基于邻居节点预状态的无线传感器网络故障诊断算法

针对无线传感器网络（WSN）故障节点率高于50%时故障检测率降低的问题,提出一种基于邻居节点预状态及邻居节点数据的无线传感器节点故障诊断算法。首先利用节点自身历史数据对节点状态进行初步预判断;然后结合节点间相似性和邻居节点的预状态对节点状态进行最终的判断;最后利用移动传感器节点将故障节点信息通过最优路径发送给基站,有效地减少了通信次数。仿真实验在100 m×100 m的方形区域内模拟WSN。实验结果表明,与传统的分布式故障诊断（DFD）算法相比,诊断精度提升了9.84个百分点,并且当节点故障率高达50%时,该算法仍能达到95%的诊断精度。在实际应用中,所提算法在提高故障诊断精度的同时,能有效地减少能量消耗、延长网络寿命。     

一种改进的DFD无线传感器网络节点故障诊断算法研究

无线传感器网络是远程分布式环境监测的重要手段。节点故障诊断作为无线传感器网络的关键技术之一,是无线传感器网络大多应用领域不可或缺的环节。DFD算法是一种可应用于无线传感器网络的节点故障诊断算法,通过网络内邻居节点间的数据交换和相互测试诊断出故障节点。对DFD算法的诊断判据进行了修改,提出了改进的DFD算法。仿真结果表明,改进的DFD算法能适用于待诊断节点的邻居节点数较少、节点故障率较高的传感器网络,且大大提高了故障诊断精度。     

多传感器网络中的分布式故障检测算法

在传感器网络中,分布式故障检测算法(DFD算法)通过与所有邻居节点的传感器数据的比较判断,实现节点传感器的故障检测。但是,在故障节点聚集的网络区域,故障节点比例的上升将导致该区域的故障检测精度显著下降。针对多传感器网络,本文利用多传感器在相同区域的故障分布差异及传感器之间关联特性对DFD故障检测算法进行改进,提出适用于多传感器网络的MDFD算法,提高了故障聚集区域的检测精度。性能分析和仿真结果表明:在节点故障率高的网络中,与DFD和IDFD算法相比,MDFD提高了故障检测精度,算法适用于节点分布稀疏和传感器故障率较高的网络。     

分簇式无线传感器网络节点故障诊断算法研究

无线传感器网络(WSNs)分布式节点故障诊断算法是一种可用于WSNs节点的故障诊断算法,通过整个网络内邻居节点之间的数据融合诊断出故障节点.但分布式算法的计算量十分巨大,浪费了大量的节点能源,而且分布式算法中使用自定义的全局阈值会降低诊断精度,分簇式的节点故障诊断算法应用LEACH-DFD算法,通过簇头节点完成故障检测...     

基于加权中值的分布式传感器网络故障检测

无线传感器网络中的错误测量数据会导致网络服务质量下降和能量浪费.提出了一种通过融合邻居节点的测量数据来实现故障检测的策略.主要做了以下3项工作:(1) 提出了一种新颖的对邻居节点测量数据进行加权的方法;(2) 提出了一种衡量测量数据之间差距的方法;(3) 提出了基于加权中值的故障诊断策略WMFDS(weighted median fault detection scheme),它同时适用于二进制决策和实数测量值.理论分析及仿真结果表明,即使节点发生故障的概率很高,提出的诊断策略也能得到很高的检测精度和较小的误判率,这表明在无线传感器网络故障检测中应用该方法具有很好的性能.     

基于簇的分布式传感器故障检测算法

针对大规模无线传感器网络(WSN)中故障检测准确率降低,并产生较大通信负载的问题,根据传感器节点的时空相关性特点,提出一种基于簇的分布式传感器故障检测算法。通过邻居节点间的数据交换和互相测试检测簇首节点,并以正常簇首节点作为参照诊断故障节点。性能分析与实验结果表明,在大规模WSN中,该算法具有良好的故障检测能力和较低的通信负载,在邻居节点数较少、节点故障率较高的情况下,能达到98%以上的故障检测准确率,并保持较低的能耗水平。     

基于时间序列相似度的无线传感网故障检测算法

针对无线传感网中节点故障率高而导致检测精度低以及能耗大的问题,提出了基于时间序列相似度的无线传感网故障检测算法(FDABTS2).该算法利用节点时间序列进行差值和相似度的计算,剔除一定故障类型的节点,并对瞬时读数故障数据进行修正.当节点为可疑节点时,利用空间相关性,与剩余邻居节点协作完成判定.在仿真环境下,与LEFD、NADST以及传统的DFD故障检测算法相比,检测精度分别提高了13％、17％和25％,误报率分别降低了8.4％、21.4％和25.4％,网络能耗分别降低了2.9％、8％和21.3％,即使在瞬时读数节点故障率高达60％时,误报率也能分别降低1.9％、26.2％和38.2％.实验结果表明,该算法在保证高检测精度的情况下,仍能有效降低能耗,延长网络生命周期.     

基于数据驱动的WSN节点故障诊断算法

节点故障诊断是无线传感器网络持续性监测服务的关键步骤。为准确高效地得到诊断结果,提出一种基于数据驱动的故障诊断算法。对每个节点获取的信息建立空间高维向量,引入自身历史数据和邻居节点数据构造十字滑动窗口,并赋予十字方向上自定义的故障权重,通过检测异常向量达到故障诊断的目的。实验结果表明,该算法能够克服计算量大、故障判定条件苛刻等不足,与分布式故障诊断算法相比,可使故障诊断正确率提高15.5%,故障误警率下降4.89%。     

信息融合在带式输送机故障诊断中的应用

针对带式输送机输送距离长、运量大、速度快等特点,为克服带式输送机系统的复杂性和单一传感器很难判断出故障所在,在分析D-S证据理论信息融合算法的基础上,将信息融合技术应用于带式输送机故障诊断中,实现多个传感器采集并充分利用多个传感器资源,提高故障诊断率。仿真结果表明,该方法能准确诊断出系统的故障,有效克服单个信息源的主观性,使故障检测误报率降低,提高检测系统的可靠性。     

基于马尔科夫预测的多传感器故障检测与诊断机制

随着无线传感器网络应用规模的不断扩大,各类应用中传感器故障检测与诊断成为系统正常作业、安全可靠性保障的关键技术。针对多传感器系统与节点工作过程定义3种状态,基于故障检测信息建立状态转移矩阵,通过马尔科夫模型预测传感器故障信息,为故障检测与诊断提供决策依据。另外,拓展数据包信息字段包括故障类型、节点定位等,故障处理后节点转移至正常状态后将故障处理和诊断特征等信息存储到网关或者汇聚节点,为改善故障检测精度和诊断效率以及系统资源利用率提供依据。实验结果表明：所提故障检测与诊断算法与传统算法相比,具有更高的故障检测精度,更短的故障诊断时延、能够准确判断故障类型等性能。     

Fault diagnosis in wireless sensor network using negative selection algorithm and support vector machine

In this article, an improved negative selection algorithm (INSA) has been proposed to identify faulty sensor nodes in wireless sensor network (WSN) and then the faults are classified into soft permanent, soft intermittent, and soft transient fault using the support vector machine technique. The performance metrics such as fault detection accuracy, false alarm rate, false positive rate, diagnosis latency (DL), energy consumption, fault classification accuracy (FCA), and false classification rate (FCR) are used to evaluate the performance of the proposed INSA. The simulation result shows that the INSA gives better result as compared to the existing algorithms in terms of performance metrics. The fault classification performance is measured by FCA and FCR. It has also seen that the proposed algorithm gives less DL and consumes less energy than that of existing algorithms proposed by Mohapatra et al, Zhang et al, and Panda et al for WSN.     

无线传感器网络疑误数据节点自动诊断方法

为了提高无线传感器网络疑误数据检测能力,提出基于轮换调度的无线传感器网络疑误数据节点自动诊断方法.通过采用分块区域特征匹配的方法,得到无线传感器网络疑误数据传输的梯度模型,采用资源优化分配方案,进行数据传输信道的均衡调度,得到节点部署分布模型.通过传感信息跟踪采样方法,得到采样信息分布,建立无线传感器网络疑误数据信息特...     

基于时间序列数据的无线传感器网络的异常检测方法

伴随着无线传感器网络的发展和广泛应用,针对传感器网络在恶劣环境下传感器之间采样值差异大以及随着无线传感器网络故障节点增多导致事件检测不准确的问题,提出一种基于传感器网络时间序列数据的检测方法.利用传感器采集的K个正常数据的中位数建立枢轴量,构造置信区间,提出一种计算数据区间差异度的方法以判断发生异常的来源.实验结果表明,本文方法对传感器网络的异常数据检测率保持在98%以上,误报率保持在0.5%以下,具有一定的实用性.     

Genetic-based Fuzzy IDS for Feature Set Reduction and Worm Hole Attack Detection

The wireless ad-hoc networks are decentralized networks with a dynamic topology that allows for end-to-end communications via multi-hop routing operations with several nodes collaborating themselves, when the destination and source nodes are not in range of coverage. Because of its wireless type, it has lot of security concerns than an infrastructure networks. Wormhole attacks are one of the most serious security vulnerabilities in the network layers. It is simple to launch, even if there is no prior network experience. Signatures are the sole thing that preventive measures rely on. Intrusion detection systems (IDS) and other reactive measures detect all types of threats. The majority of IDS employ features from various network layers. One issue is calculating a huge layered features set from an ad-hoc network. This research implements genetic algorithm (GA)-based feature reduction intrusion detection approaches to minimize the quantity of wireless feature sets required to identify worm hole attacks. For attack detection, the reduced feature set was put to a fuzzy logic system (FLS). The performance of proposed model was compared with principal component analysis (PCA) and statistical parametric mapping (SPM). Network performance analysis like delay, packet dropping ratio, normalized overhead, packet delivery ratio, average energy consumption, throughput, and control overhead are evaluated and the IDS performance parameters like detection ratio, accuracy, and false alarm rate are evaluated for validation of the proposed model. The proposed model achieves 95.5% in detection ratio with 96.8% accuracy and produces very less false alarm rate (FAR) of 14% when compared with existing techniques.     

A new self-diagnosing approach based on petri nets and correlation graphs for fault management in wireless sensor networks

In most fault-detection algorithms in wireless sensor networks (WSNs), each sensor compares its data with the data of neighboring nodes. The majority of comparative methods will not work properly if more than half of the neighboring nodes of a sensor are faulty. Moreover, such comparative methods are unable to detect common mode failures (CMFs). Hence, having noticed the deficiencies of the existing comparative methods and as a reaction against such problems, we introduced a novel self-diagnosing approach to reduce the effect of neighboring node’s data in determining the status of nodes so that a sensor’s status will be determined independently of any comparisons. A sensor will be deemed to be fault-free if its components and the inner links between the components are flawless. In this paper, the behaviors of the components of a sensor are independently analyzed by means of the proposed model based on Petri nets and the links of the sensor’s components are investigated by means of the correlation graph. In addition, the authors extended and generalized the proposed method to all the nodes of a network and evaluated their operation. Simulation results showed that the modeling implemented by the HPSim tool can cover both permanent and transient faults accurately. Moreover, using the correlation graph and Pearson correlation coefficient helped us to gain confidence in the correctness of the inner links between the components of a sensor. Evaluation of the results indicated that the statistical results from the QI Macros tool were substantially similar to those from HPSim and Matlab tools. Furthermore, simulations results demonstrated that the detection accuracy and false alarm rate of the proposed method is acceptable even when the fault probability of each sensor is generally to be high. As a result, using these mechanisms leads to the development of the self-diagnosing capability in the sensors of a WSN.     

基于无线传感器网络的大型场所火情检测与定位算法

针对商场等大型场所火灾监控存在的火情态势估计不明、监控节点孤立、预警准确率低、火源定位不准确等问题,提出一种基于 无线传感器网络的大型场所火灾检测与定位算法。采用人工神经网络对火灾检测节点数据进行学习训练和火情估计,并经过模糊推理决策,给出火灾报警信息。利用受限空间烟雾扩散模型、气体温度扩散模型实现火源定位,并准确估计火情,以提供消防人员灭火决策。从单节点神经网络火灾报警仿真实验得出单节点火灾检测概率较高,同时从多节点火情定位实验得出,火情的覆盖范围描绘准确,火源定位精度较好。理论分析和实验结果表明火灾检测和定位算法是可行的。