No abstract

Trilinear flow model is an effective method to reproduce the flow behavior for horizontal wells with multistage hydraulic fracture treatments in unconventional reservoirs. However, models developed so far for transient analysis have rarely considered the inflow performance of wells. This paper introduces a new composite dual-porosity trilinear flow model for the multiple-fractured horizontal well in the naturally fractured reservoirs. The analytical solution is derived under a constant rate condition for analyzing transient pressure behaviors and generating the transient inflow performance relationships (IPRs). The plots of pressure profiles with time could provide insightful information about various flow regimes that develop throughout the entire production cycle. Sensitivity analysis of pressure and pressure derivative response was also performed by varying different parameters (such as hydraulic fracture width and permeability, reservoir configurations, etc.) and by which the impacts of different parameters on the durations of regimes as well as the productivity index can be confirmed. The main outcomes obtained from this study are as follows: (1) the ability to characterize naturally fractured reservoirs using a new composite dual-porosity trilinear flow model; (2) the application of analytical solutions of transient analysis to generate transient IPR curves for different flow regimes; (3) understanding the effect of reservoir configurations, fractures, and matrix characteristics on pressure distribution, flow regime duration, and transient IPR. More specifically, the pressure drop increases and the productivity index decreases with the decrease of the hydraulic fracture conductivity and the increase of matrix permeability and the skin factor. Also, the larger hydraulic fracture spacing and drainage area result in the later onset of the pseudo-steady-state regime. (4) A comprehensive study on transient pressure behaviors and transient inflow performance can provide valuable information to characterize the multifractured complex systems as well as some insights into the production.

No abstract

A set of dynamic remote monitoring method of production performance based on Machine Learning is proposed for the production process of electric submersible pump (ESP) well with multi-dimensional parameters. Aiming at dealing with the characteristics of multi-dimensional parameters in the complex production system, to implement dynamic monitoring of production performance. Helping the engineers at data centers to find the anomaly remotely and make response in a timely manner. It puts forward a procedure for large amount, high dimension and low information density production data in complex production system, using the dimensionality reduction algorithm to reduce the dimensionality into one comprehensive parameter changing over time, time series analysis algorithm for the production anomaly detection and prediction based on Machine Learning. The Principal Component Analysis (PCA) is used to reduce the dimensionality and extract the crucial information. The Autoregressive Integrated Moving Average (ARIMA) model is used to conduct timing anomaly detection, and fbProphet model is used to analyze the dimensionality reduced data to provide prediction of the production. With the dimensionality reduction, time series comprehensive parameter analysis and anomaly detection method based on Machine Learning, more than 40 ESP wells with 15 dimensions production daily parameters up to 1,000 days were analyzed, which realized the comprehensive description of ESP wells with multiparameter. Although the PCA retained only 47.73% of the information in the first principal component, which may be related with the low information density of industrial big data, the subsequent analysis proved the effectiveness. The time series analysis realized many times anomaly detection during the life period of each ESP well, and visualized the production data and the anomalous events. More than 100 anomalous events were detected in advance and which were robust corresponding to the subsequence real production events, among which 95% agreement rate is achieved. The procedure proposed reported the anomaly events with high confidence up to 90%, and low misstatement rate and omission rate, realized the production perception and abnormal detection in a timely manner. Based on this algorithm, the best time for the well intervention is determined, so that the loss of production is avoided and the revenue is maximized. The novelty of the procedure of Machine Learning using the multiple production data is in the ability to provide a solution of dealing with the low information density and high noise in the complex multi- dimensional production data of production wells, realize the comprehensive description, analysis and prediction of the production. It is helpful for engineers find the abnormalities in time, and will support the decision making of production, optimization and well intervention for the production.

Although currently, large-scale and multilateral horizontal wells are an important way to improve the oil recovery in the unconventional reservoirs, the flow behavior of fluid from the reservoir into the horizontal wellbore becomes more challenged compared to the single small-scale horizontal well. One of the main challenges is that pressure loss from the well completion section and wellbore cannot be ignored in the coupling process between the reservoir and the horizontal well. In this paper, a new method is presented to solve the coupling flow between the reservoir and the horizontal well with different well completions. The new coupling model is compared with Ouyang’s model (1998) and Penmatcha’s model (1997), and the predicted data are consistent with each other at both early and late times. Meanwhile, four different cases have been proposed to verify the application of the new coupling model with different well completions, and the results indicate that the uneven inflow profile can be effectively alleviated via reasonable completion parameters and different well completions. Based on two types of flow-node units, it can quickly model and solve the coupling problem between the reservoir and the horizontal well with complex completion cases. It can also depict the inflow profile of the horizontal well with different well completions, which is conducive to understand the coupling process. The new coupling model can provide theoretical support for further optimization of completion parameters and well completions and finally improve oil recovery.