一种基于罚函数的数据协调模型

Novel Data Reconciliation Model Based on Penalty Function

如果工业测量数据中存在显著误差,则传统的数据协调模型会将显著误差分散到各个测量值中去.针对于传统数据协调模型的缺陷,本文通过添加一个基于测量值比例关系上下限的约束条件,并利用罚函数的概念将物料平衡的约束条件以软约束的形式表示,建立一种新的数据协调模型.改进后的数据协调模型只会对含有显著误差的测量值给予较大的协调量,而使得显著误差对其他测量值协调结果的影响较小,具有较高的鲁棒性.基于工业实际生产模型的仿真试验证明基于该数据协调模型的协调结果,可直接利用测量残差检测法进行显著误差检测,具有较高的错误检出率,且第I类错误率较低.

Traditional data reconciliation model tends to spread the gross errors overall the measurements, in order to avoid the problem this paper proposed a new data reconciliation model. In this work, some new constraints derived from the ratio of measurements is inducted and the constraints based on material balance are put into soft constraints form by using the method of penalty function. The data reconciliation procedure using the improved model tends to make the measurements having gross errors get more effect than the others. Thereby, the new data reconciliation model is more robust than the old. Based on the results of the new model, the measurement test method can be used to detect gross errors, and the result of simulations shows that the gross error detection base the new data reconciliation model is very sensitive to presence of gross errors and has a great probability of correctly finding one or several gross errors.