多传感器数据融合技术在动态称重系统中的应用

利用多传感器数据融合技术,通过对超声波传感器、测速传感器、电容传感器以及称重传感器测得的物料质量数据进行数据融合,大大提高了称重系统的测量精度,得到受环境干扰因素更小、精度更高的有关物料的测量数据。仿真结果表明,该方法在数据处理的精确性和稳定性方面都得到改善,可以有效地减小噪声、振动、电磁干扰等环境因素对动态称重系统测量的影响。     

基于结构输出响应的传感器故障检测研究

针对土木工程结构健康监测系统的传感器故障问题,提出了基于随机子空间识别技术和Kalman估计器的传感器故障检测方法,实现了结构健康监测系统中故障传感器的检测。首先,通过正常传感器的量测数据,基于随机子空间识别方法重构了结构的离散状态空间模型;然后通过已识别出的结构离散状态空间模型构造多路Kalman估计器,产生输出残差;最后,通过文中提出的基于输出残差的传感器故障检测策略,实现了传感器故障的检测。文章通过某典型框架结构和ASCE Benchmark 4层钢框架缩尺模型,验证了文中所提故障检测方法的有效性和实用性。     

双星编队构形保持抗干扰容错控制

为解决系统模型误差、外部干扰以及执行器故障引起的双星编队轨道控制精度低、稳定性差问题,设计一种基于观测器的抗干扰容错线性二次型调节器(LQR)控制策略.首先,根据编队双星相对运动动力学模型,设计基于双比例积分自适应律的增广观测器,同时实现对系统状态、间歇故障与快速时变故障、可建模干扰的快速精确估计,并采用H∞优化技术抑...     

数字式智能涡街流量计系统的设计

设计了以TMS320LF2407A为信号采集处理单元，P89LPC932为控制单元，配有LCD液晶显示模块和红外通讯接口的主从式数字式智能涡街流量计系统。针对目前涡街流量计易受干扰，精度不高的问题，信号采集处理单元采用基于DFT的频率估计方法，实现对传感器信号频率的估计。     

多关节移动机械臂系统的快速终端滑模控制

为了实现多关节移动机械臂系统在机械摩擦和模型误差等干扰下的精确控制,提出了快速终端滑模控制方法.首先建立了移动机械臂系统动力学和运动学模型,然后设计了运动环控制律,并将移动机械臂系统的运动指令转换为动力指令,最后针对动力环设计了快速终端滑模控制律,并通过自适应神经网络进行干扰估计,实现了对多关节移动机械臂系统的精确控制.仿真实验结果表明,提出的方法具有更好的快速性和准确性,移动平台的最大跟踪误差仅为0.8 cm,关节末端的最大跟踪误差仅为0.3 cm,干扰估计的最大误差为0.2 N·m,控制效果和精度均得到了明显的提升.     

采用滑模观测器的机械臂故障检测与控制优化

针对复合干扰影响下机械臂的故障检测和控制精度问题,提出了一种基于滑模观测器的故障检测和控制优化方法。首先建立了带有电机故障、模型误差和机械摩擦等复合干扰的机械臂系统故障模型,然后设计了滑模观测器来实现在复合干扰下对电机故障的准确检测,最后引入滑模观测器对电机故障程度进行估计,并设计了反步容错控制方法,从而实现了对机械臂系统的精确控制。仿真结果表明,基于滑模观测器的故障检测和控制优化方法能够快速、准确检测和估计电机故障,确保机械臂系统准确跟踪指令信号,角度跟踪误差范围仅为-0.2°～0.2°,能够准确估计出复合干扰的大小,估计误差范围仅为-0.1～0.1 (°)/s²,大大改善了对机械臂的控制效果。     

智能仪表中的一种数据融合方法

智能仪表中，由于工业过程的各种干扰，严重地影响了测量精度，提出一种基于普遍采用的单传感器系统数据融合方法，通过对传感器测量数据的分批估计得到误差和主差均较小的融合结果，并以实验表明这种方法优于目前广泛应用的算术平均值方法。     

电控系统传感器信号失真原因分析与研究

本文通过对典型故障实例深入分析,研究了微机控制系统中传感器信号失真的原因,详细介绍了由传感器本身电器性能、电磁干扰、线路故障等因素引起的传感器信号失真现象及产生的故障机理.     

基于噪声方差估计的稳健融合算法

给出一种基于噪声方差估计的稳健融合算法.针对集中式多传感器融合结构,利用随机逼近算法分析了各传感器权的最优分配原则,并给出了一种基于方差估计的权的自适应调整算法.结合多传感器融合跟踪系统,为了提高非线性系统的跟踪性能,滤波算法采用了非线性逼近能力更好的Unscented卡尔曼滤波算法.通过计算机仿真实验,获得了良好的融合效果.与经典的加权方法相比,在相同仿真航路条件下,融合精度和跟踪精度都得到了显著提高.     

基于ＳＧ 算法和ＢＰ神经网络的 角度传感器信号处理研究

:针对电解角度传感器在实际应用中容易受到环境因素的影响出现误差干扰,如果不加以处理 会导致定位精度降低,影响系统的控制精度的问题,提出一种旨在提高传感器测量精度的多传感信号拟合 算法。该算法首先使用ＳＧ 算法对传感信号的滤波,实现信号数据序列的平滑,降低异常数据点的出现概 率,随后使用 ＢＰ神经网络对多个角度传感器和环境温度传感器的输出信号进行误差估计,降低环境温度因 素对角度传感器的误差干扰。实验表明,综合使用这两种算法对角度传感信号进行处理能够有效提高角度 传感器的测量精度。     

The control system modeling and experiment for the tele-operated unmanned vehicle

The control system design and modeling of an unmanned vehicle by means of a new concept for better performance through a tele-operation system is suggested by sensor fusion. But, the control of a real vehicle is very difficult, because the system identification of the vehicle is hard to find the unknown factors and the disturbances of the experimental environment. For the longitudinal and lateral controls, the traction system and steering system models are set up and a tuning method to find the gain of the controller by experiments is presented. In this research, mechanical and electronic parts are implemented to operate the unmanned vehicle and data reconstruction method of information about the environment data coming from several sensors is presented by data plot for the vehicle navigation. This paper focuses on the integration of tele-operated unmanned vehicle. This vehicle mainly controlled lateral and longitudinal directions with actuators for controlling vehicle movement and sensors for the closed-loop controlled system.     

基于随机集理论的并发故障诊断信息融合方法

为了诊断并发故障,提出一种基于随机集理论的信息融合方法.首先构造包含并发故障的论域,并在此论域的超幂集上定义扩展型随机集.基于该随机集和广义集值映射给出证据组合规则的随机集模型,用其构造可以同时适用于单发和并发故障诊断的新型组合规则.此外,根据传感器提供的故障信息构造故障样板模式与待检模式的模糊隶属度函数,利用模糊集的随机集表示以及随机集似然测度,获得两种模式匹配的程度作为待融合的诊断证据.最后通过在电机柔性转子平台上的试验,证明了所提方法可有效地减少单一传感器信息诊断的不确定性,显著提高转子系统故障诊断的精度.     

载人潜水器多传感器数据采集与信息融合技术

本文介绍了一种用于载人潜水器的导航传感器的数据采集及信息融合技术.航行控制计算机通过基于工业以太网的数据通信系统对各传感器进行数据采集,采用卡尔曼滤波器完成对各传感器数据信息的融合,以便提高数据的精度和控制系统的性能,并将结果送给监控计算机,用于载人潜水器的姿态显示.     

Track fusion via track filter in dense sensor environments

At present, most track fusion approaches fuse all available sensor tracks without regard of their different contributions to system tracks. However, in dense sensor environments, some abnormal sensors or conflicted information will increase the complexity and the time of track fusion greatly, even lead to opposite results. Therefore, a track fusion algorithm via track filter (TFTF) is proposed in this paper. The track filter is based on a two-stage paradigm of abnormal sensors detection and heuristic state estimation fusion. At first, the abnormal sensors are detected by Chauvenet criterion. Then the state estimation fusion is guided by the heuristic function, in which the appropriate sensor tracks are selected and an optimal number of tracks are fused. The effectiveness and superiority of the algorithm are verified in theory and simulation.     

机器人手爪的多传感器数据采集、融合和传输系统

机器人为了灵巧地抓取物体,在手爪上配置了多种传感器,例如,指力传感器、触觉传感器和距离传感器。研制了一套基于DSP的系统,实现传感器数据的采集、融合和传输。系统硬件由数据采集模块、DSP模块和CAN传输模块组成。系统软件包括监控程序、初始化模块、看门狗模块、数据融合模块、CAN通信模块、数字量采集模块、正交编码脉冲计数模块和A/D中断服务程序。该系统实时地采集和融合手爪各传感器的信息,得到手爪与工件的安全连接状态,通过CAN总线传输给主控计算机。     

Multi-agent decision fusion for motor fault diagnosis

Improvement of recognition rate is ultimate aim for fault diagnosis researchers using pattern recognition techniques. However, the unique recognition method can only recognise a limited classification capability which is insufficient for real-life application. An ongoing strategy is the decision fusion techniques. In order to avoid the shortage of single information source coupled with unique decision method, a new approach is required to obtain better results. This paper proposes a decision fusion system for fault diagnosis, which integrates data sources from different types of sensors and decisions of multiple classifiers. First, non-commensurate sensor data sets are combined using an improved sensor fusion method at a decision level by using relativity theory. The generated decision vectors are then selected based on correlation measure of classifiers in order to find an optimal sequence of classifiers fusion, which can lead to the best fusion performance. Finally, multi-agent classifiers fusion algorithm is employed as the core of the whole fault diagnosis system. The efficiency of the proposed system was demonstrated through fault diagnosis of induction motors. The experimental results show that this system can lead to super performance when compared with the best individual classifier with single-source data.     

传感器故障诊断实时监测系统设计的探讨

对大型设备运行状态监测和故障的早期诊断与预报活动中,传感器自身故障的及时发现与判别尤为重要。本文提出以设备子系统的（或某一功能的）传感器监测参数为划分原则,将单传感器的监测信号综合作为多传感器监测而进行信息的融合处理,从而判别子系统运行状态和传感器信号的真实性的构思,并探讨传感器故障诊断实时监测系统的设计方案。     

Laser, fiber optic, and CCD array sensing systems

Lasers and fiber optics have recently been accepted in industry for sensing as well as for communications. Charge-coupled devices (CCD) and charge-injection devices (CID) are important new solid-state image sensors for fast display inputs to computers. The sensors may be coupled in a sensor fusion system by optical fibers to bring to the plant floor the advantages of intrinsic safety and immunity to radio frequency, electromagnetic, and optical noise. These new developments in sensing by lasers, fiber optics, and CCD arrays may be applied singly or in combination. For example, improved Raman spectroscopy employs a hostile environment fiber optic probe interface, an infrared laser diode to avoid fluorescence, and a CCD array detector for better sensitivity. We will examine recent developments that will help us with rapid, accurate real-time information for better monitoring and control.     

Deep Learning Based Data Fusion for Sensor Fault Diagnosis and Tolerance in Autonomous Vehicles

Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the loca-tion of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.     

多传感器信息融合及其在加工过程中的应用现状

为了提高机床的智能化水平,需使用多种类或多布点的传感器,如何合理使用多传感器来提高机床的智能化水平是关键问题,目前多传感器信息融合理论及技术是解决此问题的有效途径.对多传感器的信息融合原理和融合方法及其在加工过程中的典型应用情况进行了总结,明确智能信息融合技术在加工过程的监测与控制方面的应用具有广阔的前景.