基于DE-SVM的船舶航迹预测模型

为提高船舶航迹预测精度,解决准确建模难度大和神经网络易陷入局部最优的问题,考虑实时获取目标船AIS数据较少的特点,提出一种基于支持向量机(support vector machine,SVM)的航迹预测模型。选择AIS数据中的航速、航向和船舶经纬度作为样本特征变量;采用小波阈值去噪的方法处理训练数据;采用差分进化(differential evolution,DE)算法对模型内部参数寻优以提高模型收敛速度和预测精度。选取天津港实船某段航迹的AIS数据,比较基于DE-SVM与基于BP神经网络的航迹预测模型的仿真结果。结果表明,基于DE-SVM的航迹预测模型具有更高的预测精度,简单、可行、高效,且耗时少。     

数控机床人性化设计的研究

数控机床的人性化设计就是在人机工程的原则指导下,探讨和应用人的行为、能力、本能极限和其他的特性来对数控机床进行设计,创造一种良好的人机互动关系,体现数控机床对人性需求的关注。文章从人机工程的角度对数控机床人性化设计的内涵进行相应的分析,得到数控机床人性化设计的研究思路。     

多功能电子防丢器的设计与实现

随着现代生活节奏的加快,人们遗失东西的现象经常发生,防遗失产品也就应运而生．文中设计并实现了一款多功能电子防丢器,它由母机和子机两部分组成,子机置于防丢物品上,母机由主人随身携带,具有防丢和寻找功能．子机留有的外接插孔可与其他传感器设备相连,构成相应的防盗报警系统．电路主要采用集成芯片制作,所以具有电路简单,工作性能稳定,功耗及成本低等优点．     

基于贝叶斯网络的验证激励向量生成研究

为了解决传统数字芯片验证环节中基于仿真的验证（或动态验证）功能覆盖率收敛速度慢的缺点,提出一种新的以功能覆盖为导向的测试用例生成方法,该方法基于贝叶斯网络和机器学习技术,可实现从覆盖模型到测试用例生成器反馈回路的自动关闭,在 DUT 的验证过程中,使用该方法为所测试的设计生成新的激励。实验结果表明,基于贝叶斯网络的 CDG 技术测试用例使用较少,覆盖率收敛更快,与传统基于仿真的验证技术相比,测试用例数量减少了 43%。基于贝叶斯网络的 比于传统动态验证技术而言其芯片功能验证更完善。     

Fault diagnosis model based on fuzzy support vector machine combined with weighted fuzzy clustering

A fault diagnosis model is proposed based on fuzzy support vector machine (FSVM) combined with fuzzy clustering (FC).Considering the relationship between the sample point and non-self class,FC algorithm is applied to generate fuzzy memberships.In the algorithm,sample weights based on a distribution density function of data point and genetic algorithm (GA) are introduced to enhance the performance of FC.Then a multi-class FSVM with radial basis function kernel is established according to directed acyclic graph algorithm,the penalty factor and kernel parameter of which are optimized by GA.Finally,the model is executed for multi-class fault diagnosis of rolling element bearings.The results show that the presented model achieves high performances both in identifying fault types and fault degrees.The performance comparisons of the presented model with SVM and distance-based FSVM for noisy case demonstrate the capacity of dealing with noise and generalization.     

温控炭焙对武夷岩茶生化品质的影响

温控炭焙结合传统炭焙的优点,并结合现代温度控制技术,对于保持茶叶品质的稳定和高效利用能源具有重要作用。采用武夷岩茶为材料,在130℃、120℃和110℃温度下分别烘焙6h,分析不同炭焙温度对武夷岩茶水仙感官品质、主要理化成分的影响。结果表明：以温控炭焙130℃6h处理的茶样感官审评得分最高。氨基酸、茶多酚、咖啡碱含量呈下降趋势,水浸出物含量差异不显著。汤色RGB值CK处理最大,A3处理最小。     

Assessment of leg muscles mechanical capacities: Which jump,loading, and variable type provide the most reliable outcomes?

This study aimed to explore the strength of the force–velocity (F–V) relationship of lower limb muscles and the reliability of its parameters (maximum force [F₀], slope [a], maximum velocity [V₀], and maximum power [P₀]). Twenty-three men were tested in two different jump types (squat and countermovement jump: SJ and CMJ), performed under two different loading conditions (free weight and Smith machine: Free and Smith) with 0, 17, 30, 45, 60, and 75?kg loads. The maximum and averaged values of F and V were obtained for the F–V relationship modelling. All F–V relationships were strong and linear independently whether observed from the averaged across the participants (r?≥?0.98) or individual data (r?=?0.94–0.98), while their parameters were generally highly reliable (F₀ [CV: 4.85%, ICC: 0.87], V₀ [CV: 6.10%, ICC: 0.82], a [CV: 10.5%, ICC: 0.81], and P₀ [CV: 3.5%, ICC: 0.93]). Both the strength of the F–V relationships and the reliability of their parameters were significantly higher for (1) the CMJ over the SJ, (2) the Free over the Smith loading type, and (3) the maximum over the averaged F and V variables. In conclusion, although the F–V relationships obtained from all the jumps tested were linear and generally highly reliable, the less appropriate choice for testing the F–V relationship could be through the averaged F and V data obtained from the SJ performed either in a Free weight or in a Smith machine. Insubstantial differences exist among the other combinations tested.     

试论保守力具势的证明

本文借鉴热力学中一种巧妙的证明方法,用直观的物理论证给出了保守力具势的充分性证明,克服了以往在理论力学课程中只有利用复杂的数学工具才能进行充分性证明,学生难以理解的缺点．     

简易网球自动发球机的研制与应用

针对网球训练的技术要求,研制了简易网球自动发球机,并对其基本结构、发球的频率、角度、力量等工作原理及性能特点进行了合理的分析。实验证明简易网球自动发球机对丰富教学手段,提高教学质量具有很好的实用价值和指导意义.     

基于KNN的图像自动分类模型研究

所谓图像自动分类是指利用图像自动分类器把待分类的图像分配到预定义的图像类的过程。用于图像自动分类的方法有多种。其中K近邻算法是一种基于实例学习的方法,是一种较理想的自动分类器。本文在它的基础上提出了图像自动分类模型,整个图像自动分类过程包括图像预处理、特征表示、机器学习和图像分类4个步骤。表1。图1。参考文献13。