大型水轮发电机组状态监测与智能故障诊断系统研究

【作者】 余文宁；

【导师】 王雅琳；

【作者基本信息】 中南大学 ， 控制理论与控制工程， 2007， 硕士

【摘要】 水轮发电机组是大型机电能量转换装置，其运行状态关系到水电站能否安全、经济的供电。近百年来，以统计理论为基础，按计划定期进行小修、中修、大修的维修体制，普遍存在着过维修和不足维修，特别是近年来随着水轮发电机组的巨型化，这种维护体制更加暴露出严重的不足。因此，实现有效的机组状态监测和故障诊断，提高维修的针对性，不仅对电力工业，而且对整个国民经济都有重要的影响。本文在分析与总结水轮发电机组状态监测与故障诊断特点的基础上，重点针对机组振动故障机理、故障征兆提取方法以及混合智能诊断方法进行研究。首先，依据导致水轮发电机组振动故障的三类振源，按机械、水力、电气三类故障类型进行研究，分析振动故障机理，总结故障特征，并给出相应的故障处理意见。然后，根据水轮发电机组轴心轨迹的特点，基于分形几何学，采用分形维数来定量描述转子轴心轨迹的特征，实现图形量化，为水轮机组振动故障的在线诊断创造条件。最后，以人工智能方法为基础，提出基于模糊神经网络的专家系统故障诊断方法，阐述了水轮机组故障征兆的模糊处理、模糊神经网络故障诊断模型在水轮发电机组故障诊断专家系统中的应用。实例仿真结果验证了模糊神经网络用于水轮发电机组振动故障诊断专家系统的合理性与可行性。在此研究基础上，开发了水轮发电机组状态监测与故障诊断系统。实现了数据采集和信号分析、实时状态监测和运行趋势分析、异常参数与异常状况报警与诊断等功能，并提供操作指导，避免维修的盲目性，有利于降低企业成本，并能够提高水电站运行的安全性和可靠性。更多还原

【Abstract】 Hydroelectric generating sets are large apparatus, which convert hydraulic energy into electric power, and their running conditions determine whether the hydro-plant can supply electric power safely and economically. During the past century, the servicing system for the HGS which according to the planning based on statistics theory carrys out the minor repair, medium repair and heavy repair at the regular intervals has the shortcomings of superfluous or lacking repair generally. Especially with the hydroelectric generating set colossal-rization, the shortcomings are more obvious, which increase the cost of the enterprise. Therefore, the effective system of state monitoring and fault diagnose for HGS, which can improve the repair pertinency and enhance the security and reliability of HGS, have important effect to power industry and to entire national economy.Based on the analysis of characteristics of state monitoring and fault diagnosis for HGS, this dissertation emphasizes on the vibration fault mechanism, extracting ways for the vibration fault symptoms and the intelligent fault diagnosis technology. Firstly, according to the three kinds of causes, the vibration faults of HGS are divided into mechanical vibration fault, electromagnetic vibration fault and hydraulic vibration fault. This dissertation analyzes the fault mechanism, summarizes the fault symptoms and presents the solutions. Then, according to the shaft orbit’s characteristic, based on the fractal geometry, fractal dimension is applied to extracting structure feature of shaft orbit, in order to realize figure quantification for on-line vibration fault diagnosis. At last, based on the intelligent fault diagnosis methods, an expert system fault diagnosis method based on fuzzy neural networks is proposed. The fuzzification for the vibration fault symptom, the fuzzy neural networks model in the fault diagnosis expert system of HGS are described in detail. The simulation results show that the intelligent integrated fault diagnosis method is reasonable and feasible.Based on the research mentioned above, a state monitoring and fault diagnosis system of HGS is developed. This system can collect data and analyse signal, monitor running state and forcast the trend, give an alarm and diagnosis for unnormal detected parameters and unwonted state, the operational instructions are given at the same time, which can avoid the blindness for servicing, reduce the the cost of the enterprise, and enhance the security and reliability of plant.更多还原