盾构液压系统状态预测

为了解决固定模型预测时变系统容易出现较大误差的问题,提出模型更新算法,即将移动窗算法与传统灰色预测模型相结合的方法.通过在建模序列中删除一部分旧数据、纳入一部分新数据的方式递推更新预测模型,并分解数学模型所涉及的关键量a、b从而简化递推数学公式|讨论移动窗长度对建模精度的影响|利用国家统计年鉴的统计数据验证上述方法的有效性.以盾构管片拼装机液压系统为例,为已知故障和测试故障样本数据分别建立变量加权的有源自回归模型,依次获得自回归系数用于特征提取,利用灰色综合关联度建立系统与已知状态的时间序列,通过仿真和实验,该模型更新算法实现液压系统的状态预测.结果表明，递推更新有助于传统灰色预测模型更切实反映液压系统状态的变化.

State prediction on hydraulic system of shield

In order to solve the problem that being easy to have big error through fixed model monitoring time varying system, the methods combing moving windows algorithm with grey prediction algorithm(MWGM(1,1)) was proposed. describing detailed recursive algorithm to update prediction model adopting the way of removing part of past data from modeling sequence and absorbing new ones from sampling data, and key quantities of prediction math model that were a&b were decomposed in order to simplify recursion formula. then describing how to determine the length of windows were done. the effectiveness of such MWGM(1,1) algorithm was tested by statistical data from national statistics yearbook. Taking hydraulic system of shield for example, variable-weighted auto-regressive with extra inputs algorithm constructed system model by known fault sample and testing fault sample, to gain each autoregressive coefficients for extracting feature, and the time series about this system and known state gained by gray comprehensive relational grade, and the state prediction was realized by improving grey model. The test result shows that it is helpful to make model react the hydraulic system state changes by recursive updating effectively.