Wavelet Neural Network Based on NARMA-L2 Model for Prediction of Thermal Characteristics in a Feed System

Research of thermal characteristics has been a key issue in the development of high-speed feed system. Most of the work carried out thus far is based on the principle of directly mapping the thermal error against the temperature of critical machine elements irrespective of the operating conditions. But recent researches show that different sets of operating parameters generated significantly different error values even though the temperature of the machine elements generated was similar. As such, it is important to develop a generic thermal error model which is capable of evaluating the positioning error induced by different operating parameters. This paper ultimately aims at the development of a comprehensive prediction model that can predict the thermal characteristics under different operating conditions （feeding speed, load and preload of ballscrew） in a feed system. A novel wavelet neural network based on feedback linearization autoregressive moving averaging （NARMA-L2） model is introduced to predict the temperature rise of sensitive points and thermal positioning errors considering the different operating conditions as the model inputs. Particle swarm optimization（PSO） algorithm is brought in as the training method. According to ISO230-2 Positioning Accuracy Measurement and ISO230-3 Thermal Effect Evaluation standards, experiments under different operating conditions were carried out on a self-made quasi high-speed feed system experimental bench HUST-FS-001 by using Pt100 as temperature sensor, and the positioning errors were measured by Heidenhain linear grating scale. The experiment results show that the recommended method can be used to predict temperature rise of sensitive points and thermal positioning errors with good accuracy. The work described in this paper lays a solid foundation of thermal error prediction and compensation in a feed system based on varying operating conditions and machine tool characteristics.

The effect of enzymes on release of trace elements in feedstuffs based on in vitro digestion model for monogastric livestock

Background: This experiment was conducted to study the effect of different feed enzymes(phytase,xylanase,β-glucanase) on release rate of trace elements(Fe,Cu,Mn and Zn) in 6 commonly used feedstuffs(corn,wheat,barley,soybean meal,wheat bran,wheat middlings) by using an in vitro model,simulating the digestive processes in stomach for 2 h and then in small intestine for 6 h at 39 °C.Results: Phytase raised(P < 0.05) the release rate of Cu and Zn in corn,Cu,Zn and Mn in wheat,Cu in barley,Cu,Zn and Mn in soybean meal,Zn,Fe in wheat bran and Zn,Fe,Mn in wheat middlings.The release rate of various trace elements in feedstuffs was increased after xylanase addition.Compared with the control group,the release rate of soluble Cu in corn,wheat,barley and soybean meal,soluble Zn in corn,wheat and wheat middlings and soluble of Mn in corn,wheat,barley and wheat bran increased(P < 0.05) after xylanase treatment.After the treatment of β-glucanase,the release rate of soluble Cu in corn,wheat and wheat bran,soluble Fe in barley,soybean meal and wheat bran and soluble Mn in corn and wheat bran all increased(P < 0.05) compared with the control group.In each feedstuff,after corresponding enzyme treatment,the contents of phytic acid,xylan and β-glucan were significantly lower than those of the control group(P < 0.05).Conclusions: Results showed that bound trace elements in feedstuffs can be released by feed enzymes.It may be necessary to take the trace elements in feedstuffs into account in the actual feed preparation including feed enzymes.

Mathematical modeling and analytical solution for stretching force of automatic feed mechanism

Load of an automatic feed mechanism is composed of the stretching force of feed belt at the entrance to lower flexible guidance and the friction force between feed belt and flexible guidance. A mathematical model for computing the load was presented. An optimization problem was formulated to determine the attitude of the flexible guidance based on the principle that the potential energy stored in the system was the minimum at the equilibrium. Then the friction force was obtained according to the attitude of guide leaves and the moving velocity of the feed belt and the friction factor. Consequently, the load of the automatic feed mechanism can be calculated. Finally, an example was given to compute the load when the horizontal and elevating firing angles of the automation were respectively 45° and 30°. The computing result can be a criterion to determine the designing parameters of automat.

Development of a prediction model for enteral feeding intolerance in intensive care unit patients:A prospective cohort study

BACKGROUND Enteral nutrition(EN)is essential for critically ill patients.However,some patients will have enteral feeding intolerance(EFI)in the process of EN.AIM To develop a clinical prediction model to predict the risk of EFI in patients receiving EN in the intensive care unit.METHODS A prospective cohort study was performed.The enrolled patients’basic information,medical status,nutritional support,and gastrointestinal(GI)symptoms were recorded.The baseline data and influencing factors were compared.Logistic regression analysis was used to establish the model,and the bootstrap resampling method was used to conduct internal validation.RESULTS The sample cohort included 203 patients,and 37.93%of the patients were diagnosed with EFI.After the final regression analysis,age,GI disease,early feeding,mechanical ventilation before EN started,and abnormal serum sodium were identified.In the internal validation,500 bootstrap resample samples were performed,and the area under the curve was 0.70(95%CI:0.63-0.77).CONCLUSION This clinical prediction model can be applied to predict the risk of EFI.

Model study of log feeding technology at the dam of Ertan Hydropower Station in China

The log float technology from timber depot at the reservoir to log feeding rolls was studied by model tests. The model test was taken with the rule of gravitation similitude and ratio of 1∶10. Main parameters, like the amount of tug boats, hydro-accelerators and the structure of feeding rolls, were determined. The more suitable float process is put forward and the reliable basis for the design is supplied.

OPTIMAL MODEL OF COMBINED PHASE CENTER FOR HORN FEEDS AND ITS COMPUTATIONAL METHOD

A definition of combined phase center for horn feeds is given.Formulas of E-planeand H-plane combined phase center for conical horns and the corresponding Optimal model arepresented,and a fast optimization method for solving this model is described.By using thismethod,the phase center of corrugated horn is discussed and calculated,and the variation of thephase center with distance and operating frequency is given.

Modeling a high output marine steam generator feedwater control system which uses parallel turbine-driven feed pumps

Parallel turbine-driven feedwater pumps are needed when ships travel at high speed. In order to study marine steam generator feedwater control systems which use parallel turbine-driven feed pumps, a mathematical model of marine steam generator feedwater control system was developed which includes mathematical models of two steam generators and parallel turbine-driven feed pumps as well as mathematical models of feedwater pipes and feed regulating valves. The operating condition points of the parallel ttu-bine-driven feed pumps were calculated by the Chebyshev curve fit method. A water level controller for the steam generator and a rotary speed controller for the turbine-driven feed pumps were also included in the model. The accuracy of the mathematical models and their controllers was verified by comparing their results with those from a simulator.

Modified coupled map car-following model and its delayed feedback control scheme

A modified coupled map car-following model is proposed, in which two successive vehicle headways in front of the considering vehicle is incorporated into the optimal velocity function. The steady state under certain conditions is obtained. An error system around the steady state is studied further. Moreover, the condition for the state having no traffic jam is derived. A new control scheme is presented to suppress the traffic jam in the modified coupled map car-following model under the open boundary. A control signal including the velocity differences between the following and the considering vehicles, and between the preceding and the considering vehicles is used. The condition under which the traffic jam can be well suppressed is analysed. The results are compared with that presented by t^onishi et al. （the KKH model）. The simulation results show that the temporal behaviour obtained in our model is better than that in the KKH model. The simulation results are in good agreement with the theoretical analysis.

上消化道肿瘤患者术后早期肠内营养喂养不耐受风险预测模型的构建

目的分析上消化道肿瘤患者术后发生早期肠内营养喂养不耐受的危险因素,建立风险预测模型。方法回顾性分析2021年5月至2022年12月收治于上海市某二级甲等医院普外科的210例上消化道肿瘤患者病例资料,所有患者术后均行早期肠内营养支持治疗。根据是否发生术后早期肠内营养喂养不耐受,分为不耐受组(n=121)与耐受组(n=89),比较两组患者间的差异。运用logistic回归分析上消化道肿瘤患者术后早期肠内营养喂养不耐受的危险因素,并构建风险预测模型,同时通过受试者工作特征(ROC)曲线下面积和霍斯默-莱梅肖(H-L)评价模型的校准度及区分度。结果上消化道肿瘤患者术后早期肠内营养喂养不耐受的发生率为57.62%,多因素logistic回归分析结果显示,低蛋白血症、高血糖、胃肠内补钾、术后疼痛评分≥4分、术后3 d后下床活动为上消化道肿瘤患者术后发生早期肠内营养喂养不耐受的独立危险因素。H-L检验结果显示,χ^(2)=6.523(P=0.367),模型ROC曲线下面积为0.916(P<0.001),灵敏度为0.857,特异度为0.832。结论上消化道肿瘤患者术后早期肠内营养喂养不耐受的发生率较高,本研究所构建的风险预测模型预测效能较好,能够帮助临床医护人员识别肠内营养喂养不耐受高危人群,为早期采取护理干预措施提供参考依据。

同轴送粉激光熔覆的粉末熔化过程建模与仿真

同轴送粉激光熔覆中,粉末与激光的交互作用会直接影响熔覆成形的精度与质量,红外摄像无法直接获得激光内粉末的熔化行为,因此通过分析粉末对热量的吸收情况,使用高速摄像系统采集粉末熔化的动态行为,并建立粉末熔化过程的动态解析模型,通过仿真分析激光功率对不同熔化阶段的影响,及粉末进入熔池时的温度特征.结果表明,高速摄像系统采集粉末在激光中的动态熔化行为中存在“固态→固液两相态→液态”3个典型熔化特征阶段,粉末熔化动态行为可以使用数学解析模型解析,而不同阶段的热物理行为具有粉末与激光热交互作用的动态解析模型,分析了激光功率、离焦量、载粉气流量对粉末熔化行为的影响,同时通过仿真分析不同激光功率对各个特征阶段持续时间的影响,预测粉末颗粒到达基材的温度分布,发现激光功率从100 W增加至1 500 W时,粉末进入熔池的温度呈非线性变化,温度从750℃增加至3 250℃.

HIV/AIDS患者肠内营养治疗喂养不耐受发生风险预测模型的构建与验证

目的调查HIV/AIDS患者肠内营养治疗喂养不耐受的影响因素,建立列线图预测模型并进行验证。方法回顾性分析2015年1月1日至2021年9月30日南宁市第四人民医院收治的HIV/AIDS住院患者临床资料,通过二分类Logistic回归模型,探索HIV/AIDS患者肠内营养治疗喂养不耐受的危险因素,构建列线图预测模型并验证评价。结果共纳入174例HIV/AIDS患者,其中76例HIV/AIDS患者发生早期肠内营养喂养不耐受(43.68%)。多因素分析显示,平均动脉压≤80 mmHg[OR=2.822,95%CI(1.267,6.287)]、急性生理学与慢性健康状况评分Ⅱ>15分[OR=5.625,95%CI(1.435,22.048)]、机械通气应用[OR=5.459,95%CI(2.046,14.564)]、高效抗反转录病毒治疗[OR=2.428,95%CI(1.118,5.275)]、肌松剂应用[OR=3.833,95%CI(1.758,8.357)]、CD4^(+)T细胞计数≤200个·μL^(-1)[OR=3.785,95%CI(1.126,12.724)]、抗生素使用数量>2种[OR=2.365,95%CI(1.039,5.384)]是HIV/AIDS患者肠内营养治疗发生喂养不耐受的影响因素。列线图预测模型AUC值为0.849[95%CI(0.794,0.905)],最大约登指数为0.555时,最佳临界值为0.331,灵敏度为88.16%,特异度为67.35%;校准曲线、决策曲线评价模型具有较好的一致性及获益性。结论本研究构建的HIV/AIDS患者肠内营养治疗喂养不耐受风险预测模型可为医护人员快速识别HIV/AIDS患者喂养不耐受发生风险、及时采取预防性护理措施提供参考依据。

船载投料系统饲料颗粒流落点预测

【目的】为解决网箱养殖中使用船载投料系统的饲料颗粒流落点控制问题,提出一种用于实时分割饲料颗粒流轨迹并精确预测其落点的方法(MLBP)。【方法】考虑到输料管管内参数及饲料颗粒流出口参数获取难度较大,本研究采用高速相机获取饲料颗粒流轨迹图像,并利用提出的混合网络模型分割饲料颗粒流轨迹,以获取轨迹关键信息;为准确预测饲料颗粒流落点,利用BP神经网络的优势,将轨迹信息及投料口高度作为其输入,实现饲料颗粒流落点的预测。【结果】与相关研究方法对比,结合混合网络模型与BP神经网络的MLBP方法的系统单次运行时间降低95%,同时落点预测准确度达到96%,落点的平均误差范围与平均误差百分比也分别降低32.0%和30.5%。【结论】本研究提出的MLBP方法预测精度及实时性均能满足网箱投饵作业需求,可为相关研究提供参考。

基于“虚拟教学+双语教学”的教学方式探索——以扬州大学“牧草及饲料作物栽培学”实验教学为例

“牧草及饲料作物栽培学”是草学专业的核心专业课程。双语教学是现代高校人才培育和满足与国际接轨需求的一种重要的教学模式。虚拟现实教学则是突破传统教学局限性,基于先进数字技术实现教学目标的全新教学手段。“虚拟现实教学+双语教学”的多元教学是“双一流”建设背景下草学专业课程教学改革的必然趋势。以精心设计的课前、课中及课后教学课件为实例,以“学生为中心”为教学切入点,探讨多元教学模式如何促进“双一流”建设背景下的草学专业课“牧草及饲料作物栽培学”教学实践。

基于超前滞后环节附加前馈阻尼的VSG控制策略

虚拟同步发电机(virtual synchronous generator,VSG)在引入同步机二阶转子运动方程,增大电力系统等效惯量的同时,也引入了同步发电机的振荡特性,有功低频振荡等动态稳定性问题也随之而来。引入调速侧电力系统稳定器(governor power system stabilizer,GPSS)能有效抑制VSG的功率低频振荡,但其在超调量及调节时间方面的控制效果仍有待提高。通过建立VSG的小信号模型从极点配置角度分析其稳定性,揭示基于GPSS的VSG控制策略在功率动态响应上存在较高超调和较长调节时间的原因。基于此,参考GPSS控制思想,提出了一种基于超前滞后环节附加前馈阻尼补偿的虚拟同步发电机控制策略。并从理论上分析验证了所提控制策略在不影响系统稳态特性的前提下,能够提供调整自由度更高的正阻尼,在有效地抑制功率超调的同时提高了系统的调节速度,从而更好地抑制了有功功率的低频振荡。最后通过MATLAB/Simulink进行对比仿真,仿真结果与理论分析结果一致,证明了所提控制策略的正确性和有效性。

基于价值链的饲料企业营销模式分析

市场对动物源性食品的旺盛需求有效提高了饲料企业的经济效益,这对实现饲料企业的可持续发展具有重要的推动作用。但在复杂多变的市场环境下,饲料产品同质化、产能过剩、需求多元化等现实情况都对饲料企业的市场营销提出了挑战。为了更好地帮助饲料企业创造价值,需要从价值链的角度入手,对饲料企业的营销模式进行分析,力求通过提高产品销量来为饲料企业的可持续发展奠定基础。

干湿料饲喂方式下商品猪生产和健康指标模型构建与比较

【目的】精准饲养是当前生猪养殖产业的大趋势,但在实际应用中存在缺乏前期基础数据、各阶段湿料饲喂的采食量不明确等问题。本研究旨在探究干湿料饲喂猪只的生长发育规律、采食量动态模型和健康情况。【方法】选取132头平均初始体质量为(10.56±1.21)kg的商品猪,随机分为2组,每组11次重复,每次重复6头猪,2组分别饲喂干料和湿料,试验周期为120 d。通过Logistic、Gompertz和Von Bertalanffy 3种模型分析拟合干湿料饲喂猪只的生长曲线和采食量动态模型,并对干湿料饲喂猪只的健康情况进行研究。【结果】Von Bertalanffy模型拟合干料饲喂猪只生长曲线的效果最好,拟合度为0.999;Gomperz模型能更好地拟合湿料饲喂猪只的生长曲线,拟合度为0.999。Gomperz模型拟合干料饲喂猪只采食量模型的效果最好,拟合度为0.851;Von Bertalanffy模型能更好地拟合湿料饲喂猪只的采食量模型,拟合度为0.988。湿料饲喂保育仔猪的腹泻率和腹泻指数显著低于干料饲喂(P<0.05)。【结论】本研究构建了干湿料饲喂猪只的生长曲线和采食量模型,拟合效果较好;探明了干湿饲喂猪只的健康情况,为猪只的精准饲养提供了数据支撑。

近红外光谱技术在反刍动物营养中的应用

近红外光谱技术以其快速、便捷、无损、绿色等优点,成为动物饲料营养价值评定研究中最具潜力的方法之一。本文简述了近红外光谱技术应用于饲料营养成分含量的测定、饲料的掺假鉴别及定量分析、饲料在瘤胃的降解情况、饲料在动物体内的消化代谢情况和反刍动物采食量预测方面的有效性和准确性,并指出了后续应对已有模型进行不断优化。最终得出结论:目前近红外光谱技术结合化学计量学在饲料营养成分含量的测定、掺假鉴别和定量分析方面的准确性和稳定性较高,而对饲料在瘤胃的降解情况、动物体内消化率和采食量的预测方面,其准确性还有待进一步提高。

急性胰腺炎患儿肠内营养喂养不耐受的因素分析及风险预测模型的建立

目的通过分析急性胰腺炎(AP)患儿发生肠内营养喂养不耐受(ENFI)的影响因素,建立ENFI发生风险预测模型。方法采取目的抽样法收集2017年6月—2020年6月南京医科大学附属儿童医院消化科收治的AP患儿401例为研究对象,采用7∶3比例随机分为建模组280例和验证组121例,建模组根据是否发生ENFI分为ENFI亚组113例和非ENFI亚组167例。收集临床资料,采用单因素与多因素Logistic回归分析AP患儿发生ENFI的影响因素;采用R软件构建预测AP患儿发生ENFI的列线图模型,并评估模型预测效能。结果ENFI亚组患儿的腹内压(IAP)≤20 cmH_(2)O、APACHEⅡ评分≤20分、血清Alb水平>25 g/L、肠内营养开始时间≤72 h、CVP≤12 cmH_(2)O的比例均小于非ENFI亚组(χ^(2)/P=8.450/0.004、7.453/0.006、8.717/0.003、8.551/0.003、6.771/0.009),未添加可溶性纤维比例大于非ENFI亚组(χ^(2)/P=7.448/0.006);多因素Logistic回归分析显示,IAP>20 cmH_(2)O、未添加可溶性纤维、血清Alb水平≤25 g/L、肠内营养开始时间>72 h、CVP>12 cmH_(2)O是影响AP患儿发生ENFI的独立危险因素[OR(95%CI)=2.111(1.139~3.913)、2.019(1.036~3.935)、1.989(1.081~3.660)、1.907(1.032~3.524)、2.112(1.170~3.812)],并构建列线图模型;建模组的验证结果显示,ROC曲线下面积(AUC)为0.886(95%CI 0.850~0.922),模型预测AP患儿发生ENFI风险与实际风险具有较好的一致性。外部验证的AUC为0.890(95%CI 0.853~0.926),模型预测AP患儿发生ENFI风险与实际风险具有较好的一致性(χ^(2)=6.130,P=0.419)。结论基于IAP>20 cmH_(2)O、未添加可溶性纤维、血清Alb水平≤25 g/L、肠内营养开始时间>72 h、CVP>12 cmH 2O构建AP患儿发生ENFI的预测模型具有较好的预测价值,可为早期预测AP患儿ENFI的发生风险提供参考。

基于视频和BCE-YOLO模型的奶牛采食行为检测

【目的】动物采食行为是一个重要的动物福利评价指标,本研究旨在解决复杂饲养环境下奶牛采食行为识别精度差、特征提取不充分的问题,实现对奶牛采食行为的自动监控。【方法】本文提出了一种基于改进BCEYOLO模型的识别方法,该方法通过添加BiFormer、CoT、EMA 3个增强模块,提高YOLOv8模型特征提取的能力,进一步与优于Staple、SiameseRPN算法的Deep SORT算法结合,实现对奶牛采食时头部轨迹的跟踪。在奶牛采食过程的俯视和正视视频中提取11288张图像,按照6∶1比例分为训练集和测试集,构建采食数据集。【结果】改进的BCE-YOLO模型在前方和上方拍摄的数据集上精确度分别为77.73%、76.32%,召回率分别为82.57%、86.33%,平均精确度均值分别为83.70%、76.81%;相较于YOLOv8模型,整体性能提升6~8个百分点。Deep SORT算法相比于Staple、SiameseRPN算法,综合性能提高1~4个百分点;并且改进的BCE-YOLO模型与Deep SORT目标跟踪算法结合良好,能对奶牛采食行为进行准确跟踪且有效地抑制了奶牛ID(Identity document)的变更。【结论】本文提出的方法能有效解决复杂饲养环境下奶牛采食行为识别精度差、特征提取不充分的问题,为智能畜牧与精确养殖提供重要参考。

硅片磨床伺服进给系统仿真模型与分析

在硅片磨削时,硅片加工质量与硅片磨床的进给系统性能密切相关。为了提升硅片磨床进给系统的精度和稳定性,提出了采用上位机、运动控制卡、伺服驱动器、位置传感器进行闭环控制进给的技术方案。研究了伺服系统和机械系统两者之间的相互耦合关系,建立了动力学模型,搭建了基于PID控制的三闭环控制系统,采用MATLAB中Simulink模块对进给系统进行仿真分析。仿真结果表明,磨床进给系统速度波动量在1%以下满足硅片磨削对进给精度的要求。