Dendritic Cell Algorithm with Bayesian Optimization Hyperband for Signal Fusion

The dendritic cell algorithm(DCA)is an excellent prototype for developing Machine Learning inspired by the function of the powerful natural immune system.Too many parameters increase complexity and lead to plenty of criticism in the signal fusion procedure of DCA.The loss function of DCA is ambiguous due to its complexity.To reduce the uncertainty,several researchers simplified the algorithm program;some introduced gradient descent to optimize parameters;some utilized searching methods to find the optimal parameter combination.However,these studies are either time-consuming or need to be revised in the case of non-convex functions.To overcome the problems,this study models the parameter optimization into a black-box optimization problem without knowing the information about its loss function.This study hybridizes bayesian optimization hyperband(BOHB)with DCA to propose a novel DCA version,BHDCA,for accomplishing parameter optimization in the signal fusion process.The BHDCA utilizes the bayesian optimization(BO)of BOHB to find promising parameter configurations and applies the hyperband of BOHB to allocate the suitable budget for each potential configuration.The experimental results show that the proposed algorithm has significant advantages over the otherDCAexpansion algorithms in terms of signal fusion.

HIGH RESOLUTION RANGE PROFILE FORMATION BASED ON LFM SIGNAL FUSION OF MULTIPLE RADARS

This paper presents a new method of High Resolution Range (HRR) profile formation based on Linear Frequency Modulation (LFM) signal fusion of multiple radars with multiple frequency bands. The principle of the multiple radars signal fusion improving the range resolution is analyzed. With the analysis of return signals received by two radars,it is derived that the phase difference between the echoes varies almost linearly with respect to the frequency if the distance between two radars is neg-ligible compared with the radar observation distance. To compensate the phase difference,an en-tropy-minimization principle based compensation algorithm is proposed. During the fusion process,the B-splines interpolation method is applied to resample the signals for Fourier transform imaging. The theoretical analysis and simulations results show the proposed method can effectively increase signal bandwidth and provide a high resolution range profile.

Weighted Multi-sensor Data Level Fusion Method of Vibration Signal Based on Correlation Function

As the differences of sensor＇s precision and some random factors are difficult to control,the actual measurement signals are far from the target signals that affect the reliability and precision of rotating machinery fault diagnosis.The traditional signal processing methods,such as classical inference and weighted averaging algorithm usually lack dynamic adaptability that is easy for trends to cause the faults to be misjudged or left out.To enhance the measuring veracity and precision of vibration signal in rotary machine multi-sensor vibration signal fault diagnosis,a novel data level fusion approach is presented on the basis of correlation function analysis to fast determine the weighted value of multi-sensor vibration signals.The approach doesn＇t require knowing the prior information about sensors,and the weighted value of sensors can be confirmed depending on the correlation measure of real-time data tested in the data level fusion process.It gives greater weighted value to the greater correlation measure of sensor signals,and vice versa.The approach can effectively suppress large errors and even can still fuse data in the case of sensor failures because it takes full advantage of sensor＇s own-information to determine the weighted value.Moreover,it has good performance of anti-jamming due to the correlation measures between noise and effective signals are usually small.Through the simulation of typical signal collected from multi-sensors,the comparative analysis of dynamic adaptability and fault tolerance between the proposed approach and traditional weighted averaging approach is taken.Finally,the rotor dynamics and integrated fault simulator is taken as an example to verify the feasibility and advantages of the proposed approach,it is shown that the multi-sensor data level fusion based on correlation function weighted approach is better than the traditional weighted average approach with respect to fusion precision and dynamic adaptability.Meantime,the approach is adaptable and easy to use,can be applied to other areas of vibration measurement.

DISTRIBUTED CFAR SIGNAL DETECTION BASED ON AREA FUSION

The multisensor detection area partitioning is considered. An approach is presented to the fusion in each detection area where the sensor uses different thresholds and then at system level. The expressions of the detection probability and false alarm probability are given. An application of the method is illustrated to distributed CFAR detection systems. The result shows that the system detection probability may be improved by setting different thresholds for a detector.

Optimal multi-sensor Kalman smoothing fusion for discrete multichannel ARMA signals

Based on the multi-sensor optimal information fusion criterion weighted by matrices in the linear minimum variance sense, using white noise estimators, an optimal fusion distributed Kalman smoother is given for discrete multi-channel ARMA （autoregressive moving average） signals. The smoothing error cross-covanance matrices between any two sensors are given for measurement noises. Furthermore, the fusion smoother gives higher precision than any local smoother does.

Machine Learning for Data Fusion:A Fuzzy AHP Approach for Open Issues

Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and uncertain.Traditional data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw data.Data fusion is the process of integrating multiple data sources.Data filtering means examining a dataset to exclude,rearrange,or apportion data according to the criteria.Different sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional methods.The advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional methods.However,many open issues still exist as machine learning algorithms are used for data fusion.From the literature,nine issues have been identified irrespective of any application.The decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these issues.It helps to get the weights for each corresponding issue and rank issues based on these calculated weights.The most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted 0.141.The least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.

基于AESL-GA的BN球磨机滚动轴承故障诊断方法

针对基于知识的贝叶斯网络(BN)构建方法存在不完全和不精确的缺点,提出一种基于知识引导和数据挖掘的BN结构构建方法。针对单一信号故障诊断结果不精确的问题和故障信息中存在的不确定性问题,将电流信号与振动信号融合建立BN的特征节点,分别提取2种信号的故障特征参数,利用区分度指标法进行特征筛选,将其作为BN结构特征层的节点。将专家知识构建的初始BN结构结合自适应精英结构遗传算法(AESL-GA)进行结构优化,通过自适应限制进化过程中的搜索空间,减少自由参数的数量,提高其全局搜索能力,得到最优BN结构。通过MQY5585溢流型球磨机滚动轴承实测数据和Paderborn University轴承数据集对所提方法进行验证,结果证明了所提方法的有效性。

分布式雷达信号级融合检测的数据压缩与组网架构设计

分布式探测是雷达领域热点问题,信号级融合探测比数据级融合探测能力更强,但通常需要的通信带宽较大。为此文中针对分布式非相参信号级目标融合探测,提出了基于雷达压缩数据的信号级融合目标检测方法。所提方法通过可并行化计算的信号级融合算法实现不同雷达量测值之间的去耦,通过双门限检测避免传输局部低能量的噪声信号,通过二次量化对过门限信号进行再次压缩,最终实现以点迹通信带宽逼近信号级融合检测的能力。基于4雷达组网的数值仿真结果验证表明,通信带宽缩减至原来的1/1 000,信噪比损失不超过0.7 dB,并据此探索雷达组网的体系架构设计问题,可支撑不同场合下的信号级协同探测工程应用。

基于多模态轻量化混合模型的情绪识别

实现更加准确的情绪识别是当前面临的一项富含挑战性且十分有意义的任务。由于情绪的复杂多样性,单一模态的脑电信号难以对情绪进行全面客观的度量。因此本文提出一种多模态轻量化混合模型PCA-MWReliefFGAPSO-SVM,该混合模型由PCA-MWReliefF特征通道选择器和GAPSO-SVM分类器构成。选用脑电信号(EEG)、肌电信号(EMG)、体温信号(TEM)三模态信号进行情绪识别。在DEAP公共数据集上进行多次实验验证,在效价维度、唤醒维度和四分类中分别取得了97.5000%、95.8333%、95.8333%的分类准确率。实验结果表明,提出的混合模型有助于提高情绪识别准确率且明显优于单模态情绪识别。与近期的类似工作相比,本文提出的混合模型具有较高准确率、计算量小且通道数少的优点,更易于实际应用。

基于Lamb波损伤特征融合模型的金属结构件疲劳裂纹扩展预测

针对动态载荷环境下机械装备金属结构件疲劳裂纹扩展延伸问题,提出一种基于Lamb波损伤特征融合的疲劳裂纹扩展预测模型。首先从Lamb波信号传播特性出发,分析对比对称模式下Lamb波损伤信号和基准信号传播过程中的特性变化,在此基础上提取能够敏感表达结构损伤的相关系数和相位差异特征,通过变量标准化变换后进一步构建出疲劳裂纹扩展预测模型,最后利用金属结构件全寿命周期疲劳实验数据对模型进行验证。结果表明:所提模型能够准确预测动态载荷环境下疲劳裂纹扩展过程,与其他预测模型相比优势明显,可为机械装备关键结构件合理检修计划制定提供一定参考借鉴。

基于声振融合的二次EWT-CNN刀具磨损监测

为了实现加工过程中对刀具磨损状态的监测,提出一种基于协同过滤融合的方法。首先,对工作刀具振动信号和声音信号进行特征相关性分析后进行数据层融合;然后,将得到的声振融合信号进行二次经验小波变换(EWT)后去噪重构;最后,将重构信号进行信号增强并送入CNN实现特征提取及刀具故障识别。通过对不同故障类型的麻花钻头进行故障识别实验,在声音、振动以及声振融合信号和不同信号去噪重构方法的对比下,该方法对不同故障类型的钻头作出了98.96%的高识别率。验证了所提方法在刀具故障识别方面的优越性。

一种基于循环时空深度神经网络的手势识别方法

针对表面肌电信号解码模型因缺乏时空信息等重要性表征,面临解码精度低、鲁棒性差等问题,提出了一种基于循环时空深度神经网络的手势识别模型,来提高挖掘表面肌电信号的表征能力。首先,设计多通道卷积神经网络,并融入双向循环神经网络来提取强判别力的时空特征信息。其次,采用通道注意力机制来捕捉时空特征中通道重要性信息,设计基于时空特征的注意力模块以进一步增强时空特征信息。同时,基于特征金字塔网络思想来设计多尺度特征融合模块,从多尺度、多角度获取多级特征信息,提高模型对肌电信号的解码能力。最后,将所提出的手势识别模型在大型手势识别数据库Ninapro上进行测试,结果表明所提方法能有效提高对表面肌电信号的表征挖掘能力,为人体手势动作识别的深度学习建模工作提供借鉴意义。

雷达信号与遥感地图融合的深度学习低慢小目标检测算法

雷达复杂环境低慢小目标检测是一项具有挑战性的任务,而利用深度学习以及数据特征融合等方法是解决这一难题的有效手段。本文在雷达地图融合检测网络(Radar Map fusion Detection Network,RMDN)的基础上进行了优化,主要优化方向为将雷达与地图信息在检测过程中进行重要性程度区分,具体优化内容为减少地图特征提取模块的网络深度,加入通道注意力机制,让神经网络自主学习雷达信息与地图信息特征的权重,使神经网能够更好地利用地图信息对雷达目标进行辅助检测。在此优化基础上,本文重新设计出了雷达地图融合检测网络RMDN-V2。算法的主要思想为利用卫星遥感地图来提供背景环境信息,作为雷达信号检测的辅助,通过将目标背景中的特征信息融入检测决策中,提高目标检测的准确性和鲁棒性,减少对强杂波和移动物体的干扰敏感性,改善目标检测算法在复杂环境下的表现。最后的无人机雷达实测数据实验结果表明,本文所做的针对性优化是有效的,RMDN-V2的检测性能优于原始的RMDN,同时本文算法检测性能远超传统的雷达检测算法,同时也优于目前主流的一些深度学习雷达目标检测算法。本文为解决当下低慢小目标检测的难题提出了新的算法。

针对冲击性故障信号的谱融合特征提取算法

利用盲解卷积方法在时域中进行故障信号特征提取时,常会出现多个信号混淆分离结果,但以往的研究中只强调了分离的部分,而很少对分离后的信号进行进一步的处理,给实际应用造成不便。这里在盲解卷积和谱融合的基础之上,使用核改进的模糊c均值聚类算法,针对机械故障信号的脉冲特性,提出一种针对冲击性故障信号处理的实用型算法。计算机仿真实验证实了该算法的有效性。此算法优化了以往的聚类筛选方法,可以有效排除反卷积后诸多无用信号的干扰,将故障脉冲信号的特征准确提取出来,能提高故障诊断的效率。

表面肌电与三轴信息融合的运动判断实验

为了提高基于表面肌电与三轴加速度信号的运动识别准确率,提出了一套多源信息融合处理的实验流程与方法。该方法利用5层离散小波变换对表面肌电信号进行分解,充分提取不同运动产生的肌电信号中各频域的特征信息;再将分解后的表面肌电信号与三轴加速度信号通过滑动窗口的方法进行特征融合,构造融合肌电与空间运动特征的特征图;最后用融合特征图对深度学习模型进行训练,并结合自动状态机进行最终运动状态的识别。实验结果表明,多源信息融合处理方法可以提高运动识别的准确性,总体识别精度分别达到了95.4%和89.2%。该方法在实时性与准确性上均有良好表现。

基于小波包能量分析和信号融合的异步电机转子故障诊断

为提高异步电机转子故障诊断的可靠性,文中介绍了一种基于小波包能量分析和信号融合的异步电机转子故障诊断方法。采用定子电流信号和振动信号的频谱特征融合作为转子断条以及气隙偏心故障的诊断依据,首先对信号进行小波包分解,获得不同小波包频带节点下对应的能量分布,并与正常电机信号进行比较,进而对能量异常的信号频段进行小波包节点重构,最后通过快速傅里叶变换识别故障特征频率,诊断电机故障是否发生。通过仿真分析,验证了该方法的有效性和实用性,对于电机运行状态的准确监测具有重要意义。

基于多传感数据融合的变速运行齿轮异常振动故障诊断

变速运行齿轮异常振动故障诊断性能过差会增加汽车维护成本,缩短齿轮使用寿命。为了及时识别齿轮故障,保证汽车变速器总成具有良好的振动特性,提出基于多传感数据融合的变速运行齿轮异常振动故障诊断方法。通过分析多传感器数据融合技术,掌握变速运行齿轮异常振动故障诊断的理论框架,并以此为基础,参考传感器融合模块、特征级并行多神经网络局部诊断模块和终端分类模块,结合变分模态分解、多通道加权融合和单隐层前馈神经网络训练算法,从信号采集、信号特征提取和信号特征分类3个步骤实现变速运行齿轮异常振动故障诊断。实验结果表明:在齿轮发生轻度磨损时,磨损振动信号的幅值在20~40 mV之间,磨损振动信号的频率在0~4000 Hz区间;中度磨损时,信号的幅值在30~55 mV之间,信号频率在3000~7000 Hz区间;重度磨损时,信号幅值在50~70 mV之间,信号频率在6000~12000 Hz区间,且各阶段诊断结果均与故障程度的实际转折点吻合。由此可知在各样本数量均相同的情况下,提出的故障诊断方法预测值与真实值均相同,故障程度和故障类型的诊断性能均较好。

基于改进樽海鞘群算法的含瓦斯煤破裂过程信号特征识别

针对标准樽海鞘群算法存在的计算精度不足、易陷入局部停滞等缺陷,提出一种多策略融合的樽海鞘群算法。在初始化阶段,引入线性同余法随机发生器;利用野马算法优化樽海鞘领导者位置;采用金豺算法改进樽海鞘种群追随机制。通过测试函数寻优对比实验,证明多策略融合的樽海鞘群算法相比于其他智能算法在鲁棒性与稳定性方面均有显著提升。将多策略融合的樽海鞘群算法应用到含瓦斯煤破裂过程信号特征识别,实验结果表明:提出的含瓦斯煤破裂过程信号特征识别模型具有更好的表现,准确率可达93.33%,相比其他识别模型,识别率更高。

多通道钢丝绳的漏磁检测信号融合方法

分析了现有钢丝绳漏磁检测系统中存在的损伤信号幅值较小、前端多个磁敏元件处理方式较为简单等问题,提出了一种钢丝绳漏磁检测系统中的多通道信号融合方法。首先从磁敏元件阵列的角度出发,提出了多种磁敏元件阵列方式;其次从信号处理模拟电路的角度出发,设计了多通道信号融合硬件电路;最后,针对钢丝绳进行了实际测试,验证了此方法的可行性。

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。