Predictive diagnosis based on a fleet-wide ontology approach

Medina-Oliva, Gabriela; Voisin, Alexandre; Monnin, Maxime; Léger, Jean-Baptiste

doi:10.1016/j.knosys.2013.12.020

Cited by 67 publications

(50 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, the generally-accepted approach for structuring the domain knowledge is constructing domain ontologies to model concepts and relationships [95,96]. Ontologies offer a wide spectrum of opportunities, in particular, providing a common understanding of specific domains that can be communicated between people and application systems.…”

Section: Knowledge Engineering For the Sustainability Assessment Domainmentioning

confidence: 99%

An Ontology-Based Knowledge Modelling for a Sustainability Assessment Domain

Konys

2018

Sustainability

View full text Add to dashboard Cite

Sustainability assessment has received more and more attention from researchers and it offers a large number of opportunities to measure and evaluate the level of its accomplishment. However, proper selection of a particular sustainability assessment approach, reflecting problem properties and the evaluator's preferences, is a complex and important issue. Due to an existing number of different approaches dedicated to assessing, supporting, or measuring the level of sustainability and their structure oriented on the particular domain usage, problems with accurate matching frequently occur. On the other hand, the efficiency of sustainability assessment depends on the available knowledge of the ongoing capabilities. Additionally, actual research trends confirm that knowledge engineering gives a method to handle domain knowledge practically and effectively. Unfortunately, literature studies confirm that there is a lack of knowledge systematization in the sustainability assessment domain, however. The practical application of knowledge-based mechanisms may cover this gap. In this paper, we provide formal, practical and technological guidance to a knowledge management-based approach to sustainability assessment. We propose ontology as a form of knowledge conceptualization and using knowledge engineering, we make gathered knowledge publicly available and reusable, especially in terms of interoperability of collected knowledge.

show abstract

Section: Knowledge Engineering For the Sustainability Assessment Domainmentioning

confidence: 99%

An Ontology-Based Knowledge Modelling for a Sustainability Assessment Domain

Konys

2018

Sustainability

View full text Add to dashboard Cite

show abstract

“…To overcome these challenges, it seems worthwhile to consider and make use of the knowledge and data coming from similar equipment, forming what in the industrial context is called a fleet [6], [31], rather than relying solely on the knowledge and data coming from a single equipment. This will improve our knowledge concerning the equipment behaviour, reduce prognostics uncertainty and, thus, improve the efficiency of the fault prognostics task.…”

Section: Notation and List Of Acronymsmentioning

confidence: 99%

Remaining useful life estimation in heterogeneous fleets working under variable operating conditions

Al‐Dahidi

Maio

Baraldi

et al. 2016

Reliability Engineering & System Safety

View full text Add to dashboard Cite

Abstract. The availability of condition monitoring data for large fleets of similar equipment motivates the development of data-driven prognostic approaches that capitalize on the information contained in such data to estimate equipment Remaining Useful Life (RUL). A main difficulty is that the fleet of equipment typically experiences different operating conditions, which influence both the condition monitoring data and the degradation processes that physically determine the RUL. We propose an approach for RUL estimation from heterogeneous fleet data based on three phases: firstly, the degradation levels (states) of an homogeneous discrete-time finite-state semi-markov model are identified by resorting to an unsupervised ensemble clustering approach. Then, the parameters of the discrete Weibull distributions describing the transitions among the states and their uncertainties are inferred by resorting to the Maximum Likelihood Estimation (MLE) method and to the Fisher Information Matrix (FIM), respectively. Finally, the inferred degradation model is used to estimate the RUL of fleet equipment by direct Monte Carlo (MC) simulation. The proposed approach is applied to two case studies regarding heterogeneous fleets of aluminum electrolytic capacitors and turbofan engines. Results show the effectiveness of the proposed approach in predicting the RUL and its superiority compared to a fuzzy similarity-based approach of literature. Keywords

show abstract

“…Similar procedure is implemented in our proposed system but with PSO algorithm to improve the training phase using swarming procedure at every iterations. A ontology based automated clinical systems [13,16,17,18,22,25,26,27,29,30,31,32,33,34] has proved better in health care system and the association of fuzzy further enhanced the results [14,20,21,23,24,28]. Hence the use of ontology is inbuilt in the proposed system with fuzzy logic for Prakriti ailments.…”

Section: Related Workmentioning

confidence: 99%

Ontology Based Optimization with Adaptive Network Based Fuzzy Inference System Based Health Maintenance System

2017

IJCRR

View full text Add to dashboard Cite

In late years, economic growth and globalization have driven significant modernization of Ayurvedic Medicine in India. According to Ayurvedic Medicine, human body is divided into three constitutions/tridoshas based on the hypothesis of Prakriti. The categories of Prakriti are written based on the philosophy of tridoshas namely Vata, Pitta and Kapha. Ayurvedic clinicians' records/documents the consultation of patient along with patient's Prakriti in a paper. This is neither exchanged nor made accessible to other clinicians'. Due to rapid advancement in electronic media, the necessity of digital Ayurvedic patient management systems could help in diagnosing the patient before the consultation of clinicians. Henceforth, an electronic health record system is proposed that uses ontology oriented procedure to compute the physical constitutions of a human body. Specifically, a rule based system is developed and evaluated using Particle Swarm Optimization -Adaptive Network based Fuzzy Inference system (PSO-ANFIS). The ontological inputs to the fuzzy interface includes Doshas, food and lifestyle recommendations, obtained from clinical and textual data. Automated system created using ontology oriented PSO-ANFIS interface supports food, herbs, diet and life style recommendation to the patients'. The proposed model is evaluated with different patient and the sample is tested with the clinicians. The results proved that the proposed method fits with better results than the conventional ones.

show abstract

Predictive diagnosis based on a fleet-wide ontology approach

Cited by 67 publications

References 36 publications

An Ontology-Based Knowledge Modelling for a Sustainability Assessment Domain

An Ontology-Based Knowledge Modelling for a Sustainability Assessment Domain

Remaining useful life estimation in heterogeneous fleets working under variable operating conditions

Ontology Based Optimization with Adaptive Network Based Fuzzy Inference System Based Health Maintenance System

Contact Info

Product

Resources

About