A Comprehensive Approach for Detection, Classification and Integrated Diagnostics of Gas Turbine Sensors (DCIDS)

Ceschini, Giuseppe Fabio; Gatta, Nicolò; Venturini, Mauro; Hubauer, Thomas; Murarasu, Alin

doi:10.1115/gt2017-63411

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset selected for outlier injection contains nondimensional temperature measurements, here referred as dataset T2. A portion of the same time series is analyzed in [35], while the whole time series, together with the readings of the sensors set of the same quantity, is analyzed in [36]. This case study is selected since, as it can be seen in Figure 17, a severe transient occurs at t = 800 min.…”

Section: Of Bfmw K- Methodology By Means Of Field Data With Injected...mentioning

confidence: 99%

“…This study is part of a more comprehensive research activity developed by the authors in [35,36]. In [35], the benefits of implementing robust statistical estimators are evaluated, by considering three different approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Different scenarios are considered to evaluate statistical efficiency, resistance and robustness, by injecting outliers in field data sets. In [36], a comprehensive and straightforward tool for Detection, Classification and Integrated Diagnostics of Gas Turbine Sensors (named DCIDS) is proposed. The tool consists of two main algorithms, i.e.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series

Ceschini

Gatta

Venturini

et al. 2017

Journal of Engineering for Gas Turbines and Power

Self Cite

View full text Add to dashboard Cite

Statistical parametric methodologies are widely employed in the analysis of time series of gas turbine (GT) sensor readings. These methodologies identify outliers as a consequence of excessive deviation from a statistical-based model, derived from available observations. Among parametric techniques, the k–σ methodology demonstrates its effectiveness in the analysis of stationary time series. Furthermore, the simplicity and the clarity of this approach justify its direct application to industry. On the other hand, the k–σ methodology usually proves to be unable to adapt to dynamic time series since it identifies observations in a transient as outliers. As this limitation is caused by the nature of the methodology itself, two improved approaches are considered in this paper in addition to the standard k–σ methodology. The two proposed methodologies maintain the same rejection rule of the standard k–σ methodology, but differ in the portions of the time series from which statistical parameters (mean and standard deviation) are inferred. The first approach performs statistical inference by considering all observations prior to the current one, which are assumed reliable, plus a forward window containing a specified number of future observations. The second approach proposed in this paper is based on a moving window scheme. Simulated data are used to tune the parameters of the proposed improved methodologies and to prove their effectiveness in adapting to dynamic time series. The moving window approach is found to be the best on simulated data in terms of true positive rate (TPR), false negative rate (FNR), and false positive rate (FPR). Therefore, the performance of the moving window approach is further assessed toward both different simulated scenarios and field data taken on a GT.

show abstract

Section: Of Bfmw K- Methodology By Means Of Field Data With Injected...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series

Ceschini

Gatta

Venturini

et al. 2017

Journal of Engineering for Gas Turbines and Power

Self Cite

View full text Add to dashboard Cite

show abstract

“…The complexity of the production process makes it possible for changes in process parameters to have an unpredictable impact on the manufacturing process and product quality. Due to the global economic integration and the continuous development of international import and export trade, in the fierce market competition, high-end manufacturing enterprises have to pay more and more attention to product quality in order to gain competitive advantage [Ceschini, Gatta, Venturini et al (2017)]. In complex production processes, the complexity of manufacturing technology and manufacturing process leads to the process parameter data reaching thousands or tens of thousands of dimensions.…”

Section: Introductionmentioning

confidence: 99%

Key Process Protection of High Dimensional Process Data in Complex Production

He¹,

Shang²,

Chen³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In order to solve the problem of locating and protecting key processes and detecting outliers efficiently in complex industrial processes. An anomaly detection system which is based on the two-layer model fusion frame is designed in this paper. The key process is located by using the random forest model firstly, then the process data feature selection, dimension reduction and noise reduction are processed. Finally, the validity of the model is verified by simulation experiments. It is shown that this method can effectively reduce the prediction accuracy variance and improve the generalization ability of the traditional anomaly detection model from the experimental results.

show abstract

“…In the current paper, different solutions to improve the methodology proposed in [19] are evaluated, in order to implement the best performing statistical methodology in a comprehensive tool for Detection, Classification and Integrated Diagnostics of Gas Turbine Sensors (named DCIDS). The tool, described and tested in [20], assesses the reliability of GT sensor measurements by using both single-sensor and multi-sensor analysis.Furthermore, the DCIDS tool is able to classify anomalies according to their characteristics and identify different fault scenarios. The performance of the tool is assessed by analysing different types of field measurements taken on several Siemens gas turbines.…”

mentioning

confidence: 99%

Resistant Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series: Development and Field Validation

Ceschini

Gatta

Venturini

et al. 2017

Journal of Engineering for Gas Turbines and Power

Self Cite

View full text Add to dashboard Cite

The reliability of gas turbine (GT) health state monitoring and forecasting depends on the quality of sensor measurements directly taken from the unit. Outlier detection techniques have acquired a major importance, as they are capable of removing anomalous measurements and improve data quality. To this purpose, statistical parametric methodologies are widely employed thanks to the limited knowledge of the specific unit required to perform the analysis. The backward and forward moving window (BFMW) k–σ methodology proved its effectiveness in a previous study performed by the authors, to also manage dynamic time series, i.e., during a transient. However, the estimators used by the k–σ methodology are usually characterized by low statistical robustness and resistance. This paper aims at evaluating the benefits of implementing robust statistical estimators for the BFMW framework. Three different approaches are considered in this paper. The first methodology, k-MAD, replaces mean and standard deviation (SD) of the k–σ methodology with median and mean absolute deviation (MAD), respectively. The second methodology, σ-MAD, is a novel hybrid scheme combining the k–σ and the k-MAD methodologies for the backward and the forward windows, respectively. Finally, the biweight methodology implements biweight mean and biweight SD as location and dispersion estimators. First, the parameters of these methodologies are tuned and the respective performance is compared by means of simulated data. Different scenarios are considered to evaluate statistical efficiency, robustness, and resistance. Subsequently, the performance of these methodologies is further investigated by injecting outliers in field datasets taken on selected Siemens GTs. Results prove that all the investigated methodologies are suitable for outlier identification. Advantages and drawbacks of each methodology allow the identification of different scenarios in which their application can be most effective.

show abstract

A Comprehensive Approach for Detection, Classification and Integrated Diagnostics of Gas Turbine Sensors (DCIDS)

Cited by 8 publications

References 15 publications

Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series

Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series

Key Process Protection of High Dimensional Process Data in Complex Production

Resistant Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series: Development and Field Validation

Contact Info

Product

Resources

About