Details
| Original language | English |
|---|---|
| Article number | 112519 |
| Journal | Knowledge-based systems |
| Volume | 304 |
| Early online date | 12 Sept 2024 |
| Publication status | Published - 25 Nov 2024 |
Abstract
Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study's input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.
Keywords
- Air compressor faults, Fault diagnosis, Feature fusion, Lazy classifiers, Machine learning, Vibration analysis
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Business, Management and Accounting(all)
- Management Information Systems
- Decision Sciences(all)
- Information Systems and Management
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Knowledge-based systems, Vol. 304, 112519, 25.11.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Prediction of air compressor faults with feature fusion and machine learning
AU - Nambiar, Abhay
AU - S., Naveen Venkatesh
AU - S., Aravinth
AU - V., Sugumaran
AU - Ramteke, Sangharatna M.
AU - Marian, Max
N1 - Publisher Copyright: © 2024 The Authors
PY - 2024/11/25
Y1 - 2024/11/25
N2 - Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study's input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.
AB - Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study's input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.
KW - Air compressor faults
KW - Fault diagnosis
KW - Feature fusion
KW - Lazy classifiers
KW - Machine learning
KW - Vibration analysis
UR - http://www.scopus.com/inward/record.url?scp=85203665080&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2024.112519
DO - 10.1016/j.knosys.2024.112519
M3 - Article
AN - SCOPUS:85203665080
VL - 304
JO - Knowledge-based systems
JF - Knowledge-based systems
SN - 0950-7051
M1 - 112519
ER -