Natural Language Processing Applied to Reduction of False and Missed Alarms in Kick and Lost Circulation Detection

2021 ◽  
Author(s):  
Michael Yi ◽  
Pradeepkumar Ashok ◽  
Dawson Ramos ◽  
Taylor Thetford ◽  
Spencer Bohlander ◽  
...  
Keyword(s):  
Time Series ◽  
Natural Language Processing ◽  
North America ◽  
Natural Language ◽  
Language Processing ◽  
Time Series Data ◽  
Series Data ◽  
False Alarms ◽  
Lost Circulation ◽  
Good Flow

Abstract Kick and lost circulation events are large contributors to non-productive time. Therefore, early detection of these events is crucial. In the absence of good flow in and flow out sensors, pit volume trends offer the best possibility for influx/loss detection, but errors occur since external mud addition /removal to the pits is not monitored or sensed. The goal is to reduce false alarms caused by such mud additions and removal. Data analyzed from over 100s of wells in North America show that mud addition and removal results in certain unique pit volume gain / loss trends, and these trends are quite different from a kick, a lost circulation or a wellbore breathing event trend. Additionally, driller's input text memos into the data aggregation system (EDR) and these memos often provide information with regards to pit operations. In this paper, we introduce a method that utilizes a Bayesian network to aggregate trends detected in time-series data with events identified by natural language processing (NLP) of driller memos critical to greatly improve the accuracy and robustness of kick and lost circulation detection. The methodology was implemented in software that is currently running on rigs in North America. During the test phase, we applied it on several historical wells with lost circulation events and several historical wells with kick events. We were able to identify and quantify the losses even during connections and mud additions, where usually pit volume was increasing despite continual losses. Also, the real-time simultaneous analysis of driller memos provides context to pit volume trends and further reduce the false alarms. The algorithm is also able to take account of pit volume that was reduced due to drilling. Quantification of the losses offers more insight into what lost circulation material to use and the changes in the rate of loss while drilling. This approach was very robust in discovering kicks as well and differentiating it from mud removal and wellbore breathing events. These historical case studies will be detailed in this paper. This is the first time that patterns in mud volume addition and removal detected from time-series data have been used along with driller memos using NLP to reduce false alerts in kick and lost circulation detection. This approach is particularly useful in identifying kick and lost circulation events from pit volume data, especially when good flow in and flow out sensors are not available. The paper provides guidance on how real-time sensor data can be combined with textual data to improve the outputs from an advisory system.

scholarly journals Wave2Vec: Vectorizing Electroencephalography Bio-Signal for Prediction of Brain Disease

2018 ◽  
Vol 15 (8) ◽  
pp. 1750 ◽  
Author(s):  
Seonho Kim ◽  
Jungjoon Kim ◽  
Hong-Woo Chun
Keyword(s):  
Artificial Intelligence ◽  
Time Series ◽  
Feature Selection ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Data Analysis ◽  
Natural Language ◽  
Real Number ◽  
Real Time ◽  
Language Processing

Interest in research involving health-medical information analysis based on artificial intelligence, especially for deep learning techniques, has recently been increasing. Most of the research in this field has been focused on searching for new knowledge for predicting and diagnosing disease by revealing the relation between disease and various information features of data. These features are extracted by analyzing various clinical pathology data, such as EHR (electronic health records), and academic literature using the techniques of data analysis, natural language processing, etc. However, still needed are more research and interest in applying the latest advanced artificial intelligence-based data analysis technique to bio-signal data, which are continuous physiological records, such as EEG (electroencephalography) and ECG (electrocardiogram). Unlike the other types of data, applying deep learning to bio-signal data, which is in the form of time series of real numbers, has many issues that need to be resolved in preprocessing, learning, and analysis. Such issues include leaving feature selection, learning parts that are black boxes, difficulties in recognizing and identifying effective features, high computational complexities, etc. In this paper, to solve these issues, we provide an encoding-based Wave2vec time series classifier model, which combines signal-processing and deep learning-based natural language processing techniques. To demonstrate its advantages, we provide the results of three experiments conducted with EEG data of the University of California Irvine, which are a real-world benchmark bio-signal dataset. After converting the bio-signals (in the form of waves), which are a real number time series, into a sequence of symbols or a sequence of wavelet patterns that are converted into symbols, through encoding, the proposed model vectorizes the symbols by learning the sequence using deep learning-based natural language processing. The models of each class can be constructed through learning from the vectorized wavelet patterns and training data. The implemented models can be used for prediction and diagnosis of diseases by classifying the new data. The proposed method enhanced data readability and intuition of feature selection and learning processes by converting the time series of real number data into sequences of symbols. In addition, it facilitates intuitive and easy recognition, and identification of influential patterns. Furthermore, real-time large-capacity data analysis is facilitated, which is essential in the development of real-time analysis diagnosis systems, by drastically reducing the complexity of calculation without deterioration of analysis performance by data simplification through the encoding process.

Using time series and natural language processing to identify viral moments in the 2016

2019 ◽  
Author(s):  
Josephine Lukito ◽  
Prathusha K Sarma ◽  
Jordan Foley ◽  
Aman Abhishek
Keyword(s):  
Time Series ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing

Teaching Visual Analysis of Time Series Data

1996 ◽  
Vol 24 (3) ◽  
pp. 247-261 ◽  
Author(s):  
Ian A. James ◽  
Paul S. Smith ◽  
Derek Milne
Keyword(s):  
Time Series ◽  
Visual Analysis ◽  
Time Series Data ◽  
Mean Shift ◽  
High Sensitivity ◽  
Training Programme ◽  
High Rate ◽  
Series Data ◽  
False Alarms ◽  
Single Subject

Visual analysis, or “eyeballing”, of single subject (N=l) data is the commonest technique for analysing time series data. The present study examined firstly, psychologists' abilities to determine significant change between baseline (A) and therapeutic (B) phases, and secondly, the decision making process in relation to the visual components of such graphs. Thirdly, it looked at the effect that a training programme had on psychologists' abilities to identify significant A−B change. The results revealed that the participants were poor at identifying significant effects from non-significant changes. In particular, the study found a high rate of false alarms (Type 1 errors), and a low rate of misses (Type 2 errors), i.e. high sensitivity but poor specificity. The only visual components to significantly alter decisions were the degree of serial dependency and the mean shift component. The teaching influenced the participants' judgements. In general, participants became more conservative, but there was limited evidence of a significant improvement in their judgements following the teaching.

scholarly journals The Correlation between Energy Cost Share, Human, and Economic Development: Using Time Series Data from Australasia, Europe, North America, and the BRICS Nations

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2405 ◽  
Author(s):  
Ryan Roberts ◽  
Josephine Musango ◽  
Alan Brent ◽  
Matthew Heun
Keyword(s):  
Time Series ◽  
Economic Development ◽  
North America ◽  
Strong Correlation ◽  
Energy Cost ◽  
Time Series Data ◽  
Series Data ◽  
Cost Share ◽  
Social And Economic Development ◽  
Per Capita

This paper investigates how a change in a region’s energy cost share (ECS), a ratio of a region’s energy expenditure as a fraction of its gross domestic product (GDP), affects the region’s social and economic development. Nations from four regions of the world, namely Australasia, Europe, North America, and the BRICS nations (Brazil, Russia, India, China, and South Africa) were chosen for this study. Using time series data from the period of 1978 to 2010, the annual ECS of each country was compared to the year-on-year GDP change, as well as the components of the human development index (HDI). High ECS values were seen to correlate with low economic development. The existence of an ECS threshold was found in 14 of the 15 countries, for all the regions, and for the worldwide analysis, with very strong correlation coefficients obtained for periods of high ECS. New to this field of research, this study also investigated the effects of ECS on gross national income (GNI) per capita change, as well as the effects of 0, 1, 2, and 3 year lags. This investigation found that ECS has a very strong correlation to GNI per capita change, which was much stronger than the correlation between ECS and GDP change. The effects of ECS on social and economic development occurred after varying time lags, and it is unique to each country and region. Regions with similar ECS dynamics were identified, with possible reasons for the similarities being provided.

scholarly journals Neural Activity Classification with Machine Learning Models Trained on Interspike Interval Time-Series Data

2021 ◽  
Author(s):  
Ivan Lazarevich ◽  
Ilya Prokin ◽  
Boris Gutkin ◽  
Victor Kazantsev
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Language Processing ◽  
Neural Activity ◽  
Time Series Data ◽  
Series Data ◽  
Neural Decoding ◽  
Learning Models ◽  
Wide Range ◽  
Machine Learning Models

Modern well-performing approaches to neural decoding are based on machine learning models such as decision tree ensembles and deep neural networks. The wide range of algorithms that can be utilized to learn from neural spike trains, which are essentially time-series data, results in the need for diverse and challenging benchmarks for neural decoding, similar to the ones in the fields of computer vision and natural language processing. In this work, we propose a spike train classification benchmark, based on open-access neural activity datasets and consisting of several learning tasks such as stimulus type classification, animal’s behavioral state prediction and neuron type identification. We demonstrate that an approach based on hand-crafted time-series feature engineering establishes a strong baseline performing on par with state-of-the-art deep learning based models for neural decoding. We release the code allowing to reproduce the reported results 1.

scholarly journals Tsunami arrival time detection system applicable to discontinuous time series data with outliers

2016 ◽  
Vol 16 (12) ◽  
pp. 2603-2622
Author(s):  
Jun-Whan Lee ◽  
Sun-Cheon Park ◽  
Duk Kee Lee ◽  
Jong Ho Lee
Keyword(s):  
Time Series ◽  
Arrival Time ◽  
Time Series Data ◽  
Detection System ◽  
Detection Algorithm ◽  
Series Data ◽  
False Alarms ◽  
Detection Algorithms ◽  
Tsunami Detection ◽  
Tsunami Signal

Abstract. Timely detection of tsunamis with water level records is a critical but logistically challenging task because of outliers and gaps. Since tsunami detection algorithms require several hours of past data, outliers could cause false alarms, and gaps can stop the tsunami detection algorithm even after the recording is restarted. In order to avoid such false alarms and time delays, we propose the Tsunami Arrival time Detection System (TADS), which can be applied to discontinuous time series data with outliers. TADS consists of three algorithms, outlier removal, gap filling, and tsunami detection, which are designed to update whenever new data are acquired. After calibrating the thresholds and parameters for the Ulleung-do surge gauge located in the East Sea (Sea of Japan), Korea, the performance of TADS was discussed based on a 1-year dataset with historical tsunamis and synthetic tsunamis. The results show that the overall performance of TADS is effective in detecting a tsunami signal superimposed on both outliers and gaps.

Sign in / Sign up

Export Citation Format

Share Document