Application of machine learning to accidents detection at directional drilling

Gurina, Ekaterina; Klyuchnikov, Nikita; Zaytsev, Alexey; Romanenkova, Evgenia; Antipova, Ksenia; Simon, Igor; Макаров, В. А.; Koroteev, Dmitry

doi:10.1016/j.petrol.2019.106519

Cited by 51 publications

(26 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies on investigating the possibility of predicting failures and accidental events can be performed. [ 39 ]…”

Section: Suggestions and Discussionmentioning

confidence: 99%

“…Gurina et al [ 39 ] have demonstrated an ML algorithm to detect accidental events in directional wells by comparing real‐time MWD data with past data. The proposed model performs anomaly detection by analyzing the similarity of events using time series comparison and gradient boosting classification.…”

Section: And Da Applications In Upstream Petroleum Industrymentioning

confidence: 99%

“…[38] Studies on investigating the possibility of predicting failures and accidental events can be performed. [39] More investigations can be performed to optimize the drilling parameters using other methods such as random K-nearest neighbor and comparing the performance. [40] The model performance has been shown and compared with other models very well.…”

Section: Exploration and Drilling Operationsmentioning

confidence: 99%

See 2 more Smart Citations

Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

2020

View full text Add to dashboard Cite

In the mid-19th century, the first oil well was drilled, which marked the beginning of the world oil economy. This era embarked on the phase of evolution and development of society in every aspect, with huge dependence on petroleum products, which subsequently led to tremendous growth in terms of technological advancements in the exploration and production activities over time. With the existing petroleum fields approaching toward depletion, the global need for energy resources is increasing simultaneously. This continuously rising demand has led us to move to complex environments for oil and gas exploration and production activities. Moreover, the real-time monitoring of reservoirs and well operations produces enormous data, which require efficient processing and analysis tools for decisionmaking regarding field development and asset management. [1,2] Subsequently, the need for optimum facilities design, [3] transportation [4] and refining [5] activities at reduced cost has also grown. Several attempts [6-9] are also being made to develop unconventional fields commercially based on technoeconomic viability. The implementation of computer-based techniques has proven to be promising toward many challenging problems for various oilfield operations. Several researchers have shown that the machine learning (ML) and data analytics (DA) approaches hold promising solutions toward the operational challenges being encountered at present in the industry and can efficiently help in resolving the issues related to interpretation and analysis of large datasets. [10-15] Nikravesh and Aminzadeh [16] have shown the use of neural networks (NNs) and fuzzy logic for mining petroleum data. Li and Li [17] combined a NN and cluster analysis to put forth a predictive model for identifying complex lithology. Fath et al. [18] proposed a novel approach for bubble point pressure prediction using an NN model with reservoir temperature, solution gas oil ratio (GOR), oil gravity, and gas specific gravity as input attributes. Ahmadi and Bahadori [19] showed the use of a supervised learning algorithm to determine the well placement and conning occurrence in horizontal wells. Maucec et al. [20] performed data mining and ML on well stimulation data for enhancing the prediction capabilities. Gupta et al. [21] applied DA for safeguarding real-time electrical submersible pumping operations. Cadei et al. [22] forecasted operational upsets using advanced analytics in an upstream production system. Dongxiao et al. [23] presented in their research that long short-term memory (LSTM), cascaded LSTM, and a fully connected NN can be utilized for generating synthetic well logs by supplementing the missing logging input data. Ghorbani et al. [24] proposed an artificial Intelligence (AI)based approach to predict the flow rate of oil from an orifice

show abstract

“…Studies on investigating the possibility of predicting failures and accidental events can be performed. [ 39 ]…”

Section: Suggestions and Discussionmentioning

confidence: 99%

Section: And Da Applications In Upstream Petroleum Industrymentioning

confidence: 99%

Section: Exploration and Drilling Operationsmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

2020

View full text Add to dashboard Cite

show abstract

“…These accidents can be recognized by utilizing different applications or some other vehicle communication system. Although, the algorithms generated by the machine can straightforwardly find out the accidents [20] by using the speed of the vehicle or by some sudden jerks. Accidents or different occurrences can be viewed as irregularities in rush hour jams, information and machine algorithms [21,6] can be utilized to distinguish these exceptions.…”

Section: Introductionmentioning

confidence: 99%

Accident Detection and Disaster Response Framework Utilizing IoT

Hassan¹,

Chen²,

Mahmood³

et al. 2020

IJACSA

View full text Add to dashboard Cite

The internet of things (IoT) leads the noteworthy edges above customary information and communication technologies (ICT) for Intelligent Transportation Systems (ITS). The progression in the transportation system, the increment in vehicles and the accidents happened on the roads are cumulative up to an alarming situation. Additionally, 1.256 million people expire by the road bumps every year and it is very problematic to find the precise accident location of the user. If an accident occurs, the survival rate of the victim increases, if he is given instantaneous remedial assistance. You can provide remedial assistance to the victim only when you identify the precise location of accident. The main persistence of this system is to identify an accident and find the location of the user. After tracing the location, the system will search nearby hospitals for remedial treatment. System will send a message that contains user's current location, to the nearby hospitals in case of an emergency. System will acquire recommended contacts from the cloud and also send message to them for user's support by using API. If the user is safe, he can cancel the message that is being sent to the nearest hospital and the recommended contacts. This system will help the users in saving their lives within minimal time.

show abstract

“…In the case of failure detection on robotic systems, [7] shows a comparison between classic ma-chine learning, statistical procedures, and the hybrid boosted gradient method, which is an improvement of the logistic regression. There is also an application of machine learning techniques for failure detection on directional drilling of oil wells [8], where the training process was performed using significant historical data from more than 80 oil wells for training a boosted gradient algorithm. Besides, machine learning can also be employed for Cyber-Physical Systems.…”

Section: Introductionmentioning

confidence: 99%

FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing Failure Detection Method

Viola

Chen

Wang

2019

2019 1st International Conference on Industrial Artificial Intelligence (IAI)

View full text Add to dashboard Cite

Failure detection is employed in the industry to improve system performance and reduce costs due to unexpected malfunction events. So, a good dataset of the system is desirable for designing an automated failure detection system. However, industrial process datasets are unbalanced and contain little information about failure behavior due to the uniqueness of these events and the high cost for running the system just to get information about the undesired behaviors.

show abstract

Application of machine learning to accidents detection at directional drilling

Cited by 51 publications

References 12 publications

Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

Accident Detection and Disaster Response Framework Utilizing IoT

FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing Failure Detection Method

Contact Info

Product

Resources

About