离散元法和计算流体力学（DEM-CFD）相结合的方法，研究了不同管道长度、套筒轴向开口和螺旋轴导轨对装置供种能力的影响。通过对管道长度、套筒轴向开口、螺旋轴导轨与供种性能指标进行二次回归模型拟合，得到该装置的最优参数组合。通过台架试验，研究了不同种子类型和螺旋轴转速对装置性能的影响。结果表明,结构参数的最佳组合套管轴向开放的设备是44.153毫米,56.228毫米的螺旋轴向导,和644.998毫米的管道长度,和种子供应率、种子供应率的变异系数稳定,和种子破碎率仿真验证以下24.72 g s−1 2.04%和1.66%分别和替补席上的偏差验证仿真结果验证结果0.15 g s−1)0.08%,和0.2%，验证了仿真试验参数优化结果的有效性。

{"title":"Design and experiment of air-assisted spiral seed-supply device for high-speed narrow-row dense planting of maize","authors":"Wensheng Sun , Shujuan Yi , Hailong Qi , Yifei Li , Zhibo Dai , Yupeng Zhang , Song Wang , Yunxiao Liu","doi":"10.1016/j.biosystemseng.2025.104358","DOIUrl":"10.1016/j.biosystemseng.2025.104358","url":null,"abstract":"<div><div>To solve the problem of large seeding volume of the planter under the dense planting mode of maize, and the high requirements on the seed-supplying capacity of the seed-supplying device during high-speed operation, an air-assisted spiral seed-supply device is designed. The combination of spiral seed relocation and airflow seed delivery is used for efficient seed supply. The coupling of discrete element method and computational fluid dynamics (DEM-CFD) was used to investigate the influence of different pipe lengths, sleeve axial openings, and spiral shaft guides on the device's ability to seed-supply. A quadratic regression model was fitted between pipe lengths, sleeve axial openings, and spiral shaft guides, and seed-supply performance indexes, to obtain the optimal parameter combinations of the device. The effects of different types of seeds and the rotational speed of the spiral shaft on the performance of the device were investigated through bench tests. The results show that the optimal combination of structural parameters of the device is 44.153 mm of sleeve axial opening, 56.228 mm of spiral shaft guide, and 644.998 mm of pipe length, and the seed supply rate, the coefficient of variation of seed supply rate stability, and the seed breakage rate under the simulation validation are 24.72 g s<sup>−1</sup>, 2.04 %, and 1.66 % respectively, and the deviation of the bench validation results from the simulation validation results is 0.15 g s<sup>−1</sup>, 0.08 %, and 0.2 % respectively, which verifies the validity of the optimisation results of the simulation test parameters.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104358"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023375","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

Nonlinear model predictive control for autonomous driving in terrain 地形自动驾驶非线性模型预测控制

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-19 DOI: 10.1016/j.biosystemseng.2025.104375

Jere Knuutinen , Tabish Badar , Juha Backman , Arto Visala

Forestry machines used nowadays function in a wide variety of terrains. In order to make these vehicles operate autonomously advanced control methods are needed. However, current research related to autonomous driving generally assumes flat terrain in the control as well as in the estimation. Therefore concerning this matter, this paper addresses potential solutions by investigating and applying nonlinear model predictive control (NMPC) for autonomous driving in uneven terrain. This paper proposes a hybrid model derived from the dynamic six-degrees-of-freedom (6-DOF) model for motion control purposes. The developed NMPC method utilises a path tracking approach and aims to minimise the time-independent tracking error between the position of the vehicle and path by utilising the proposed hybrid model and three-dimensional (3D) terrain map. The effectiveness of the predictive controller is tested using three different test paths and terrains. An all-terrain electric vehicle (ATV) called Polaris is utilised to test and confirm the functionality of the control method. In addition, the paper proposes a rollover avoidance method and tests it in simulation environment. The method aims to lower the vehicle speed in the presence of high roll angles. The results from the actual tests with the implementation of the NMPC method indicate that accurate path-tracking results can be obtained with the proposed controller in the test paths used in this study with the tracking errors being 0.11 m, 0.07 m and 0.1 m.

现在使用的林业机械可以在各种各样的地形上使用。为了使这些车辆能够自主运行，需要先进的控制方法。然而，目前与自动驾驶相关的研究，无论是在控制还是在估计中，都普遍假设地形是平坦的。因此，本文通过研究和应用非线性模型预测控制（NMPC）来解决这一问题。本文提出了一种基于动态六自由度（6-DOF）模型的混合运动控制模型。开发的NMPC方法利用路径跟踪方法，旨在通过利用所提出的混合模型和三维（3D）地形图，最大限度地减少车辆位置和路径之间的时间无关跟踪误差。通过三种不同的测试路径和地形对预测控制器的有效性进行了测试。一辆名为北极星的全地形电动汽车（ATV）被用来测试和确认控制方法的功能。此外，本文还提出了一种避免侧翻的方法，并在仿真环境下进行了测试。该方法旨在降低车辆的速度，在存在大的侧倾角。实施NMPC方法的实际测试结果表明，在本研究使用的测试路径上，所提出的控制器可以获得准确的路径跟踪结果，跟踪误差分别为0.11 m、0.07 m和0.1 m。

{"title":"Nonlinear model predictive control for autonomous driving in terrain","authors":"Jere Knuutinen , Tabish Badar , Juha Backman , Arto Visala","doi":"10.1016/j.biosystemseng.2025.104375","DOIUrl":"10.1016/j.biosystemseng.2025.104375","url":null,"abstract":"<div><div>Forestry machines used nowadays function in a wide variety of terrains. In order to make these vehicles operate autonomously advanced control methods are needed. However, current research related to autonomous driving generally assumes flat terrain in the control as well as in the estimation. Therefore concerning this matter, this paper addresses potential solutions by investigating and applying nonlinear model predictive control (NMPC) for autonomous driving in uneven terrain. This paper proposes a hybrid model derived from the dynamic six-degrees-of-freedom (6-DOF) model for motion control purposes. The developed NMPC method utilises a path tracking approach and aims to minimise the time-independent tracking error between the position of the vehicle and path by utilising the proposed hybrid model and three-dimensional (3D) terrain map. The effectiveness of the predictive controller is tested using three different test paths and terrains. An all-terrain electric vehicle (ATV) called Polaris is utilised to test and confirm the functionality of the control method. In addition, the paper proposes a rollover avoidance method and tests it in simulation environment. The method aims to lower the vehicle speed in the presence of high roll angles. The results from the actual tests with the implementation of the NMPC method indicate that accurate path-tracking results can be obtained with the proposed controller in the test paths used in this study with the tracking errors being 0.11 m, 0.07 m and 0.1 m.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104375"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146022865","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

Coping styles in Holstein Heifers: Relationship between proactivity and habituation to automatic milking system 荷斯坦小母牛的应对方式：主动与适应自动挤奶系统的关系

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-16 DOI: 10.1016/j.biosystemseng.2026.104394

Giovanna Marliani , Martina Lamanna , Giovanni Buonaiuto , Damiano Cavallini , Pier Attilio Accorsi

Research on the influence of personality on animal welfare, health, and productivity is gaining significant attention in both the scientific community and the dairy industry. This study explores how proactivity, a coping style associated with risk-taking, influences heifers’ adaptation to the Automatic Milking System (AMS). Prior to calving, the behavioural responses of twenty-three heifers were assessed through three tests: the Individual Novel Human Test (NHi), the Individual Novel Object Test (NOi), and the Novel Object Test in Group (NOg). Following parturition, each heifer was video-recorded during their first ten automated milkings, and the videos were analysed using the BORIS© software.

Statistical analysis distinguished proactive and reactive individuals in each test, revealing key differences. Proactive animals in the NOi test exhibited a significantly lower stepping rate (p < 0.05) during milking. In contrast, reactive heifers in the NHi test displayed a higher kicking rate (p < 0.05). Additionally, proactive subjects in the NOg test spent significantly less time in the robot (p < 0.05) and were less likely to pull the teat cup off (p < 0.05). These findings suggest that proactive animals, with differences between tests, were generally less nervous during the automated milking process, indicating better habituation. This highlights the importance of considering coping styles in animal management to improve both welfare and productivity in dairy farming.

Science4Impact Statement (S4IS).

This study highlights how personality in heifers, particularly considering the coping style in response to the environment, influence their ability to adapt to Automatic Milking Systems (AMS). Proactive animals exhibited better adaptability, showing less stressful behaviours (e.g., reduced kicking and stepping rates), suggesting lower stress levels during milking. These findings provide practical evidence to support decision-making processes for stakeholders, including farmers and policymakers, in the development of precision livestock farming systems. By identifying behavioural profiles that influence heifers’ adaptation to automatic milking, our results highlight specific traits that could be integrated into sensor-based monitoring and decision-support algorithms (Lamanna, Bovo, et al., 2025; Lamanna, Bovo, & Cavallini, 2025; Cavallini et al., 2025). This integration can help Precision Livestock Farming (PLF) technologies predict stress responses, optimise training strategies, and reduce human intervention, thereby contributing to improved welfare and labour efficiency. Such systems not only enhance animal welfare but also promote greater sustainability, aligning with global goals to reduce the environmental impact of intensive agriculture.

个性对动物福利、健康和生产力的影响的研究在科学界和乳制品行业都得到了极大的关注。本研究探讨了主动性，一种与冒险相关的应对方式，如何影响小母牛对自动挤奶系统（AMS）的适应。产犊前，研究人员通过三个测试对23头小母牛的行为反应进行了评估：个体新人类测试（NHi）、个体新物体测试（NOi）和群体新物体测试（NOg）。分娩后，对每头小母牛的前10次自动挤奶过程进行录像，并使用BORIS©软件对录像进行分析。统计分析在每个测试中区分了主动和被动个体，揭示了关键差异。NOi试验中主动性动物在挤奶过程中踏步率显著降低（p < 0.05）。相比之下，NHi试验反应性犊牛的踢脚率更高（p < 0.05）。此外，在NOg测试中，积极主动的受试者在机器人上花费的时间显著减少（p < 0.05），并且不太可能将奶杯拉下来（p < 0.05）。这些发现表明，在不同的测试中，主动的动物在自动挤奶过程中通常不那么紧张，表明更好的习惯。这突出了在动物管理中考虑应对方式以提高奶牛养殖业福利和生产力的重要性。科学影响声明（S4IS）。这项研究强调了小母牛的个性，特别是考虑到对环境的应对方式，如何影响它们适应自动挤奶系统（AMS）的能力。主动的动物表现出更好的适应性，表现出更少的压力行为（例如，减少踢腿和踩踏率），表明挤奶时的压力水平更低。这些发现为支持包括农民和决策者在内的利益相关者在发展精准畜牧业系统方面的决策过程提供了实际证据。通过识别影响小母牛适应自动挤奶的行为特征，我们的研究结果突出了可以整合到基于传感器的监测和决策支持算法中的特定特征（Lamanna， Bovo等，2025;Lamanna， Bovo等；Cavallini等，2025）。这种整合可以帮助精准畜牧业（PLF）技术预测压力反应，优化培训策略，减少人为干预，从而有助于提高福利和劳动效率。这样的系统不仅提高了动物福利，而且促进了更大的可持续性，与减少集约化农业对环境影响的全球目标保持一致。

{"title":"Coping styles in Holstein Heifers: Relationship between proactivity and habituation to automatic milking system","authors":"Giovanna Marliani , Martina Lamanna , Giovanni Buonaiuto , Damiano Cavallini , Pier Attilio Accorsi","doi":"10.1016/j.biosystemseng.2026.104394","DOIUrl":"10.1016/j.biosystemseng.2026.104394","url":null,"abstract":"<div><div>Research on the influence of personality on animal welfare, health, and productivity is gaining significant attention in both the scientific community and the dairy industry. This study explores how proactivity, a coping style associated with risk-taking, influences heifers’ adaptation to the Automatic Milking System (AMS). Prior to calving, the behavioural responses of twenty-three heifers were assessed through three tests: the Individual Novel Human Test (NHi), the Individual Novel Object Test (NOi), and the Novel Object Test in Group (NOg). Following parturition, each heifer was video-recorded during their first ten automated milkings, and the videos were analysed using the BORIS© software.</div><div>Statistical analysis distinguished proactive and reactive individuals in each test, revealing key differences. Proactive animals in the NOi test exhibited a significantly lower stepping rate (p < 0.05) during milking. In contrast, reactive heifers in the NHi test displayed a higher kicking rate (p < 0.05). Additionally, proactive subjects in the NOg test spent significantly less time in the robot (p < 0.05) and were less likely to pull the teat cup off (p < 0.05). These findings suggest that proactive animals, with differences between tests, were generally less nervous during the automated milking process, indicating better habituation. This highlights the importance of considering coping styles in animal management to improve both welfare and productivity in dairy farming.</div><div>Science4Impact Statement (S4IS).</div><div>This study highlights how personality in heifers, particularly considering the coping style in response to the environment, influence their ability to adapt to Automatic Milking Systems (AMS). Proactive animals exhibited better adaptability, showing less stressful behaviours (e.g., reduced kicking and stepping rates), suggesting lower stress levels during milking. These findings provide practical evidence to support decision-making processes for stakeholders, including farmers and policymakers, in the development of precision livestock farming systems. By identifying behavioural profiles that influence heifers’ adaptation to automatic milking, our results highlight specific traits that could be integrated into sensor-based monitoring and decision-support algorithms (Lamanna, Bovo, et al., 2025; Lamanna, Bovo, & Cavallini, 2025; Cavallini et al., 2025). This integration can help Precision Livestock Farming (PLF) technologies predict stress responses, optimise training strategies, and reduce human intervention, thereby contributing to improved welfare and labour efficiency. Such systems not only enhance animal welfare but also promote greater sustainability, aligning with global goals to reduce the environmental impact of intensive agriculture.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104394"},"PeriodicalIF":5.3,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145973593","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

Advancing pig lameness detection with a multi-task framework: Leveraging multi-view 3D pose estimation and wavelet convolution 用多任务框架推进猪跛足检测：利用多视图三维姿态估计和小波卷积

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2026-01-15 DOI: 10.1016/j.biosystemseng.2026.104393

Li Xiang , Haidong Wang , Zixuan Hu , Tomas Norton , Tian Jiang , Yueju Xue

Lameness in pigs presents significant challenges to animal welfare and livestock productivity, necessitating precise detection of both lameness severity and the affected limb. Conventional single-view 2D methods are often constrained by occlusions and variability in viewing angles within dynamic farm environments. Although 3D camera-based approaches provide higher accuracy, their high costs and inability to support long-term monitoring limit their practicality. To address these challenges, this study employs multi-view 3D pose estimation to reconstruct 3D skeletal of pigs from multi-view 2D video, which effectively mitigates issues related to occlusion and viewpoint dependency. Building on this, a novel multi-task classification framework, PoseGait-MT, is proposed to simultaneously detect lameness severity and identify affected limbs. The framework extracts 3D gait spatiotemporal features, including spatial tracking distance (sTRK), head bobbing amplitude (HBA), and joint flexion angles (JFA). These features are integrated into a unified low-dimensional feature map that incorporates both 3D global and relative motion trajectories. To enhance the extraction of low-frequency features and suppress high-frequency noise, wavelet convolution (WTConv) is incorporated. Experimental results demonstrated that PoseGait-MT achieved an average accuracy of 94.7 % for lameness severity classification and 95.7 % for affected limb identification with a 5-fold cross-validation, confirming its effectiveness. Additionally, on an independent test set collected from a separate pen, the model achieved 89 % and 91.4 % accuracy for the respective tasks, highlighting its robustness in real-world conditions. The proposed approach provides a practical and efficient solution for automated lameness detection in livestock farming.

猪的跛行对动物福利和牲畜生产力提出了重大挑战，需要精确检测跛行严重程度和受影响的肢体。传统的单视图2D方法经常受到遮挡和动态农场环境中视角变化的限制。尽管基于3D摄像机的方法提供了更高的精度，但它们的高成本和无法支持长期监测限制了它们的实用性。为了解决这些问题，本研究采用多视角3D姿态估计从多视角2D视频中重建猪的3D骨骼，有效地缓解了与遮挡和视点依赖相关的问题。在此基础上，提出了一种新的多任务分类框架——PoseGait-MT，以同时检测跛行严重程度和识别影响肢体。该框架提取三维步态时空特征，包括空间跟踪距离（sTRK）、头部摆动幅度（HBA）和关节屈曲角度（JFA）。这些特征被集成到一个统一的低维特征映射中，该映射包含了3D全局和相对运动轨迹。为了增强低频特征的提取和抑制高频噪声，引入了小波卷积（WTConv）。实验结果表明，经过5次交叉验证，posegat - mt对跛行严重程度分类的平均准确率为94.7%，对患肢识别的平均准确率为95.7%，证实了其有效性。此外，在从单独的笔收集的独立测试集上，该模型在各自的任务上达到了89%和91.4%的准确率，突出了其在现实世界条件下的鲁棒性。本文提出的方法为畜牧业的自动化跛行检测提供了一种实用、高效的解决方案。

{"title":"Advancing pig lameness detection with a multi-task framework: Leveraging multi-view 3D pose estimation and wavelet convolution","authors":"Li Xiang , Haidong Wang , Zixuan Hu , Tomas Norton , Tian Jiang , Yueju Xue","doi":"10.1016/j.biosystemseng.2026.104393","DOIUrl":"10.1016/j.biosystemseng.2026.104393","url":null,"abstract":"<div><div>Lameness in pigs presents significant challenges to animal welfare and livestock productivity, necessitating precise detection of both lameness severity and the affected limb. Conventional single-view 2D methods are often constrained by occlusions and variability in viewing angles within dynamic farm environments. Although 3D camera-based approaches provide higher accuracy, their high costs and inability to support long-term monitoring limit their practicality. To address these challenges, this study employs multi-view 3D pose estimation to reconstruct 3D skeletal of pigs from multi-view 2D video, which effectively mitigates issues related to occlusion and viewpoint dependency. Building on this, a novel multi-task classification framework, PoseGait-MT, is proposed to simultaneously detect lameness severity and identify affected limbs. The framework extracts 3D gait spatiotemporal features, including spatial tracking distance (sTRK), head bobbing amplitude (HBA), and joint flexion angles (JFA). These features are integrated into a unified low-dimensional feature map that incorporates both 3D global and relative motion trajectories. To enhance the extraction of low-frequency features and suppress high-frequency noise, wavelet convolution (WTConv) is incorporated. Experimental results demonstrated that PoseGait-MT achieved an average accuracy of 94.7 % for lameness severity classification and 95.7 % for affected limb identification with a 5-fold cross-validation, confirming its effectiveness. Additionally, on an independent test set collected from a separate pen, the model achieved 89 % and 91.4 % accuracy for the respective tasks, highlighting its robustness in real-world conditions. The proposed approach provides a practical and efficient solution for automated lameness detection in livestock farming.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"263 ","pages":"Article 104393"},"PeriodicalIF":5.3,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145973592","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