97,301 Hits in 6.2 sec

A Machine Learning-Based Framework for Building Application Failure Prediction Models

Alessandro Pellegrini, Pierangelo Di Sanzo, Dimiter R. Avresky
2015 2015 IEEE International Parallel and Distributed Processing Symposium Workshop  
In this paper, we present the Framework for building Failure Prediction Models (F 2 PM), a Machine Learning-based Framework to build models for predicting the Remaining Time to Failure (RTTF) of applications  ...  F 2 PM uses measurements of a number of system features in order to create a knowledge base, which is then used to build prediction models.  ...  In this paper, we present the Framework for building Failure Prediction Models (F 2 PM), a Machine Learning (ML) based Framework aimed at building system failure prediction models.  ... 
doi:10.1109/ipdpsw.2015.110 dblp:conf/ipps/PellegriniSA15 fatcat:isyozzyjm5el7f4chw27bms6aq

Predictive Maintenance in Building Facilities: A Machine Learning-Based Approach

Yassine Bouabdallaoui, Zoubeir Lafhaj, Pascal Yim, Laure Ducoulombier, Belkacem Bennadji
2021 Sensors  
In this paper, a predictive maintenance framework based on machine learning techniques is proposed.  ...  Then, a deep learning model was used to predict failures. The case study showed the potential of this framework to predict failures.  ...  Acknowledgments: The authors are grateful to Bouygues Energies Et Services Facility Maintenance's Team for facilitating and cooperating in this research.  ... 
doi:10.3390/s21041044 pmid:33546418 pmcid:PMC7913483 fatcat:ojhfyz6nuvcj5e7y3kkr3eu2ya


Etibar Vazirov, Azerbaijan State Oil and Industry University
2020 Azerbaijan Journal of High Performance Computing  
Besides, this framework should predict the reasons for failure and provide new capabilities to recover from application failures.  ...  This provisional information has an irreplaceable value in learning to predict where applications may face dynamic and interactive behavior when resource failures occur.  ...  In this paper, a supervised ML technique has been proposed to build a training model that predicts runtime failures using application resources and performance features.  ... 
doi:10.32010/26166127.2020. fatcat:w2tlha4vtncarg5igk6uvohlqe

Proactive Maintenance Strategy Based on Resilience Empowerment for Complex Buildings [chapter]

Francesco Rota, Maria Cinzia Luisa Talamo, Giancarlo Paganin
2020 Smart Innovation, Systems and Technologies  
More specifically, proactive maintenance, through Industry 4.0 (I4.0) tools, can enact control strategies for mitigating both endogenous riskssuch as equipment failure, aging and obsolesce not always deeply  ...  Anticipation of disruptive events of systems and control of endogenous risks is possible thanks the introduction of IoT and machine learning tools which may allow to modify the traditional corrective maintenance  ...  (2018) Sensor data Fault prediction for subsystems DT, SVM, KNN, RF A Simple State-Based Prognostic Model for Filter Clogging.  ... 
doi:10.1007/978-3-030-52869-0_21 fatcat:4dgcbwsennbgxekozpdjzs4d3q

SOPHIA: An Event-Based IoT and Machine Learning Architecture for Predictive Maintenance in Industry 4.0

Matteo Calabrese, Martin Cimmino, Francesca Fiume, Martina Manfrin, Luca Romeo, Silvia Ceccacci, Marina Paolanti, Giuseppe Toscano, Giovanni Ciandrini, Alberto Carrotta, Maura Mengoni, Emanuele Frontoni (+1 others)
2020 Information  
In this work, we use a data-driven approach based on machine learning applied to woodworking industrial machines for a major woodworking Italian corporation.  ...  Our predictive maintenance approach deployed on a Big Data framework allows screening simultaneously multiple connected machines by learning from terabytes of log data.  ...  Appendix A. Supplementary Information  ... 
doi:10.3390/info11040202 fatcat:6ko3ze2msbfhnfwbd42jpo3bo4

The Digital Twin Landscape at the Crossroads of Predictive Maintenance, Machine Learning and Physics Based Modeling [article]

Brian Kunzer, Mario Berges, Artur Dubrawski
2022 arXiv   pre-print
The application of a digital twin framework is highlighted in the field of predictive maintenance, and its extensions utilizing machine learning and physics based modeling.  ...  A definition for a minimally viable framework to utilize a digital twin is also provided based on seven essential elements.  ...  Thereafter, the paper highlights the application of a digital twin framework in the field of predictive maintenance, and its extensions utilizing machine learning and physics based modeling.  ... 
arXiv:2206.10462v2 fatcat:fznude7xvjbi3e73k5tzqp7sce

Advancing from Predictive Maintenance to Intelligent Maintenance with AI and IIoT [article]

Haining Zheng and Antonio R. Paiva and Chris S. Gurciullo
2020 arXiv   pre-print
This AI and IIoT based Intelligent Maintenance framework is composed of (1) latest machine learning algorithms including probabilistic reliability modelling with deep learning, (2) real-time data collection  ...  , transfer, and storage through wireless smart sensors, (3) Big Data technologies, (4) continuously integration and deployment of machine learning models, (5) mobile device and AR/VR applications for fast  ...  In addition, classification models can help identify failure types. Unsupervised Learning Anomaly detection is the most common unsupervised learning framework for maintenance analytics.  ... 
arXiv:2009.00351v1 fatcat:vqewkmeeezh7hjfsqh2a6rljyu

Digital Fleet Management: A Scalable Cloud Framework based on Data-driven Prediction Models

Sherin Thomas, Abhishek Dubey, Daniel E Viassolo, Magson Zanette
2020 Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM  
An end-to-end automated scalable cloud framework is described in detail. This framework integrates failure prediction models for each single asset in the fleet of tools.  ...  The proposed method integrates the tasks of: fetching data from 200,000+ tools, performing feature engineering, modeling via Machine Learning (ML) , and visualizing into a cloud pipeline.  ...  Data-driven approaches employing pattern recognition and machine learning (Schwabacher & Goebel, 2007) are integrated to the cloud framework for predicting a risk factor for each of the tools.  ... 
doi:10.36001/phmconf.2020.v12i1.1273 fatcat:hzu3h3pa5ndfljbiqkjihcupni

Software aging prediction and rejuvenation in cloud computing environment: a new approach

Shruthi P, Nagaraj G Cholli
2021 Indonesian Journal of Electrical Engineering and Computer Science  
In model based approach, analytic models are built for capturing system degradation and rejuvenation process.  ...  In measurement based approach, attributes are periodically monitored and that may indicate signs of software aging. In this work, a prototype of measurement based model has been developed.  ...  model using machine learning framework, prediction of software aging and framework for software rejuvenation easily.  ... 
doi:10.11591/ijeecs.v22.i2.pp1006-1012 fatcat:kgjlfbula5gd5armzvs2rcoanm

A Comprehensive Big Data Analytics Based Framework for Premature Recognition of Breast Cancer

This paper surveys various literatures available on application of big data analysis for breast cancer. Subsequently a comprehensive framework is being proposed based on the gaps identified.  ...  Different machine learning algorithms which can be applied in the framework is also detailed in the paper.  ...  learning based methods have been very effective in building predictive models for forecasting breast cancer.  ... 
doi:10.35940/ijitee.c8793.019320 fatcat:6ullhqr4wbe4zbu72d27cd62ry

Predicting Web Server Crashes: A Case Study in Comparing Prediction Algorithms

Javier Alonso, Jordi Torres, Ricard Gavaldà
2009 2009 Fifth International Conference on Autonomic and Autonomous Systems  
We study which machine learning algorithms build a more accurate model of the behavior of the anomaly system, and focus on Linear Regression and Decision Tree algorithms.  ...  In this paper, we propose a new framework to predict time-to-failure when the system is suffering transient failures that consume resources randomly.  ...  The flexibility of our framework is that allows to add new machine learning algorithms to build the model, or even to have a set of algorithms to build the model and choose the algorithm according to different  ... 
doi:10.1109/icas.2009.56 dblp:conf/icas/AlonsoTG09 fatcat:qdrbtitn2zgshioe2jgatgnqjy

Physics Informed Self Supervised Learning For Fault Diagnostics and Prognostics in the Context of Sparse and Noisy Data

Weikun Deng, Khanh T. P. Nguyen, Kamal Medjaher
2022 Proceedings of the European Conference of the Prognostics and Health Management Society (PHME)  
Big data volume but poor quality with scarce healthy states information limits the performance of training machine learning (ML) and physics-based failure modeling.  ...  data, providing a solution for deep physics knowledge-ML fusion by physics-informed machine learning algorithms.  ...  These challenges prompt PHM techniques into a hybrid framework. Hence, this thesis aims to explore the combination of PBMs and ML by physics informed machine learning (PIML).  ... 
doi:10.36001/phme.2022.v7i1.3298 fatcat:qffvco4yozb7zideemftooxy54

Proactive Cloud Management for Highly Heterogeneous Multi-cloud Infrastructures

Alessandro Pellegrini, Pierangelo Di Sanzo, Dimiter R. Avresky
2016 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)  
It uses machine learning models to predict failures of virtual machines and to proactively redirect the load to healthy machines/cloud regions.  ...  These policies use predictions about the mean time to failure of virtual machines.  ...  F 2 PM is designed to build ML-based prediction models which are completely agnostic of the running application.  ... 
doi:10.1109/ipdpsw.2016.124 dblp:conf/ipps/0001SA16 fatcat:4sber5ohy5fvtppkdqsnjm5sfy

Predicting Asset Maintenance Failure Using Supervised Machine Learning Techniques

Gregory Opara, Johnwendy Nwaukwa, Felix Uloko, Clinton Oborindo
2021 World Journal of Innovative Research  
Different machine learning techniques have been used for predicting maintenance, and to the best of our knowledge, Neural Network was only used for the prediction of the brake pad failure.  ...  Our research focused on condition monitoring which is a form of predictive maintenance for brake pad failure for heavy-duty vehicles asset.  ...  According to [23] , he made prediction of brake pad failure using Artificial Neural Network, in this research, we will enhance on his research by building a supervised machine learning model for prediction  ... 
doi:10.31871/wjir.11.3.6 fatcat:fp46tjrpjbeanjxtsf3h5iefvu

Big Data Preventive Maintenance for Hard Disk Failure Detection

Su Chuan-Jun, Jorge A. Quan Yon
2018 International Journal of Information and Education Technology  
This research focuses on hard drive failure prediction, with big data analysis and machine learning technology, we have developed a Preventive Monitoring System (PMS).  ...  Finally, we use random forest algorithm to construct the predictive model.  ...  At the beginning of batch training stage, in order to generate a machine learning model, we collect historical data as the data set, then build a prediction model based on it.  ... 
doi:10.18178/ijiet.2018.8.7.1085 fatcat:ca4fodutwbcxxaqqe2q6sg543a
« Previous Showing results 1 — 15 out of 97,301 results