A Conventional Neural Network Lithology Classification Method Based on Vibration Data

Abstract

Drilling string vibration data is a high-density ancillary data and it has the advantages of low-latency and low-cost which can be acquired in real time. In this study, vibration dataset is used as signal source, and the original vibration signal is filtered by Butterworth (BHPF). vibration time-frequency characteristics are extracted into time frequency images with the application of short-time Fourier transform (STFT). This paper develops lithology classification models using new data sources based on convolutional neural network (CNN) combining with Mobilenet and ResNet. This model is used for complex formation lithology including fine gravel sandstone, fine sandstone and mudstone. In order to improve the trustworthiness of decision-making results, the gradient-weighted class-activated thermal localization map is applied to interpret the results of the model. The final vertification test shows that the single-sample decision time of the model is 10ms, the test macro precision rate is 90.0%, and the macro recall rate is 89.3%. The lithology classification model is more efficiency and accessible. In conclusion, The CNN model using drill string vibration supplies a superior method of lithology classification. This study provides low-latency and low-cost lithology judgment methods to ensure safe and rapid drilling.

Machine Learning Solution for Predicting Vibrations while Drilling the Curve Section

“…33 The vibration data itself was found to be correlated with the drilled formation lithology, and research was accomplished to classify the drilled lithology using the conventional neural network (CNN) technique by feeding the model with the drilling vibration data. 34 The main objective of this research is to make significant contributions to the field of vibration detection by surface drilling. Over the existing literature work, there is a shortage to cover machine learning research for autodetecting the three modes of vibrations that is already accomplished through the current study to autodetect the drilling string vibration modes (three types) in real-time during the drilling of the curve sections.…”

“…The tool categorizes vibration data into low, medium, and high categories and compares the overall tool accuracy to the downhole actual measurements . The vibration data itself was found to be correlated with the drilled formation lithology, and research was accomplished to classify the drilled lithology using the conventional neural network (CNN) technique by feeding the model with the drilling vibration data …”

“… 33 The vibration data itself was found to be correlated with the drilled formation lithology, and research was accomplished to classify the drilled lithology using the conventional neural network (CNN) technique by feeding the model with the drilling vibration data. 34 …”