Automated ESP Failure Root Cause Identification and Analyses Using Machine Learning and Natural Language Processing Technologies

2021 ◽  
Author(s):  
Saniya Karnik ◽  
Navya Yenuganti ◽  
Bonang Firmansyah Jusri ◽  
Supriya Gupta ◽  
Prasanna Nirgudkar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Failure Analysis ◽  
Language Processing ◽  
Process Efficiency ◽  
Processing Technologies ◽  
Root Cause ◽  
Equipment Production ◽  
Electrical Submersible Pump ◽  
Human Effort ◽  
Root Cause Identification

Abstract Today, the Dismantle, Inspection, and Failure Analysis (DIFA) process for electrical submersible pump (ESP) failure analysis is a tedious, human-intensive, and time-consuming activity. The activity involves a set of data and various information formats from several activities in the ESP operation lifecycle. This paper proposes a novel artificial intelligence workflow to improve the efficiency of the DIFA process using an ensemble of machine learning (ML) algorithms. This ensemble of algorithms brings together structured/unstructured data across equipment, production, operations, and failure reports to automate root-cause identification and analysis post breakdown. As a result, the time and human effort required in the process has been reduced, and process efficiency has drastically improved.

Advancement in Data Engineering and Feature Processing Workflow by Using Deep Learning Techniques for the Automation of ESP Failure Root Cause Analyses

2021 ◽  
Author(s):  
Saniya Karnik ◽  
Navya Yenuganti ◽  
Bonang Firmansyah Jusri ◽  
Supriya Gupta ◽  
Prasanna Nirgudkar ◽  
...  
Keyword(s):  
Deep Learning ◽  
Failure Analysis ◽  
Language Processing ◽  
Turnaround Time ◽  
Process Efficiency ◽  
Root Cause ◽  
Feature Processing ◽  
Learning Techniques ◽  
Electrical Submersible Pump ◽  
Root Cause Identification

Abstract Today, Electrical Submersible Pump (ESP) failure analysis is a tedious, human-intensive, and time-consuming activity involving dismantle, inspection, and failure analysis (DIFA) for each failure. This paper presents a novel artificial intelligence workflow using an ensemble of machine learning (ML) algorithms coupled with natural language processing (NLP) and deep learning (DL). The algorithms outlined in this paper bring together structured and unstructured data across equipment, production, operations, and failure reports to automate root cause identification and analysis post breakdown. This process will result in reduced turnaround time (TAT) and human effort thus drastically improving process efficiency.

Electrical Submersible Pump Prognostics and Health Monitoring Using Machine Learning and Natural Language Processing

2021 ◽  
Author(s):  
Rajeev Ranjan Sinha ◽  
Supriya Gupta ◽  
Praprut Songchitruksa ◽  
Saniya Karnik ◽  
Amey Ambade
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Operating Conditions ◽  
Learning Approaches ◽  
Submersible Pump ◽  
Gas Industry ◽  
Electrical Submersible Pump ◽  
Low Efficiency

Abstract Electrical Submersible Pump (ESP) systems efficiently pump high volumes of production fluids from the wellbore to the surface. They are extensively used in the oil and gas industry due to their adaptability, low maintenance, safety and relatively low environmental impact. They require specific operating conditions with respect to the power, fluid level and fluid content. Oilfield operation workflows often require extensive surveillance and monitoring by subject-matter experts (SMEs). Detecting issues like formation of unwanted gas and emulsions in ESPs requires constant analysis of downhole data by SMEs. The lack of adequate and accurate monitoring of the downhole pumps can lead to low efficiency, high lifting costs, and frequent repair and replacements. There are 3 workflows described in the paper which demonstrate that the maintenance costs of the ESPs can be significantly reduced, and production optimized with the augmentation of machine learning approaches typically unused in ESP surveillance and failure analysis.

Defect patterns study of pick-and-place machine using automated optical inspection data

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yuqiao Cen ◽  
Jingxi He ◽  
Daehan Won
Keyword(s):  
Machine Learning ◽  
Content Type ◽  
Component Placement ◽  
Root Cause ◽  
Machine Learning Methods ◽  
Optical Inspection ◽  
Pick And Place ◽  
Automated Optical Inspection ◽  
Inspection Data ◽  
Root Cause Identification

Purpose This paper aims to study the component pick-and-place (P&P) defect patterns for different root causes based on automated optical inspection data and develop a root cause identification model using machine learning. Design/methodology/approach This study conducts experiments to simulate the P&P machine errors including nozzle size and nozzle pick-up position. The component placement qualities with different errors are inspected. This study uses various machine learning methods to develop a root cause identification model based on the inspection result. Findings The experimental results revealed that the wrong nozzle size could increase the mean and the standard deviation of component placement offset and the probability of component drop during the transfer process. Moreover, nozzle pick-up position can affect the rotated component placement offset. These root causes of defects can be traced back using machine learning methods. Practical implications This study provides operators in surface mount technology assembly lines to understand the P&P machine error symptoms. The developed model can trace back the root causes of defects automatically in real line production. Originality/value The findings are expected to lead the regular preventive maintenance to data-driven predictive and reactive maintenance.

scholarly journals Prediction of Workplace Absenteeism Time using Machine Learning

2019 ◽  
Vol 9 (2) ◽  
pp. 3489-3493
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Prediction Model ◽  
Language Processing ◽  
Negatively Associated ◽  
Root Cause ◽  
Lost Productivity ◽  
Processing Techniques ◽  
Available Information

Absenteeism in the workplace is a significant cause of lost productivity of the organization and the root cause of the company's performance to many employers. Managing absenteeism is inevitable, but making sudden changes without knowing the cause of the problem is a terrible mistake. This paper aims to develop a reliable workplace absenteeism prediction model using machine learning and natural language processing techniques to aid employers with analyzation of given minimal available information about the employees’ demographics. ‘Distance from residence to work,’ ‘disciplinary failure’ and ‘weight’ was negatively associated with absenteeism time in hours. ‘Age,’ ‘son,’ and ‘height’ were positively associated with absenteeism time in hours

Data-Driven Concept Network for Inspiring Designers’ Idea Generation

2020 ◽  
Vol 20 (3) ◽  
Author(s):  
Qiyu Liu ◽  
Kai Wang ◽  
Yan Li ◽  
Ying Liu
Keyword(s):  
Machine Learning ◽  
Conceptual Design ◽  
Language Processing ◽  
Idea Generation ◽  
Data Driven ◽  
Design Problems ◽  
Web Documents ◽  
Processing Technologies ◽  
External Knowledge ◽  
Concept Network

Abstract Big-data mining brings new challenges and opportunities for engineering design, such as customer-needs mining, sentiment analysis, knowledge discovery, etc. At the early phase of conceptual design, designers urgently need to synthesize their own internal knowledge and wide external knowledge to solve design problems. However, on the one hand, it is time-consuming and laborious for designers to manually browse massive volumes of web documents and scientific literature to acquire external knowledge. On the other hand, how to extract concepts and discover meaningful concept associations automatically and accurately from these textual data to inspire designers’ idea generation? To address the above problems, we propose a novel data-driven concept network based on machine learning to capture design concepts and meaningful concept combinations as useful knowledge by mining the web documents and literature, which is further exploited to inspire designers to generate creative ideas. Moreover, the proposed approach contains three key steps: concept vector representation based on machine learning, semantic distance quantification based on concept clustering, and possible concept combinations based on natural language processing technologies, which is expected to provide designers with inspirational stimuli to solve design problems. A demonstration of conceptual design for detecting the fault location in transmission lines has been taken to validate the practicability and effectiveness of this approach.

scholarly journals Machine Learning Based Essay Grading System

2021 ◽  
Vol 9 (VI) ◽  
pp. 5465-5472
Author(s):  
Ojasvi Daga
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Regression Models ◽  
Grading System ◽  
Maximum Correlation ◽  
Essay Writing ◽  
Machine Learning Model ◽  
Human Effort ◽  
Essay Grading ◽  
Best Fit

Machine Learning and automation has progressed immensely over the years and has tend to make human lives simpler with reducing human effort and time on tasks by enabling a machine to perform them. One such task is to grade essays. Essay writing is an integral part for anyone willing to learn a language or skill or to simply exhibit one’s thoughts and ideas on a topic. This leads us to the reason why essay grading is important. When a work is scored against some parameters, a scope of improvement is possible. Hence, when essays are graded and feedbacks are provided, it guides the writer to analyse the work and to have a better understanding of the topic in general. Although, manual grading of essays could create discrepancy because of being graded by different individuals having different perceptions of the same content. It also consumes a lot of human time and effort. Therefore, automatic grading of essays could prove to be the saviour. In this project, we build a machine learning model which grades essays based on various features extracted using Natural Language Processing. We also test the model’s performance using several regression models like Linear, Lasso, and Ridge, and methods like Artificial Neural Network to find the best fit giving the maximum correlation with human grades.

Root Cause Finding of a Diode Leakage Failure Using Scanning Magnetic Microscopy and ToF-SIMS as Key Methods

2006 ◽  
Author(s):  
H. Preu ◽  
W. Mack ◽  
T. Kilger ◽  
B. Seidl ◽  
J. Walter ◽  
...  
Keyword(s):  
Failure Analysis ◽  
Quantum Interference ◽  
Leakage Currents ◽  
Root Cause ◽  
Microelectronic Devices ◽  
Successful Approach ◽  
Magnetic Microscopy ◽  
Leakage Failure ◽  
Root Cause Identification

Abstract One challenge in failure analysis of microelectronic devices is the localization and root cause finding of leakage currents in passives. In this case study we present a successful approach for failure analysis of a diode leakage failure. An analytical flow will be introduced, which contains standard techniques as well as SQUID (superconducting quantum interference device) scanning magnetic microscopy and ToFSIMS as key methods for localization and root cause identification. [1]

Failure Mechanism Studies and Root Cause Identification of Nonstick on Pad on Microchip Al Bondpads

2014 ◽  
Author(s):  
Hua Younan ◽  
Zhou Yongkai ◽  
Chen Yixin ◽  
Fu Chao ◽  
Li Xiaomin
Keyword(s):  
Failure Analysis ◽  
Failure Mechanism ◽  
Wafer Fabrication ◽  
Assembly Process ◽  
Root Cause ◽  
Barrier Metal ◽  
Root Cause Identification ◽  
Induced Defects

Abstract It is well-known that underetch material, contamination, particle, pinholes and corrosion-induced defects on microchip Al bondpads will cause non-stick on pads (NSOP) issues. In this paper, the authors will further study NSOP problem and introduce one more NSOP failure mechanism due to Cu diffusion caused by poor Ta barrier metal. Based on our failure analysis results, the NSOP issue was not due to the assembly process, but due to the wafer fabrication. The failure mechanism might be that the barrier metal Ta was with pinholes, which caused Cu diffused out to the top Al layer, and then formed the “Bump-like” Cu defects and resulted in NSOP on Al bondpads during assembly process.

Advanced Scan Chain Failure Analysis Using Laser Modulation Mapping and Continuous Wave Probing

2011 ◽  
Author(s):  
Steven Kasapi ◽  
William Lo ◽  
Joy Liao ◽  
Bruce Cory ◽  
Howard Marks
Keyword(s):  
Failure Analysis ◽  
Continuous Wave ◽  
Wafer Level ◽  
Root Cause ◽  
Non Invasive ◽  
Laser Probing ◽  
Volume Yield ◽  
Scan Chain ◽  
Leakage Failure ◽  
Root Cause Identification

Abstract A variety of EFA techniques have been deployed to improve scan chain failure isolation. In contrast to other laser techniques, modulation mapping (MM) does not require electrically perturbing of the device. Beginning with a review of MM and continuous-wave (CW) probing as well as shift debug using MM, this paper presents three case studies involving scan chains with subtle resistive and leakage failure mechanisms, including transition, bridge, and slow-to-rise/fall failures, using a combination of these techniques. Combining modulation mapping with laser probing has proven to be a very effective and efficient methodology for isolating shift defects, even challenging timing-related shift defects. So far, every device submitted for physical failure analysis using this workflow has led to successful root cause identification. The techniques are sufficiently non-invasive and straightforward that they can be successfully applied at wafer level for volume, yield-oriented EFA.

Sign in / Sign up

Export Citation Format

Share Document