Filters








728 Hits in 4.4 sec

A textual transform of multivariate time-series for prognostics [article]

Abhay Harpale
2017 arXiv   pre-print
The proposed approach is shown to be superior in terms of prediction accuracy, lead time to prediction and interpretability.  ...  The approach has been deployed and successfully tested on large scale multivariate time-series data from commercial aircraft engines.  ...  Let X i = arXiv:1709.06669v1 [stat.ML] 19 Sep 2017 Fig. 1 : 1 Time-series dataset notation Fig. 2 : 2 Process workflow for converting time-series to textual bag-of-words representation entropy H(D,  ... 
arXiv:1709.06669v1 fatcat:tcfwqfaq7vfjbmrfmyeyto4ede

A Hybrid Approach: Dynamic Diagnostic Rules for Sensor Systems in Industry 4.0 Generated by Online Hyperparameter Tuned Random Forest

Ahlam Mallak, Madjid Fathi
2020 Sci  
time-series multivariate sensor readings.  ...  The architecture of the proposed method is demonstrated in a comprehensive manner, and the dynamic rules extraction phase is applied using a case study on condition monitoring of a hydraulic test rig using  ...  Funding: This research was funded by the DFG research grants LO748/11-1 and OB384/5-1. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/sci2040075 fatcat:kec7wdou5zelli7xvgat3tsuua

Finding the Different Patterns in Buildings Data Using Bag of Words Representation with Clustering

Usman Habib, Gerhard Zucker
2015 2015 13th International Conference on Frontiers of Information Technology (FIT)  
Then the SAX symbols are converted to bag of words representation for hierarchical clustering. Moreover, the proposed technique is applied to real life data of adsorption chiller.  ...  Additionally, the results from the proposed method and dynamic time warping (DTW) approach are also discussed and compared.  ...  Bag of Words Representation (BoWR) The SAX transformation will transform the time series data in the symbols.  ... 
doi:10.1109/fit.2015.60 dblp:conf/fit/HabibZ15 fatcat:j3jbcuozzrhc3kn5yraqfeukii

A Hybrid Approach: Dynamic Diagnostic Rules for Sensor Systems in Industry 4.0 Generated by Online Hyperparameter Tuned Random Forest

Ahlam Mallak, Madjid Fathi
2020 Sci  
time-series multivariate sensor readings.  ...  The architecture of the proposed method is demonstrated in a comprehensive manner, and the dynamic rules extraction phase is applied using a case study on condition monitoring of a hydraulic test rig using  ...  Funding: This research was funded by the DFG research grants LO748/11-1 and OB384/5-1. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/sci2040061 fatcat:kpwatw25fjdtbcjeo7r6gfqegi

Correlating Time Series Signals and Event Logs in Embedded Systems

Kazimierz Krosman, Janusz Sosnowski
2021 Sensors  
The correlation process must take into account clock inconsistencies between the data acquisition and monitored devices, which provide time series signals and event logs, respectively.  ...  This leads to the investigation of two types of data: time series, representing signal periodic samples in a background of noise, and sporadic event logs.  ...  Most research papers on signal monitoring and analysis deal with time series decomposition, classification, prediction, and characteristic features; some publications are commented on and referred to in  ... 
doi:10.3390/s21217128 pmid:34770436 pmcid:PMC8588274 fatcat:qq35khp47ncxvak27bbklire5a

A multimodal deep learning-based fault detection model for a plastic injection molding process

Gyeongho Kim, Jae Gyeong Choi, Minjoo Ku, Hyewon Cho, Sunghoon Lim
2021 IEEE Access  
The proposed multimodal deep learning-based fault detection model takes two types of multivariate data at a time: tabular and time-series data.  ...  Chadha et al. use CNN and its variants to conduct fault detection with time-series data in multiple manufacturing processes [62] .  ... 
doi:10.1109/access.2021.3115665 fatcat:bd3mrq56mzcwjetxwt75vw3j4m

LS-SVM based spectral clustering and regression for predicting maintenance of industrial machines

Rocco Langone, Carlos Alzate, Bart De Ketelaere, Jonas Vlasselaer, Wannes Meert, Johan A.K. Suykens
2015 Engineering applications of artificial intelligence  
For the time-series analysis with the NAR model data 443 acquired by a thermal camera, which directly measures the dirt accumulation in 444 the jaws, are processed.  ...  These measurements give an information on the current 17 status of a machine and can be used to predict the faults due to deterioration of 18 key components [23, 10].  ...  Here the vibration signals used to monitor the dirt accumulation in 212 the jaws are 190-dimensional time-series (as shown in the bottom part of .  ... 
doi:10.1016/j.engappai.2014.09.008 fatcat:a74vgxaid5dt7hg2273qgndr4e

Complex building's energy system operation patterns analysis using bag of words representation with hierarchical clustering

Usman Habib, Khizar Hayat, Gerhard Zucker
2016 Complex Adaptive Systems Modeling  
Afterward, the symbols are converted to bag of words representation (BoWR) for hierarchical clustering. A gap statistics method is used to find the best number of clusters in the data.  ...  A bag of word representation method with hierarchical clustering has been proposed to assess the performance of a building energy system.  ...  Acknowledgements This work was partly funded by the Austrian Funding Agency in the funding programme e!MISSION within the project "extrACT", Project Number 838688.  ... 
doi:10.1186/s40294-016-0020-0 fatcat:jpwsw67vobfqtdan3k2i6soh7u

Predictive Maintenance in the Automotive Sector: A Literature Review

Fabio Arena, Mario Collotta, Liliana Luca, Marianna Ruggieri, Francesco Gaetano Termine
2021 Mathematical and Computational Applications  
With the rapid advancement of sensor and network technology, there has been a notable increase in the availability of condition-monitoring data such as vibration, temperature, pressure, voltage, and other  ...  In this scenario, this paper presents a systematic literature review of statistical inference approaches, stochastic methods, and AI techniques for predictive maintenance in the automotive sector.  ...  All authors have read and agreed to the published version of the manuscript.  ... 
doi:10.3390/mca27010002 fatcat:sgr35l7wxjdhnda23myr7sekwa

A big data MapReduce framework for fault diagnosis in cloud-based manufacturing

Ajay Kumar, Ravi Shankar, Alok Choudhary, Lakshman S. Thakur
2016 International Journal of Production Research  
In this paper we use the binary prediction of faults 'Yes' and 'No'. We Table 3 and 4.  ...  In their study, EasyEnsemble and BalanceCascade used bagging in the first ensemble and later on for each bag AdaBoost was also used.  ... 
doi:10.1080/00207543.2016.1153166 fatcat:ftbeqcpwefdkxoarzsi2bq65qy

The Canonical Interval Forest (CIF) Classifier for Time Series Classification [article]

Matthew Middlehurst, James Large, Anthony Bagnall
2020 arXiv   pre-print
The time series forest (TSF) classifier is one of the most well known interval methods, and has demonstrated strong performance as well as relative speed in training and predictions.  ...  One of these groups describes classifiers that predict using phase dependant intervals.  ...  Our thanks to Carl Lubba for help with setting up and running the sktime catch22 version used in our initial investigations.  ... 
arXiv:2008.09172v1 fatcat:4wddw5vygjdy3bixwqv7pqrtya

Robust Detection of Incipient Faults in VSI-Fed Induction Motors Using Quality Control Charts

Luis Angel Garcia-Escudero, Oscar Duque-Perez, Miguel Fernandez-Temprano, Daniel Morinigo-Sotelo
2017 IEEE transactions on industry applications  
But, obviously, the new motor to be diagnosed cannot be the same that has been used during the training process; it may be a motor with different characteristics and fed from a completely different source  ...  These different conditions between the training process and the testing one can deeply influence the diagnosis.  ...  ACKNOWLEDGMENT The authors would like to thank the editor and two anonymous reviewers for their comments, which lead to this improved version of the paper.  ... 
doi:10.1109/tia.2016.2617300 fatcat:ucvra7vljneeng4gfzagqz46vq

Fault Detection of Fuel Systems Using Polynomial Regression Profile Monitoring

Mahmoud Awad
2016 Quality and Reliability Engineering International  
We present in this paper a new monitoring framework for smart fuel systems utilizing outlying observations detection and monitoring using ccharts.  ...  Anomaly detection is the characterization of a normal behavior of a system or process and identification of any deviation from such normal behavior.  ...  Finally, the third class of approaches known as multiscale multivariate SPC is based on transforming the auto-correlated time-series structure into other forms using transforming families such as wavelet  ... 
doi:10.1002/qre.2068 fatcat:ct5zfytvivhdfke3jyy37onx3a

Wind power prediction using bootstrap aggregating trees approach to enabling sustainable wind power integration in a smart grid

Fouzi Harrou, Ahmed Saidi, Ying Sun
2019 Energy Conversion and Management  
The overarching goal of this study is to design an approach enabling an 84 efficient prediction of wind power production based on times series supervisory control and data acquisition 85 (SCADA) data from  ...  After computing the latent variables 101 in the process being investigated, then these fewer number of variables are used instead of using the raw 102 data.  ...  The designed prediction models when using 386 fault-free data mimics the nominal behavior of wind turbine can be very useful in designing monitoring 387 schemes to prevent faults before they occur and  ... 
doi:10.1016/j.enconman.2019.112077 fatcat:dyzjkxallrh7ffcdmtsozniwqa

Machine Learning for Process Monitoring and Control of Hot-Melt Extrusion: Current State of the Art and Future Directions

Nimra Munir, Michael Nugent, Darren Whitaker, Marion McAfee
2021 Pharmaceutics  
near-infrared (NIR), Raman, and UV–Vis, coupled with various machine learning algorithms, to monitor and control the HME process in real time.  ...  The main current challenges in the application of machine learning algorithms for pharmaceutical processes are discussed, with potential future directions for the industry.  ...  , and to monitor in-process degradation as well. with time for pure cultures than for mixed cultures, which, in other words, suggested higher degradation for pure cultures than mixed cultures (see Figure  ... 
doi:10.3390/pharmaceutics13091432 pmid:34575508 fatcat:zte3z54uw5g63cnszkpvdfjhxy
« Previous Showing results 1 — 15 out of 728 results