Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring

Daniel Zurita; Enric Sala; Jesús A. Carino; Miguel Delgado; Juan A. Ortega

doi:10.1109/DEMPED.2015.7303692

Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring

Daniel Zurita
, Enric Sala
, Jesús A. Carino
, Miguel Delgado
, Juan A. Ortega

Polytechnic University of Catalonia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Time series forecasting represents a critical factor, mainly in the industrial sector, in order to assure the proper operation of the manufacturing processes. In this work, a classical ANFIS forecasting scheme is enhanced by the proposal of a dynamics boosting strategy. First, the objective signal is decomposed by means of the Empirical Mode to highlight the main characteristics functions. Next, the dynamics of the functions in regard to the performance of the ANFIS is analyzed. Thus, the functions are separated into different sets. Then, the forecasting is faced with the employment of multiple ANFIS models focused on different dynamics modes. The performance of the proposed system is validated experimentally. According to the obtained results, the proposed approach outperforms the classical methods and represents a reliable and feasible methodology suitable to multiple applications.

Original language	English
Title of host publication	Proceedings - SDEMPED 2015
Subtitle of host publication	IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	212-218
Number of pages	7
ISBN (Electronic)	9781479977437
DOIs	https://doi.org/10.1109/DEMPED.2015.7303692
Publication status	Published - 21 Oct 2015
Externally published	Yes
Event	10th IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2015 - Guarda, Portugal Duration: 1 Sept 2015 → 4 Sept 2015

Publication series

Name	Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives

Conference

Conference	10th IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2015
Country/Territory	Portugal
City	Guarda
Period	1/09/15 → 4/09/15

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Artificial intelligence
Condition monitoring
Fuzzy neural networks
Machine learning
Predictive models
Prognosis
Time series analysis

Access to Document

10.1109/DEMPED.2015.7303692

Cite this

Zurita, D., Sala, E., Carino, J. A., Delgado, M., & Ortega, J. A. (2015). Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring. In Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (pp. 212-218). Article 7303692 (Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEMPED.2015.7303692

Zurita, Daniel ; Sala, Enric ; Carino, Jesús A. et al. / Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring. Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 212-218 (Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives).

@inproceedings{6e523393ca344bccbce2bcf64beabb90,

title = "Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring",

abstract = "Time series forecasting represents a critical factor, mainly in the industrial sector, in order to assure the proper operation of the manufacturing processes. In this work, a classical ANFIS forecasting scheme is enhanced by the proposal of a dynamics boosting strategy. First, the objective signal is decomposed by means of the Empirical Mode to highlight the main characteristics functions. Next, the dynamics of the functions in regard to the performance of the ANFIS is analyzed. Thus, the functions are separated into different sets. Then, the forecasting is faced with the employment of multiple ANFIS models focused on different dynamics modes. The performance of the proposed system is validated experimentally. According to the obtained results, the proposed approach outperforms the classical methods and represents a reliable and feasible methodology suitable to multiple applications.",

keywords = "Artificial intelligence, Condition monitoring, Fuzzy neural networks, Machine learning, Predictive models, Prognosis, Time series analysis",

author = "Daniel Zurita and Enric Sala and Carino, \{Jes{\'u}s A.\} and Miguel Delgado and Ortega, \{Juan A.\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 10th IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2015 ; Conference date: 01-09-2015 Through 04-09-2015",

year = "2015",

month = oct,

day = "21",

doi = "10.1109/DEMPED.2015.7303692",

language = "English",

series = "Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "212--218",

booktitle = "Proceedings - SDEMPED 2015",

address = "United States",

}

Zurita, D, Sala, E, Carino, JA, Delgado, M & Ortega, JA 2015, Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring. in Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives., 7303692, Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, Institute of Electrical and Electronics Engineers Inc., pp. 212-218, 10th IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2015, Guarda, Portugal, 1/09/15. https://doi.org/10.1109/DEMPED.2015.7303692

Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring. / Zurita, Daniel; Sala, Enric; Carino, Jesús A. et al.
Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives. Institute of Electrical and Electronics Engineers Inc., 2015. p. 212-218 7303692 (Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring

AU - Zurita, Daniel

AU - Sala, Enric

AU - Carino, Jesús A.

AU - Delgado, Miguel

AU - Ortega, Juan A.

PY - 2015/10/21

Y1 - 2015/10/21

N2 - Time series forecasting represents a critical factor, mainly in the industrial sector, in order to assure the proper operation of the manufacturing processes. In this work, a classical ANFIS forecasting scheme is enhanced by the proposal of a dynamics boosting strategy. First, the objective signal is decomposed by means of the Empirical Mode to highlight the main characteristics functions. Next, the dynamics of the functions in regard to the performance of the ANFIS is analyzed. Thus, the functions are separated into different sets. Then, the forecasting is faced with the employment of multiple ANFIS models focused on different dynamics modes. The performance of the proposed system is validated experimentally. According to the obtained results, the proposed approach outperforms the classical methods and represents a reliable and feasible methodology suitable to multiple applications.

AB - Time series forecasting represents a critical factor, mainly in the industrial sector, in order to assure the proper operation of the manufacturing processes. In this work, a classical ANFIS forecasting scheme is enhanced by the proposal of a dynamics boosting strategy. First, the objective signal is decomposed by means of the Empirical Mode to highlight the main characteristics functions. Next, the dynamics of the functions in regard to the performance of the ANFIS is analyzed. Thus, the functions are separated into different sets. Then, the forecasting is faced with the employment of multiple ANFIS models focused on different dynamics modes. The performance of the proposed system is validated experimentally. According to the obtained results, the proposed approach outperforms the classical methods and represents a reliable and feasible methodology suitable to multiple applications.

KW - Artificial intelligence

KW - Condition monitoring

KW - Fuzzy neural networks

KW - Machine learning

KW - Predictive models

KW - Prognosis

KW - Time series analysis

UR - https://www.scopus.com/pages/publications/84959288531

U2 - 10.1109/DEMPED.2015.7303692

DO - 10.1109/DEMPED.2015.7303692

M3 - Conference contribution

AN - SCOPUS:84959288531

T3 - Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives

SP - 212

EP - 218

BT - Proceedings - SDEMPED 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2015

Y2 - 1 September 2015 through 4 September 2015

ER -

Zurita D, Sala E, Carino JA, Delgado M, Ortega JA. Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring. In Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives. Institute of Electrical and Electronics Engineers Inc. 2015. p. 212-218. 7303692. (Proceedings - SDEMPED 2015: IEEE 10th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives). doi: 10.1109/DEMPED.2015.7303692

Enhanced time series forecasting by means of dynamics boosting for industrial process monitoring

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this