基于WSN的井下人员定位融合算法研究

发布时间：2018-04-10 08:05

本文选题：无线传感器网络　切入点：自组织竞争网络　出处：《中国矿业大学》2017年硕士论文

【摘要】：无线传感器网络(Wireless Sensor Network,WSN)技术是一门涉及多学科的网络通信技术,也是实现物联网快速发展的基础。该领域一直受到众多学者的关注。由于该领域发展相对缓慢,在很多技术层面还有很大的欠缺,因此国内外的科研人员与学者一直对该领域保持着高度的关注。随着经济社会的发展,人员定位在人们生活中的需求越来越多,无线传感器网络节点由于具有节点能耗低、成本少、功能齐全等特点,因此WSN在人员定位技术中得到广泛应用,例如煤矿井下人员定位。但是在定位过程中,由于环境的影响,基于WSN井下人员定位的精度受到很大影响。由于井下环境复杂多变,多径效应明显,井下结构特殊等因素的存在,导致在井下人员定位过程中,对测量信号造成干扰,最终导致定位精度无法提高。为提高井下人员定位精度,本文针对井下特殊环境中人员定位技术进行分析研究,主要内容如下:针对多径效应导致信号失真、错误以及非失真信号的干扰,利用自组织神经网络对信号进行训练,筛选掉失真错误信号,而对于非失真信号主要在反馈滤波基础上利用RSSI(Received Signal Strength Indication)与LQI(link quality indicator)获得一个权重值a,根据不同的数据测量范围选择不同的权重值a作为标准来对RSSI进行滤波处理。针对井下环境以及结构的特殊性,在最终定位时无法利用精简有效的信号进行定位,对此首先利用相似度对未知节点进行初步定位,其次根据相似度选取合适有效的信标节点,利用相似度作为加权系数,并结合质心算法进行最终的精确定位。文章最后给出了人员定位的应用模型,在学校教四楼的504实验室和楼道走廊内进行了实验,并通过软件仿真对定位效果进行对比和分析,结果证明文中提出的融合型定位算法达到了预期的效果,一定程度上满足了井下复杂环境中的人员定位需求。
[Abstract]:Wireless Sensor Network (WSNs) technology is a multi-disciplinary network communication technology, which is also the basis of the rapid development of the Internet of things.This field has been concerned by many scholars.Because the development of this field is relatively slow and there are still many technical deficiencies in this field, researchers and scholars at home and abroad have been paying close attention to this field.With the development of economy and society, there are more and more demands for personnel positioning in people's life. Wireless sensor network nodes have the characteristics of low energy consumption, low cost and complete functions, so WSN has been widely used in personnel positioning technology.For example, underground coal mine personnel positioning.However, due to the influence of environment, the positioning accuracy of underground personnel based on WSN is greatly affected in the positioning process.Due to the complex and changeable environment, obvious multipath effect and the existence of special underground structure, the measurement signal is interfered in the process of underground personnel positioning, and the positioning accuracy can not be improved.In order to improve the positioning accuracy of underground personnel, this paper analyzes and studies the human positioning technology in the special underground environment. The main contents are as follows: the multipath effect leads to signal distortion, error and non-distortion signal interference.The self-organizing neural network is used to train the signal and filter out the distorted error signal.On the basis of feedback filtering, RSSI(Received Signal Strength indication and LQI(link quality indicator are used to obtain a weight value a. According to different measurement range, different weight value a is chosen as the standard to filter RSSI.In view of the particularity of underground environment and structure, it is impossible to use the reduced and effective signal to locate the location in the final location. Firstly, the unknown node is located by similarity, and then the appropriate effective beacon node is selected according to the similarity.The similarity is used as the weighting coefficient and the centroid algorithm is used for the final accurate location.Finally, the application model of personnel positioning is given, and the experiment is carried out in 504 laboratory and corridor on the fourth floor of the school, and the effect of location is compared and analyzed by software simulation.The results show that the fusion localization algorithm proposed in this paper achieves the desired effect and meets the needs of personnel location in the complex underground environment to some extent.
【学位授予单位】：中国矿业大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TN92;TP212.9

【参考文献】