An LSTM based method for stage performance degradation early warning with consideration of time-series information

Li, Xingshuo; Liu, Jinfu; Bai, Mingliang; Li, Jiajia; Li, Xianling; Yan, Peng; Yu, Daren

doi:10.1016/j.energy.2021.120398

Cited by 14 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 1, the values of those features are exhibited in some instances. Columns 1–6 represent the input values of different valve lift ratio of the machine, whose fluctuations have impacts on the power and FDEM of the turbine unit [3]. More importantly, the actual flow is used to fault analysis on spot of manual detection by experienced engineers.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…Numerous sensors arranged on the turbine are used to monitor the working status of various parts, and then judge the turbine status by monitoring its abnormal parameters [2]. In the production process, many faults, such as sensor failure and abnormal equipment parts operation, could cause the fluctuation of various monitoring parameters, which result in considerable difficulties for the research on fault diagnosis methods [3]. However, it is also a difficult problem to find the anomaly nodes of every sensor.…”

Section: Introductionmentioning

confidence: 99%

“…In the era of big data, with massive monitor data of steam turbines, anomaly detection is more than important before diagnosing the fault. According to the actual operation data of steam turbine, the typical abnormal phenomenon is the sudden load change, which will affect the Automatic Generation Control (AGC) performance evaluation of high‐power thermal power units in power grid [3]. Actually, there are two cases that can cause sudden change of turbine load: the first one is the hardware problem of regulating valve, which causes the abnormal output power of the unit, which is a real fault; the other one is the noise problem when measuring the changes of power signal.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Anomaly detection of steam turbine with hierarchical pre‐warning strategy

Yao

Fan

Wang

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

Anomaly detection of steam turbines is to recognize infrequent instances within sensor data that plays a vital role in stable power supply. Machine learning models have been applied to diagnose the faults of turbine and verified useful for identifying engine problem. To detect anomalies of steam turbines with machine learning methods, here, an approach called hierarchical pre-warning strategy is proposed that combines clustering methods with classification methods. Three different clustering methods, K-means, Isolation Forest and Local Outlier Factor, are chosen to separate anomalies from normal data. Since clustering results cannot give unanimous decision, the clustering instances are labelled with three classes, real anomalies, suspected anomalies and normal data, according to their overlapping recognition. Subsequently, five classification algorithms, k-nearest neighbour, support vector machine, decision tree, random forest and gradient boosting decision tree, have been examined to train the labelled data set. The classification results illustrate that gradient boosting decision tree and random forest are much more precise to detect real anomalies of steam turbines. The real anomalies identified by clustering methods have been classified into suspected anomalies by this approach that is more practicable and consistent with ground truth.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly detection of steam turbine with hierarchical pre‐warning strategy

Yao

Fan

Wang

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…PHM makes it possible to adopt an appropriate maintenance mode for fundamental components of FOWT structures based on its operating condition (condition-based maintenance) [9]. Consequently, developing a robust PHM framework can lead to a reduced downtime for maintenance, thereby significantly improving operational reliability and reducing maintenance costs [10].…”

Section: Introductionmentioning

confidence: 99%

Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism

Bashir

Yang

et al. 2022

Renewable Energy

View full text Add to dashboard Cite

“…In the era of big data, people can store huge amount of historical operational data of gas turbines. Deep neural networks [24][25][26][27] have the strong ability to extract knowledge from big data and is becoming increasingly popular in the era of big data. Deep neural networks have the strong ability to deal with various complex learning tasks, and researchers have attempted deep neural networks in gas turbine fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A comparative study on class-imbalanced gas turbine fault diagnosis

Bai

Liu

Long

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part G:

Self Cite

View full text Add to dashboard Cite

Gas turbines are widely used in various fields, and the failure of gas turbines can cause catastrophic consequences. Health condition monitoring and fault diagnosis of gas turbines can detect faults timely, avoid serious faults, and significantly reduce maintenance costs. Thus, fault diagnosis of gas turbines has great significance. Current researches on gas turbine fault diagnosis mainly focus on the case of abundant fault samples. However, fault data are very rare and the number of normal samples is much larger than the number of fault samples in the industrial scene. This class-imbalance problem widely exists but is hardly focused in the field of gas turbine fault diagnosis. Aiming to solve this problem, this paper introduces the concept of class-imbalanced learning from the machine learning field, summarizes three kinds of class-imbalance addressment methods including oversampling, undersampling, and sample weighting, and proposes a new combination method of focal loss and random oversampling for addressing class-imbalance in deep neural networks, and performs a systematic comparative study on class-imbalanced gas turbine fault diagnosis. Experimental results show that class-imbalance can seriously reduce the fault diagnosis accuracy. Through these class-imbalance addressment methods, diagnosis accuracy is greatly improved. Comparative experiments also show that the proposed combination method can obtain the best diagnosis accuracy among all the compared methods in class-imbalanced situation. Through this comparative study, a detailed guideline for improving diagnosis accuracy under class-imbalanced circumstance is provided.

show abstract

An LSTM based method for stage performance degradation early warning with consideration of time-series information

Cited by 14 publications

References 14 publications

Anomaly detection of steam turbine with hierarchical pre‐warning strategy

Anomaly detection of steam turbine with hierarchical pre‐warning strategy

Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism

A comparative study on class-imbalanced gas turbine fault diagnosis

Contact Info

Product

Resources

About