How to suppress the adverse effects of the uncertainty of renewable energy on power systems has always been a major technical requirement for power system operation, which has not been sufficiently considered in the traditional power system controller. Therefore, it is necessary to study the power system control under stochastic disturbances. In this paper, a controlled single-machine infinite-bus system model is established based on the stochastic averaging method of quasi-Hamiltonian systems, and a one-dimensional diffusion equation based on energy function with control item is obtained. According to the stochastic optimal control theory, the optimal control law of the system is obtained from the diffusion equation with the maximum reliability of the bounded fluctuation of the system as the control target. The effectiveness of the control method is verified by simulation.

在点云配准过程中,针对经典采样一致性(SAC-IA)粗配准算法耗时长和经典迭代最近点(ICP)精配准算法在待配准点云无初始位置下易陷入局部配准最优问题,提出了一种基于改进SAC-IA和ICP的快速高效点云配准算法.通过对待配准点云进行特征超体分割,对分割后的点云进行特征点提取,并进一步采用RANSAC方法去除错误匹配特征点,优化粗配准,最后采用双向KD-tree搜索优化ICP算法完成精配准.仿真实验表明,与经典SAC-IA和经典ICP算法相比,提出的算法可有效减少经典算法配准时间的 40%～60%,使最终的配准误差降低了 10-1 量级.

为了解决DeepLabv3p网络在检测汽车轮胎胎面花纹图像上呈现的边缘分割模糊、模型参数量大、训练速度慢等问题,提出了一种融合双重十字交叉注意力模块(URCCA)的轻量级图像分割算法——DeepLabNLAS.首先,采用STDC2代替DeepLabv3p网络中的特征提取网络来降低模型的参数量和体积,提升模型的训练速度;然后,将URCCA模块与ASPP(atous spatial pyramid pooling)模块并联来获取长距离密集的上下文信息;之后,将两个模块的特征图相融合送入解码器进行上采样恢复至输入图像的分辨率大小.实验结果表明,本文改进算法在语义分割公用数据集城市景观数据集Cityscapes以及本文数据集Tread_pattern上的效果都优于DeepLabv3p网络.在公用数据集Cityscapes上,DeepLabNLAS比DeepLabv3p网络和文献[9]的平均交并比分别提高了 1.22％和2.68％,在数据集Tread_pattern上分别提高了 2.13％和3.41％.

In this paper, a novel correlation analysis-based parameter learning scheme for Hammerstein nonlinear systems with output noise is presented. The developed Hammerstein system contains a static nonlinear block approximated by neural fuzzy network and a linear dynamic block modeled by transfer function, and parameter separation learning of the nonlinear block and linear block are realized by using combined signals. Firstly, based on the input and output of the separable signal, the correlation analysis algorithm is applied to estimate linear block parameters, thereby the interference of moving average noise is dramat-ically handled. Moreover, to improve parameter estimation precision of the learned Hammerstein system, multi-innovation theory and data filtering technology are introduced, and a data filtering-based multi -innovation stochastic gradient learning scheme is implemented for jointly estimating nonlinear block pa-rameters and noise model using random signals. Studies with a numerical simulation and a practical nonlinear process demonstrate the efficiency. In the numerical simulation, when the noise to signal ratio is less than 33.37%, estimate error of the linear block parameters using least squares method is less than 0.0796. In contrast, estimate error of the proposed method is less than 0.0338. For the modeling ability of the nonlinear block, the proposed method has an improvement of 67.07% than the MI-ESG method with innovation length of six. With regard to practical nonlinear process, when the concentration set value is 0.1, the rise time of the proposed method is 0.021 h, while the rise time of MPC and traditional PI controller and is 0.055 h and 0.143 h, respectively. (c) 2023 European Control Association. Published by Elsevier Ltd. All rights reserved.

Aiming at the low efficiency of manual sample inspection of dust suppression spraying quality in railway coal transportation, a detection system combining a high-pressure gas spraying and laser backscattering detection technology is presented in this paper. In terms of hardware, it is composed of gas excitation, powdered coal concentration detection and a control unit. The gas excitation device, including nozzle, camera and electric control platform, is designed for realizing the dust suppressant spraying quality detection by nozzle jet gas impacts on a coal surface. In terms of software, the programs for the system were developed based on the LabVIEW development platform, realizing the system parameter adjustment, detection signal display, gas excitation control and real-time data storage functions. Experimental results show that the gas pressure of the field test should be maintained at 0.9 MPa–1.23 MPa and the distance between the equipment and the target vehicle is more than 2000 mm. The proposed system can detect 3–4 times spot checks with a single carriage for the train under the speed of 3 m s −1 –5 m s −1 , which solves the problems of low efficiency and high risk of manual detection.

提出了一种基于高斯核函数的Hammerstein非线性系统参数辨识方法.Hammerstein非线性系统由一个静态非线性模块和一个动态线性模块串联组成,利用高斯核函数神经网络和传递函数模型分别建立Hammerstein系统的静态非线性模块和动态线性模块.首先,基于可分离信号的输入输出数据,采用相关性分析方法估计动态线性模块的参数,有效抑制噪声的干扰.其次,针对Hammerstein非线性系统的不可测噪声项,利用残差的估计值代替不可测变量,推导了递推增广最小二乘辨识方法,根据随机信号的输入输出数据辨识静态非线性模块和噪声模型的参数.仿真结果表明,针对有色噪声干扰的Hammerstein非线性系统,所提方法具有较好的辨识精度和鲁棒性.

为了剔除点云中离散点噪声和密集平面噪声且保留点云的特征,提出了一种改进的具有半径滤波和RANSAC优点的点云图像去噪新方法.首先利用体素下采样对原始点云数据进行精简,然后针对离散点噪声,使用半径滤波将其剔除,最后在保留原始RANSAC算法的基础上,引入高度信息参数对拟合出的平面进行区分,据此进一步剔除点云中的密集平面噪声.实验结果表明,经过本方法去噪后SNR比传统方法和新方法处理后的分别高出152.94％和79.17％;同时本方法在运行时间上也分别快了 96.27％和98.56％.

针对电气类专业课程体系与教学模式中存在的课程门类繁多、理论教学与实践教学衔接性较差、教学方法过于流于形式等问题,提出了一种基于OBE(Outcomes-based Education,OBE)的电气类专业课程体系的重构方法,引入案例分析思想,创新教学内容,并构建"三结合"教学模式,旨在重构电气类专业课程体系,探索新的教学模式与方法,为电气类专业课程教学改革提供一种新思路.

针对销孔工件的目标点云和模型(源)点云空间坐标系不一致问题,提出了一种采用主元分析法(PCA)校正的改进ICP点云配准方法.首先,采用主元分析法(PCA)计算销孔工件目标点云和模型点云数据的主轴方向、并求得初始转换矩阵;其次,对初始转换矩阵进行误差分析,采用双向KD树近邻搜索最近点的方法加速两片点云初始转换矩阵的误差校正,得到校正后的转换矩阵,从而完成粗配准;然后,引入法向量夹角阈值约束剔除错误匹配点对改进ICP算法实现精配准,最终将两片点云坐标系调整一致.通过实验进行了比较分析,实验结果表明,该方法可以有效实现销孔工件的点云配准,同时获得较优的配准速度和精度,采用该方法最终的配准误差为0.0354mm,平均配准耗时4.639s.

In order to give full play to the advantages of power battery and super-capacitor in the hybrid energy storage system (HESS) of hybrid electric vehicles (HEV), a new control strategy based on the subtractive clustering (SC) and adaptive fuzzy neural network (AFNN) was proposed to solve the problem of power distribution between the two energy sources when the driving schedule changes. Firstly, we used the SC to determine the structure of AFNN. Secondly, in order to improve the learning efficiency of AFNN, the back-propagation hybrid least square algorithm was applied to optimize the antecedent and conclusion parameters of network. Finally, the fuzzy membership function and rule set automatically generated by the neural network were used to the power distribution control of HESS in HEV. We verified the SC and AFNN control strategy by simulation and experiment based on the ADVISOR 2002 simulation software and the experimental platform, and the results show that the proposed control strategy can give full play to the advantages of HESS, and improve the energy storage performance of HEV.

针对含有有色噪声的非线性Hammerstein-Wiener模型,提出一种基于组合式信号源的辨识方法.通过利用可分离信号和随机信号组成的组合信号源实现有色噪声干扰下Hammerstein-Wiener模型各串联模块参数辨识的分离,简化辨识过程.首先,基于可分离信号的输入和输出,采用相关分析方法抑制过程噪声的干扰,辨识输出静态非线性模块和动态线性模块的参数;然后,基于辅助模型技术,利用辅助模型的输出和残差的估计值分别取代辨识模型中的不可测中间变量和噪声变量,推导辅助模型递推增广最小二乘方法,根据随机信号的输入输出数据辨识输入静态非线性模块和噪声模型的参数;最后,通过理论分析和仿真结果表明,所提出方法能够有效辨识有色噪声干扰下的非线性Hammerstein-Wiener模型,具有较好的鲁棒性.

To reduce the injury caused by the fall and solve the problems of low efficiency and low accuracy of traditional fall prediction methods, an optimized BP neural network fall prediction model based on the Sparrow Search Algorithm (SSA) is established. Taking sliding window to extract discrete features, selecting the maximum value, minimum value, mean value, and variance as the output indicator, the three-axis acceleration and resultant acceleration as the input of influencing factors, the fall prediction model is established for error prediction after data preprocessing. Experimental results show that the improved BP neural network could avoid falling into the locally optimal solution, and the convergence speed is faster, the fall detection accuracy of 98.3%, 92.0% and 96.1% based on DLR, Smart Fall and URFall datasets, respectively. This study may provide technical supports for wearable fall detection that can adapt to different environmental requirements, portable and low power consumption.

随着信息技术与课堂教学的深度融合,智慧教学已成为当前教育及新技术应用领域的研究热点之一.基于雨课堂教学平台开展智慧教学,在课前预习环节,通过平台推送相关学习资料,并进行预习测试,在掌握学情的基础上科学设计课堂教学;在课中环节,运用平台功能完成课程导入、问题竞猜、小组合作学习等教学活动,充分调动学生课堂参与的积极性,培养其创新、合作等方面的意识与能力;课后复习环节,基于平台对学生课后作业完成情况进行分析,教师开展有针对性的辅导.通过"自动控制原理"课程的教学实验,发现基于雨课堂的智慧教学相较传统教学模式,教学质量有显著的提高.

针对实际工业过程中普遍存在有色噪声,提出了有色噪声干扰下Hammerstein非线性系统两阶段辨识方法.采用设计的组合式信号实现Hammerstein系统各模块参数辨识分离,简化了辨识过程.在第一阶段,基于可分离信号的输入输出数据,利用相关分析算法估计线性模块参数,减少了有色噪声对辨识的干扰.在第二阶段,基于随机信号的输入输出数据,在最小二乘算法中引入滤波技术,推导了滤波递推增广最小二乘算法,提高了非线性模块参数和噪声模型参数的辨识精度.仿真结果表明:提出的两阶段辨识方法提高了辨识精度,有效地抑制了有色噪声的干扰.

为了能更好地对手机数据接口的缺陷进行检测,提出一种基于Faster R-CNN的检测算法.将Faster R-CNN检测架构中的RoIPooling替换成RoIAlign,解决RoIPooling计算过程中2次量化造成的目标回归位置的偏差.使用ResNet50融合FPN的网络作为特征提取网络,提高模型对小型目标缺陷的检测效果.最后使用测试集进行预测,实验表明本文提出算法的均值平均精度(mAP)达到了91.17％,比使用VGG为特征提取网络时的mAP提高了24.72个百分点,比单独使用ResNet50为特征提取网络的mAP提高了2.58个百分点,因此,本文提出的算法对手机数据接口缺陷检测有显著的效果提升,为手机数据接口缺陷检测提供了一种更有效的检测方法.

随着智能植保机的广泛应用,其自主定位与导航要求更高,PS/INS组合导航系统存在遮挡物导致信号弱、民用型导航偏差较大局限性,基于激光的自主定位建图技术(SLAM)在现代农业大棚中有精度高、灵活性好等优点,但激光SLAM技术存在激光点云扫描不能准确区别目标农作物和其他障碍物,从而难以保障植保机运行轨迹的正确性.提出了基于激光SLAM技术、ROS系统融入深度学习的目标检测算法,以正确区分扫描目标物体,从而为基于SLAM技术的植保机提供了更为有效的导航方法,提高其工作效率.

A novel data-driven learning approach of nonlinear system represented by neural fuzzy Hammerstein-Wiener model is presented. The Hammerstein-Wiener system has two static nonlinear blocks represented by two independent neural fuzzy models surrounding a dynamic linear block described by finite impulse response model. The multisignal theory is designed for employing Hammerstein-Wiener system to separate parameter learning issues. To begin with, the output nonlinearity parameters are learned utilizing separable signal with different amplitudes. Furthermore, correlation analysis method is implemented for estimating linear block parameters using separable signal inputs and outputs; thereby, the interference of process noise is effectively handled. Finally, multi-innovation learning technology is introduced to improve system learning accuracy, and then, multi-innovation extended stochastic gradient algorithm is obtained for optimizing input nonlinearity and noise model using multi-innovation technique and gradient search method. The simulation results display that presented data-driven learning approach has the availability of learning Hammerstein-Wiener system.

针对电气类专业课程传统教学模式存在的理论教学与实践教学衔接性差、学生学习效率低等问题,提出一种基于"理论教学—案例分析—实践教学"的全新教学模式.在理论教学和实践教学之间加入案例分析环节,发挥案例分析的桥梁与缓冲作用,使得学生通过案例分析充分理解理论知识,并为后续实践教学做好铺垫.列举的单相交流调压电路和直流升降压斩波电路实例充分验证了该教学模式的有效性.

针对机器人无序工件分拣过程中在遮挡情况下不同外形工件识别率差异较大的问题,对全局特征描述子和局部特征描述子的描述及投票过程进行详细地分析,分别选取其中实时性较好的PPF(Point Pair Fea-ture)和 SHOT(Signature of Histograms of OrienTations)描述子在不同程度遮挡情况下使用不同外形工件进行识别实验,有针对性地对机器人无序分拣中不同外形工件适用的算法进行实验对比和总结,使在不同外形工件上的识别率达到最大化,实验结果表明:PPF全局描述子对工件点云模型的外形特征和遮挡较为敏感,特征不明显工件的识别率为0％,对于外形特征明显、无遮挡的点云模型工件识别速度较快(1 s内)且准确率较高,SHOT局部描述子对遮挡的鲁棒性较强,并且对外形特征不明显工件有一定的识别能力,特征明显与特征不明显工件的识别率均保持在90％以上.

Due to the risk of failure of LED luminaries induced by the driver power, performance testing is especially important to driver power in some critical industries production and acceptance of work. A test system of LED driver based on LabVIEW is proposed to detect multiple physical parameters, including input voltage, output current, driver power efficiency, peak factor of current ripple and total harmonic distortion etc. The component selection of the system was investigated and the framework of the proposed system was presented. The hardware of this system mainly consists of signal conditioning modules, data acquisition card, test cables and computer. The software is designed by LabVIEW to realize the calculation, display and analysis of the collected data. The experimental results show that the system can realize the test of LED driver, and real-time grade determination of the test results according to relevant standards or the exact level specified by client. In addition, the system has simple structure and high expansibility, which is convenient for early use and later maintenance. The stability and bias was carried out to evaluate the proposed system by Minitab software, which ensured the measurement accuracy.