Multi-Head Attention Spatial-Temporal Graph Neural Networks for Traffic Forecasting

Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.

Flow patterns and boundary conditions for inlet and outlet conduits of large pump system with low head

The flow patterns in the inlet and outlet conduits have a decisive effect on the safe, stable, and highly efficient operation of the pump in a large pumping station with low head. The numerical simulation of three-dimensional （3D） turbulence flow in conduits is an important method to study the hydraulic performance and conduct an optimum hydraulic design for the conduits. With the analyses of the flow patterns in the inlet and outlet conduits, the boundary conditions of the numerical simulation for them can be determined. The main obtained conclusions are as follows： （i） Under normal operation conditions, there is essentially no pre-swirl flow at the impeller chamber inlet of an axial-flow pump system, based on which the boundary condition at the inlet conduit may be defined. （ii） The circulation at the guide vane outlet of an axial-flow pump system has a great effect on the hydraulic performance of the outlet conduit, and there is optimum circulation for the performance. Therefore, it is strongly suggested to design the guide vane according to the optimum circulation. （iii） The residual circulation at the guide vane outlet needs to be considered for the inlet boundary condition of the outlet conduit, and the value of the circulation may be measured in a specially designed test model.

Cross influence of discharge and circulation on head loss of conduit of pump system with low head

The relationship between the head loss and the discharge and circulation of the conduit of a pump system with low head is an important problem with an obvious influence on the improvement of its hydraulic performance. The velocity circulation from the pump guide vane makes the relationship more complicated, which has to be understood comprehensively. The results indicate that, under the condition of zero circulation, the head loss of the inlet and outlet conduits is in proportion to the square of discharge. Under the condition that the Reynolds number is satisfied with the resistant square area, the conduit loss is in proportion to the square of discharge for the similar working points with different speeds in a certain rotational speed range, indicating that the pump system efficiency is constant. The outlet conduit loss of design discharge for a pump system with low head depends on the velocity circulation from the guide vane exit, and the relationship between the loss and the circulation is an open curve with an upward direction, meaning that there is an optimal circulation for the loss. Under the condition of various working points for a pump system with low head, the head loss of the outlet conduit is under the cross influence of both the discharge and the circulation. As a result, the relationship between the head loss and the discharge is almost linear, and the mechanism needs to be further studied.

Preoperative defining system for pancreatic head cancer considering surgical resection

AIM: To provide appropriate treatment, it is crucial to share the clinical status of pancreas head cancer among multidisciplinary treatment members.METHODS: A retrospective analysis of the medical records of 113 patients who underwent surgery for pancreas head cancer from January 2008 to December 2012 was performed. We developed preoperative defining system of pancreatic head cancer by describing “resectability - tumor location - vascular relationship - adjacent organ involvement - preoperative CA19-9 (initial bilirubin level) - vascular anomaly”. The oncologic correlations with this reporting system were evaluated.RESULTS: Among 113 patients, there were 75 patients (66.4%) with resectable, 34 patients (30.1%) with borderline resectable, and 4 patients (3.5%) with locally advanced pancreatic cancer. Mean disease-free survival was 24.8 mo (95%CI: 19.6-30.1) with a 5-year disease-free survival rate of 13.5%. Pretreatment tumor size ≥ 2.4 cm [Exp(B) = 3.608, 95%CI: 1.512-8.609, P = 0.044] and radiologic vascular invasion [Exp(B) = 5.553, 95%CI: 2.269-14.589, P = 0.002] were independent predictive factors for neoadjuvant treatment. Borderline resectability [Exp(B) = 0.222, P = 0.008], pancreatic head cancer involving the pancreatic neck [Exp(B) = 9.461, P = 0.001] and arterial invasion [Exp(B) = 6.208, P = 0.010], and adjusted CA19-9 ≥ 50 [Exp(B) = 1.972 P = 0.019] were identified as prognostic clinical factors to predict tumor recurrence.CONCLUSION: The suggested preoperative defining system can help with designing treatment plans and also predict oncologic outcomes.

Fuzzy Sliding Mode Observer for Vehicular Attitude Heading Reference System

In low-cost Attitude Heading Reference Systems (AHRS), the measurements made by Micro Electro-Mechanical Systems (MEMS) type sensors are affected by uncertainties, noises and unknown disturbances. In this paper, considering the robustness of sliding mode observers against structured and unstructured uncertainties, and also exogenous inputs, the process of design and implementation of a sliding mode observer (SMO) is proposed based on a linearized model of the AHRS. To decrease the chattering phenomenon is the main difficulty of the SMO. Through smoothing the discontinuity term, the tracking performance of the observer is attenuated. Boundary layer technique, for example, using a saturation term, is the common smoother to remove the chattering drawbacks. However, through poor tracking performance, the high range chattering could not be removed by this method. Therefore, a knowledge-based Mamdani-type fuzzy SMO (FSMO) is proposed to decrease the chattering effects intelligently, which in turn could obtain the high accuracy tracking performance of the SMO. Following proving the stability of the proposed SMOs based on direct Lyapunov’s method, the performance of the proposed observers is compared with that of the extended Kalman filter through simulation and real experiments of an AHRS.

农田灌溉光伏水泵系统性能测试分析

【目的】探究农田灌溉光伏水泵系统综合用能需求特性,提高该系统性能可靠性和实用性。【方法】基于高效水泵和研发的逆变器,构建了农田灌溉光伏水泵系统,结合系统装置构成与运行特点,对不同扬程运行工况下的电性能参数和扬水效率特性及水泵流量与功率特性等进行测试分析。【结果】在一定太阳辐射强度范围内,调速运行的水泵流量与输出频率有较好一致性;稳定运行时段的水泵流量可达到2 m^(3)·h^(-1);定扬程24.8 m下,系统最大扬水效率达12.7%,日平均扬水效率11.6%,日扬水量13.1 m^(3);当扬程降低到14.0 m时,最大扬水效率和日平均效率分别比前者低3.2%和3.6%,表明减低扬程并不一定能提高系统扬水效率,但对输出流量有影响。【结论】该农田灌溉光伏水泵系统配置稳态和动态性能良好,扬水能力可满足省水微灌和植被绿化等基本农业生产需要。

高精度无心车床刀盘系统动态特性分析

无心车床是线性棒料表面处理的重要设备,刀盘系统是无心车床的重要部分,可以直接影响加工精度。这里以XF-WXC无心车床刀盘系统为研究对象,对刀盘系统进行模态分析,得到前六阶固有频率和模态振型,再通过设置不同工况转速,分析不同转速对刀盘系统模态频率的影响规律,并基于模态分析结果进行不同工况下的谐响应分析,研究刀盘系统的动态特性。分析结果表明:刀盘系统的刀尖位置为受力变形最大部位;易发生共振的激励频率在278Hz、449Hz和480Hz附近,在共振频率处的最大形变位移为0.036mm;同时利用实际切削实验结果验证仿真分析的可靠性。为无心车床的进一步优化设计提供理论依据。

面向对象技术的智能插秧机控制系统设计研究

以插秧机智能控制系统为研究对象,基于面向控制对象技术设计一种无人驾驶插秧机智能控制系统,并在水泥路面和水田两种不同环境中对插秧机进行性能试验测试。试验结果表明:在水泥路面上插秧机行进过程最大横向偏差小于50mm,最大航向偏差小于2°;在水田内插秧机行进过程最大横向偏差小于60mm,最大航向偏差小于3°,表明智能控制系统在使用过程中具有较高的可靠性和稳定性。

考虑激励幅值慢变的卷绕头转子系统动力学建模

卷绕头转子系统结构之间的耦合振动和时频变激励使振动问题十分复杂,为了更准确地研究其动力学特性,根据转子动力学理论,使用有限元方法建立了考虑多盘质量慢变的卷绕头非线性转子系统整机动力学模型,运用Newmark-β数值积分方法对其动力学特性求解,得到仅存在初始不平衡量以及卷装不良带来的激励频率、幅值慢变下的非线性动力学行为。通过分析轴心轨迹、时域波形和幅频特性曲线等结果,发现卷绕头转子系统对因卷装不良引起的激励幅值慢变较为敏感,出现新的频率成分。进一步对比分析了不同节点处的振动频谱,其结果可为卷绕头转子系统动力学设计和故障识别提供一定理论支持。

虚拟仿真技术在服装教学系统中的应用

围绕以体验为特征的学习模式,从5个方面进行服装教学系统的科学研究,解决服装教育行业关键技术问题。运用VR和AR技术、3D仿真技术、多媒体技术和集互联网技术于服装教学中取得了突破;对传统教学方法存在的问题进行深度研究,提出运用虚拟技术与教学各个环节密切结合的教学方法,有效地解决了教学资源浪费、学生学习兴趣不高、抬头率低、知识点难记等问题;开发了可支持教学各个环节的数字化教学平台;构建了完善的数字化教学系统、立体化教学资源库、虚实教学环境等系统,打破了实践教学中空间限制问题,实现了教材立体化、知识动态化、教学资源共享等功能。

Image-Based Methods for Interaction with Head-Worn Worker-Assistance Systems

In this paper, a mobile assistance-system is described which supports users in performing manual working tasks in the context of assembling complex products. The assistance system contains a head-worn display for the visualization of information relevant for the workflow as well as a video camera to acquire the scene. This paper is focused on the interaction of the user with this system and describes work in progress and initial results from an industrial application scenario. We present image-based methods for robust recognition of static and dynamic hand gestures in realtime. These methods are used for an intuitive interaction with the assistance-system. The segmentation of the hand based on color information builds the basis of feature extraction for static and dynamic gestures. For the static gestures, the activation of particular sensitive regions in the camera image by the user’s hand is used for interaction. An HMM classifier is used to extract dynamic gestures depending on motion parameters determined based on the optical flow in the camera image.

国有企业负责人经营业绩考核:制度特征分析与指标维度优化

业绩考核制度是落实企业责任、激发企业活力,并由此推动经济社会运行的重要机制。在对比股东主导和市场主导两种业绩考核逻辑,分析、认知国有企业负责人经营业绩考核制度的基础上,探究了业绩考核制度的本质特征,即国有企业负责人经营业绩考核制度是一项以考核为抓手的产权管理体系,是以目标设定与过程管理为核心的“自驱式”机制设计。强调应唯经营(而非考核)出业绩,并且正向激励与风险容错是业绩考核赋能企业发展的重要属性。现行业绩考核指标体系还难以引导国有企业高质量发展,建议围绕“产业布局、经营生态、创新驱动、风险管理、财务收益”五个维度进一步优化国有企业负责人经营业绩考核指标,且以年度考核为核心,形成导向明确、相对稳定、可预期的考核指标体系,并赋予企业负责人一定的自由裁量权,以提高考核制度效果,助力中国经济高质量发展。

九轴MEMS微型AHRS设计及其在矢量水听器中的应用

为了精确测量矢量水听器的姿态,设计了一种体积为20 mm×20 mm×5 mm、重量为1.8 g的微型航姿参考系统(AHRS)。利用微机电系统(MEMS)陀螺仪测定角速度,用四元数等效旋转矢量算法求解姿态角;采用扩展卡尔曼滤波器对姿态角估计值进行修正,并估计出MEMS陀螺仪的角速度漂移量。测试结果表明,所提AHRS的俯仰、横滚和航向角误差均方根值分别为0.04°、0.04°和0.34°。最后,将AHRS集成到矢量水听器中,并在加窗直方图统计波达方向估计算法中加入姿态修正。海上实验结果表明,对于航速为8 kn的目标船,经AHRS修正后的单矢量水听器方位角误差均方根值约为3.8°,减小了平台运动导致的方位测量误差。

基于IPOA-LSSVM模型的高压直流输电线路故障定位

故障定位在长距离高压直流输电系统中起着至关重要的作用.针对线路衰减系数计算不准和二次波头难以捕捉的问题,提出了一种改进鹈鹕优化算法(IPOA)优化最小二乘支持向量(LSSVM)的故障定位模型.根据行波衰减原理,推导故障距离和线路两端线模分量模极大值比的计算公式,发现二者具有非线性关系.使用LSSVM泛化二者之间的关系,将改进后的POA算法对LSSVM的关键参数进行寻优,建立IPOA-LSSVM故障定位模型.通过在两端采集故障信号,对其进行小波变换得到首波头幅值比作为模型的输入量,故障距离作为输出量进行仿真验证.仿真结果表明,该模型不受过渡电阻和故障类型的影响,能够可靠准确地定位.

基于上位机的工业机器人磨头工具坐标系自动标定技术研究

将工业机器人自动标定引入制造领域,能够在需要更换执行工具时实现快速标定,提高效率。针对目前工业机器人工具坐标系需要人工操作示教器进行标定的情况,设计了一种基于上位机的机器人磨头工具坐标系自动标定系统。该系统通过上位机软件实现对FANUC M20iA/20M工业机器人磨头工具坐标系的自动标定,包括工具中心点位置标定和工具中心点姿态标定,降低了示教器的介入,减少了标定时间。工具中心点位置标定通过四点标定法求解末端连杆坐标系位姿数据,应用最小二乘法求解磨头工具坐标系位置,采用四元数表示法降低计算量;工具中心点姿态标定保持工具坐标系位姿不变,记录不同标定点的末端连杆坐标系数据,并设计关节运动控制模块、设置坐标系模块和位姿标定线性移动模块。上位机通过Socket与机器人通信联动,发送控制指令,实现自动标定过程控制。仿真与实验结果表明,所设计标定系统能够对磨头工具坐标系实现自动高精度标定,标定精度±0.3 mm,满足实际加工需求,为后续的工业机器人磨抛加工应用奠定了基础。

行人过街事件网联HUD预警系统对驾驶行为的影响

为探索行人过街事件网联环境下平视显示预警系统在不同天气条件下对驾驶行为的影响,以论证预警系统的有效性。文中首先设计基线条件(Baseline)、低头显示(HDD)、平视显示(HUD)3种预警系统,依托驾驶模拟平台开发晴天和雾天天气条件下城市道路网联场景,通过实验测试提取驾驶行为参数;然后,从微观层面刻画行人过街事件网联HUD预警系统作用下驾驶行为的整个空间变化过程,分析预警系统和天气状况两种因素对驾驶行为的作用规律,构建包含避险阶段和恢复阶段的驾驶行为影响模式,提出了反映避险阶段安全水平、恢复阶段恢复水平以及全过程稳定水平等3个层面的综合指标体系,包括首次制动距离、最小冲突距离、恢复稳定时间、速度恢复量、最大减速度和最大加速度;最后,量化不同预警系统(Baseline/HDD/HUD)、天气状况(晴天/雾天)以及两因素间交互作用对驾驶行为的影响。结果表明:行人过街网联HUD预警系统对驾驶人在避险阶段和恢复阶段中的驾驶行为存在显著性作用,显著提高避险阶段驾驶行为的安全水平,同时对恢复阶段恢复效率具有明显的提升作用,也显著影响全过程运行特性的稳定水平;在雾天条件下行人过街网联HUD预警系统表现出更为明显的优势。

系统性红斑狼疮并发股骨头坏死的临床特点及危险因素分析

目的:探索系统性红斑狼疮(SLE)并发股骨头坏死(ONFH)患者的临床特点及其危险因素。方法:回顾性收集2016年1月至2022年6月在郑州人民医院治疗的SLE患者的临床资料。共17例并发ONFH的患者组成ONFH组,同时随机抽取51例未并发ONFH的SLE患者作为对照组。比较2组SLE患者的一般情况、临床特征、实验室检查,及治疗情况,并采用二元Logistics回归进行多因素分析。结果:ONFH组纤维蛋白原>3.5 g·L^(-1)、白细胞减少、抗β2GPⅠ抗体阳性的比例均高于对照组(P<0.05);ONFH组病情复发率(41.18%)明显高于对照组(15.69%),但差异无统计学意义(P=0.063)。多因素Logistic回归分析发现,病情复发(OR=4.194,95%CI=[1.053,16.702],P=0.042)、纤维蛋白原>3.5 g·L^(-1)(OR=9.974,95%CI=[1.457,68.286],P=0.019)是SLE并发ONFH的危险因素。进一步分组分析发现,病情复发的SLE患者中,糖皮质激素(GC)治疗时间及GC累积量>10 g的比例均高于未复发者(P<0.05)。结论:病情复发及纤维蛋白原>3.5 g·L^(-1)是SLE患者并发ONFH的危险因素。病情复发患者ONFH风险增高可能与GC治疗时间及累积量增加有关。

系统性红斑狼疮并发股骨头坏死危险因素列线图预测模型的建立和验证

背景:股骨头坏死是系统性红斑狼疮患者常见的并发症,若能早期对其发生风险进行预测与验证,将有助于避免或延缓股骨头坏死的发展。目的:分析系统性红斑狼疮患者并发股骨头坏死的危险因素,构建系统性红斑狼疮患者并发股骨头坏死的列线图预测模型并进行验证。方法:回顾性分析2013年1月至2022年12月首次就诊于河南中医药大学第一附属医院的914例系统性红斑狼疮患者的病历资料,根据是否发生股骨头坏死分为发生股骨头坏死组(n=100)和未发生股骨头坏死组(n=814)。采用单因素、LASSO回归和多因素Logistic回归分析筛选和确定系统性红斑狼疮并发股骨头坏死的危险因素。同时将数据集按照7∶3的比例随机分为训练集和测试集,并基于多因素Logistic回归分析结果,构建系统性红斑狼疮并发股骨头坏死的列线图预测模型。同时,使用受试者工作特征曲线、Hosmer-Lemeshow校准曲线和决策曲线对列线图的性能进行评估。结果与结论:①股骨头坏死组与未发生股骨头坏死组患者在系统性红斑狼疮病程、系统性红斑狼疮疾病活动度评分、狼疮性肾炎、呼吸系统受累、胃肠道受累、干燥综合征、骨质疏松、抗核糖核蛋白抗体阳性、补体C3降低、环磷酰胺、吗替麦考酚酯、生物抑制剂、糖皮质激素最大日剂量、糖皮质激素冲击治疗方面差异有显著性意义(P<0.05);②采用LASSO回归分析方法筛选出10个与系统性红斑狼疮并发股骨头坏死风险相关的预测变量,将其纳入多因素Logistic回归分析,结果显示系统性红斑狼疮病程、呼吸系统受累、干燥综合征、骨质疏松、抗核糖核蛋白抗体阳性、环磷酰胺、吗替麦考酚酯、生物抑制剂、糖皮质激素最大日剂量是系统性红斑狼疮患者发生股骨头坏死的独立危险因素(P<0.05);③训练集中预测发生风险的受试者工作特征曲线下面积为0.802(95%CI=0.742-0.862),测试集预测发生股骨头坏死风险受试者工作特征曲线下面积为0.811(95%CI=0.745-0.876);Hosmer-Lemeshow校准曲线拟合度较好(训练集,P=0.447;验证集,P=0.870);决策曲线显示使用列线图预测模型预测系统性红斑狼疮患者发生股骨头坏死的风险是有益的;④月经异常为女性系统性红斑狼疮患者并发股骨头坏死的危险因素之一;⑤此次研究结果提示,系统性红斑狼疮并发股骨头坏死的危险因素是多因素的,同时建立了一个包含9个危险因素的列线图预测模型,可将其用于预测系统性红斑狼疮患者发生股骨头坏死的风险;此外,首次报道了月经异常为女性系统性红斑狼疮并发股骨头坏死的危险因素之一。

开架发电机组冷却系统性能评估及结构改进

发电机组冷却系统流场分析及冷却性能评估有助于确认冷却系统总流量大小、冷却风量分配比例和冷却风流速分布特性,确保风道流量分配均匀和高温区域冷却良好。以某开架发电机组为研究对象,根据冷却系统设计要点对其冷却系统进行了初始布局结构设计,采用流体分析软件STAR-CCM+搭建了开架发电机组冷却系统流场分析模型。结果表明,缸头风道风量占发动机风道总风量的48.77%,箱体底部风量占比为6.7%,不利于发动机缸头和机油的冷却。通过调整导流罩与散热片间距、风扇罩更改为渐扩线形式、箱体开孔与散热片形状及导流的匹配改动、拉盘开孔增大等方式形成了开架发电机组冷却系统结构改进方案。改进后该机组缸头风道风量占发动机风道总风量的61.83%,箱体底部风量占比为13.04%。缸头风道风量及箱体底部风量基本满足发动机缸温及油温的冷却需求。发动机各风道冷却风速度分布均匀,电机冷却较好,空滤器进风均来源于外界冷却风;消声器表面风速分布均匀,不存在流动死区且靠排气管处风速较大。该发电机组冷却系统可对机组实现较好的冷却,保障机组正常且长时间运行。研究结果可为发电机组冷却系统布局设计及结构改进提供参考。

基于虹吸原理的水轮机顶盖排水系统优化

水轮机顶盖排水系统是机组安全、稳定运行的核心。当机组主供水方式为顶盖取水时,顶盖部分会出现漏水量大、潜水泵启动时间长、设备损耗率高的问题,同时会带来水淹厂房的风险。对此,从苗尾电站的实际运行情况出发,提出改造方案,并与改造前的运行情况进行对比分析。结果表明,改造后顶盖虹吸排水系统的耗电成本仅为改造前的0.976%,且改造成本短期内即可收回,同时,改造使水轮机顶盖排水效率提升84.2%。此次改造降低了设备的运维费用、延长了设备的使用寿命、显著提升了排水效率,为机组的安全、稳定运行提供了保障。