A strategy for out-of-roundness damage wheels identification in railway vehicles based on sparse autoencoders

Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness(OOR) damage wheels, such as wheel flats and polygonal wheels. This automatic damage identification algorithm is based on the vertical acceleration evaluated on the rails using a virtual wayside monitoring system and involves the application of a two-step procedure. The first step aims to define a confidence boundary by using(healthy) measurements evaluated on the rail constituting a baseline. The second step of the procedure involves classifying damage of predefined scenarios with different levels of severities. The proposed procedure is based on a machine learning methodology and includes the following stages:(1) data collection,(2) damage-sensitive feature extraction from the acquired responses using a neural network model, i.e., the sparse autoencoder(SAE),(3) data fusion based on the Mahalanobis distance, and(4) unsupervised feature classification by implementing outlier and cluster analysis. This procedure considers baseline responses at different speeds and rail irregularities to train the SAE model. Then, the trained SAE is capable to reconstruct test responses(not trained) allowing to compute the accumulative difference between original and reconstructed signals. The results prove the efficiency of the proposed approach in identifying the two most common types of OOR in railway wheels.

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning method.We demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model structure.However,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial obstacle.This issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data security.To address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

Research of Genetic Training Algorithm for Identifying Mechanical Failure Modes within the Framework of Case-Based Reasoning

The combination of case-based reasoning （CBR） and genetic algorithm （GA） is considered in the problem of failure mode identification in aeronautical component failure analysis. Several imple- mentation issues such as matching attributes selection, similarity measure calculation, weights learning and training evaluation policies are carefully studied. The testing applications illustrate that an accuracy of 74.67 % can be achieved with 75 balanced-distributed failure cases covering 3 failure modes, and that the resulting learning weight vector can be well applied to the other 2 failure modes, achieving 73.3 % of recognition accuracy. It is also proved that its popularizing capability is good to the recognition of even more mixed failure modes.

Filtering algorithm and direction identification in relative position estimation based on induction loop-cable

A filtering algorithm and direction identification method are presented for the positioning system of the mid-speed maglev train. Considering the special structure of the mid-speed maglev train, the ground position estimation method is adopted for its traction system. As the train is running, the induction loop-cable receives the signal sent by the on-board antenna to detect the position and direction of the train. But the height of the on-board antenna relative to the loop-cable is highly vulnerable to the change of the suspension height and the magnetic field produced by the traction during traveling, which may lead to amplitude fluctuation of the received signal. Consequently, the position estimation may be inaccurate. Therefore, a discrete second-order nonlinear trackdifferentiator is proposed based on the boundary characteristic curves, and the new differentiator could also extract the running direction of the train for the traction system. The experimental results show that the tracking differentiator can effectively filter out the signal interference and can provide accurate direction signal.

Hybrid force control of astronaut rehabilitative training robot under active loading mode

In order to mitigate the effects of space adaptation syndrome(SAS) and improve the training efficiency of the astronauts, a novel astronaut rehabilitative training robot(ART) was proposed. ART can help the astronauts to carry out the bench press training in the microgravity environment. Firstly, a dynamic model of cable driven unit(CDU) was established whose accuracy was verified through the model identification. Secondly, to improve the accuracy and the speed of the active loading, an active loading hybrid force controller was proposed on the basis of the dynamic model of the CDU. Finally, the actual effect of the hybrid force controller was tested by simulations and experiments. The results suggest that the hybrid force controller can significantly improve the precision and the dynamic performance of the active loading with the maximum phase lag of the active loading being 9° and the maximum amplitude error being 2% at the frequency range of 10 Hz. The controller can meet the design requirements.

Fault Current Identification of DC Traction Feeder Based on Optimized VMD and Sample Entropy

A current identification method based on optimized variational mode decomposition(VMD)and sample entropy(SampEn)is proposed in order to solve the problem that the main protection of the urban rail transit DC feeder cannot distinguish between train charging current and remote short circuit current.This method uses the principle of energy difference to optimize the optimal mode decomposition number k of VMD;the optimal VMD for DC feeder current is decomposed into the intrinsic modal function(IMF)of different frequency bands.The sample entropy algorithm is used to perform feature extraction of each IMF,and then the eigenvalues of the intrinsic modal function of each frequency band of the current signal can be obtained.The recognition feature vector is input into the support vector machine model based on Bayesian hyperparameter optimization for training.After a large number of experimental data are verified,it is found that the optimal VMD_SampEn algorithm to identify the train charging current and remote short circuit current is more accurate than other algorithms.Thus,the algorithm based on optimized VMD_SampEn has certain engineering application value in the fault current identification of the DC traction feeder.

Small-Sided Games and Technical Skills in Soccer Training： Systematic Review and Implications for Sport and Physical Education Practitioners

High-level of technical skills and tactical behaviour are key factors for an optimal performance in soccer games. About the most used and innovative training methods, the small-sided games （SSGs） seem to be a worthy and valid methodology to train simultaneously many skills by reproducing several conditions of a real match. Accordingly, the aim of this study was to conduct a systematic review of the available literature to lead an improved understanding in the usefulness of SSGs for improving technical skills in soccer. To ensure a rigorous and reliable approach, the review was performed according to PRISMA （Preferred Reporting Items for Systematic review and Meta-analyses） guidelines. 1031 records were initially identified, but only 26 studies were further included in the review. Moreover, other two studies were added after a check of the bibliography of two major reviews. So, each of these studies was analysed according to the aforementioned guidelines and using inclusion criteria related to SSG and training in soccer. The current analysis provided several indications and recommendations for coaches and trainers of soccer teams in order to improve several technical skills by means of the use of SSGs. Furthermore, several evidences for using SSGs in school environment are also provided.

Torque effect on vibration behavior of high-speed train gearbox under internal and external excitations

The high-speed train transmission system,experiencing both the internal excitation originating from gear meshing and the external excitation originating from the wheel-rail interaction,exhibits complex dynamic behavior in the actual service environment.This paper focuses on the gearbox in the high-speed train to carry out the bench test,in which various operat-ing conditions(torques and rotation speeds)were set up and the excitation condition covering both internal and external was created.Acceleration responses on multiple positions of the gearbox were acquired in the test and the vibration behavior of the gearbox was studied.Meanwhile,a stochastic excitation modal test was also carried out on the test bench under different torques,and the modal parameter of the gearbox was identified.Finally,the sweep frequency response of the gearbox under gear meshing excitation was analyzed through dynamic modeling.The results showed that the torque has an attenuating effect on the amplitude of gear meshing frequency on the gearbox,and the effect of external excitation on the gearbox vibration cannot be ignored,especially under the rated operating condition.It was also found that the torque affects the modal param-eter of the gearbox significantly.The torque has a great effect on both the gear meshing stiffness and the bearing stiffness in the transmission system,which is the inherent reason for the changed modal characteristics observed in the modal test and affects the vibration behavior of the gearbox consequently.

Tutor培训对医学院教师成长发展的促进作用

研讨型教学已成为我国医学院医学教学改革的主要内容。东南大学医学院自2011年起在本科教育中逐步开展研讨型教学改革,包括PBL、CBL和RBL,并建立了完整的Tutor培训与评估体系,为医学教学改革提供了有力保障。学院在Tutor培训与评估体系的建立及教师的发展成长方面积累了一定经验,本文就此作一初步探讨,以期为我国的医学教师发展提供借鉴。

Sound Source Localisation for a High-Speed Train and Its Transfer Path to Interior Noise

Noise is one of the key issues in the operation of high-speed railways, with sound source localisation and its transfer path as the two major aspects. This study investigates both the exterior and interior sound source distribution of a high-speed train and presents a method for performing the contribution analysis of airborne sound with regard to the interior noise. First, both exterior and interior sound source locations of the high-speed train are identified through in-situ measurements. Second, the sound source contribution for di erent regions of the train and the relationships between the exterior and interior noises are analysed. Third, a method for conducting the contribution analysis of airborne sound with regard to the interior noise of the high-speed train is described. Lastly, a case study on the sidewall area is carried out, and the contribution of airborne sound to the interior noise of this area is obtained. The results show that, when the high-speed train runs at 310 km/h, dominant exterior sound sources are located in the bogie and pantograph regions, while main interior sound sources are located at the sidewall and roof. The interior noise, the bogie area noise and the sound source at the middle of the coach exhibit very similar rates of increase with increasing train speed. For the selected sidewall area, structure-borne sound dominates in most of the 1/3 octave bands.

An investigation into high-speed train interior noise with operational transfer path analysis method

Passengers’demands for riding comfort have been getting higher and higher as the high-speed railway develops.Scientific methods to analyze the interior noise of the high-speed train are needed and the operational transfer path analysis(OTPA)method provides a theoretical basis and guidance for the noise control of the train and overcomes the shortcomings of the traditional method,which has high test efficiency and can be carried out during the working state of the targeted machine.The OTPA model is established from the aspects of“path reference point-target point”and“sound source reference point-target point”.As for the mechanism of the noise transmission path,an assumption is made that the direct sound propagation is ignored,and the symmetric sound source and the symmetric path are merged.Using the operational test data and the OTPA method,combined with the results of spherical array sound source identification,the path contribution and sound source contribution of the interior noise are analyzed,respectively,from aspects of the total value and spectrum.The results show that the OTPA conforms to the calculation results of the spherical array sound source identification.At low speed,the contribution of the floor path and the contribution of the bogie sources are dominant.When the speed is greater than 300 km/h,the contribution of the roof path is dominant.Moreover,for the carriage with a pantograph,the lifted pantograph is an obvious source.The noise from the exterior sources of the train transfer into the interior mainly through the form of structural excitation,and the contribution of air excitation is non-significant.Certain analyses of train parts provide guides for the interior noise control.

青少年篮球训练运动中关节损伤预警模型

为准确预警青少年在篮球训练中的关节损伤,构建了青少年篮球训练运动中关节损伤预警模型。使用基于独立成分分析和经验模态分解的关节受力信号去噪方法,保留有效信号,在CNN网络中提取关节受力特征后,输入LSTM网络识别关节受力信号的损伤级别后通过蜂鸣器预警。结果显示:所构建模型对青少年篮球训练运动中关节损伤级别识别结果符合实际,预警错误次数为0次,预警结果具有可信度。

“双导师制”在病理专硕研究生实践创新能力培养中的探索

专业学位研究生教育是培养高层次应用型专门人才的主渠道,学校自从2015年开始招收病理专硕研究生以来,在病理专硕培养与住院医师规范化培训“双轨合一”过程中遇到培训模式单一、缺乏科研思维训练、基础病理与临床病理隔离等。针对以上问题,本课题整合基础医学院病理学系和医院病理科的骨干力量,组建双导师团队,将“双导师制”培养模式贯穿于临床病理学研究生培养全过程,包括研究生录取、培养方案制定、病理规范化培训、科研训练、开题、毕业答辩等各个环节,充分发挥学校和医院的优势,取得一定成效。该培养模式不仅促进基础与临床的深度融合,而且对培养具有较高病理诊断水平、解决临床问题能力的高素质临床病理人才有积极的推动作用,有力提升了病理专硕研究生的实践创新能力。

导师制在血液内科规范化培训护士带教中的应用

目的 探索导师制在血液内科规范化培训护士带教工作中的应用效果。方法 研究以2021年3月—2023年3月轮转到重庆医科大学附属第二医院血液内科的规范化培训护士70名为研究对象,对每轮规范化培训护士采用随机数表法分为对照组和观察组,其中对照组34名,观察组36名。对照组接受传统的带教模式,由资深护士指导学习和实践;观察组实施导师制带教模式,由专业导师负责培养和辅导。通过对比2组护士的理论知识、操作技能、综合素质和教学满意度等指标,评价导师制教学模式在规范化培训护士培训中的应用效果。结果 观察组的理论知识成绩为(93.00±2.28)分、操作技能成绩为(93.36±1.66)分、综合素质考核成绩为(97.11±1.47)分、教学满意度为100%,高于对照组[理论知识成绩(89.65±6.71)分、操作技能成绩(91.44±3.93)分、综合素质考核成绩(94.18±2.89)分、教学满意度83.60%],差异有统计学意义(P <0.05)。结论 对血液科规范化培训护士实施导师制教学模式,可以使规范化培训护士的专科理论知识、操作技能、综合素质等方面的能力得到全面的提高。

导师组协同制联合分阶段递进培养模式在风湿免疫科住院医师规范化培训中的应用探索

目的探索导师组协同制联合分阶段递进培养模式在风湿免疫科住院医师规范化培训(简称“住培”)中的应用效果。方法选取2021年6月—2023年6月在风湿免疫科规范化培训的第一年住培学员40名,随机分为对照组(n=20)和试验组(n=20)。对照组采用常规培养模式,试验组采用导师组协同制联合分阶段递进培养模式。培训结束后,通过出科考核、综合评价和满意度调查评价培训效果。结果试验组出科考核总得分、理论考试、技能考试和病例分析题得分分别为(84.10±3.88)、(88.40±4.48)、(82.50±5.06)和(85.86±7.62)分,均高于对照组学员的(77.05±3.07)、(82.50±6.43)、(77.17±6.42)和(75.25±4.65)分,差异均有统计学意义(均P<0.05)。试验组综合评价总得分为(90.45±2.50)分,高于对照组的(86.60±3.56)分;试验组在临床能力及临床思维方面得分分别为(18.50±0.89)、(17.85±1.27)分,高于对照组的(17.10±1.62)、(16.85±1.31)分,差异有统计学意义(均P<0.05)。试验组住培学员对培训方法、师资力量及培训效果的满意度评价均高于对照组[95%vs.75%,100%vs.75%,95%vs.65%,均P<0.05]。结论导师组协同制联合分阶段递进培养模式在风湿免疫科住培中的应用效果较好,有助于提升学员的理论、技能水平以及临床思维能力,且得到学员认可。

面向工科高层次创新人才培养的导师能力提升研究

高层次创新人才培养需要优秀的研究生导师来实现,而导师能力的提升也是高层次创新人才培养的必要条件。该研究分析导师能力提升的困境,构建针对工科高层次创新人才培养的导师能力体系,并提出有效的导师能力提升路径。这些路径包括创新导师遴选机制、提高导师立德树人实效性、建立高效的导师培训机制以及构建跨学科导师交流机制。通过这些措施,期望提高导师的指导水平,促进研究生创新能力的培养,为高等教育改革提供参考借鉴。

基于轴箱高频振动的车轮不圆辨识方法研究

为实现对高速列车车轮高阶不圆的实时检测,研究了轴箱高频振动与车轮不圆的频谱特征和映射关系,采用频域积分方法对车轮不圆的幅值和阶次进行辨识.首先,通过静态测试和台架试验,研究我国高速铁路车轮多边形、钢轨波磨和轨道模态的表现形式;其次,通过高速列车长期服役性能跟踪试验,掌握转向架轴箱振动的时频特征和演化规律;最后,以现场出现车轮20阶多边形的车辆为研究对象,提出基于频域积分的车轮不圆阶次和幅值辨识方法.研究结果表明:CRTS-Ⅱ型轨道板钢轨三阶弯曲频率为592 Hz;列车以300 km/h运行时,20阶车轮多边形和136 mm波长钢轨波磨的响应频率分别为580 Hz和613 Hz;钢轨模态、车轮多边形以及钢轨波磨的振动主频较为集中,轴箱高频振动幅值随车速和镟后里程的增大而增大;采用加速度频域积分方法,从理论上可实现对车轮不圆幅值和阶次的辨识;基于线路实测轴箱加速度的20阶车轮多边形辨识结果与静态测试值相对误差不超过5%.

立德树人视域下研究生导师团队育人模式探索——以数学学科为例

研究生导师团队制度是提高研究生培养质量和推进研究生培养模式改革的一种有效形式,也是研究生导师进行学术紧密合作和跨学科交流的一个良好的平台。在立德树人视域下,以烟台大学数学学科研究生培养为例,针对研究生导师团队制度建设、课程思政融入研究生教育课程体系建设等进行了研究和探索,在教学过程中进行了全过程育人引导,完善了研究生的人格,夯实了其价值观,提升了其专业素养,形成了数学学科研究生导师团队育人新模式,并取得了初步成效。

改进粒子滤波跟踪的视听双模态语音识别仿真

噪声环境下视听语音不易被识别,为提升语音识别效果,提出改进粒子滤波跟踪的视听双模态语音识别方法。采用谱减法去除噪声数据,完成视听双模态语音的消噪处理;根据人语和唇动信息之间的相关性,采用改进粒子滤波跟踪方法提取视听双模态语音特征信息,构建transformer语音识别模型,将提取的特征信息输入到模型内实施并行训练,实现视听双模态语音的有效识别。实验结果表明,通过对上述方法开展信噪比测试、识别性能测试,验证了上述方法的可行性高、可靠性强。

纵深发展:导师引领下的医学硕士生分层培养探讨

通过对医学教育现状的深入分析,揭示出医学研究生教育面临的五大问题。提出了导师引领下的医学硕士生分层培养模式,深入探讨了其背后的理念。在策略实施上,分层教学中的职责被明确划分,尤其强调了导师与高年级学生的关键角色。为确保此模式的高效实施,建立了一套完善的培训计划,并引入定期的成果汇报与全面的评估机制。这不仅确保了教学任务的明确分配,还使得整个培养系统能够根据反馈进行持续优化。此培养模式为医学教育改革提供了新的视角和方法。