Support of Drilling Operations Using a Central Computer and Communications Facility With Real-Time MWD Capability and Networked Personal Computers

Abstract Due to high demand for energy, oil and gas companies started to drill wells in remote areas and unconventional environments. This raised the complexity of drilling operations, which were already challenging and complex. To adapt, drilling companies expanded their use of the real-time operation center (RTOC) concept, in which real-time drilling data are transmitted from remote sites to companies’ headquarters. In RTOC, groups of subject matter experts monitor the drilling live and provide real-time advice to improve operations. With the increase of drilling operations, processing the volume of generated data is beyond a human's capability, limiting the RTOC impact on certain components of drilling operations. To overcome this limitation, artificial intelligence and machine learning (AI/ML) technologies were introduced to monitor and analyze the real-time drilling data, discover hidden patterns, and provide fast decision-support responses. AI/ML technologies are data-driven technologies, and their quality relies on the quality of the input data: if the quality of the input data is good, the generated output will be good; if not, the generated output will be bad. Unfortunately, due to the harsh environments of drilling sites and the transmission setups, not all of the drilling data is good, which negatively affects the AI/ML results. The objective of this paper is to utilize AI/ML technologies to improve the quality of real-time drilling data. The paper fed a large real-time drilling dataset, consisting of over 150,000 raw data points, into Artificial Neural Network (ANN), Support Vector Machine (SVM) and Decision Tree (DT) models. The models were trained on the valid and not-valid datapoints. The confusion matrix was used to evaluate the different AI/ML models including different internal architectures. Despite the slowness of ANN, it achieved the best result with an accuracy of 78%, compared to 73% and 41% for DT and SVM, respectively. The paper concludes by presenting a process for using AI technology to improve real-time drilling data quality. To the author's knowledge based on literature in the public domain, this paper is one of the first to compare the use of multiple AI/ML techniques for quality improvement of real-time drilling data. The paper provides a guide for improving the quality of real-time drilling data.

Download Full-text

Impact of Data Quality on Well Operations: Case Study of Work-over Operations

10.2118/afrc-2556845-ms ◽

2016 ◽

Author(s):

Alfred Enyekwe ◽

Osahon Urubusi ◽

Raufu Yekini ◽

Iorkam Azoom ◽

Oloruntoba Isehunwa

Keyword(s):

Data Quality ◽

Data Management ◽

Real Time ◽

Data Management System ◽

Quality Data ◽

Process Safety ◽

Well Control ◽

Drilling Operations ◽

Short Time

ABSTRACT Significant emphasis on data quality is placed on real-time drilling data for the optimization of drilling operations and on logging data for quality lithological and petrophysical description of a field. This is evidenced by huge sums spent on real time MWD/LWD tools, broadband services, wireline logging tools, etc. However, a lot more needs to be done to harness quality data for future workover and or abandonment operations where data being relied on is data that must have been entered decades ago and costs and time spent are critically linked to already known and certified information. In some cases, data relied on has been migrated across different data management platforms, during which relevant data might have been lost, mis-interpreted or mis-placed. Another common cause of wrong data is improperly documented well intervention operations which have been done in such a short time, that there is no pressure to document the operation properly. This leads to confusion over simple issues such as what depth a plug was set, or what junk was left in hole. The relative lack of emphasis on this type of data quality has led to high costs of workover and abandonment operations. In some cases, well control incidents and process safety incidents have arisen. This paper looks at over 20 workover operations carried out in a span of 10 years. An analysis is done on the wells’ original timeline of operation. The data management system is generally analyzed and a categorization of issues experienced during the workover operations is outlined. Bottlenecks in data management are defined and solutions currently being implemented to manage these problems are listed as recommended good practices.

Download Full-text

Psychoeducational Testing and the Personal Computer

Journal of Special Education Technology ◽

10.1177/016264348900900302 ◽

1989 ◽

Vol 9 (3) ◽

pp. 136-143 ◽

Cited By ~ 2

Author(s):

M. Bryce Fifield

Keyword(s):

Social Skills ◽

Real Time ◽

Personal Computer ◽

Content Validity ◽

Cognitive Abilities ◽

Academic Skills ◽

Personal Computers ◽

Assessment Instruments ◽

Response Data ◽

Use Of Assessment

The use of personal computers to aid in the administration, scoring, and interpretation of individual psychoeducational tests is growing. Currently computers are used to assist in managing assessment information, scoring and interpreting tests, and administering tests of cognitive abilities, academic skills, adaptive behaviors, and social skills. Although the content validity of assessment instruments developed for computer administration may have certain practical limitations, several useful advantages can be gained by using the computer to administer tests. Some of the advantages include improved levels of standardization in the procedures used during test administration, scoring, and interpretation; the collection of response data in real time; and the development and use of assessment models that were heretofore too complex for human presentation.

Download Full-text