Convolutional Neural Networks to Classify Oil, Water and Gas Wells Fluid Using Acoustic Signals

Abstract

Identifying the fluid type and predicting the amount of each fluid in the fluid mixture within the well pipes are important for oil and gas production energy industry and borehole water supply. Therefore automating this process will be very valuable for the oil industry because it maximises the quality and quantity of extracted oil and reduces the cost. The current study contributes to our knowledge by addressing this important issue using machine learning algorithms. The presented paper investigates the classification algorithms that identify the fluid type in oil, water and gas pipes using acoustic signals. The datasets analysed in this study are collected from real oil, water and gas well pipes under the sea where there is no controlled environment and data contains lots of noisy signals due to unpredicted events under the sea. Data is recorded during 24 hours from Distributed Acoustic Sensors which is attached alongside the 3500 m of three well pipes: oil, water and gas. The acoustic dataset are in time-distance domain and are converted to frequency-wave number domain using 2D fast Fourier transform. The outcome of 2D fast Fourier transform is sampled and fed into Artificial Neural Networks and Conventional Neural Networks algorithms to classify each fluid type. Both algorithms are trained on three datasets (oil, gas and water) and tested on another dataset. The result of this study shows Artificial Neural Networks and Conventional Neural Networks algorithms classify the fluid type with the accuracy of 79.5% and 99.3% respectively when applied on the test dataset.

A Survey on Distributed Fibre Optic Sensor Data Modelling Techniques and Machine Learning Algorithms for Multiphase Fluid Flow Estimation

“…Several different approaches can be used to measure the multiphase flow, including but not limited to, conventional dedicated hardware-based flow meters [ 7 , 10 , 14 , 15 , 43 ], virtual flow meters [ 17 , 18 , 39 , 42 , 45 , 46 , 47 ], and distributed sensor flow estimations [ 8 , 37 , 40 , 48 ]. This paper focuses on providing a comprehensive review of the last approach, using distributed sensors with physical flow modelling and machine learning algorithms for multiphase flow estimation.…”

“…It is the main backbone within the overall machine learning workflow. The data preprocessing includes gathering, cleansing, slicing, and transforming the input data to be forwarded and processed into the next step [ 37 , 99 ]. With the large size of the DS data, offline preprocessing sometimes is required to simplify the learning process and speed up the overall implementation, similar to that demonstrated in Vahabi et al’s work [ 37 ].…”

“…The handcrafted feature engineering techniques derive new properties using various algorithms or physical formulations based on the understanding of the physical phenomenons captured in the input data. The FFT transformation [ 37 ], bandpass filtering [ 99 ], F-K filtering [ 103 ], and physical flow feature transformations in Section 4.2 are considered handcrafted feature engineering techniques. On the other hand, the non-handcrafted techniques generate new properties without understanding the physical phenomenons surrounding the input data.…”

“…The aim is to provide new representations of the input data that are useful for achieving accurate prediction. Multi Layer Perceptron (MLP) [ 104 ], Binary Descriptor [ 105 ], and multi-stage CNNs [ 37 ] are considered as the non-handcrafted engineering techniques that can be used for multiphase estimation. Dimensional reduction algorithm, such as Principle Component Analysis (PCA), can be used to reduce the number of features while selecting highly relevant features for multiphase estimation objective [ 57 , 106 ].…”

“…In recent years, the ability to perform similar tasks using data-driven machine learning algorithms have been explored. For example, Convolutional Neural Network (CNN) and Artificial Neural Network (ANN) have been used to perform flow regime classification and multiphase estimation [ 36 , 37 ]. Subsequently, the ANN with Long Short-Term Memory (LSTM) algorithm has also been used to perform fluid flow rate estimation [ 38 , 39 , 40 , 41 ].…”