Biosystems Engineering最新文献_第10页

AI-driven real-time weed detection and robotic smart spraying for optimised performance and operational speed in vegetable production 人工智能驱动的实时杂草检测和机器人智能喷洒，优化蔬菜生产的性能和操作速度

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-16 DOI: 10.1016/j.biosystemseng.2025.104288

Vinay Vijayakumar , Yiannis Ampatzidis , Christian Lacerda , Tom Burks , Won Suk Lee , John Schueller

For effective weed control in vegetable farms, enhancing precision spraying through improved real-time detection is crucial. Over the years, weed detection studies have evolved from traditional feature-based methods to deep learning approaches, particularly convolutional neural networks (CNNs). While numerous studies have focused on improving detection accuracy by experimenting with different backbones, architectures, and hyperparameter tuning, fewer have addressed the real-time implementation of these models in field conditions. Existing research primarily benchmarks model inference speed but often neglects the broader algorithmic efficiency, which includes sensor data integration, processing pipelines, and microcontroller output handling. Furthermore, real-world deployment challenges, such as camera performance at different robot speeds, the optimal operational range for high detection accuracy, and the end-to-end latency of the machine vision system, remain underexplored. This study addresses these gaps by training a custom YOLOv8 nano model to detect three weed types (broadleaf, nutsedge, and grass) and two crop types (pepper and tomato) in plasticulture beds. The system runs on a robotic smart sprayer in real time, integrating GPS and camera data while transmitting control signals to the microcontroller. Beyond detection performance, we evaluate the entire processing pipeline by measuring the total loop time and its variation with the number of detections per frame. Additionally, the optimal robot operational speed was determined, finding that 0.45–0.89 m s⁻¹ provides the best balance between detection accuracy and system responsiveness. By focusing on end-to-end real-time performance on vegetable beds, this study provides insights into the practical deployment of smart spraying, often been overlooked in prior research.

为了有效地控制蔬菜农场的杂草，通过改进实时检测来提高精确喷洒是至关重要的。多年来，杂草检测研究已经从传统的基于特征的方法发展到深度学习方法，特别是卷积神经网络（cnn）。虽然许多研究都专注于通过试验不同的主干、架构和超参数调优来提高检测精度，但很少有研究解决这些模型在现场条件下的实时实现问题。现有的研究主要以模型推理速度为基准，但往往忽略了更广泛的算法效率，包括传感器数据集成、处理管道和微控制器输出处理。此外，现实世界的部署挑战，如不同机器人速度下的摄像头性能、高检测精度的最佳操作范围以及机器视觉系统的端到端延迟，仍未得到充分探索。本研究通过训练定制的YOLOv8纳米模型来检测塑料栽培床上的三种杂草（阔叶草、坚果草和草）和两种作物类型（辣椒和番茄），从而解决了这些空白。该系统在机器人智能喷雾器上实时运行，集成GPS和摄像头数据，同时将控制信号传输到微控制器。除了检测性能之外，我们还通过测量总循环时间及其随每帧检测次数的变化来评估整个处理流程。此外，确定了机器人的最佳操作速度，发现0.45-0.89 m s−1在检测精度和系统响应性之间提供了最佳平衡。通过关注蔬菜床的端到端实时性能，本研究为智能喷洒的实际部署提供了见解，这在以前的研究中经常被忽视。

{"title":"AI-driven real-time weed detection and robotic smart spraying for optimised performance and operational speed in vegetable production","authors":"Vinay Vijayakumar , Yiannis Ampatzidis , Christian Lacerda , Tom Burks , Won Suk Lee , John Schueller","doi":"10.1016/j.biosystemseng.2025.104288","DOIUrl":"10.1016/j.biosystemseng.2025.104288","url":null,"abstract":"<div><div>For effective weed control in vegetable farms, enhancing precision spraying through improved real-time detection is crucial. Over the years, weed detection studies have evolved from traditional feature-based methods to deep learning approaches, particularly convolutional neural networks (CNNs). While numerous studies have focused on improving detection accuracy by experimenting with different backbones, architectures, and hyperparameter tuning, fewer have addressed the real-time implementation of these models in field conditions. Existing research primarily benchmarks model inference speed but often neglects the broader algorithmic efficiency, which includes sensor data integration, processing pipelines, and microcontroller output handling. Furthermore, real-world deployment challenges, such as camera performance at different robot speeds, the optimal operational range for high detection accuracy, and the end-to-end latency of the machine vision system, remain underexplored. This study addresses these gaps by training a custom YOLOv8 nano model to detect three weed types (broadleaf, nutsedge, and grass) and two crop types (pepper and tomato) in plasticulture beds. The system runs on a robotic smart sprayer in real time, integrating GPS and camera data while transmitting control signals to the microcontroller. Beyond detection performance, we evaluate the entire processing pipeline by measuring the total loop time and its variation with the number of detections per frame. Additionally, the optimal robot operational speed was determined, finding that 0.45–0.89 m s<sup>−1</sup> provides the best balance between detection accuracy and system responsiveness. By focusing on end-to-end real-time performance on vegetable beds, this study provides insights into the practical deployment of smart spraying, often been overlooked in prior research.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104288"},"PeriodicalIF":5.3,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099583","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

Parameter optimisation of a centrifugal fan for rice combine harvesters based on airflow resistance coefficients and CFD simulations 基于气流阻力系数和CFD模拟的水稻联合收割机离心风机参数优化

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-13 DOI: 10.1016/j.biosystemseng.2025.104287

Zhenwei Liang , Million Eyasu Wada

In this work, both experimental and numerical simulations were employed to identify optimal fan parameter settings for achieving efficient cleaning performance during high-yield rice harvesting. First, field experiments were conducted to analyse the distribution of threshed outputs within the cleaning shoe, and then airflow resistance coefficients created by the fluidised grain and cleaning sieves in each zone were calculated. Subsequently, perforated plates were designed based on the calculated airflow resistance coefficients in different sieve zones to represent the cleaning load. The computational fluid dynamics (CFD) simulation results were validated by using measured airflow velocity at multiple points beneath the perforated plates. After validation, additional CFD simulations were performed under various fan parameter settings, incorporating porous media to simulate the fan's working load. The results indicated that a sieve opening of 26 mm, guide plate angles (I) of 38° and (II) of 36°, and a fan speed of 1300 rpm significantly improved airflow and pressure distribution within the fan. Finally, a field experiment validated the cleaning performance using the selected parameter combinations, achieving a grain sieve loss ratio of 0.78 % and a grain impurity ratio of 1.15 % at a feed rate of 6 kg s⁻¹. This innovative approach not only provides an accurate method for determining the fan's working load but also enables the evaluation of fan performance under varying load conditions through CFD simulations, ultimately enhancing the cleaning performance of rice combine harvesters through optimised parameter selection.

在这项工作中，采用实验和数值模拟来确定在高产水稻收获期间实现高效清洁性能的最佳风扇参数设置。首先，通过田间试验，分析了脱粒产品在清洗鞋内的分布，然后计算了各区域内流化颗粒和清洗筛子产生的气流阻力系数。随后，根据计算出的不同筛区气流阻力系数，设计了代表清洗负荷的穿孔板。计算流体力学（CFD）模拟结果通过测量多孔板下多个点的气流速度进行验证。验证后，在不同风扇参数设置下进行了额外的CFD模拟，并采用多孔介质来模拟风扇的工作负荷。结果表明：筛孔为26 mm，导板角(I)为38°，导板角（II）为36°，风机转速为1300 rpm时，可显著改善风机内气流和压力分布。最后，通过田间试验验证了所选参数组合的清洗性能，在进料速度为6 kg s−1时，颗粒筛失率为0.78%，颗粒杂质率为1.15%。这种创新的方法不仅为确定风机的工作负荷提供了准确的方法，而且可以通过CFD模拟来评估风机在不同负荷条件下的性能，最终通过优化参数选择来提高水稻联合收割机的清洁性能。

{"title":"Parameter optimisation of a centrifugal fan for rice combine harvesters based on airflow resistance coefficients and CFD simulations","authors":"Zhenwei Liang , Million Eyasu Wada","doi":"10.1016/j.biosystemseng.2025.104287","DOIUrl":"10.1016/j.biosystemseng.2025.104287","url":null,"abstract":"<div><div>In this work, both experimental and numerical simulations were employed to identify optimal fan parameter settings for achieving efficient cleaning performance during high-yield rice harvesting. First, field experiments were conducted to analyse the distribution of threshed outputs within the cleaning shoe, and then airflow resistance coefficients created by the fluidised grain and cleaning sieves in each zone were calculated. Subsequently, perforated plates were designed based on the calculated airflow resistance coefficients in different sieve zones to represent the cleaning load. The computational fluid dynamics (CFD) simulation results were validated by using measured airflow velocity at multiple points beneath the perforated plates. After validation, additional CFD simulations were performed under various fan parameter settings, incorporating porous media to simulate the fan's working load. The results indicated that a sieve opening of 26 mm, guide plate angles (I) of 38° and (II) of 36°, and a fan speed of 1300 rpm significantly improved airflow and pressure distribution within the fan. Finally, a field experiment validated the cleaning performance using the selected parameter combinations, achieving a grain sieve loss ratio of 0.78 % and a grain impurity ratio of 1.15 % at a feed rate of 6 kg s<sup>−1</sup>. This innovative approach not only provides an accurate method for determining the fan's working load but also enables the evaluation of fan performance under varying load conditions through CFD simulations, ultimately enhancing the cleaning performance of rice combine harvesters through optimised parameter selection.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104287"},"PeriodicalIF":5.3,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047041","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

Application of weight prediction for Holstein dairy cows in non-pregnant and postpartum stages 体重预测在荷斯坦奶牛非妊娠期和产后期的应用

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-11 DOI: 10.1016/j.biosystemseng.2025.104276

Hsin-I Chiang , Jia-Ming Zhou , Wen-Lin Chu

A non-contact weight prediction system for Holstein dairy cows was developed based on depth sensing technology, designed to predict weight changes during non-pregnant and postpartum stages. The system utilises an Intel RealSense D455 depth camera to capture depth image information from cow's dorsal, hips, and side regions, extracting effective body surface feature data through a systematic data processing workflow. Experimental results demonstrate that the Gaussian Process Regression (GPR) model performed most excellently in the cow's dorsal region. For example, with cow number cid603 during the non-pregnant period, prediction accuracy reached a root mean square error (RMSE) of 19.37 kg and a mean absolute percentage error (MAPE) of 1.82 %; with cow number cid700 in the postpartum stage, the model maintained an RMSE of 22.35 kg and MAPE of 2.74 %, exhibiting robust model generalisation capability. Compared to traditional farm methods based on body length and heart girth measurements, the weight prediction system proposed in this study significantly improved the accuracy and stability of weight prediction, especially in capturing physiological state changes (such as postpartum weight loss). Experimental results indicate that the GPR model exhibited the best predictive ability and generalisation with feature data from the dorsal region, effectively supporting precise monitoring of dairy cow weight. Future research directions should focus on optimising image preprocessing techniques, incorporating more physiological parameters (such as feed intake), and integrating depth information from different angles to enhance the system's adaptability in complex environments, thereby strengthening the universality and reliability of the weight prediction model.

基于深度传感技术，研制了荷斯坦奶牛非接触式体重预测系统，用于预测奶牛非妊娠期和产后体重变化。该系统利用英特尔RealSense D455深度摄像头，从奶牛的背部、臀部和侧面区域捕获深度图像信息，通过系统的数据处理工作流程提取有效的体表特征数据。实验结果表明，高斯过程回归（Gaussian Process Regression， GPR）模型在奶牛背部区域的表现最为优异。以非妊娠期奶牛号cid603为例，预测精度均方根误差（RMSE）为19.37 kg，平均绝对百分比误差（MAPE）为1.82%；产后奶牛数为cid700时，模型的RMSE为22.35 kg， MAPE为2.74%，具有较强的模型泛化能力。与传统的基于体长和胸围测量的农场方法相比，本研究提出的体重预测系统显著提高了体重预测的准确性和稳定性，特别是在捕捉生理状态变化（如产后体重减轻）方面。实验结果表明，GPR模型对奶牛背部特征数据的预测能力和泛化能力最好，可有效支持奶牛体重的精确监测。未来的研究方向应侧重于优化图像预处理技术，纳入更多的生理参数（如采食量），整合不同角度的深度信息，增强系统对复杂环境的适应性，从而增强权重预测模型的通用性和可靠性。

{"title":"Application of weight prediction for Holstein dairy cows in non-pregnant and postpartum stages","authors":"Hsin-I Chiang , Jia-Ming Zhou , Wen-Lin Chu","doi":"10.1016/j.biosystemseng.2025.104276","DOIUrl":"10.1016/j.biosystemseng.2025.104276","url":null,"abstract":"<div><div>A non-contact weight prediction system for Holstein dairy cows was developed based on depth sensing technology, designed to predict weight changes during non-pregnant and postpartum stages. The system utilises an Intel RealSense D455 depth camera to capture depth image information from cow's dorsal, hips, and side regions, extracting effective body surface feature data through a systematic data processing workflow. Experimental results demonstrate that the Gaussian Process Regression (GPR) model performed most excellently in the cow's dorsal region. For example, with cow number cid603 during the non-pregnant period, prediction accuracy reached a root mean square error (RMSE) of 19.37 kg and a mean absolute percentage error (MAPE) of 1.82 %; with cow number cid700 in the postpartum stage, the model maintained an RMSE of 22.35 kg and MAPE of 2.74 %, exhibiting robust model generalisation capability. Compared to traditional farm methods based on body length and heart girth measurements, the weight prediction system proposed in this study significantly improved the accuracy and stability of weight prediction, especially in capturing physiological state changes (such as postpartum weight loss). Experimental results indicate that the GPR model exhibited the best predictive ability and generalisation with feature data from the dorsal region, effectively supporting precise monitoring of dairy cow weight. Future research directions should focus on optimising image preprocessing techniques, incorporating more physiological parameters (such as feed intake), and integrating depth information from different angles to enhance the system's adaptability in complex environments, thereby strengthening the universality and reliability of the weight prediction model.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104276"},"PeriodicalIF":5.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047040","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 bump-enhanced conditioning rollers for uniform alfalfa stem damage 设计和优化颠簸增强调节辊均匀苜蓿茎损伤

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-11 DOI: 10.1016/j.biosystemseng.2025.104251

Qiao Jin , Hongqian Li , Decheng Wang , Yong You , Yunting Hui , Sibiao Li

Conditioning is a critical step in alfalfa hay harvesting, directly influencing its quality. A conditioning model was developed to identify the key factors affecting conditioning effectiveness. To address the issue of uneven stem damage caused by conventional conditioning rollers, a surface bump structure was designed. By arranging these bumps spatially, the rollers applied micro-rubbing actions to the alfalfa stems, thereby enhancing structural disruption. Parametric optimisation studies clarified how bump diameter, non-interference distance and helix angle influence stem disruption efficiency. The design was further refined using the finite element method. Subsequently, a Box–Behnken experimental design was employed to optimise three key operational parameters: feed rate, roller gap, and roller rotational speed. Drying tests were then conducted to compare the conditioning performance of different roller designs. Results showed that the minimum number of broken branches (0.67) and maximum number of non-fracture damage occurrences (7.67) were achieved with a bump diameter of 2.85 mm, a non-interference distance of 1.61 mm, and a helix angle of 23.85°. Aiming to maximise the conditioning while minimising the conditioning loss rate and energy consumption, the optimal parameters were determined to be a roller rotational speed of 683 r min⁻¹, a roller gap of 3.13 mm and a feed rate of 779 g s⁻¹. The moisture content of alfalfa conditioned using the roller with bumps dropped to around 40 % within the first 60 min. Compared with the other two conditioning rollers, this design demonstrated superior performance.

调理是苜蓿干草收获的关键步骤，直接影响苜蓿干草的品质。为了确定影响条件反射效果的关键因素，建立了条件反射模型。针对常规调质辊对阀杆损伤不均匀的问题，设计了一种表面凹凸结构。通过在空间上安排这些凸起，滚子对苜蓿茎施加了微摩擦作用，从而增强了结构破坏。参数优化研究阐明了碰撞直径、非干涉距离和螺旋角对阀杆断裂效率的影响。采用有限元法进一步完善了设计。随后，采用Box-Behnken实验设计来优化三个关键操作参数：进给速度、滚轮间隙和滚轮转速。然后进行了干燥试验，比较了不同设计的滚筒的调理性能。结果表明，在凹凸直径2.85 mm、互不干涉距离1.61 mm、螺旋角23.85°的情况下，断枝数最少（0.67），非断裂损伤发生数最多（7.67）。为了最大限度地提高调理效果，同时使调理损失率和能量消耗最小，确定了最优参数为辊转速为683 rmin - 1，辊间隙为3.13 mm，进料速率为779 g s - 1。使用带凸起滚筒的苜蓿含水率在前60分钟内下降到40%左右。与其他两种调理辊相比，该设计表现出优越的性能。

{"title":"Design and optimisation of bump-enhanced conditioning rollers for uniform alfalfa stem damage","authors":"Qiao Jin , Hongqian Li , Decheng Wang , Yong You , Yunting Hui , Sibiao Li","doi":"10.1016/j.biosystemseng.2025.104251","DOIUrl":"10.1016/j.biosystemseng.2025.104251","url":null,"abstract":"<div><div>Conditioning is a critical step in alfalfa hay harvesting, directly influencing its quality. A conditioning model was developed to identify the key factors affecting conditioning effectiveness. To address the issue of uneven stem damage caused by conventional conditioning rollers, a surface bump structure was designed. By arranging these bumps spatially, the rollers applied micro-rubbing actions to the alfalfa stems, thereby enhancing structural disruption. Parametric optimisation studies clarified how bump diameter, non-interference distance and helix angle influence stem disruption efficiency. The design was further refined using the finite element method. Subsequently, a Box–Behnken experimental design was employed to optimise three key operational parameters: feed rate, roller gap, and roller rotational speed. Drying tests were then conducted to compare the conditioning performance of different roller designs. Results showed that the minimum number of broken branches (0.67) and maximum number of non-fracture damage occurrences (7.67) were achieved with a bump diameter of 2.85 mm, a non-interference distance of 1.61 mm, and a helix angle of 23.85°. Aiming to maximise the conditioning while minimising the conditioning loss rate and energy consumption, the optimal parameters were determined to be a roller rotational speed of 683 r min<sup>−1</sup>, a roller gap of 3.13 mm and a feed rate of 779 g s<sup>−1</sup>. The moisture content of alfalfa conditioned using the roller with bumps dropped to around 40 % within the first 60 min. Compared with the other two conditioning rollers, this design demonstrated superior performance.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104251"},"PeriodicalIF":5.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145047039","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 general discrete element modelling method and harvest process for wheat plants 一种通用的离散元建模方法及小麦收获过程

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-09 DOI: 10.1016/j.biosystemseng.2025.104284

Jianhua Fan , Liang Zhang , Kai Sun , Xiaoyan Qian , Lu Wang , Jianqun Yu

A general modelling approach for mature wheat plants with continuous deformation and breakable characteristics is proposed. First, by analysing the shape and size of three typical wheat plants as well as the coordinates of the discrete particles, the geometrical models of the wheat stalk, ear and grain that compose the wheat plant are constructed. Then, the physical and contact mechanical parameters of the wheat plant are determined and verified via a series of actual tests, including moisture measurement, drainage method, slope test and inclined plane drop test. In addition, the bonding mechanical parameters are obtained by analysing the results of the tensile, compression and shear experiments. On the basis of the above work, the mechanical model of the wheat ear, grain and stalk is constructed considering Hertz-Mindlin contact and bonding models with the discrete element method. Finally, the proposed wheat plant model is validated and verified by comparing the experiment and simulation results in terms of the harvest process including cutting and threshing. The results showed that the cutting force and total threshing rate obtained from the simulations differ from the actual test values by no more than 4.4 % and 9 %, respectively. The strong agreement between the simulation and experimental results indicates the feasibility and reliability of the proposed general modelling method for the wheat plant. In summary, the present study provides an effective tool to analyse the wheat harvest process and agricultural machinery design.

提出了一种具有连续变形和易碎特性的成熟小麦植株的通用建模方法。首先，通过分析三个典型小麦植株的形状和大小以及离散粒子的坐标，构建了组成小麦植株的麦秆、穗和籽粒的几何模型。然后，通过水分测量、排水法、坡度试验和斜面跌落试验等一系列实际试验，确定并验证了小麦植株的物理力学参数和接触力学参数。通过对拉伸、压缩和剪切试验结果的分析，得到了粘结力学参数。在上述工作的基础上，采用离散元法建立了考虑Hertz-Mindlin接触和粘接模型的小麦穗、籽粒和茎秆的力学模型。最后，通过对比实验结果和模拟结果，从收割、脱粒等收获过程对所提出的小麦植株模型进行了验证和验证。结果表明，模拟得到的切削力和总脱粒率与实际试验值的差异分别不超过4.4%和9%。模拟结果与实验结果吻合较好，表明所提出的小麦植株综合建模方法的可行性和可靠性。总之，本研究为小麦收获过程分析和农机设计提供了有效的工具。

{"title":"A general discrete element modelling method and harvest process for wheat plants","authors":"Jianhua Fan , Liang Zhang , Kai Sun , Xiaoyan Qian , Lu Wang , Jianqun Yu","doi":"10.1016/j.biosystemseng.2025.104284","DOIUrl":"10.1016/j.biosystemseng.2025.104284","url":null,"abstract":"<div><div>A general modelling approach for mature wheat plants with continuous deformation and breakable characteristics is proposed. First, by analysing the shape and size of three typical wheat plants as well as the coordinates of the discrete particles, the geometrical models of the wheat stalk, ear and grain that compose the wheat plant are constructed. Then, the physical and contact mechanical parameters of the wheat plant are determined and verified via a series of actual tests, including moisture measurement, drainage method, slope test and inclined plane drop test. In addition, the bonding mechanical parameters are obtained by analysing the results of the tensile, compression and shear experiments. On the basis of the above work, the mechanical model of the wheat ear, grain and stalk is constructed considering Hertz-Mindlin contact and bonding models with the discrete element method. Finally, the proposed wheat plant model is validated and verified by comparing the experiment and simulation results in terms of the harvest process including cutting and threshing. The results showed that the cutting force and total threshing rate obtained from the simulations differ from the actual test values by no more than 4.4 % and 9 %, respectively. The strong agreement between the simulation and experimental results indicates the feasibility and reliability of the proposed general modelling method for the wheat plant. In summary, the present study provides an effective tool to analyse the wheat harvest process and agricultural machinery design.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104284"},"PeriodicalIF":5.3,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020542","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

Effect of sampling density and location on airflow rate measurements in a naturally ventilated pig barn with an outdoor exercise yard: A boundary layer wind tunnel study 采样密度和位置对带室外运动场地的自然通风猪舍气流速率测量的影响：边界层风洞研究

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-08 DOI: 10.1016/j.biosystemseng.2025.104275

Xuefei Wu , Sabrina Hempel , David Janke , Barbara Amon , Guoqiang Zhang , Jürgen Zentek , Thomas Amon , Qianying Yi

An accurate ventilation rate estimation is the basis for developing ventilation strategies, optimising indoor air quality and determining pollutant emissions from livestock buildings. To accurately quantify the airflow rate of a novel naturally ventilated pig barn with an outdoor exercise yard, the influence of sampling density and location on the airflow rate measurement was studied. The experiment was conducted in a large atmospheric boundary layer wind tunnel by measuring the airflow velocity at the openings (the yard opening and the window of the indoor room) of a scaled pig barn model. Under four wind directions (0

°

, 60

°

, 120

°

, and 180

°

), the study evaluated four sampling densities distributed separately along the vertical or the lateral directions of the opening, different mesh-like sampling strategies, and airflow rate measurement with or without considering the edge effects of the opening. The results showed that: 1) Sampling densities distributed vertically and laterally along the yard opening, as well as those distributed vertically along the window, were significantly affected by wind directions (p < 0.05). 2) The mesh-like sampling strategy can ensure accurate measurement results with a difference ratio of less than 5 %. 3) Suitable sampling densities without considering the wall effect caused by the vertical edge of the opening can still support reliable airflow rate measurement. The results of this study contribute to developing the direct method of airflow rate measurements in naturally ventilated livestock buildings.

准确的通风率估算是制定通风策略、优化室内空气质量和确定畜舍污染物排放的基础。为了准确量化带室外运动场地的新型自然通风猪舍的风量，研究了采样密度和采样位置对风量测量的影响。实验在大型大气边界层风洞中，通过测量按比例猪舍模型的开口（院子开口和室内房间窗户）处的气流速度进行。在4个风向（0°、60°、120°和180°）下，研究评估了沿开口垂直或横向分别分布的4种采样密度、不同的网状采样策略以及考虑或不考虑开口边缘效应的风速测量。结果表明：1)沿院落开口垂直和横向分布以及沿窗垂直分布的采样密度受风向影响显著（p < 0.05）；2)类网格采样策略可以保证测量结果的准确性，差比小于5%。3)适当的采样密度，不考虑开口垂直边缘引起的壁面效应，仍然可以支持可靠的流速测量。本研究的结果有助于发展直接测量自然通风畜舍气流速率的方法。

{"title":"Effect of sampling density and location on airflow rate measurements in a naturally ventilated pig barn with an outdoor exercise yard: A boundary layer wind tunnel study","authors":"Xuefei Wu , Sabrina Hempel , David Janke , Barbara Amon , Guoqiang Zhang , Jürgen Zentek , Thomas Amon , Qianying Yi","doi":"10.1016/j.biosystemseng.2025.104275","DOIUrl":"10.1016/j.biosystemseng.2025.104275","url":null,"abstract":"<div><div>An accurate ventilation rate estimation is the basis for developing ventilation strategies, optimising indoor air quality and determining pollutant emissions from livestock buildings. To accurately quantify the airflow rate of a novel naturally ventilated pig barn with an outdoor exercise yard, the influence of sampling density and location on the airflow rate measurement was studied. The experiment was conducted in a large atmospheric boundary layer wind tunnel by measuring the airflow velocity at the openings (the yard opening and the window of the indoor room) of a scaled pig barn model. Under four wind directions (0 <span><math><mrow><mo>°</mo></mrow></math></span>, 60 <span><math><mrow><mo>°</mo></mrow></math></span>, 120 <span><math><mrow><mo>°</mo></mrow></math></span>, and 180 <span><math><mrow><mo>°</mo></mrow></math></span>), the study evaluated four sampling densities distributed separately along the vertical or the lateral directions of the opening, different mesh-like sampling strategies, and airflow rate measurement with or without considering the edge effects of the opening. The results showed that: 1) Sampling densities distributed vertically and laterally along the yard opening, as well as those distributed vertically along the window, were significantly affected by wind directions (p < 0.05). 2) The mesh-like sampling strategy can ensure accurate measurement results with a difference ratio of less than 5 %. 3) Suitable sampling densities without considering the wall effect caused by the vertical edge of the opening can still support reliable airflow rate measurement. The results of this study contribute to developing the direct method of airflow rate measurements in naturally ventilated livestock buildings.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104275"},"PeriodicalIF":5.3,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010734","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

Experimental research on mechanised strip application process based on DEM of compressed granulated straw 基于DEM的压缩粒状秸秆机械化条带化工艺试验研究

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-05 DOI: 10.1016/j.biosystemseng.2025.104274

Guibin Chen , Jiaming Yang , Fuzeng Yang , Qingjie Wang , Zhijie Liu , Zhengdao Liu

Returning the entire straw to the field can lead to excessive buildup, obstructing the seeding process and reducing quality. To address this, technologies like straw granulation and strip application enhance straw decomposition and soil organic matter. However, differing sizes of granulated straw can impact seeding quality. This paper presents a straw-crushing device with a differential counter roller that breaks long straw particles during rotation. It also includes trenching shovels, covering discs, and compaction wheels for practical mechanised application. The discrete element method (DEM) was used to simulate the straw crushing capacity and analyse the factors affecting the crushing rate. The work determined that the centre distance between the two rollers is 99 mm, the teeth height H is 15 mm, teeth width b₁ is 10 mm, and teeth thickness b₂ is 10 mm. It was found that the minimal variation in the straw crushing rate varied between 0.77 and 1.77 kg s⁻¹. Optimal crushing rates are achieved when the upper roller's rotation speed ranges from 100 to 200 r·min⁻¹ and the lower roller's speed ranges from 300 to 400 r·min⁻¹. A simulation model is also developed to analyse the mechanised strip application process. Through single-factor tests and orthogonal test methods, the operational parameters were optimised. The findings indicated that an upper roller speed of 150 r·min⁻¹, a lower roller speed of 300 r·min⁻¹, a strip application depth of 150 mm, and a forward speed of 5 km h⁻¹ resulted in a straw crushing rate of 33.6 %. The uniformity variation coefficient of strip application is determined to be 14.4 %, which complies with the strip application requirements. Field validation of the test parameters yielded an average coefficient of variation of 14.9 %; the average crushing rate of granulated straw is 41.5 %, with an error margin of 0.5 % and 7.9 % compared to field tests. The optimised parameters achieve the necessary standards for mechanised strip application, providing valuable technical support for developing new granulated straw strip application methodologies.

将整个秸秆还田会导致秸秆过度堆积，阻碍播种过程，降低质量。为了解决这个问题，秸秆造粒和条施等技术可以促进秸秆分解和土壤有机质。然而，不同大小的粒状秸秆会影响播种质量。本文介绍了一种带有差动计数器的秸秆粉碎装置，该装置在旋转过程中粉碎长秸秆颗粒。它还包括挖沟铲、覆盖盘和用于实际机械化应用的压实轮。采用离散元法（DEM）对秸秆破碎能力进行了数值模拟，分析了影响秸秆破碎率的因素。工作确定两辊之间的中心距离为99 mm，齿高H为15 mm，齿宽b1为10 mm，齿厚b2为10 mm。秸秆破碎率的最小变化在0.77 ~ 1.77 kg s−1之间。当上辊转速为100 ~ 200 r·min - 1，下辊转速为300 ~ 400 r·min - 1时，破碎率最佳。建立了模拟模型，对带钢机械化应用过程进行了分析。通过单因素试验和正交试验对工艺参数进行了优化。结果表明：当上辊速度为150 r·min−1，下辊速度为300 r·min−1，带材施深为150 mm，前进速度为5 km h−1时，秸秆破碎率为33.6%；确定带材均匀度变化系数为14.4%，符合带材使用要求。对试验参数进行现场验证，平均变异系数为14.9%；颗粒状秸秆的平均破碎率为41.5%，与现场试验相比误差为0.5%和7.9%。优化后的参数达到机械化条带化应用的必要标准，为开发新的粒状秸秆条带化应用方法提供了宝贵的技术支持。

{"title":"Experimental research on mechanised strip application process based on DEM of compressed granulated straw","authors":"Guibin Chen , Jiaming Yang , Fuzeng Yang , Qingjie Wang , Zhijie Liu , Zhengdao Liu","doi":"10.1016/j.biosystemseng.2025.104274","DOIUrl":"10.1016/j.biosystemseng.2025.104274","url":null,"abstract":"<div><div>Returning the entire straw to the field can lead to excessive buildup, obstructing the seeding process and reducing quality. To address this, technologies like straw granulation and strip application enhance straw decomposition and soil organic matter. However, differing sizes of granulated straw can impact seeding quality. This paper presents a straw-crushing device with a differential counter roller that breaks long straw particles during rotation. It also includes trenching shovels, covering discs, and compaction wheels for practical mechanised application. The discrete element method (DEM) was used to simulate the straw crushing capacity and analyse the factors affecting the crushing rate. The work determined that the centre distance between the two rollers is 99 mm, the teeth height <em>H</em> is 15 mm, teeth width <em>b</em><sub>1</sub> is 10 mm, and teeth thickness <em>b</em><sub>2</sub> is 10 mm. It was found that the minimal variation in the straw crushing rate varied between 0.77 and 1.77 kg s<sup>−1</sup>. Optimal crushing rates are achieved when the upper roller's rotation speed ranges from 100 to 200 r·min<sup>−1</sup> and the lower roller's speed ranges from 300 to 400 r·min<sup>−1</sup>. A simulation model is also developed to analyse the mechanised strip application process. Through single-factor tests and orthogonal test methods, the operational parameters were optimised. The findings indicated that an upper roller speed of 150 r·min<sup>−1</sup>, a lower roller speed of 300 r·min<sup>−1</sup>, a strip application depth of 150 mm, and a forward speed of 5 km h<sup>−1</sup> resulted in a straw crushing rate of 33.6 %. The uniformity variation coefficient of strip application is determined to be 14.4 %, which complies with the strip application requirements. Field validation of the test parameters yielded an average coefficient of variation of 14.9 %; the average crushing rate of granulated straw is 41.5 %, with an error margin of 0.5 % and 7.9 % compared to field tests. The optimised parameters achieve the necessary standards for mechanised strip application, providing valuable technical support for developing new granulated straw strip application methodologies.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"259 ","pages":"Article 104274"},"PeriodicalIF":5.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997568","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

Online multi-view multispectral detection for early bruised apple 早伤苹果在线多视点多光谱检测

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-09-01 DOI: 10.1016/j.biosystemseng.2025.104273

Jia-Yong Song , Ze-Sheng Qin , Chang Ma , Li-Feng Bian , Chen Yang

Online multispectral dynamic inspection is crucial for smart agriculture, particularly in acquiring multispectral image data across the entire surface of fruits during the inspection process. This study focuses on early bruises in apples, presenting an online multispectral multi-surface imaging strategy. The proposed strategy is based on an imaging model using two side mirrors, combined with an imaging sensor with a lens-filter array. This configuration enables the rapid capture of spatial texture and multispectral information from the multiple viewing directions for a sample in a single imaging process of one CCD. During the design process, a monochromatic LED-based integrating sphere optical system is introduced to uniformly illuminate the entire surface of the apple samples. Based on this, a mathematical model is established for the side mirror layout and system geometric parameters to determine the system configuration that scans the sample surface. In practical applications, the proposed method achieved an effective classification rate of 91 % for three quality categories of apples—sound, slightly bruised, and severely bruised—at a detection speed of about 3 per second. These results suggest that this study provides potential technical support for apple quality monitoring in smart agriculture.

在线多光谱动态检测对于智能农业至关重要，特别是在检测过程中获取整个水果表面的多光谱图像数据。本研究的重点是苹果的早期瘀伤，提出了一种在线多光谱多表面成像策略。所提出的策略是基于使用两个侧镜的成像模型，结合带有透镜滤光器阵列的成像传感器。这种配置可以在一个CCD的单一成像过程中从多个观察方向快速捕获样品的空间纹理和多光谱信息。在设计过程中，引入了基于单色led的积分球光学系统，均匀地照亮苹果样品的整个表面。在此基础上，建立了侧镜布局和系统几何参数的数学模型，确定了扫描样品表面的系统配置。在实际应用中，该方法在检测速度约为3个/秒的情况下，对健全、轻度擦伤和严重擦伤三个质量类别的苹果实现了91%的有效分类率。本研究为智能农业中苹果品质监测提供了潜在的技术支持。

{"title":"Online multi-view multispectral detection for early bruised apple","authors":"Jia-Yong Song , Ze-Sheng Qin , Chang Ma , Li-Feng Bian , Chen Yang","doi":"10.1016/j.biosystemseng.2025.104273","DOIUrl":"10.1016/j.biosystemseng.2025.104273","url":null,"abstract":"<div><div>Online multispectral dynamic inspection is crucial for smart agriculture, particularly in acquiring multispectral image data across the entire surface of fruits during the inspection process. This study focuses on early bruises in apples, presenting an online multispectral multi-surface imaging strategy. The proposed strategy is based on an imaging model using two side mirrors, combined with an imaging sensor with a lens-filter array. This configuration enables the rapid capture of spatial texture and multispectral information from the multiple viewing directions for a sample in a single imaging process of one CCD. During the design process, a monochromatic LED-based integrating sphere optical system is introduced to uniformly illuminate the entire surface of the apple samples. Based on this, a mathematical model is established for the side mirror layout and system geometric parameters to determine the system configuration that scans the sample surface. In practical applications, the proposed method achieved an effective classification rate of 91 % for three quality categories of apples—sound, slightly bruised, and severely bruised—at a detection speed of about 3 per second. These results suggest that this study provides potential technical support for apple quality monitoring in smart agriculture.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"258 ","pages":"Article 104273"},"PeriodicalIF":5.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932857","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

Modelling machine-induced soil deformation in forest soils using stump proximity and machine learning 利用树桩接近和机器学习模拟机器引起的森林土壤变形

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-08-27 DOI: 10.1016/j.biosystemseng.2025.104255

Gunta Grube , Stefano Grigolato , Jari Ala-Ilomäki , Johanna Routa , Harri Lindeman , Rasmus Astrup , Bruce Talbot

Soil deformation is a key challenge in sustainable timber harvesting, particularly in environments with low bearing capacity. In mechanised forestry, this issue is especially pronounced in peatlands, where rutting arises from soil displacement and root shearing within the soft, organic substrate. While tree roots are known to reinforce soil, the specific role of stump-root systems in mitigating rut formation remains underexplored. This study examines the influence of stump presence on rut depth using Unmanned Aerial Vehicle (UAV) based digital terrain models (DTMs), manual field measurements, spatial modelling, and machine learning techniques. UAV-derived rut depth estimates were first compared with manual data, revealing slightly lower values in deeper ruts, particularly in curved trails, with mean discrepancies of 3 cm. Statistical analysis confirmed that cumulative stump influence significantly reduced rut depth, with a small to medium effect in straight trails (

ɛ^{2}

= 0.04–0.20) and a moderate to large effect in curved trails (

ɛ^{2}

= 0.02–0.32). Machine learning models achieved high predictive accuracy (

R^{2}

= 0.69–0.85), identifying stump-related variables and soil shear modulus as key predictors of rut formation. These findings emphasise the importance of incorporating stump-root reinforcement into forest planning to optimise machine path selection and minimise soil disturbance. Future research should refine species-specific reinforcement models and explore advanced root mapping techniques, such as ground-penetrating radar (GPR), to strengthen decision-support tools for sustainable forestry.

Science4Impact statement (S4IS)

This study presents a spatially informed methodology to evaluate the influence of tree stump-root systems on rut formation in peatland soils. By integrating UAV mapping and machine learning, this study enables the predictive identification of low-impact areas, reducing site disturbance and supporting climate-smart forestry. These findings offer a practical starting point and a potential tool for optimising skid trail layout, improving operational efficiency, and minimising soil disturbance and site damage. The approach supports evidence-based decision-making in peatland conservation, helping align forest operations with broader environmental and climate goals.

土壤变形是可持续木材采伐的关键挑战，特别是在承载力低的环境中。在机械化林业中，这个问题在泥炭地尤其明显，那里的车辙是由土壤位移和柔软的有机基质内的根系剪切引起的。虽然已知树根可以加固土壤，但残根系统在减轻车辙形成方面的具体作用仍未得到充分探索。本研究使用基于无人机（UAV）的数字地形模型（dtm）、人工现场测量、空间建模和机器学习技术来研究树桩存在对车辙深度的影响。首先将无人机得出的车辙深度估计值与人工数据进行比较，发现更深的车辙深度估计值略低，特别是在弯曲的轨迹上，平均误差为3厘米。统计分析证实，累积残桩影响显著降低了车辙深度，在直道中影响小到中等，在弯道中影响中等，在弯道中影响较大，在弯道中影响较大。机器学习模型的预测精度很高（R2 = 0.69-0.85），识别出树桩相关变量和土壤剪切模量是车辙形成的关键预测因子。这些发现强调了将树桩根加固纳入森林规划以优化机器路径选择和减少土壤干扰的重要性。未来的研究应完善特定树种的加固模型，探索先进的根系测绘技术，如探地雷达（GPR），以加强可持续林业的决策支持工具。本研究提出了一种基于空间信息的方法来评估泥炭地土壤树桩-根系对车辙形成的影响。通过集成无人机测绘和机器学习，该研究能够预测识别低影响区域，减少现场干扰并支持气候智能型林业。这些发现为优化滑轨布局、提高作业效率、减少土壤干扰和场地破坏提供了一个实用的起点和潜在的工具。该方法支持泥炭地保护的循证决策，帮助森林作业与更广泛的环境和气候目标保持一致。

{"title":"Modelling machine-induced soil deformation in forest soils using stump proximity and machine learning","authors":"Gunta Grube , Stefano Grigolato , Jari Ala-Ilomäki , Johanna Routa , Harri Lindeman , Rasmus Astrup , Bruce Talbot","doi":"10.1016/j.biosystemseng.2025.104255","DOIUrl":"10.1016/j.biosystemseng.2025.104255","url":null,"abstract":"<div><div>Soil deformation is a key challenge in sustainable timber harvesting, particularly in environments with low bearing capacity. In mechanised forestry, this issue is especially pronounced in peatlands, where rutting arises from soil displacement and root shearing within the soft, organic substrate. While tree roots are known to reinforce soil, the specific role of stump-root systems in mitigating rut formation remains underexplored. This study examines the influence of stump presence on rut depth using Unmanned Aerial Vehicle (UAV) based digital terrain models (DTMs), manual field measurements, spatial modelling, and machine learning techniques. UAV-derived rut depth estimates were first compared with manual data, revealing slightly lower values in deeper ruts, particularly in curved trails, with mean discrepancies of 3 cm. Statistical analysis confirmed that cumulative stump influence significantly reduced rut depth, with a small to medium effect in straight trails (<span><math><msup><mrow><mi>ɛ</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.04–0.20) and a moderate to large effect in curved trails (<span><math><msup><mrow><mi>ɛ</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.02–0.32). Machine learning models achieved high predictive accuracy (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.69–0.85), identifying stump-related variables and soil shear modulus as key predictors of rut formation. These findings emphasise the importance of incorporating stump-root reinforcement into forest planning to optimise machine path selection and minimise soil disturbance. Future research should refine species-specific reinforcement models and explore advanced root mapping techniques, such as ground-penetrating radar (GPR), to strengthen decision-support tools for sustainable forestry.</div><div><strong>Science4Impact statement (S4IS)</strong></div><div>This study presents a spatially informed methodology to evaluate the influence of tree stump-root systems on rut formation in peatland soils. By integrating UAV mapping and machine learning, this study enables the predictive identification of low-impact areas, reducing site disturbance and supporting climate-smart forestry. These findings offer a practical starting point and a potential tool for optimising skid trail layout, improving operational efficiency, and minimising soil disturbance and site damage. The approach supports evidence-based decision-making in peatland conservation, helping align forest operations with broader environmental and climate goals.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"258 ","pages":"Article 104255"},"PeriodicalIF":5.3,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908251","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

Monitoring and blockage diagnosis in axial flow threshing and separation device under variable feed conditions 变进料条件下轴流脱粒分离装置的监测与堵塞诊断

IF 5.3 1区农林科学 Q1 AGRICULTURAL ENGINEERING

Biosystems Engineering

Pub Date : 2025-08-27 DOI: 10.1016/j.biosystemseng.2025.104262

Yongle Zhu , Zheng Ma , Zhiping Wu , Zelin Zhang , Yaoming Li , Liang Wang , Yu Pan

To prevent blockage in axial flow threshing and separation devices caused by varying material moisture and feeding rates while simplifying monitoring and diagnostic system, a test bench was used to collect vibration signals from four monitoring points of devices, analyse blockage tendencies under different conditions. Signals were denoised and reconstructed with the Slime Mould Algorithm and Variational Mode Decomposition, and segmented with overlapping moving time windows. Time, frequency, and time-frequency domain features were extracted to assess device operating status and sensitivity of signal changes at different monitoring points. Findings revealed that the duration of a slight blockage tendency was long under normal moisture content and small increments of feeding rate. With high moisture content and large increments of feeding rate, the duration of slight blockage tendency will decrease and quickly enter a severe blockage tendency state, with continued feeding resulting in immediate blockage. The monitoring point directly below the concave grate exhibited the most sensitive signal changes, with the largest waveform variations and standard deviation deviations. Feature dimensionality reduction was performed using Relief-F algorithm, and Bayesian-optimised machine learning models were trained for state identification. The diagnostic model of a monitoring point directly below the concave grate demonstrated high diagnostic accuracy, recall, and reliability, indicative of an effective monitoring point. The Bayesian-optimised Support Vector Machine model achieved the best performance, with 85.1 % and 93.6 % accuracy under different conditions and rapid prediction speeds (53000 and 40000 obs s⁻¹). This met the requirements for a simplified, accurate, and fast online monitoring system.

为了防止物料含水率和进料率变化引起轴流脱粒分离装置堵塞，同时简化监测诊断系统，利用试验台采集了轴流脱粒分离装置四个监测点的振动信号，分析了不同工况下的堵塞趋势。利用黏菌算法和变分模态分解对信号进行去噪和重构，并用重叠运动时间窗对信号进行分割。提取时间、频率和时频域特征，评估设备在不同监测点的运行状态和信号变化的灵敏度。结果表明，在正常含水率和小进料速率下，轻度堵塞趋势持续时间较长。含水率高，进料速率增量大，轻度堵塞倾向持续时间缩短，迅速进入严重堵塞倾向状态，继续进料，立即堵塞。凹栅正下方监测点的信号变化最为敏感，波形变化和标准差偏差最大。使用Relief-F算法进行特征降维，并训练贝叶斯优化的机器学习模型进行状态识别。凹栅正下方监测点的诊断模型具有较高的诊断准确率、召回率和可靠性，表明监测点是有效的。贝叶斯优化的支持向量机模型取得了最好的性能，在不同条件下的准确率分别为85.1%和93.6%，预测速度快（53000和40000 obs - 1）。这满足了简化、准确、快速的在线监测系统的要求。

{"title":"Monitoring and blockage diagnosis in axial flow threshing and separation device under variable feed conditions","authors":"Yongle Zhu , Zheng Ma , Zhiping Wu , Zelin Zhang , Yaoming Li , Liang Wang , Yu Pan","doi":"10.1016/j.biosystemseng.2025.104262","DOIUrl":"10.1016/j.biosystemseng.2025.104262","url":null,"abstract":"<div><div>To prevent blockage in axial flow threshing and separation devices caused by varying material moisture and feeding rates while simplifying monitoring and diagnostic system, a test bench was used to collect vibration signals from four monitoring points of devices, analyse blockage tendencies under different conditions. Signals were denoised and reconstructed with the Slime Mould Algorithm and Variational Mode Decomposition, and segmented with overlapping moving time windows. Time, frequency, and time-frequency domain features were extracted to assess device operating status and sensitivity of signal changes at different monitoring points. Findings revealed that the duration of a slight blockage tendency was long under normal moisture content and small increments of feeding rate. With high moisture content and large increments of feeding rate, the duration of slight blockage tendency will decrease and quickly enter a severe blockage tendency state, with continued feeding resulting in immediate blockage. The monitoring point directly below the concave grate exhibited the most sensitive signal changes, with the largest waveform variations and standard deviation deviations. Feature dimensionality reduction was performed using Relief-F algorithm, and Bayesian-optimised machine learning models were trained for state identification. The diagnostic model of a monitoring point directly below the concave grate demonstrated high diagnostic accuracy, recall, and reliability, indicative of an effective monitoring point. The Bayesian-optimised Support Vector Machine model achieved the best performance, with 85.1 % and 93.6 % accuracy under different conditions and rapid prediction speeds (53000 and 40000 obs s<sup>−1</sup>). This met the requirements for a simplified, accurate, and fast online monitoring system.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"258 ","pages":"Article 104262"},"PeriodicalIF":5.3,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903120","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