智能断路器机械特性在线监测及故障诊断

发布时间：2018-03-21 22:13

本文选题：智能断路器　切入点：机械特性　出处：《西安工程大学》2015年硕士论文　论文类型：学位论文

【摘要】：智能断路器作为变电站必不可少的设备之一,起着保护及控制作用,其健康状况的优良和电力系统能否正常运作息息相关。为确保电力系统的可靠运转,对断路器的使用寿命及质量提出严格要求。因此,智能断路器机械特性在线监测及故障诊断技术应运而生。该技术能够实时把握高压断路器的健康状况,并针对出现的异常情况进行相应的故障诊断,以便于及时维修,这对提高电力设备的智能化水平具有重要作用。首先,本文介绍了断路器各机械参量的监测原理,并针对监测原理提出了机械参量的计算及分析方法。本文针对TMS320F28335芯片给出了智能断路器在线监测装置的硬件设计和软件流程思想,该芯片集成了许多功能模块,从而简化了PCB电路板的设计,在线监测装置的综合软件程序能够稳定可靠的采集设备的机械参量数据信息。与此同时本文还提出了原始采集参数的数据预处理及滤波方法,保证了数据采集的精确性。智能断路器在线监测装置监测的机械参量主要包括分合闸线圈电流、储能电机电流、动触头行程-时间特性、辅助接点状态等。其次,针对智能断路器运行的特点,论文详细介绍并分析了一种基于粗糙集-RBF神经网络的故障诊断算法。该部分首先利用粗糙集理论获得智能断路器运行情况的最小诊断决策表,最后利用该决策表建立的RBF神经网络对智能断路器故障进行综合诊断。在该合成算法中,粗糙集能够简化监测设备采集量所构成的复杂网络,获得能够满足实际需求的最简网络,从而减少了RBF神经网络的训练时间,并且在很大程度上提高了网络的诊断能力。智能断路器机械特性在线监测装置已在浙江江山勾山变电站成功运行。勾山变电站的专家软件系统中融合的粗糙集-RBF神经网络算法能够对各断路器的健康状况作出准确诊断。由此说明,智能断路器机械特性在线监测及故障诊断技术可以良好的应用于实际工程中,对于未来电网建设具有重要意义。
[Abstract]:As one of the essential equipments in substation, intelligent circuit breaker plays a protective and control role. The good health of intelligent circuit breaker is closely related to the normal operation of power system. Strict requirements for the service life and quality of circuit breakers are put forward. Therefore, the on-line monitoring and fault diagnosis of mechanical characteristics of intelligent circuit breakers emerge as the times require. This technology can grasp the health status of high voltage circuit breakers in real time. And the corresponding fault diagnosis is carried out in order to facilitate timely maintenance, which plays an important role in improving the intelligent level of power equipment. Firstly, this paper introduces the monitoring principle of the mechanical parameters of circuit breakers. According to the principle of monitoring, the calculation and analysis method of mechanical parameters is put forward. In this paper, the hardware design and software flow of intelligent circuit breaker on-line monitoring device are presented for TMS320F28335 chip, which integrates many functional modules. Therefore, the design of PCB circuit board is simplified, and the comprehensive software program of on-line monitoring device can acquire the mechanical parameter data information of the equipment stably and reliably. At the same time, this paper also puts forward the data preprocessing and filtering method of the original acquisition parameters. It ensures the accuracy of data acquisition. The mechanical parameters of the on-line monitoring device of intelligent circuit breaker mainly include the current of closing coil, the current of energy storage motor, the travel time characteristic of dynamic contact, the state of auxiliary contact, and so on. According to the characteristics of intelligent circuit breaker, a fault diagnosis algorithm based on rough set RBF neural network is introduced and analyzed in detail. Finally, the intelligent circuit breaker fault diagnosis is made by using the RBF neural network established by the decision table. In this synthesis algorithm, rough set can simplify the complex network made up of the data collected by the monitoring equipment. The minimum network can be obtained to meet the actual needs, thus reducing the training time of the RBF neural network. The on-line monitoring device for mechanical characteristics of intelligent circuit breakers has been successfully operated in Zhejiang Jiangshan Gushan Substation. Rough set -RBF fused in expert Software system of Gushan Substation. The neural network algorithm can accurately diagnose the health status of the circuit breakers. On-line monitoring and fault diagnosis of mechanical characteristics of intelligent circuit breakers can be well applied in practical engineering, which is of great significance for future power grid construction.
【学位授予单位】：西安工程大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TM561

【相似文献】