ROP Modeling using Neural Network and Drill String Vibration Data

2012 ◽  
Author(s):  
Abdolali Esmaeili ◽  
Behzad Elahifar ◽  
Rudolf Konrad Fruhwirth ◽  
Gerhard Thonhauser
Keyword(s):  
Neural Network ◽  
Drill String ◽  
Vibration Data ◽  
String Vibration

scholarly journals A New Method of Lithology Classification Based on Convolutional Neural Network Algorithm by Utilizing Drilling String Vibration Data

Energies ◽  
2020 ◽  
Vol 13 (4) ◽  
pp. 888 ◽  
Author(s):  
Gang Chen ◽  
Mian Chen ◽  
Guobin Hong ◽  
Yunhu Lu ◽  
Bo Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Well Logging ◽  
Low Latency ◽  
Time Frequency ◽  
Vibration Data ◽  
String Vibration ◽  
Lithology Identification ◽  
Drilling String

Formation lithology identification is of great importance for reservoir characterization and petroleum exploration. Previous methods are based on cutting logging and well-logging data and have a significant time lag. In recent years, many machine learning methods have been applied to lithology identification by utilizing well-logging data, which may be affected by drilling fluid. Drilling string vibration data is a high-density ancillary data, and it has the advantages of low-latency, which can be acquired in real-time. Drilling string vibration data is more accessible and available compared to well-logging data in ultra-deep well drilling. Machine learning algorithms enable us to develop new lithology identification models based on these vibration data. In this study, a vibration dataset is used as the signal source, and the original vibration signal is filtered by Butterworth (BHPF). Vibration time–frequency characteristics were 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 a convolutional neural network (CNN) combined with Mobilenet and ResNet. This model is used for complex formation lithology, including fine gravel sandstone, fine sandstone, and mudstone. This study also carries out related model accuracy verification and model prediction results interpretation. 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 verification test shows that the single-sample decision time of the model is 10 ms, the test macro precision rate is 90.0%, and the macro recall rate is 89.3%. The lithology identification model based on vibration data is more efficient and accessible than others. In conclusion, the CNN model using drill string vibration supplies a superior method of lithology identification. This study provides low-latency lithology classification methods to ensure safe and fast drilling.

scholarly journals Unsupervised Damage Detection for Offshore Jacket Wind Turbine Foundations Based on an Autoencoder Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3333
Author(s):  
Maria del Cisne Feijóo ◽  
Yovana Zambrano ◽  
Yolanda Vidal ◽  
Christian Tutivén
Keyword(s):  
Neural Network ◽  
Wind Turbine ◽  
Environmental Conditions ◽  
Wind Farms ◽  
Offshore Wind ◽  
Offshore Wind Turbine ◽  
Small Subset ◽  
Scaled Model ◽  
Vibration Data ◽  
Large Water

Structural health monitoring for offshore wind turbine foundations is paramount to the further development of offshore fixed wind farms. At present time there are a limited number of foundation designs, the jacket type being the preferred one in large water depths. In this work, a jacket-type foundation damage diagnosis strategy is stated. Normally, most or all the available data are of regular operation, thus methods that focus on the data leading to failures end up using only a small subset of the available data. Furthermore, when there is no historical precedent of a type of fault, those methods cannot be used. In addition, offshore wind turbines work under a wide variety of environmental conditions and regions of operation involving unknown input excitation given by the wind and waves. Taking into account the aforementioned difficulties, the stated strategy in this work is based on an autoencoder neural network model and its contribution is two-fold: (i) the proposed strategy is based only on healthy data, and (ii) it works under different operating and environmental conditions based only on the output vibration data gathered by accelerometer sensors. The proposed strategy has been tested through experimental laboratory tests on a scaled model.

Diffractive index determination by Tikhonov regularization on forced string vibration data

2009 ◽  
Author(s):  
Irina Asekritova ◽  
Börje Nilsson ◽  
Sara Rydström ◽  
Börje Nilsson ◽  
Louis Fishman ◽  
...  
Keyword(s):  
Tikhonov Regularization ◽  
Vibration Data ◽  
String Vibration

Surface Roughness Prediction Model of Cylinder Grinding

2012 ◽  
Vol 157-158 ◽  
pp. 123-126 ◽  
Author(s):  
Ning Ding ◽  
Yi Chen Wang ◽  
Ding Tong Zhang ◽  
Yu Xiang Shi ◽  
Jian Shi
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Prediction Model ◽  
Fuzzy Neural Network ◽  
Vibration Signal ◽  
Feed Speed ◽  
Vibration Data ◽  
Proposed Model ◽  
Fuzzy Neural ◽  
Roughness Prediction

Based on the theory of roughness during cylinder grinding and the theory of fuzzy-neural network, a surface roughness intelligent prediction model is developed in this paper. The feed, speed, and the vibration data are the inputs for the model. An accelerometer is used to gather the vibration signal in real time. The model is used in the grinding experiment, and verifies the feasibility of the proposed model.

Longitudinal and Angular Drill-String Vibrations With Damping

1968 ◽  
Vol 90 (4) ◽  
pp. 671-679 ◽  
Author(s):  
D. W. Dareing ◽  
B. J. Livesay
Keyword(s):  
Viscous Friction ◽  
Field Measurements ◽  
Computer Programs ◽  
Drill String ◽  
Recording Instrument ◽  
String Vibration ◽  
String Vibrations ◽  
Different Types ◽  
Drilling Operations ◽  
Computer Calculations

This paper discusses longitudinal and angular drill-string vibrations and supporting field measurements taken with a special downhole recording instrument. Computer programs based on the theory are used to calculate longitudinal and angular vibrations (caused by periodic bit motions) along the drill string; field measurements made during actual drilling operations are used to check computer calculations. The main difference between this and other theory on the same problem is the inclusion of friction, which acts along the length of a drill string and impedes longitudinal and angular vibrations. For the sake of simplicity, the effect of different types of friction, such as fluid, rubbing, and material, which act along the string, is approximated by the effect produced by viscous friction. This approximation is generally accepted and appears to give adequate results for the drill-string vibration problem.

Formation Prediction Model based on Drill String Vibration Measurements Using Laboratory Scale Rig

2013 ◽  
Author(s):  
Abdolali Esmaeili ◽  
Behzad Elahifar ◽  
Rudolf Konrad Fruhwirth ◽  
Gerhard Thonhauser
Keyword(s):  
Prediction Model ◽  
Drill String ◽  
Laboratory Scale ◽  
Vibration Measurements ◽  
String Vibration ◽  
Model Based
Sign in / Sign up

Export Citation Format

Share Document