Optimal Sensor Network Upgrade for Fault Detection Using Principal Component Analysis

Rodríguez, Leandro; Cedeño, Marco V.; Sánchez, Mabel

doi:10.1021/acs.iecr.5b02599

Cited by 7 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the PCA of matrix X can be expressed as follows:

boldX = \sum_{i = 1}^{l} t_{i} p_{i}^{Τ} + boldE

where t i is the score vector, p i is the loading vector, and the score vector of X is also the principal component of X . The matrix T composed of t i is the score matrix, and the matrix P composed of p i is the loading matrix …”

Section: Principal Component Analysismentioning

confidence: 99%

Fault detection based on weighted difference principal component analysis

Guo

Wang

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

Recently, multivariate statistical methods, such as principal component analysis (PCA), have drawn increasing attention for fault detection applications in industrial processes. However, industrial processes typically have complex multimodal and nonlinear characteristics. In these situations, the traditional PCA method performs poorly due to its assumption that the process data are linear and unimodal. To improve fault detection performance in nonlinear and multimode industrial processes, this paper proposes a new fault detection method based on weighted difference principal component analysis (WDPCA). Weighted difference principal component analysis first eliminates the multimodal and nonlinear characteristics of the original data by using the weighted difference method. Then, PCA is applied to the preprocessed data, neglecting the influences of multimodality and nonlinearity. Two numerical examples and an industrial application in a semiconductor manufacturing process are used to verify the effectiveness of WDPCA. The simulation results demonstrate that WDPCA shows better fault detection performance than the PCA, kernel principal component analysis (KPCA), independent component analysis (ICA), k-nearest neighbor rule (kNN), and local outlier factor (LOF) methods. KEYWORDS fault detection, multimodal data, nonlinear data, principal component analysis, weighted difference principal component analysis | INTRODUCTIONWith the development of modern automation technology in recent years, industrial systems are constantly increasing in scale, complexity, and degree of integration. However, such improvements also increase the probability of fault occurrence. To address this issue, fault detection technology has been developed and is now widely used in production processes. Data-driven fault detection technology has received extensive attention in academic research. Moreover, multivariate statistical analysis methods, such as principal component analysis (PCA) and independent component analysis (ICA), have developed rapidly, and several new fault detection methods have been derived. [1][2][3][4][5][6][7][8][9] Chemical production is an important industrial production field, and its processes increasingly reflect the nonlinear and multimodal characteristics of more complex control systems. The question of how to effectively extract the important information from the chemical production process data and achieve fault detection in nonlinear and multimode processes has also attracted an increasing amount of attention from scholars. [10][11][12][13][14][15][16][17] Lee proposed ICA to extract the higher order features of data. 18 However, ICA is still unable to address the problem of fault detection for nonlinear data.

show abstract

“…Thus, the PCA of matrix X can be expressed as follows:

boldX = \sum_{i = 1}^{l} t_{i} p_{i}^{Τ} + boldE

Section: Principal Component Analysismentioning

confidence: 99%

Fault detection based on weighted difference principal component analysis

Guo

Wang

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Let us assume that engineers have set process deviation limits (PDLs) for some process variables taking into account operation and safety issues and that a simulation procedure which sensibly represents the process dynamic response is available. ,, If the simulation of the j th fault ( j = 1, ..., J ) is performed until the time for which one or more variables reach their PDLs, then the vector of standardized variable values for that time, x j , is obtained. A set of simulated data that represents the normal process variability can be employed for the standardization.…”

Section: Sensor Network Upgrade For Fault Detection and Isolationmentioning

confidence: 99%

“…Other strategies select instruments to satisfy the detection of certain process faults before their magnitudes exceed critical limits. Those methodologies assume that a simulation procedure which sensibly represents the process dynamic response is available. , Some researchers have formulated an optimization problem whose objective function is a global penalty index . It is made up of the total instrumentation cost and a penalization term, which is calculated as a function of the minimum fault magnitude that PCA’s statistics can detect.…”

Section: Introductionmentioning

confidence: 99%

“…Its calculus is conservative; therefore, the strategy may neglect lower-cost feasible solutions. This inconvenience is avoided using fault detection constraints straightaway defined in terms of the PCA’s statistics, which have been used to solve instrumentation upgrade problems by applying an enhanced traversal tree search . Furthermore, the robustness of the SN in the presence of sensor failures or outliers has been ensured by introducing the Key Fault Detection Degree concept as constraint of the optimization problem …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sensor Location for Enhancing Fault Diagnosis

Rodríguez

Cedeño

Sánchez

2016

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Multivariate statistical control techniques have been successfully applied to the detection and isolation of process faults. Because those strategies evaluate the current process state using the measurement values and the normal operation model, their performance is strongly influenced by the sensor network installed in the plant. Nevertheless, very few sensor location approaches have been presented to enhance faults isolation, and they do not guarantee that a fault can be distinguished from the other ones before its magnitude reaches a certain critical value. In this work a strategy for updating process instrumentation is presented that aims at detecting and isolating a given set of process failures using statistical monitoring procedures before the fault magnitudes exceed predefined threshold values. In this sense, fault isolation constraints are formulated and incorporated to the instrumentation update optimization problem. The proposed restrictions are expressed in terms of the variable contributions to the inflated statistics. These are used on line to determine the set of observations by which a fault is revealed, but they have not been incorporated into the sensor location problem for fault diagnosis until now. That problem is solved using an enhanced level traversal tree search, which takes advantage of the fact that the structural determinability of a fault is a necessary condition for its isolability. Application results of the methodology to the Tennessee Eastman Process are presented.

show abstract

“…This method could reduce the error of multi-objective function and enhance the system robustness, thereby detecting the fault quickly and effectively. Rodriguez et al (Rodriguez et al , 2016) applied PCA to optimise the sensor fault detection system; this optimised system could detect the sensor’s abnormal value in operation state and define the time fault occurred. Tipaldi and Bruenjes (Tipaldi and Bruenjes, 2014) proposed an unsupervised statistical anomaly detection approach based on PCA latent space methodology.…”

Section: Introductionmentioning

confidence: 99%

A data-driven method of health monitoring for spacecraft

2018

AEAT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to detect the occurrence of anomaly and fault in a spacecraft, investigate various tendencies of telemetry parameters and evaluate the operation state of the spacecraft to monitor the health of the spacecraft. Design/methodology/approach This paper proposes a data-driven method (empirical mode decomposition-sample entropy-principal component analysis [EMD-SE-PCA]) for monitoring the health of the spacecraft, where EMD is used to decompose telemetry data and obtain the trend items, SE is utilised to calculate the sample entropies of trend items and extract the characteristic data and squared prediction error and statistic contribution rate are analysed using PCA to monitor the health of the spacecraft. Findings Experimental results indicate that the EMD-SE-PCA method could detect characteristic parameters that appear abnormally before the anomaly or fault occurring, could provide an abnormal early warning time before anomaly or fault appearing and summarise the contribution of each parameter more accurately than other fault detection methods. Practical implications The proposed EMD-SE-PCA method has high level of accuracy and efficiency. It can be used in monitoring the health of a spacecraft, detecting the anomaly and fault, avoiding them timely and efficiently. Also, the EMD-SE-PCA method could be further applied for monitoring the health of other equipment (e.g. attitude control and orbit control system) in spacecraft and satellites. Originality/value The paper provides a data-driven method EMD-SE-PCA to be applied in the field of practical health monitoring, which could discover the occurrence of anomaly or fault timely and efficiently and is very useful for spacecraft health diagnosis.

show abstract

Optimal Sensor Network Upgrade for Fault Detection Using Principal Component Analysis

Cited by 7 publications

References 15 publications

Fault detection based on weighted difference principal component analysis

Fault detection based on weighted difference principal component analysis

Sensor Location for Enhancing Fault Diagnosis

A data-driven method of health monitoring for spacecraft

Contact Info

Product

Resources

About