融合双注意力机制的人群计数算法

针对背景复杂、遮挡、人群分布不均等人群计数常见问题,提出了一种结合联合损失的空间-通道双注意力机制卷积神经网络模型(joint loss-based space-channel dual attention network, JL-SCDANet).该网络前端进行图像粗粒度特征提取,中间加入空间注意力机制以及通道注意力机制突出图像重点区域,后端使用可加大感受野且不丢失图像分辨率的空洞卷积提取深层二维特征.此外,该模型结合联合损失函数进行训练,以增强模型的鲁棒性.为了验证模型的改进效果,在3个公共数据集(ShanghaiTech Part B、mall和UCF＿CC＿50)上分别进行了对比实验,在ShanghaiTech Part B数据集中平均绝对误差(MAE)和均方误差(MSE)分别达到了8.13和13.13;在mall数据集中MAE、MSE达到了1.78和2.28;在UCF＿CC＿50数据集中MAE、MSE分别达到了182.12和210.24,实验结果证明了该网络在提高人数统计准确率上的有效性.     

混合遗传蚁群算法优化BP神经网络预测空气质量

为了进一步提高空气质量指数预测精度,提出一种混合遗传蚁群算法优化BP神经网络的方式对空气质量指数进行预测.首先初始化蚁群算法的信息素分布,对不满足适应度条件的进行遗传算法的交叉、变异操作,进而计算蚁群的状态转移概率和信息素浓度,当适应度值满足条件要求时,将寻优结果作为BP神经网络的最优权值和阈值,来改善单一BP神经网络的不足.最后通过运用西安市的空气质量指数日历史数据进行验证,实验表明,本文所提模型的各个评价指标相对其他对比模型误差更小,在预测精度方面具有更高的说服力,因此能够有效地预测空气质量指数.     

Nonlinear cascade control of an electro-hydraulic actuator with large payload variation

Electro-hydraulic actuators have been widely used in industrial production, but the unknown variable payload seriously affects its position control accuracy. Therefore, a radial basis function neural network disturbance observer is designed to estimate the lumped disturbance force through strong online learning ability in the absence of force sensor. Besides, a nonlinear cascade controller with double loop structure is proposed in this paper. A global fast terminal sliding mode control method is firstly applied in the outer loop position system, which can eliminate chattering and improve convergence speed comparing to traditional sliding mode control. The inner loop force system adopts a backstepping control method to calculate the actual input of the whole system. Theoretical analysis indicates that the proposed controller is stable even if existing time-variant disturbance. Moreover, three comparative controllers are designed and tested in both simulations and experiments. Comparative results show that the developed method has absolute average errors of 1.14 and 0.49 mm in different position tracking, which means more satisfactory tracking performance compared to the contrast controllers.     

Vapor Phase Growth of Centimeter-Sized Band Gap Engineered Cesium Lead Halide Perovskite Single-Crystal Thin Films with Color-tunable Stimulated Emission

Single crystal metal halide perovskites thin films are considered to be a promising optical, optoelectronic materials with extraordinary performance due to their low defect densities. However, it is still difficult to achieve large-scale perovskite single-crystal thin films (SCTFs) with tunable bandgap by vapor-phase deposition method. Herein, the synthesis of CsPbCl_3(1–x)Br_3x SCTFs with centimeter size (1 cm × 1 cm) via vapor-phase deposition is reported. The Br composition of CsPbCl_3(1–x)Br_3x SCTFs can be gradually tuned from x = 0 to x = 1, leading the corresponding bandgap to change from 2.29 to 2.91 eV. Additionally, an low-threshold (≈23.9 µJ cm⁻²) amplified spontaneous emission is achieved based on CsPbCl_3(1–x)Br_3x SCTFs at room temperature, and the wavelength is tuned from 432 to 547 nm by varying the Cl/Br ratio. Importantly, the high-quality CsPbCl_3(1–x)Br_3x SCTFs are ideal optical gain medium with high gain up to 1369.8 ± 101.2 cm⁻¹. This study not only provides a versatile method to fabricate high quality CsPbCl_3(1–x)Br_3x SCTFs with different Cl/Br ratio, but also paves the way for further research of color-tunable perovskite lasing.     

Few-shot node classification via local adaptive discriminant structure learning

Node classification has a wide range of application scenarios such as citation analysis and social network analysis. In many real-world attributed networks, a large portion of classes only contain limited labeled nodes. Most of the existing node classification methods cannot be used for few-shot node classification. To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples, in this paper, we propose a local adaptive discriminant structure learning (LADSL) method for few-shot node classification. LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlarging inter-class differences. Extensive experiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.     

An adaptive reaching law of chattering-free discrete-time sliding mode control for systems with external disturbance

An adaptive reaching law of chattering-free discrete-time sliding mode control is proposed for the systems with external disturbance. An adaptive function is proposed in the reaching law which can increase reaching speed as sliding variable is far away from zero and avoid undesired chattering when sliding variable is close to origin. Moreover, a third-order backward difference of disturbance is added to obtain a narrower quasi-sliding mode band (QSMB). Both the closed-loop system performance and finite reaching steps to achieve the desired QSMB are theoretically analyzed. The simulation results verify the effectiveness of the proposed control strategy.     

Combustion timing control of HCCI engine based on NNPC and Elman-NN model under complex conditions

Homogeneous Charge Compression Ignition (HCCI) combines the characteristics of gasoline engine and diesel engine with high thermal efficiency and low emissions. However, since there is no direct initiator of combustion, it is difficult to control the combustion timing in HCCI engines under complex working conditions. In this paper, Neural Network Predictive Control (NNPC) for combustion timing of the HCCI engine is designed and implemented. First, the black box model based on Elman neural network is designed and developed to estimate the combustion timing. The fuel equivalence ratio, intake valve closing timing, intake manifold temperature, intake manifold gas pressure, and engine speed are chosen as the system inputs. Then, a NNPC controller is designed to control combustion timing by controlling the intake valve closing timing. Simulation results show that the Elman neural network black box model is capable of estimating the HCCI engine combustion timing. In addition, regardless of whether the HCCI engine is in constant or complex condition, the designed NNPC controller is capable of keeping the combustion timing within the ideal range. In particular, under New European Driving Cycle (NEDC) working conditions, the maximum overshoot of the controller is 28.95% and the average error is 1.03 crank angle degree. It is concluded that the controller has good adaptability and robustness.     

Quasi-min-max MPC for visual servoing stabilization of omnidirectional wheeled mobile robots

This paper proposes a new visual servoing quasi-min-max MPC algorithm for stabilization control of an omnidirectional wheeled mobile robot subject to physical and visual constraints. The visual servoing dynamics of the robot are modeled as the state-dependent linear error system with nonlinear control inputs of rotation and deflection velocities of wheels. The state-dependent linear error system is covered as linear parameters-varying models which is used to design the visual servoing quasi-min-max MPC controller. The actual control inputs of the robot are then computed by the solution of an inverse algebraic equation of the MPC actions. The recursive feasibility and stability of the new visual servoing MPC are ensured by some LMIs conditions. The performance and practicability of the visual servoing MPC are verified by some simulation and experiment results.     

Sliding mode learning control for T-S fuzzy system and an application to hypersonic flight vehicle

Sliding mode-based learning control is presented for T-S fuzzy system. A T-S fuzzy model with both uncertainties and unmodeled dynamics is proposed firstly, in which the information of uncertainties and unmodeled dynamics are assumed to be unknown. Then, according to a given reference model, state-tracking error system is built. Respecting facts, the input matrices of the built T-S fuzzy model are different from each other. An extended state observer is built for estimating the unknown uncertainties and unmodeled dynamics, and a corresponding sliding surface is proposed. A learning controller is then presented for the closed loop system. Moreover, a numerical simulation result on hypersonic flight vehicles is considered to testify the controller's availability.     

基于压电力显微镜的铌酸锂电畴稳定性研究

研究了Z切700 nm厚的单晶铌酸锂(LiNbO₃)薄膜电畴的调控方法。利用X射线衍射仪(XRD)和原子力显微镜(AFM)对单晶LiNbO₃薄膜的晶向和形貌进行了表征,并通过外加电场对单晶LiNbO₃薄膜电畴进行调控。研究结果表明,该LiNbO₃薄膜具有单一的(006)衍射峰,表面光滑、粗糙度低(均方根粗糙度小于1 nm)。通过外加电场和预设电畴图案对LiNbO₃电畴进行精准调控,并测试了电畴稳定性。测试结果显示,调控后的电畴在温度为25~150℃内处于稳定状态,且在30 d内保持稳定,未发生弛豫现象。该研究为LiNbO₃电畴工程器件的研发和应用提供了重要的技术支撑。