Drilling condition recognition based on D-S evidence fusion and BP neural network

Drilling condition is the presentation of the operating state of the drilling system, and accurate identification of it can make drilling process safely and efficiently. At present, drilling condition recognition generally relies on personnel manual experience of worker, which has problems such as low accuracy, information lag and so on. In order to improve the accuracy and efficiency of recognition, and at the same time, to solve the problem of temporal discontinuity commonly found in current drilling condition recognition models. This article combines information entropy theory, correlation analysis, and expert experience to select the most suitable combination of drilling process parameters, founds an intelligent drilling condition recognition model based on the D-S evidence fusion and BP neural network. Finally, simulation experiments were conducted using real drilling data to evaluate the model's application.