摘要 在无线传感器网络(WSN)中,容易因为故障节点存在冗余的故障属性、噪声数据以及数据可靠性等问题,从而产生传输错误数据,这将极大地消耗WSN节点中能量和带宽,向用户形成错误的决策。为此,提出了基于蚁群算法和BP神经网络模型的WSN节点故障检测方法。通过使用蚁群算法,使用户通过寻找优化路径来定位WSN节点的位置,通过这种随机搜索算法以及蚁群算法的搜索策略使用户对WSN故障节点的位置进行总体把握。然后又基于BP神经网络模型对获取的WSN故障节点信息进一步学习,在数据训练过程中,依据WSN故障节点预测误差,并进一步调整网络的权值和阈值,增加了故障诊断的精度。采用的算法对检测WSN故障节点具有较好的性能,使无线传感器网络的服务质量大大提高,增强了系统的稳定性,实验结果验证了算法的可行性和有效性。 In the wireless sensor network(WSN),it is easy to generate and transmit erroneous data due to redundant fault attributes,noise data,and data reliability of the faulty node.Thereby generating and transmitting erroneous data,which will greatly consume energy and bandwidth in the WSN node,and form an erroneous decision to the user.Aiming at this problem,this paper proposes a WSN node fault detection method based on ant colony algorithm and BP neural network model.By using the ant colony algorithm,the user locates the location of the WSN node by searching for an optimized path.The random search algorithm and the ant colony algorithm search strategy enable the user to grasp the overall location of the WSN fault node.Then,based on the BP neural network model,the WSN fault node information is further learned.In the data training process,the WSN fault node prediction error is further adjusted,and the weight and threshold of the network are further adjusted to increase the accuracy of fault diagnosis.The algorithm used has better performance for detecting WSN fault nodes,which greatly improves the service quality of wireless sensor networks and enhances the stability of the system.The experimental results verify the feasibility and effectiveness of the algorithm.
出处 《计算技术与自动化》 2021年第1期38-42,共5页 Computing Technology and Automation
关键词 WSN节点 故障检测 蚁群算法 BP神经网络模型 定位 WSN node fault detection ant colony algorithm BP neural network model localization
