Intelligent Recognition Method of Insufficient Fluid Supply of Oil Well Based on Convolutional Neural Network

Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.

On the experimental characterization of the fluid volume influence on the friction between rough surfaces

The load-bearing behaviour of lubricated contacts depends primarily on the normal force,the relative velocity,and the geometry.Thus,with the aid of the Stribeck curve,it is usually well possible to characterize whether hydrodynamics,mixed friction,or boundary friction is more likely to be present.The fact that the load regime can also depend on the fluid quantity is obvious,but has hardly been systematically investigated so far.Especially for contacts with microscopic roughness,the defined application of a very small amount of fluid is a very challenging requirement.In this paper,a very fundamental study shows how a pin-on-disc tribometer can be used to achieve the transition from dry friction via mixed friction to predominant hydrodynamics by the amount of supplied fluid.The experiments are carried out on samples filed with different coarseness.In addition,the simultaneous influence of partial filling and normal force as well as relative velocity is also shown.Very good reproducibility has been practically reached over the entire range of the tests.Regarding the quantities for the coefficient of friction(COF),it was concluded that close to full filling,a reduction of the fluid quantity has a similar effect on the COF as the reduction of the velocity.This property goes along with the common theory of starved lubricated systems.Such behaviour was not observed to the same extent for the normal force.In the vicinity of smaller fluid quantities,the COF increases very rapidly with further reduction in fluid quantity,far more disproportionately than that with reduction in velocity.With a deeper understanding of this problem,various practical issues such as idling or the run-up process in bearings can also be studied in a more focused manner.