Research on Data-Driven Schedule Measurement Algorithm for Oil and Gas Pipeline Engineering

In this paper, a data-driven progress measurement algorithm based on untracked Kalman filter (UKF) and data fusion technology is proposed to solve the complex problems in the progress measurement of oil and gas pipeline engineering. The algorithm aims to realize the optimal estimation and progress prediction of multi-source data. Firstly, a data-driven method is used to construct a dynamic model of engineering progress, which integrates historical data and real-time data to improve the accuracy of the model. Then, the state of nonlinear system is estimated by UKF algorithm, and the process of data fusion is optimized to improve the accuracy of schedule prediction. In the system simulation, a variety of complex conditions are designed, and the progress prediction effect under different conditions is analyzed in detail. The analysis results show that with the support of multi-source data fusion, the proposed algorithm significantly reduces the prediction error and improves the accuracy and stability of progress measurement. Especially in the high noise environment, the simulation data clearly demonstrate the robustness of the algorithm and its application potential in complex scenarios.