An Artificial Neural Network Approach To Identify the Well Test Interpretation Model: Applications

Abstract

SPE Members Abstract The objective of this paper is to present the application of a new approach to identify a preliminary well test interpretation model from derivative plot data. Our approach is based on artificial neural networks technology. In this approach, a neural nets simulator which employs back propagation as the learning algorithm is trained on representative examples of derivative plots for a wide range of well test interpretation models. The trained nets are then used to identify the well test interpretation model from new well tests. In this paper we show that using artificial neural networks technology is a significant improvement over pattern recognition techniques currently used (e.g., syntactic pattern recognition) in well test interpretation. Artificial neural networks have the ability to generalize their understanding of the pattern recognition space they are taught to identify. This implies that they can identify patterns from incomplete and distorted data. This ability is very patterns from incomplete and distorted data. This ability is very useful when dealing with well tests which often have incomplete and noisy data. Moreover, artificial neural networks eliminate the need for elaborate data preparation (e.g., smoothing, segmenting, and symbolic transformation) and they do not require writing complex rules to identify a pattern. Artificial neural networks eliminate the need for using rules by automatically building an internal understanding of the pattern recognition space in the form of weights that describe the strength of the connections between the net processing units. The paper illustrates the application of this new approach with a field example. The mathematical derivation and implementation of this approach can be found in Ref. 1. Introduction In a pressure transient test a signal of pressure vs. time is recorded. When this signal is plotted using specialized plotting functions, it produces diagnostic plots such as derivative or Horner plots which we use often in the interpretation process. The signal on these plots is deformed and shaped by some underlying mechanisms in the formation and the wellbore. These mechanisms are known as the well test interpretation model. The objective of this work is to identify these mechanisms from the signatures present on the derivative plot. The problem of identifying the well test interpretation model has been described in the literature as the inverse problem. The traditional way of solving an inverse problem is to use inverse theory techniques (e.g., regression analysis). A major disadvantage of such techniques is that we have to assume an interpretation model. The inverse theory provides estimates of the model parameters but not the model itself. Realizing that more than one interpretation model can produce the same signal. This approach can lead to misleading results. What we seek in this study is the model itself rather than its parameters. Finding the model parameter after identifying the model is a simple problem. In this study we trained a neural nets simulator to identify the well test interpretation model from the derivative plot. The neural nets simulator can be part of a well test expert system or a computer enhanced well test interpretation. The mathematical derivation and implementation of this approach are detailed in Ref 1. LITERATURE REVIEW In 1988, Allain and Horne used syntactic pattern recognition and a rule-based approach to identify the well test interpretation model automatically from the derivative plot. Their approach is based on transforming the derivative plot into a symbolic form. The symbols generated (e.g., UP, DOWN, etc.) are used by a rule. based system to construct the shapes (e.g., maxima, minima, stabilizations) present on the derivative plot and, consequently present on the derivative plot and, consequently identify the well test interpretation model. The transformation process from digital data to symbols is carried out by process from digital data to symbols is carried out by approximating the derivative curve by a sequence of straight lines. The linear approximation is assumed successful when the fit error of each straight line is within an allowable tolerance. The attributes(e.g, the slope) of each straight line are used to describe the orientation (i.e., UP, DOWN, FLAT) of the curve segments based on preselected angle thresholds. Symbolic merging (i.e., grouping similar consecutive symbols as one symbol) is executed to reduce the symbols to the least possible number. This step is necessary to arrive at a finite number of rules which identify the well test interpretation model from the derivative symbolic form. P. 213