Statistical Modeling and Sensor Fault Diagnosis Using PCA PDF Download

Author: Edward Y. Bai
Publisher:
ISBN:
Category : Fault location (Engineering)
Languages : en
Pages : 224

View

Book Description

Author: Mahmoudreza Sharifi
Publisher:
ISBN:
Category :
Languages : en
Pages :

View

Book Description
The purpose of this research is to address the problem of fault diagnosis of sensors which measure a set of direct redundant variables. This study proposes: 1. A method for linear senor fault diagnosis 2. An analysis of isolability and detectability of sensor faults 3. A stochastic method for the decision process 4. A nonlinear approach to sensor fault diagnosis. In this study, first a geometrical approach to sensor fault detection is proposed. The sensor fault is isolated based on the direction of residuals found from a residual generator. This residual generator can be constructed from an input-output model in model based methods or from a Principal Component Analysis (PCA) based model in data driven methods. Using this residual generator and the assumption of white Gaussian noise, the effect of noise on the isolability is studied, and the minimum magnitude of isolable fault in each sensor is found based on the distribution of noise in the measurement system. Next, for the decision process a probabilistic approach to sensor fault diagnosis is presented. Unlike most existing probabilistic approaches to fault diagnosis, which are based on Bayesian Belief Networks, in this approach the probabilistic model is directly extracted from a parity equation. The relevant parity equation can be found using a model of the system or through PCA analysis of data measured from the system. In addition, a sensor detectability index is introduced that specifies the level of detectability of sensor faults in a set of redundant sensors. This index depends only on the internal relationships of the variables of the system and noise level. Finally, the proposed linear sensor fault diagnosis approach has been extended to nonlinear method by separating the space of measurements into several local linear regions. This classification has been performed by application of Mixture of Probabilistic PCA (MPPCA). The proposed linear and nonlinear methods are tested on three different systems. The linear method is applied to sensor fault diagnosis in a smart structure and to the Tennessee Eastman process model, and the nonlinear method is applied to a data set collected from a fully instrumented HVAC system.

Author: Majdi Mansouri
Publisher: Elsevier
ISBN: 0128191651
Category : Technology & Engineering
Languages : en
Pages : 322

View

Book Description
Data-Driven and Model-Based Methods for Fault Detection and Diagnosis covers techniques that improve the quality of fault detection and enhance monitoring through chemical and environmental processes. The book provides both the theoretical framework and technical solutions. It starts with a review of relevant literature, proceeds with a detailed description of developed methodologies, and then discusses the results of developed methodologies, and ends with major conclusions reached from the analysis of simulation and experimental studies. The book is an indispensable resource for researchers in academia and industry and practitioners working in chemical and environmental engineering to do their work safely. Outlines latent variable based hypothesis testing fault detection techniques to enhance monitoring processes represented by linear or nonlinear input-space models (such as PCA) or input-output models (such as PLS) Explains multiscale latent variable based hypothesis testing fault detection techniques using multiscale representation to help deal with uncertainty in the data and minimize its effect on fault detection Includes interval PCA (IPCA) and interval PLS (IPLS) fault detection methods to enhance the quality of fault detection Provides model-based detection techniques for the improvement of monitoring processes using state estimation-based fault detection approaches Demonstrates the effectiveness of the proposed strategies by conducting simulation and experimental studies on synthetic data

Author: L.H. Chiang
Publisher: Springer Science & Business Media
ISBN: 1447103475
Category : Technology & Engineering
Languages : en
Pages : 281

View

Book Description
Early and accurate fault detection and diagnosis for modern chemical plants can minimize downtime, increase the safety of plant operations, and reduce manufacturing costs. This book presents the theoretical background and practical techniques for data-driven process monitoring. It demonstrates the application of all the data-driven process monitoring techniques to the Tennessee Eastman plant simulator, and looks at the strengths and weaknesses of each approach in detail. A plant simulator and problems allow readers to apply process monitoring techniques.

Author: Fausto Pedro García Márquez
Publisher: BoD – Books on Demand
ISBN: 1789842131
Category : Mathematics
Languages : en
Pages : 177

View

Book Description
This book presents the main concepts, state of the art, advances, and case studies of fault detection, diagnosis, and prognosis. This topic is a critical variable in industry to reach and maintain competitiveness. Therefore, proper management of the corrective, predictive, and preventive politics in any industry is required. This book complements other subdisciplines such as economics, finance, marketing, decision and risk analysis, engineering, etc. The book presents real case studies in multiple disciplines. It considers the main topics using prognostic and subdiscipline techniques. It is essential to link these topics with the areas of finance, scheduling, resources, downtime, etc. to increase productivity, profitability, maintainability, reliability, safety, and availability, and reduce costs and downtime. Advances in mathematics, modeling, computational techniques, dynamic analysis, etc. are employed analytically. Computational techniques, dynamic analysis, probabilistic methods, and mathematical optimization techniques are expertly blended to support the analysis of prognostic problems with defined constraints and requirements. The book is intended for graduate students and professionals in industrial engineering, business administration, industrial organization, operations management, applied microeconomics, and the decisions sciences, either studying maintenance or needing to solve large, specific, and complex maintenance management problems as part of their jobs. The work will also be of interest to researches from academia.

Author: Mohamed N. Nounou
Publisher:
ISBN:
Category : Electronic books
Languages : en
Pages : 0

View

Book Description
Principal component analysis (PCA) is a linear data analysis technique widely used for fault detection and isolation, data modeling, and noise filtration. PCA may be combined with statistical hypothesis testing methods, such as the generalized likelihood ratio (GLR) technique in order to detect faults. GLR functions by using the concept of maximum likelihood estimation (MLE) in order to maximize the detection rate for a fixed false alarm rate. The benchmark Tennessee Eastman Process (TEP) is used to examine the performance of the different techniques, and the results show that for processes that experience both shifts in the mean and/or variance, the best performance is achieved by independently monitoring the mean and variance using two separate GLR charts, rather than simultaneously monitoring them using a single chart. Moreover, single-valued data can be aggregated into interval form in order to provide a more robust model with improved fault detection performance using PCA and GLR. The TEP example is used once more in order to demonstrate the effectiveness of using of interval-valued data over single-valued data.

Author: Zhiwen Chen
Publisher: Springer
ISBN: 3658167564
Category : Technology & Engineering
Languages : en
Pages : 124

View

Book Description
Zhiwen Chen aims to develop advanced fault detection (FD) methods for the monitoring of industrial processes. With the ever increasing demands on reliability and safety in industrial processes, fault detection has become an important issue. Although the model-based fault detection theory has been well studied in the past decades, its applications are limited to large-scale industrial processes because it is difficult to build accurate models. Furthermore, motivated by the limitations of existing data-driven FD methods, novel canonical correlation analysis (CCA) and projection-based methods are proposed from the perspectives of process input and output data, less engineering effort and wide application scope. For performance evaluation of FD methods, a new index is also developed.

Author: Mohamad Yusup Abd Wahab
Publisher:
ISBN:
Category : Multivariate analysis
Languages : en
Pages : 53

View

Book Description
Multivariate Statistical Process Control (MSPC) technique has been widely used for fault detection and diagnosis. Currently, contribution plots are used as basic tools for fault diagnosis in MSPC approaches. This plot does not exactly diagnose the fault, it just provides greater insight into possible causes and thereby narrow down the search. Hence, the cause of the faults cannot be found in a straightforward manner. Therefore, this study is conducted to introduce a new approach for detecting and diagnosing fault via correlation technique. The correlation coefficient is determined using multivariate analysis techniques, namely Principal Component Analysis (PCA). In order to overcome these problems, the objective of this research is to develop new approaches, which can improve the performance of the present conventional MSPC methods. The new approaches have been developed, the Outline Analysis Approach for examining the distribution of Principal Component Analysis (PCA) scores, the Correlation Coefficient Approach for detecting changes in the correlation structure within the variables. This research proposed PCA Outline Analysis Control Chart for fault detection. The result from the conventional method and ne approach were compared based on their accuracy and sensitivity. Based on the results of the study, the new approaches generally performed better compared to the conventional approaches, particularly the PCA Outline Analysis Control Chart.

Author: Abdalhamid Ahmad Rahoma
Publisher:
ISBN:
Category :
Languages : en
Pages :

View

Book Description
Data based methods are widely used in process industries for fault detection and diagnosis. Among the data-based methods multivariate statistical methods, for example, Principal Component Analysis (PCA), Projection to Latent Squares (PLS), and Independent Component Analysis (ICA) are most widely used methods. These methods in general are successful in detecting process fault, however, diagnosis of the root cause is always not very accurate. The primary goal of the thesis is to improve the fault diagnosis ability of PCA based methods. In PCA, each Principal Component (PC) is a linear combination of all the variables, therefore makes it difficult to identify the root cause from the violation of a PC. Sparse Principal Component Analysis (SPCA) is one version of PCA that gets a sparse description of the PCA loading matrix making it more suitable for fault diagnosis. The present research aims to devise novel strategies to find the sparse description of loading matrix, more aligned with process fault detection and diagnosis. The thesis also looks into improving the fault diagnosis of PCA using clustering methods. The entire thesis can be divided into three major tasks. First, a novel fault detection and diagnosis method is proposed based on the Sparse Principal Component Analysis (SPCA) approach. This approach incorporates a new criterion based on the Fault Detection Rates (FDRs) and False Alarm Rates (FARs) into Zou et al.'s (2006) SPCA algorithms. The objective here is to find appropriate the (Number of Non-Zero Loadings) NNZLs for SPCs that can result in low FARs and high FDRs. A comparison between PCA and four SPCA-based methods for FDD using a continuous stirred tank heater (CSTH) as a benchmark system is also carried out. The results indicate that shortcomings of the PCA can be overcome using the Sparse Principal Component Analysis (SPCA) that uses the novel NNZL criterion. The FDR-FAR SPCA approach gives the highest FDRs for the SPE statistic (93.8%). The second task focuses on developing statistical methods to decide on the non-zero elements of the loading elements of SPCA. Rather than using heuristics, the proposed methods use the distribution of the loading elements to decide if an element should be set to zero. Two SPCA algorithms are proposed to find the NNZL and its position of each PC. The first algorithm is based on bootstrapping of the data, and the second approach is based Iterative Principal Component Analysis (IPCA). The proposed methods are implemented on a CSTH process to test the performance with PCA- and other SPCA-based methods for fault detection and diagnosis. The results reveal that the approaches have superior performance in fault detection, as well as diagnosis of the root cause of fault. Both the Bootstrap-SPCA and Sparse-IPCA methods give the highest FDRs for fault 1 for the SPE statistic (99.3% and 95.76%, respectively) As the third task, this research combines the clustering (k-means) algorithm and PCA algorithm to improve the detection and diagnosis of the fault. PCA has the advantage of detecting the fault without the need for data labelling, while clustering is able to distinguish data from different fault groups into separate clusters. By combining these two algorithms we are able to have better detection and diagnosis of fault and eliminate the need for data labelling. The performance of the proposed method is demonstrated in simulated and large-scale industrial case studies.

Author: Hong-Yue Zhang
Publisher: Elsevier
ISBN: 9780080555393
Category : Science
Languages : en
Pages : 1576

View

Book Description
The safe and reliable operation of technical systems is of great significance for the protection of human life and health, the environment, and of the vested economic value. The correct functioning of those systems has a profound impact also on production cost and product quality. The early detection of faults is critical in avoiding performance degradation and damage to the machinery or human life. Accurate diagnosis then helps to make the right decisions on emergency actions and repairs. Fault detection and diagnosis (FDD) has developed into a major area of research, at the intersection of systems and control engineering, artificial intelligence, applied mathematics and statistics, and such application fields as chemical, electrical, mechanical and aerospace engineering. IFAC has recognized the significance of FDD by launching a triennial symposium series dedicated to the subject. The SAFEPROCESS Symposium is organized every three years since the first symposium held in Baden-Baden in 1991. SAFEPROCESS 2006, the 6th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes was held in Beijing, PR China. The program included three plenary papers, two semi-plenary papers, two industrial talks by internationally recognized experts and 258 regular papers, which have been selected out of a total of 387 regular and invited papers submitted. * Discusses the developments and future challenges in all aspects of fault diagnosis and fault tolerant control * 8 invited and 36 contributed sessions included with a special session on the demonstration of process monitoring and diagnostic software tools