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.

No abstract

This study was conducted to estimate the downhole speed of flow in oil wells and determined the flow direction by analyzing acoustic data recorded by fibre optic distributed acoustic sensors. The signals generated from acoustic data are in the time versus distance domain that are then normalized and differentiated with respect to distance. A 2D Fast Fourier Transform is used to convert time to frequency and distance to wave-number for subsequent calculation. A Gamma correction function was employed to enhance an intensity of the signal in the frequency wevenumber domain. Also, decaying function was successfully applied to enhance the signals with a very low frequencies. We developed a novel method called integration along the radius in polar coordinate to measure the speed of sound and calculating the speed of oil flow. We compared the performance of our method with a Radon transform and proved our method outperforms an existing methods in both processing time and accuracy. The data sets used in this study are recorded from real oil and gas pipes which means there is no controlled environment and there are lots of noisy signals as a result of unpredicted events under the sea. The result of this study is applicable in Oil and Gas production energy industry, Hydraulic fracturing and shale gas extraction energy industry, Borehole water supply industry, Gas pipeline transportation energy industry and Carbon Dioxide Sequestration industry.

No abstract

Optical fiber sustains scratches, pits and other types of defects on the end face during the polishing process. Hence, fiber end face inspection is a significant process for fiber manufactures when analysing the performance of a fiber. In order to identify the defects present on the fiber end face, a novel model is presented in this paper. Our model combined filtering methods to enhance the contrast of the images so scratches can be successfully detected. However, because the photos have been taken with different gains and exposures, they can not be processed with standard image processing techniques. We developed a method to analyse the defects intensity that could be located under different gains and exposures. We established that the images taken with the high gains and exposures performed well for optical fiber defect recognition.