An algorithm study for determination of dynamic fluid level based on the state space reconstruction and BH-LSSVM
Tong Wang, Lai Haozhe, Zijian Jiang · 2014
The dynamic fluid level of oil well is essential for the submersible motor. The prediction of dynamic fluid level is a popular research direction. This paper describes an approach to short-termly determine the dynamic fluid level by using the algorithm which combines the state space reconstruction and black hole least squares support vector machine (BH-LSSVM) algorithm together. The chaotic time series has to be reconstructed in the state space. Then based on the data of the reconstructed state space, the fluid levels will be determined dynamically, by using BH-LSSVM algorithm. The simulation results show that this algorithm has much higher accuracy on measurement of dynamic fluid level for oil well. It fulfills the requirements of the oil-well task. It can be deployed in oil well to measure the dynamic fluid level.