Review on uncertainty analysis and information fusion diagnosis of aircraft control system

In the aircraft control system,sensor networks are used to sample the attitude and environmental data.As a result of the external and internal factors(e.g.,environmental and task complexity,inaccurate sensing and complex structure),the aircraft control system contains several uncertainties,such as imprecision,incompleteness,redundancy and randomness.The information fusion technology is usually used to solve the uncertainty issue,thus improving the sampled data reliability,which can further effectively increase the performance of the fault diagnosis decision-making in the aircraft control system.In this work,we first analyze the uncertainties in the aircraft control system,and also compare different uncertainty quantitative methods.Since the information fusion can eliminate the effects of the uncertainties,it is widely used in the fault diagnosis.Thus,this paper summarizes the recent work in this aera.Furthermore,we analyze the application of information fusion methods in the fault diagnosis of the aircraft control system.Finally,this work identifies existing problems in the use of information fusion for diagnosis and outlines future trends.

SPOT WELDING QUALITY FUZZY CONTROL SYSTEM BASED ON MULTISENSOR INFORMATION FUSION

The multisensor information fusion technology is adopted for real time measuring the four parameters which are connected closely with the weld nugget size（welding current, electrode displacement, dynamic resistance, welding time）, thus much more original information is obtained. In this way, the difficulty caused by measuring indirectly weld nugget size can be decreased in spot welding quality control, and the stability of spot welding quality can be improved. According to this method, two-dimensional fuzzy controllers are designed with the information fusion result as input and the thyristor control signal as output. The spot welding experimental results indicate that the spot welding quality intelligent control method based on multiscnsor information fusion technology can compensate the influence caused by variable factors in welding process and ensure the stability of welding quality.

Sensor Fusion with Square-Root Cubature Information Filtering

This paper derives a square-root information-type filtering algorithm for nonlinear multi-sensor fusion problems using the cubature Kalman filter theory. The resulting filter is called the square-root cubature Information filter (SCIF). The SCIF propagates the square-root information matrices derived from numerically stable matrix operations and is therefore numerically robust. The SCIF is applied to a highly maneuvering target tracking problem in a distributed sensor network with feedback. The SCIF’s performance is finally compared with the regular cubature information filter and the traditional extended information filter. The results, presented herein, indicate that the SCIF is the most reliable of all three filters and yields a more accurate estimate than the extended information filter.

AN INFORMATION FUSION METHOD FOR SENSOR DATA RECTIFICATION

In the applications of water regime monitoring, incompleteness, and inaccuracy of sensor data may directly affect the reliability of acquired monitoring information. Based on the spatial and temporal correlation of water regime monitoring information, this paper addresses this issue and proposes an information fusion method to implement data rectification. An improved Back Propagation (BP) neural network is used to perform data fusion on the hardware platform of a stantion unit, which takes Field-Programmable Gate Array (FPGA) as the core component. In order to verify the effectiveness, five measurements including water level, discharge and velocity are selected from three different points in a water regime monitoring station. The simulation results show that this method can recitify random errors as well as gross errors significantly.

Sensor management based on fisher information gain

Multi-sensor system is becoming increasingly important in a variety of military and civilian applications. In general, single sensor system can only provide partial information about environment while multi-sensor system provides a synergistic effect, which improves the quality and availability of information. Data fusion techniques can effectively combine this environmental information from similar and/or dissimilar sensors. Sensor management, aiming at improving data fusion performance by controlling sensor behavior, plays an important role in a data fusion process. This paper presents a method using fisher information gain based sensor effectiveness metric for sensor assignment in multi-sensor and multi-target tracking applications. The fisher information gain is computed for every sensor-target pairing on each scan. The advantage for this metric over other ones is that the fisher information gain for the target obtained by multi-sensors is equal to the sum of ones obtained by the individual sensor, so standard transportation problem formulation can be used to solve this problem without importing the concept of pseudo sensor. The simulation results show the effectiveness of the method.

Neural Network Based Algorithm and Simulation of Information Fusion in the Coal Mine

The concepts of information fusion and the basic principles of neural networks are introduced. Neural net-works were introduced as a way of building an information fusion model in a coal mine monitoring system. This assures the accurate transmission of the multi-sensor information that comes from the coal mine monitoring systems. The in-formation fusion mode was analyzed. An algorithm was designed based on this analysis and some simulation results were given. Finally,conclusions that could provide auxiliary decision making information to the coal mine dispatching officers were presented.

Altitude information fusion method and experiment for UAV

Altitude regulation is a fundamental problem in UAV(unmanned aerial vehicles) control to ensure hovering and autonomous navigation performance.However,data from altitude sensors may be unstable by interference.A digital-filter-based improved adaptive Kalman method is proposed to improve accuracy and reliability of the altitude measurement information.A unique sensor data fusion structure is designed to make different sensors switch automatically in different environment.Simulation and experimental results show that an improved Sage-Husa adaptive extended Kalman filter(SHAEKF) is adopted in altitude data fusion which means that altitude error is limited to 1.5m in high altitude and 1.2m near the ground.This method is proved feasible and effective through hovering flight test and three-dimensional track flight experiment.

A multi-rate sensor fusion approach using information filters for estimating aero-engine performance degradation

Gas-path performance estimation plays an important role in aero-engine health management, and Kalman Filter(KF) is a well-known technique to estimate performance degradation. In previous studies, it is assumed that different kinds of sensors are with the same sampling rate, and they are used for state estimation by the KF simultaneously. However, it is hard to achieve state estimation using various kinds of sensor measurements at the same sampling rate due to a complex network and physical characteristic differences between sensors, especially in an advanced multisensor architecture. For this purpose, a multi-rate sensor fusion using the information filtering approach is proposed based on the square-root cubature rule, which is called Multi-rate Squareroot Cubature Information Filter(MSCIF) to track engine performance degradation. Soft measurement synchronization of the MSCIF is designed to provide a sensor fusion condition for multiple sampling rates of measurement, and a fault sensor is isolated by maximum likelihood validation before state estimation. The contribution of this paper is to supply a novel multi-rate informationfilter approach for sensor fault tolerant health estimation of an aero-engine in a multi-sensor system. Tests are conducted for aero-engine performance degradation estimation with multiple sampling rates of sensor measurement on both digital simulation and semi-physical experiment.Experimental results illustrate the superiority of the proposed algorithm in terms of degradation estimation accuracy and robustness to sensor failure in a multi-sensor system.

Mutual-information based weighted fusion for target tracking in underwater wireless sensor networks

Underwater wireless sensor networks(UWSNs)can provide a promising solution to underwater target tracking.Due to limited energy and bandwidth resources,only a small number of nodes are selected to track a target at each interval.Because all measurements are fused together to provide information in a fusion center,fusion weights of all selected nodes may affect the performance of target tracking.As far as we know,almost all existing tracking schemes neglect this problem.We study a weighted fusion scheme for target tracking in UWSNs.First,because the mutual information(MI)between a node’s measurement and the target state can quantify target information provided by the node,it is calculated to determine proper fusion weights.Second,we design a novel multi-sensor weighted particle filter(MSWPF)using fusion weights determined by MI.Third,we present a local node selection scheme based on posterior Cramer-Rao lower bound(PCRLB)to improve tracking efficiency.Finally,simulation results are presented to verify the performance improvement of our scheme with proper fusion weights.

Fault diagnosis method of hydraulic system based on fusion of neural network and D-S evidence theory

According to fault type diversity and fault information uncertainty problem of the hydraulic driven rocket launcher servo system（HDRLSS） , the fault diagnosis method based on the evidence theory and neural network ensemble is proposed. In order to overcome the shortcomings of the single neural network, two improved neural network models are set up at the com-mon nodes to simplify the network structure. The initial fault diagnosis is based on the iron spectrum data and the pressure, flow and temperature（PFT） characteristic parameters as the input vectors of the two improved neural network models, and the diagnosis result is taken as the basic probability distribution of the evidence theory. Then the objectivity of assignment is real-ized. The initial diagnosis results of two improved neural networks are fused by D-S evidence theory. The experimental results show that this method can avoid the misdiagnosis of neural network recognition and improve the accuracy of the fault diagnosis of HDRLSS.

SELF-TUNING WEIGHTED MEASUREMENT FUSION WHITE NOISE DECONVOLUTION ESTIMATOR

For the multi-sensor linear discrete time-invariant stochastic systems with correlated measurement noises and unknown noise statistics,an on-line noise statistics estimator is obtained using the correlation method.Substituting it into the optimal weighted fusion steady-state white noise deconvolution estimator based on the Kalman filtering,a self-tuning weighted measurement fusion white noise deconvolution estimator is presented.By the Dynamic Error System Analysis(DESA) method,it proved that the self-tuning fusion white noise deconvolution estimator converges to the steady-state optimal fusion white noise deconvolution estimator in a realization.Therefore,it has the asymptotically global optimality.A simulation example for the tracking system with 3 sensors and the Bernoulli-Gaussian input white noise shows its effectiveness.

基于多传感器信息融合的机床测量数据自动补偿系统

机床测量数据自动补偿能够减少加工误差,为提高机床加工精度,设计基于多传感器信息融合的机床测量数据自动补偿系统。首先设计温度传感器、单片机主控与补偿脉冲发生装置,获取机床运动数据,然后采用多传感器融合算法融合采集信息,对信息中误差处理,采用粗糙集理论寻找最佳补偿值,实现机床测量数据自动补偿。实验结果表明,该系统能够有效减少加工误差,可以满足实际应用要求。

地面移动机器人路径避障控制策略研究

针对地面移动机器人在复杂工作环境的避障要求,分别设计了模糊控制器算法和模糊神经网络算法。首先在在地面移动机器人上的安装多传感器检测系统,在此基础上设计了自适应加权多传感器信息融合模型,将融合算法的结果作为避障控制算法的输入。分别在模糊神经网络算法和模糊控制器基础上,真实的模拟出地面移动机器人避障路径,结果表明模糊神经网络算法下的地面移动机器人避障运动路径更平滑,地面移动机器人路径与障碍物的距离更大。最后通过地面移动机器人实验平台上的避障实验,验证了模糊神经网络避障算法的优越性和可靠性。

基于无线传感网络的现代建筑多传感安防预警系统设计

预警系统是现代建筑智慧体系中重要组成部分,对保证建筑安全具有重要作用,但目前系统功能与性能还有待提高,在实际中错误报警比例比较高,而且反应性能比较弱,提出基于无线传感网络的现代建筑多传感安防预警系统设计。系统采用应用层、业务逻辑层、网络层与感知层四层体系结构,硬件方面对温度、烟雾、湿度、图像多种无线传感器和报警器选型与设计,利用无线传感网络对传感数据传输,软件方面通过对多传感信息融合处理,评价建筑安全等级并预警响应,以此完成基于无线传感网络的现代建筑多传感安防预警系统设计。经实验证明,设计系统错误报警比例不超过1%,反应时间不超过0.25s,在现代建筑安全防护预警领域具有良好的应用前景。

传感器信息融合下新能源汽车动力电池信号故障检测方法

新能源汽车作为节能环保的新产品具有较好社会前景,内在的动力电池是新能源汽车的主动力源,但电池发动机是一个较为复杂的系统,在处于恶劣环境时,可能出现各种故障问题。新能源汽车的动力电池若发生故障,不但会使汽车的系统性能下降,还会造成灾难性的后果,为此,研究传感器信息融合下新能源汽车动力电池信号故障检测方法。通过一致性定律整理电池系统传感器数据,在近似概率和频率中估算新能源汽车动力电池信号;选择熵权重法理论对数据信号进行区分,以时刻内单体电压作为评价指标,在预处理后构建判断信号故障矩阵;通过故障判断矩阵确定异常信号,在传感器信息融合算法下修订权值,以最大误差范围检测信号输出,检测新能源汽车动力电池信号故障,完成检测方法设计。实验以四组不同类型的新能源汽车作为测试对象,对其动力电池的运动工况进行信号模拟,在不同的接口处获取故障电压信号并完成检测测试,设计的电池信号故障检测方法能够实现精准的故障信号跟踪,完成较为精准的故障信号检测,具有一定的应用价值。

ADAS系统视觉与毫米波雷达分布式抗差卡尔曼滤波融合算法

自动驾驶车辆常常利用多传感器对周围目标进行检测和跟踪,但受限于传感器多源异构特性和复杂多变的驾驶环境,准确的多目标检测和跟踪仍是实现自动驾驶的一大困难和挑战。本文面向高级驾驶辅助系统(ADAS)的多目标检测与跟踪任务,采用了基于1个视觉传感器和5个毫米波雷达(1V5R)的传感器配置方案,且设计了基于分布式抗差卡尔曼滤波器的多传感器信息融合算法以实现对周围目标的准确感知。首先,针对不同传感器数据特征,采用不同的线性卡尔曼滤波器和扩展卡尔曼滤波器进行数据融合,并基于分布式卡尔曼滤波建立了1V5R多传感器信息融合框架。其次,为降低传感器动态误差对于融合精度的影响,在卡尔曼加权观测融合的基础上,引入抗差估计方法,实现了对传感器动态误差的实时估计和修正。最后,通过离线仿真和实车道路试验对所提出的基于分布式抗差卡尔曼滤波的多传感器融合算法进行了验证。试验结果表明,与单一传感器的测量值相比,所提出的算法能有效融合多个传感器的信息以提升目标的检测与跟踪精度,且鲁棒性较好。

基于自适应多尺度注意力机制的CNN-GRU矿用电动机健康状态评估

利用多传感器信息融合技术进行电动机健康状态评估时,矿用电动机监测数据中存在异常值和缺失值,而卷积神经网络和循环神经网络等深度学习模型在数据质量下降严重的情况下难以有效提取数据特征和更新网络权重,导致梯度消失或爆炸等问题。针对上述问题,提出了一种基于自适应多尺度注意力机制的CNN-GRU(CNN-GRU-AMSA)模型,用于评估矿用电动机健康状态。首先,对传感器采集的电动机运行数据进行填补、剔除和标准化处理,并以环境温度变化作为依据对矿用电动机运行数据进行工况划分。然后,根据马氏距离计算出电动机电流、电动机三相绕组温度、电动机前端轴承温度和电动机后端轴承温度等健康评估指标的健康指数(HI),采用Savitzky–Golay滤波器对指标HI进行降噪、平滑、归一化处理,并结合主成分分析法计算的不同指标对矿用电动机的贡献度,对指标HI进行加权融合得到矿用电动机HI。最后,将矿用电动机HI输入CNN-GRU-AMSA模型中,该模型通过动态调整注意力权重,实现对不同尺度特征的信息融合,从而准确输出电动机健康状态评估结果。实验结果表明,与其他常见的深度学习模型CNN,CNN-GRU,CNN-LSTM,CNN-LSTM-Attention相比,CNN-GRU-AMSA模型在均方根误差、平均绝对误差、准确率、Macro F1及Micro F1等评价指标上更优,且预测残差的波动范围更小,稳定性更优。

改进的多传感器信息融合算法及其应用

针对量测噪声未知的问题,提出一种改进的多传感器信息融合方法,首先对量测噪声进行实时跟踪与估计,接着基于估计的量测噪声进行最优加权融合,解决常规加权法权值不是最优的问题,最后将融合的结果进行卡尔曼滤波,得到系统的状态估计。将改进的多传感器信息融合方法应用某型无人机(UAV)垂向高度信息融合系统中,经仿真验证,表明该方法具有一定的工程实用价值。

GNSS/多传感器融合定位中的欺骗检测技术

全球卫星导航系统(GNSS)与多传感器组成的融合定位系统由于其精确性和鲁棒性,已经在自动驾驶和无人探测等领域得到广泛应用。然而,GNSS容易受到欺骗干扰影响,导致融合定位系统输出错误信息,进而引发严重后果。鉴于传感器能够提供不受GNSS欺骗干扰的载体状态信息,融合定位系统能够通过GNSS和传感器信息的相互校验实现欺骗检测。本文对此类GNSS欺骗检测技术进行了综述,首先概述了GNSS/多传感器融合定位的传感器组成和信息融合算法;其次将现有GNSS/多传感器定位中的欺骗检测技术分为独立信息一致性监测和信息融合异常检测2类,并总结分析了不同算法的基本原理、实现方法和性能效果;最后对GNSS/多传感器融合定位中欺骗检测技术的未来发展趋势进行了展望。