Feature engineering –based machine learning models for operational state recognition of rotating machines

Jukka Junttila; Ville Lämsä; Leonardo Espinosa-Leal; Anssi Sillanpaa

doi:10.54985/peeref.2303p8483224

Feature engineering –based machine learning models for operational state recognition of rotating machines

Jukka Junttila^*
, Ville Lämsä
, Leonardo Espinosa-Leal
, Anssi Sillanpaa

^*Corresponding author for this work

Research output: Contribution to conference › Conference Poster › Scientific

Abstract

Data-based models for operational state recognition and
detection of abnormal operation of a gas engine generating
set (genset) in near real-time were provided. One model can
classify the current power output level very accurately, and
the other can detect abnormal operation (novelties), e.g., in
fault situations, at a specific load level. Thus, a fast and
accurate two-step state recognition model can be built.

Original language	English
Number of pages	1
DOIs	https://doi.org/10.54985/peeref.2303p8483224
Publication status	Published - 21 Mar 2023
MoE publication type	Not Eligible
Event	FCAI AI Day 2022 - Dipoli, Aalto University, Espoo, Finland Duration: 16 Nov 2022 → 16 Nov 2022 https://fcai.fi/ai-day-2022

Conference

Conference	FCAI AI Day 2022
Country/Territory	Finland
City	Espoo
Period	16/11/22 → 16/11/22
Internet address	https://fcai.fi/ai-day-2022

Keywords

Operational state recognition
Classification
Simulation
Mechanical vibration
Internal combustion engine
Feature engineering

Access to Document

10.54985/peeref.2303p8483224

2 Conference article in proceedings
1 Article
1 Master's thesis

Extreme Learning Machine-Based Operational State Recognition: A Feasibility Study with Mechanical Vibration Data
Junttila, J., Lämsä, V. & Espinosa-Leal, L., 2023, Proceedings of ELM 2021: Theory, Algorithms and Applications. Björk, K.-M. (ed.). Springer, p. 114-123 (Proceedings in Adaptation, Learning and Optimization, Vol. 16).
Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
Physics-Based Digital Twins Merging With Machines: Cases of Mobile Log Crane and Rotating Machine
Kurvinen, E., Kutvonen, A., Ukko, J., Khadim, Q., Hagh, Y. S., Jaiswal, S., Neisi, N., Zhidchenko, V., Kortelainen, J., Timperi, M., Kokkonen, K., Virtanen, J., Zeb, A., Lämsä, V., Nieminen, V., Junttila, J., Savolainen, M., Rantala, T., Valjakka, T. & Donoghue, I. & 12 others, Elfvengren, K., Nasiri, M., Rantala, T., Kurinov, I., Sikanen, E., Pyrhönen, L., Hannola, L., Handroos, H., Rantanen, H., Saunila, M., Sopanen, J. & Mikkola, A., 25 Apr 2022, In: IEEE Access. 10, p. 45962-45978 17 p.
Research output: Contribution to journal › Article › Scientific › peer-review

Open Access
24 Link opens in a new tab Citations (Scopus)
Validation of Simulated Mechanical Vibration Data for Operational State Recognition System
Junttila, J., Sillanpää, A. & Lämsä, V., 8 Sept 2022, 2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science, IRI 2022. IEEE Institute of Electrical and Electronic Engineers, p. 138-143
Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Cite this

@conference{8f917dbef4d04cd99c63ee7221c7d66e,

title = "Feature engineering –based machine learning models for operational state recognition of rotating machines",

abstract = "Data-based models for operational state recognition and detection of abnormal operation of a gas engine generating set (genset) in near real-time were provided. One model can classify the current power output level very accurately, and the other can detect abnormal operation (novelties), e.g., in fault situations, at a specific load level. Thus, a fast and accurate two-step state recognition model can be built.",

keywords = "Operational state recognition, Classification, Simulation, Mechanical vibration, Internal combustion engine, Feature engineering",

author = "Jukka Junttila and Ville L{\"a}ms{\"a} and Leonardo Espinosa-Leal and Anssi Sillanpaa",

year = "2023",

month = mar,

day = "21",

doi = "10.54985/peeref.2303p8483224",

language = "English",

note = "FCAI AI Day 2022 ; Conference date: 16-11-2022 Through 16-11-2022",

url = "https://fcai.fi/ai-day-2022",

}

TY - CONF

T1 - Feature engineering –based machine learning models for operational state recognition of rotating machines

AU - Junttila, Jukka

AU - Lämsä, Ville

AU - Espinosa-Leal, Leonardo

AU - Sillanpaa, Anssi

PY - 2023/3/21

Y1 - 2023/3/21

N2 - Data-based models for operational state recognition and detection of abnormal operation of a gas engine generating set (genset) in near real-time were provided. One model can classify the current power output level very accurately, and the other can detect abnormal operation (novelties), e.g., in fault situations, at a specific load level. Thus, a fast and accurate two-step state recognition model can be built.

AB - Data-based models for operational state recognition and detection of abnormal operation of a gas engine generating set (genset) in near real-time were provided. One model can classify the current power output level very accurately, and the other can detect abnormal operation (novelties), e.g., in fault situations, at a specific load level. Thus, a fast and accurate two-step state recognition model can be built.

KW - Operational state recognition

KW - Classification

KW - Simulation

KW - Mechanical vibration

KW - Internal combustion engine

KW - Feature engineering

U2 - 10.54985/peeref.2303p8483224

DO - 10.54985/peeref.2303p8483224

M3 - Conference Poster

T2 - FCAI AI Day 2022

Y2 - 16 November 2022 through 16 November 2022

ER -

Feature engineering –based machine learning models for operational state recognition of rotating machines

Abstract

Conference

Keywords

Access to Document

Fingerprint

Research output

Extreme Learning Machine-Based Operational State Recognition: A Feasibility Study with Mechanical Vibration Data

Physics-Based Digital Twins Merging With Machines: Cases of Mobile Log Crane and Rotating Machine

Validation of Simulated Mechanical Vibration Data for Operational State Recognition System

Cite this