科创中国

The current research of real-time observation for vehicle roll steer angle and compliance steer angle(both of them comprehensively referred as the additional steer angle in this paper) mainly employs the linear vehicle dynamic model, in which only the lateral acceleration of vehicle body is considered. The observation accuracy resorting to this method cannot meet the requirements of vehicle real-time stability control, especially under extreme driving conditions. The paper explores the solution resorting to experimental method. Firstly, a multi-body dynamic model of a passenger car is built based on the ADAMS/Car software, whose dynamic accuracy is verified by the same vehicle's roadway test data of steady static circular test. Based on this simulation platform, several influencing factors of additional steer angle under different driving conditions are quantitatively analyzed. Then ε-SVR algorithm is employed to build the additional steer angle prediction model, whose input vectors mainly include the sensor information of standard electronic stability control system(ESC). The method of typical slalom tests and FMVSS 126 tests are adopted to make simulation, train model and test model's generalization performance. The test result shows that the influence of lateral acceleration on additional steer angle is maximal(the magnitude up to 1°), followed by the longitudinal acceleration-deceleration and the road wave amplitude(the magnitude up to 0.3°). Moreover, both the prediction accuracy and the calculation real-time of the model can meet the control requirements of ESC. This research expands the accurate observation methods of the additional steer angle under extreme driving conditions.

P2P流媒体占用大量带宽,且容易传播病毒,有必要对其进行识别.分析了Abacus方法的不足,提出一种基于SVM概率输出的P2P流媒体识别法P-Abacus.P-Abacus将待识别样本属于已知应用可能性的大小反映在概率输出上.对输出结果进行排序,根据最大概率,判决样本是属于最大概率类应用还是未知应用,或是需要进一步判断.若需进一步判断,则通过计算前两大类构建SVM概率输出的差值,来判断样本是属于其中的一类,还是未知应用.由于SVM概率输出包含大量可用信息,使得P-Abacus具有更好的识别效果.实验表明,P-Abacus比Abacus具有更高的识别率和更低的误判率,且时间开销增加有限.

摔倒作为人体活动的一部分,是影响人体健康的一大因素,尤其对病人和老年人而言,摔倒检测至关重要。基于MEMS三轴加速度传感器采集的人体活动加速度信号,提出了一种基于固定阈值的信号幅度向量滑动平均法SVMSA。该方法根据人体活动时的加速度信号特征,利用预先设定的阈值对加速度信号幅度向量SVM的滑动平均SVMSA进行判决,同时使用差分信号幅度域DSMA区分快速跑步等剧烈运动,准确实现了人体的摔倒检测。主要优势在于分析并区别了人体快速跑步等剧烈运动对摔倒检测的影响。通过对8位实验者的测试,该算法实现了94.4%的精确度。实验表明该算法能够较为准确地实现人体的摔倒检测。

针对瓦斯涌出量受多因素影响,传统的预测方法难以建立准确的数学模型,导致预测精度低这一问题。提出一种经改进的粒子群算法( MPSO)优化的基于柯西分布加权的最小二乘支持向量机( CWLS-SVM)算法来预测非线性动态瓦斯涌出量。柯西分布加权的最小二乘支持向量机根据预测误差的统计特性,确定加权规则参数,以达到赋予训练样本不同权值的目的。并用MPSO算法对CWLS-SVM模型的正则化参数λ和高斯核参数σ寻优。利用无线传感器网络采集到的各项历史数据进行实例分析。结果表明,该算法有效的提高了瓦斯涌出量的预测精度,降低了预测误差,为煤矿瓦斯防治提供理论支持。