风力发电机组振动状态监测与故障诊断系统研究-机械工程专业论文.docxVIP

摘要 摘要 I I 摘 要 风力发电机组传动系统自身结构复杂，在故障检测和维修中都会占用很长时 间，对电力生产造成的影响也很大，因此对风力发电机组传动系统的故障进行预 警和诊断具有重要的实际价值。论文依据信号分析和人工智能技术，对风力发电 机组传动系统振动监测与故障诊断系统展开研究。 论文首先以某风场某型号 1.5 兆瓦风力发电机组齿轮箱和轴承为研究对象， 计算了齿轮箱各级齿轮和轴承的故障特征频率，分析了齿轮箱高速轴测点的振动 信号，提取了 3 种故障信号的特征，特征分析结果与开箱检查的故障相符合，为 专家系统的故障特征知识库的建立奠定了基础。 然后论文构建了专家系统的知识库和推理机，结合传动系统的信号处理， 分析了正常和故障零件的峭度指标值、频谱能量分布值、信息熵值的差异。确定 了峭度指标作为监测特征参数，以频谱能量分布值与信息熵作为故障特征参数。 以训练后 BP 神经网络作为专家系统故障诊断的推理机，将提取到的齿轮箱振动 信号的故障特征参数作为输入样本进行仿真测试，测试结果显示推理机能够实现 故障诊断的目标。 最后，基于 LabVIEW 软件的开发环境，设计了风力发电机组传动系统振动 监测与故障诊断系统，系统能实现的功能主要包括信号的时域波形显示、频域分 析、降噪处理、故障预警、故障诊断、数据管理等。 关键字：风力发电机组，传动系统，状态监测，故障诊断，专家系统 Ab Abstract II II Abstract The structure of wind turbine drive system is large and complex, whose fault detection and repair would take long time and the impact on electric power production is also great. Therefore, it has important practical value for early warning and fault diagnosis on the drive system of wind turbine. Based on signal analysis and artificial intelligence technology, the wind turbine drive system of vibration monitoring and fault diagnosis system was studied. Firstly, in this paper，it takes a type of 1.5MW wind turbine gearbox and bearing as the study object, calculates the fault characteristic frequency of gearbox and bearing, analyses vibration signal on the high speed shaft measuring point of gearbox, extracts the characteristics of three kinds of fault signal. The result of analysis is consistent with fault check out of the box, laid the foundation for the fault feature of the knowledge base of expert system. Secondly, the knowledge base and reasoning machine of expert system were constructed. In this paper，combined with the signal processing, the differences between the normal and fault parts of the kurtosis index and the spectral energy distribution, information entropy were analyzed, the knowledge base were constructed whose monitoring parameter is kurtosis index and fault characteristic parameter is spectrum energy value and the