A new vibration-based hybrid anomaly detection model for preventing high-power generator failures in power plants

Kırbaş, İsmail; Kerem, Alper

doi:10.1080/15567036.2021.1960654

Cited by 4 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Industrial case studies demonstrated that their evaluation method had higher fault prediction rates and lower false alarm rates compared to traditional methods [22]. Kirbaş et al designed a hybrid anomaly detection model combining multiple linear regression, response surface methods, and a multilayer perceptron for detecting faults in high-power generators [23]. Qiao et al developed a meta-learning-based CNN approach for wind turbine fault early warning.…”

Section: Literature Reviewmentioning

confidence: 99%

A Fault Warning Approach Using an Enhanced Sand Cat Swarm Optimization Algorithm and a Generalized Neural Network

Pi,

Tan,

Golmohammadi

et al. 2023

Processes

View full text Add to dashboard Cite

With the continuous development and complexity of industrial systems, various types of industrial equipment and systems face increasing risks of failure during operation. Important to these systems is fault warning technology, which can timely detect anomalies before failures and take corresponding preventive measures, thereby reducing production interruptions and maintenance costs, improving production efficiency, and enhancing equipment reliability. Machine learning techniques have proven highly effective for fault detection in modern production processes. Among numerous machine learning algorithms, the generalized neural network stands out due to its simplicity, effectiveness, and applicability to various fault warning scenarios. However, the increasing complexity of systems and equipment presents significant challenges to the generalized neural network. In real-world scenarios, it suffers from drawbacks such as difficulties in determining parameters and getting trapped in local optima, which affect its ability to meet the requirements of high efficiency and accuracy. To overcome these issues, this paper proposes a fault warning method based on an enhanced sand cat swarm optimization algorithm combined with a generalized neural network. First, we develop an enhanced sand cat swarm optimization algorithm that incorporates an improved chaotic mapping initialization strategy, as well as Cauchy mutation and reverse elite strategies based on adaptive selection. Subsequently, we utilize this algorithm to optimize the generalized neural network and determine its optimal parameters, effectively improving the accuracy and reliability of system fault warnings. The proposed method is validated using actual industrial system data, specifically for generator fault warning, and is demonstrated to outperform other advanced fault warning techniques. This research provides valuable insights and promising directions for enhancing industrial fault warning capabilities.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Fault Warning Approach Using an Enhanced Sand Cat Swarm Optimization Algorithm and a Generalized Neural Network

Pi,

Tan,

Golmohammadi

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…The model-based methods can avoid the above-mentioned problems since the collected original features are fed directly into the model. In 2021, Kirba and Kerem [20] proposed a hybrid anomaly detection model for preventing high-power generator failures in power plants. The dataset used in the experiments consisted of 28 effective sensors.…”

Section: Introductionmentioning

confidence: 99%

“…The literature [20][21][22][23] use model-based methods for anomaly detection or fault diagnosis tasks, and the acquire raw signal features are fed directly into the model. It avoids the limitations of feature extraction and feature selection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly detection of industrial motors under few-shot feature conditions based on causality

Cen¹,

Li²,

Cen³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

It is observed that previous research studies focusing on few-shot feature data for fault diagnosis or anomaly detection have a limitation, that is, feature extraction methods to solve few-shot feature data problems will also have scenarios where they may not always be applicable. In this paper, a motor anomaly detection model with generalization performance is proposed to meet the anomaly detection needs in the above scenarios. The model consists of a reinforcement unit and a diagnosis unit. Firstly, the reinforcement unit extracts the adjacent features with different timestamps through ensemble learning. Secondly, the temporal convolutional network (TCN) model is nested to increase the receptive field of the reinforcement unit. Additionally, a residual network is introduced to improve the generalization performance. Finally, features obtained from the reinforcement unit are used for final anomaly detection through neural networks in the diagnosis unit. Experimental results indicate that the proposed model achieve an anomaly detection accuracy of 97.96% in factory motor dataset, while the model has the superior generalization ability.

show abstract

A fast and time-efficient glitch classification method: A deep learning-based visual feature extractor for machine learning algorithms

Bişkin

Kırbaş

Çelik

2023

Astronomy and Computing

View full text Add to dashboard Cite

A new vibration-based hybrid anomaly detection model for preventing high-power generator failures in power plants

Cited by 4 publications

References 35 publications

A Fault Warning Approach Using an Enhanced Sand Cat Swarm Optimization Algorithm and a Generalized Neural Network

A Fault Warning Approach Using an Enhanced Sand Cat Swarm Optimization Algorithm and a Generalized Neural Network

Anomaly detection of industrial motors under few-shot feature conditions based on causality

A fast and time-efficient glitch classification method: A deep learning-based visual feature extractor for machine learning algorithms

Contact Info

Product

Resources

About