模型水轮机初生空化的特征谱提取识别方法  

Extraction and recognition method of characteristic spectra for incipient cavitation of model turbines

作　　者：韩文福 倪晋兵 桂中华 满哲 丁景焕 肖微 李东阔 汪刚 HAN Wenfu;NI Jinbing;GUI Zhonghua;MAN Zhe;DING Jinghuan;XIAO Wei;LI Dongkuo;WANG Gang(Institute of Pumped Storage Technology and Economics,State Grid Xinyuan Group Co.,LTD,Beijing 100053,China;DongFang Electric Machinery Co.,Ltd,DongFang Electric Corporation,Deyang 618000,China)

机构地区：[1]国网新源集团有限公司抽水蓄能技术经济研究院,北京100053 [2]中国东方电气集团有限公司东方电机有限公司,四川德阳618000

出　　处：《水力发电学报》2023年第8期69-79,共11页Journal of Hydroelectric Engineering

基　　金：国网新源公司科技项目资助(525730210006)。

摘　　要：目前水轮机模型初生空化识别方法仍采用人工识别法,这种方法获得结果的周期较长、主观性强、准确度及效率都较低。针对于此,对水轮机模型初生空化识别方法进行了研究与优化创新,提出了一种基于炮声谱与特殊脉动谱特征提取的水轮机空化智能识别方法,即多态泡音智能识别方法 PSVFR。该方法依据自主开发的水轮机空化噪声多态算法MTCSPC,对数据进行处理,通过采集初生空化音态特征向量,建立矩阵模型,与样本数据库中的定性矩阵进行特征比对、计算、判断,以帮助机器完成对模型水轮机空化噪声的学习和识别。与现有技术相比,该方法能够提高机器对水轮机初生空化现象的识别准确度和识别效率,识别效率可达80%。At present,incipient cavitation in a model turbine is identified as before using the manual method whose shortcomings are a long period of data acquisition,strong subjectivity,low accuracy,and low efficiency.To improve incipient cavitation identification,this paper develops an intelligent identification method of turbine cavitation-namely the intelligent recognition method of multimodal bubble sound PSVFR based on feature extraction of cannon sound spectra and special pulsation spectra.In this method,turbine cavitation noise data are processed using MTCSPC,a multistate algorithm independently-developed by the authors.By collecting the feature vectors of incipient cavitation tones,a matrix model is constructed;then calculation and judgment are made through feature comparison with the qualitative matrix in the sample database,so as to help the machine complete the learning and recognition of model turbine cavitation noise.Compared with previous technologies,this method improves the accuracy and efficiency of machine identification of turbine incipient cavitation,with a recognition efficiency reaching up to 80%.

关 键 词：模型水轮机空化 空化识别 泡音智能识别 音态特征向量 特征谱 

分 类 号：TK730[交通运输工程—轮机工程]