Nodal screw compressor failure analysis using data analytics—CSG application

2015 ◽  
Vol 55 (1) ◽  
pp. 59
Author(s):  
Prashant Parulekar
Keyword(s):  
Statistical Analysis ◽  
Data Analytics ◽  
Screw Compressor ◽  
Cause Analysis ◽  
Root Cause ◽  
Statistical Measures ◽  
Using Data ◽  
Filter Signal ◽  
Data Analytic ◽  
Insight Into

An engine-driven oil-injected screw compressor in CSG service failed catastrophically. Instrumentation provided on the package was ineffective in predicting or detecting the failure. As part of the Root Cause Analysis (RCA) process, a statistical analysis of the logged instrument data, as measured across a period of six months prior to the failure, was carried out. This paper uses data analytic methods to process instrument data, data visualisation techniques, advanced statistical analysis of the instrument data, and techniques to filter signal noise. The analysis recognised the multivariate behaviour and interrelationships between various operating parameters. The paper further provides insight into the interpretation of statistical measures and how to draw conclusions that explain the failure mechanism. The outcomes of the analysis presented in this paper then provided insights into establishing operating envelopes, proposed instrumentation upgrades to be provided in future and helped establish an operation and maintenance regime that should assist in preventing such failures in future.

Root cause analysis of rattle noise in twin-tube vehicle dampers

2021 ◽  
pp. 095440702110652
Author(s):  
Marian Sikora ◽  
Janusz Gołdasz
Keyword(s):  
Design Of Experiment ◽  
Ride Comfort ◽  
Design Parameters ◽  
Vehicle Suspension ◽  
Experiment Study ◽  
Cause Analysis ◽  
Root Cause ◽  
Main Effect ◽  
Definition Of ◽  
Insight Into

The aim of this work is to provide an insight into the rattle noise phenomena occurring in double-tube (twin-tube) vehicle suspension dampers. In the dampers the particular phenomenon results from interactions between the valve(s) and the fluid passing through them. The rattling noise phenomena is known to degrade the vehicle passenger’s perception of ride comfort as well as to influence the performance of the dampers at low and medium speeds in particular. In the paper the authors reveal the results of a DOE (Design of Experiment) study involving several design parameters known to affect rattling occurrence. By running a series of purpose-designed tests the authors investigate not only the contribution of each particular parameter but the interactions between them. The results are presented in the form of pareto charts, main effect plots as well as interaction plots. It is expected the outcome of the analysis will aid in a better comprehension of the phenomena as well the definition of valve configurations to minimize their performance degradation.

scholarly journals Unplanned return presentations of older patients to the emergency department: a root cause analysis

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Babiche E. J. M. Driesen ◽  
Hanneke Merten ◽  
Cordula Wagner ◽  
H. Jaap Bonjer ◽  
Prabath W. B. Nanayakkara
Keyword(s):  
Older Patients ◽  
Root Cause Analysis ◽  
Initial Presentation ◽  
Future Research ◽  
Process Of Care ◽  
Related Factors ◽  
Cause Analysis ◽  
Root Cause ◽  
Progression Of Disease ◽  
Insight Into

Abstract Background In line with demographic changes, there is an increase in ED presentations and unplanned return presentations by older patients (≥70 years). It is important to know why these patients return to the ED shortly after their initial presentation. Therefore, the aim of this study was to provide insight into the root causes and potential preventability of unplanned return presentations (URP) to the ED within 30 days for older patients. Methods A prospective observational study was conducted from February 2018 to November 2018 in an academic hospital in Amsterdam. We included 83 patients, aged 70 years and older, with an URP to the ED within 30 days of the initial ED presentation. Patients, GPs and doctors at the ED were interviewed by trained interviewers and basic administrative data were collected in order to conduct a root cause analysis using the PRISMA-method. Results One hundred fifty-one root causes were identified and almost half (49%) of them were disease-related. Fifty-two percent of the patients returned to the ED within 7 days after the initial presentation. In 77% of the patients the URP was related to the initial presentation. Patients judged 17% of the URPs as potentially preventable, while doctors at the ED judged 25% and GPs 23% of the URPs as potentially preventable. In none of the cases, there was an overall agreement from all three perspectives on the judgement that an URP was potentially preventable. Conclusion Disease-related factors were most often identified for an URP and half of the patients returned to the ED within 7 days. The majority of the URPs was judged as not preventable. However, an URP should trigger healthcare workers to focus on the patient’s process of care and their needs and to anticipate on potential progression of disease. Future research should assess whether this may prevent that patients have to return to the ED.

scholarly journals Exploring Big Data Analytic Approaches to Cancer Blog Text Analysis (Preprint)

2018 ◽  
Author(s):  
Viju Raghupathi ◽  
Yilu Zhou ◽  
Wullianallur Raghupathi
Keyword(s):  
Social Media ◽  
Big Data ◽  
Data Analytics ◽  
Word Association ◽  
Early Stage ◽  
Big Data Analytics ◽  
Free Text ◽  
Health Related ◽  
Data Analytic ◽  
Insight Into

BACKGROUND In recent years researchers have begun to realize the value of social media as a source for data that helps us understand health-related phenomena. Health blogs in particular are rich with information for decision-making. While there are web crawlers and blog analysis software that generate statistics related to blogs, these are relatively primitive and are not useful computationally to aid with the analysis and understanding of the social networks and medical blogs that are evolving around healthcare. There is a need for sophisticated tools to fill this gap. Furthermore, to our knowledge there are not many big data studies or applications in the text analytics of cancer blogs. This study attempts to fill this specific gap while analyzing cancer blogs. OBJECTIVE In this exploratory research, we examine the potential of applying big data analytic techniques to the analysis of blogs that exist in the cancer domain. Our objective is twofold: to extract from the blogs, patterns and insight about cancer diagnosis, treatment, and management; and to apply advanced computation techniques in processing large amounts of unstructured health data. METHODS We applied the big data analytics architecture of Hadoop MapReduce via the Cloudera platform to the analysis of cancer blog content, in order to extract patterns and insight on cancer diagnoses. We apply a series of algorithms to gain insight into the content and develop a vocabulary and taxonomy of keywords based on existing medical nomenclature. By applying a number of algorithms, we gained insight into the blog content. The study identifies, for instance, the most discussed topics as well as associations that relate to key phenomena RESULTS Using several text analytic algorithms, including word count, word association, clustering, and classification, we were able to identify and analyze the patterns and keywords in cancer blog postings. This gave insight into some of the key issues that are discussed in blogs such as the type of cancer (breast cancer being the dominant topic), diagnosis, treatments, and others. CONCLUSIONS In general, big data analytics has the potential to transform the way practitioners and researchers gain insight from health social media, especially those in free text, unstructured form. Big data analytics and applications in health-related social media are still at an early stage, and rapid acceleration is possible with the advancements in models, tools, and technologies.

scholarly journals Human Animal Conflict in State of Maharashtra using Data Analytics

2021 ◽  
Vol 9 (VI) ◽  
pp. 808-820
Author(s):  
Arnav Gandhe
Keyword(s):  
Statistical Analysis ◽  
Data Analytics ◽  
Negative Impact ◽  
Current Situation ◽  
The State ◽  
Wild Animals ◽  
Animal Conflict ◽  
Human Animal ◽  
Using Data ◽  
Advanced Computer

Maharashtra, a land rich in its biodiversity, well known for its wildlife. Maharashtra stands 3rd in terms of Human-Animal Conflict behind Uttarakhand and Karnataka. Human–Animal conflict refers to the interaction between wildlife and people leading to a resultant negative impact on people, their resources, wild animals and their habitat. The paper discusses a 2year study(1st Jan-2019 to 1st Jan 2021) carried out on human-animal interactions in Maharashtra -focusing on various factors involved under Human-animal conflict, and its current situations in the state. The Paper further focuses on use of advanced computer technologies, and techniques like Data Analytics & Statistical Analysis to study the actual current situation of Human-Animal Conflict in Maharashtra.

scholarly journals Documentation of Prognostication Discussion

2021 ◽  
Vol 27 ◽  
pp. 222-229
Author(s):  
Divakaran E. Edassery ◽  
Rajashree K. Chittezhathu ◽  
Jyothi Jayan Warrier
Keyword(s):  
Palliative Care ◽  
Statistical Analysis ◽  
Patient Encounter ◽  
Care Clinic ◽  
Cause Analysis ◽  
Root Cause ◽  
Ishikawa Diagram ◽  
Documentation Status ◽  
Key Drivers ◽  
A3 Method

Background: Our organization is a NGO that provides palliative and supportive care at outpatient (OP), home visits and inpatient (IP), and Hospice settings. During patient encounter at different settings, documentation of discussion on prognostication was not done on the patients’ case sheets. This had created communication gap between the professionals, the patients and their family members. Due to this, there was a mismatch between the patients’ expectations and the services provided. Aims: The aim of the study was to implement A3 protocol and to increase the documentation status from zero to 75% by the end of five months after the commencement of the project. Settings and Design: OP - Department of Palliative Care Clinic A3 method. Material and Methods: The process map of the newly registered patients was followed. Root cause analysis was done using the Ishikawa Diagram. The main cause was that there was no specific format for documentation of prognostication. The professionals also felt some difficulty in disclosing the information as they were not following any prognostication tools upon which such discussions can be made. The key drivers were identified. Interventions were focused with specific contributors. A run chart was maintained to assess the progress of the interventions Statistical Analysis Used: Percentage calculation. Results: This endeavor has resulted in raising the documentation status from 0 to 80%. Conclusion: A3 protocol has been successful in developing the format for documentation of prognostication. Our team has gained confidence in implementing the A3 in other domains too.

scholarly journals Simplified Data Analytics for the Accurate Evaluation of a New Venture's Market Potential

2006 ◽  
Vol 9 (2) ◽  
pp. 9-17 ◽  
Author(s):  
Michael D. Mattei ◽  
Stephen Hellebusch
Keyword(s):  
Information Technology ◽  
Decision Support ◽  
Statistical Analysis ◽  
Data Analytics ◽  
Data Warehousing ◽  
Cost Effective ◽  
Market Potential ◽  
Mathematical Technique ◽  
Accurate Evaluation ◽  
Data Analytic

This article examines the creation of an accurate market projection designed with easy-to-use, cost-effective data analytic techniques. Many of the techniques explored are derived from the subdisciplines of decision support and data warehousing found in the information technology arena. Two significant contributions are presented: a simple mathematical technique that eliminates the need for heuristics, and the simplification of the process to the point where no computer or sophisticated statistical analysis is needed.

Not So Fuzzy Audit Analytics

2020 ◽  
Author(s):  
Jamie Hoelscher ◽  
Trevor Shonhiwa
Keyword(s):  
Data Analytics ◽  
Microsoft Excel ◽  
Comprehensive Data ◽  
Using Data ◽  
Data Analytic

In this case, students are introduced to audit analytics, specifically the use of the fuzzy lookup tool available in Microsoft Excel.  Students will use both conditional formatting and the fuzzy lookup tool to examine a dataset for possible instances of fictitious vendor fraud, a common and often costly type of fraud.  The case takes students through the comprehensive data analytics cycle as students are instructed how to test for fictitious vendors using data analytic techniques.  Students will then rely on the underlying data to analyze potential relationships and trends and communicate results via a memorandum, while being introduced to other common preventive and detective controls related to mitigate the risk of fictitious vendors.

Sign in / Sign up

Export Citation Format

Share Document