A Comparative Assessment on Static and Dynamic PCA for Fault Detection in Natural Gas Transmission Systems

2017 ◽  
Author(s):  
Horacio Pinzón ◽  
Cinthia Audivet ◽  
Melitsa Torres ◽  
Javier Alexander ◽  
Marco Sanjuán
Keyword(s):  
Natural Gas ◽  
Fault Detection ◽  
Large Scale ◽  
Detection System ◽  
Principal Component ◽  
Data Driven ◽  
Transmission Systems ◽  
Alarm Management ◽  
Detection Algorithms ◽  
Natural Gas Transmission

Sustainability of natural gas transmission infrastructure is highly related to the system’s ability to decrease emissions due to ruptures or leaks. Although traditionally such detection relies in alarm management system and operator’s expertise, given the system’s nature as large-scale, complex, and with vast amount of information available, such alarm generation is better suited for a fault detection system based on data-driven techniques. This would allow operators and engineers to have a better framework to address the online data being gathered. This paper presents an assessment on multiple fault-case scenarios in critical infrastructure using two different data-driven based fault detection algorithms: Principal component analysis (PCA) and its dynamic variation (DPCA). Both strategies are assessed under fault scenarios related to natural gas transmission systems including pipeline leakage due to structural failure and flow interruption due to emergency valve shut down. Performance evaluation of fault detection algorithms is carried out based on false alarm rate, detection time and misdetection rate. The development of modern alarm management frameworks would have a significant contribution in natural gas transmission systems’ safety, reliability and sustainability.

An Extended Implementation of Fault Detection in Multi-State Systems Based on Warp Analysis: A Case Study on Natural Gas Transmission Systems in Tropical Regions

2017 ◽  
Author(s):  
Horacio Pinzón ◽  
Cinthia Audivet ◽  
Ivan Portnoy ◽  
Marlon Consuegra ◽  
Javier Alexander ◽  
...  
Keyword(s):  
Natural Gas ◽  
Fault Detection ◽  
Large Scale ◽  
Detection Algorithm ◽  
Operating Conditions ◽  
Underlying Structure ◽  
Transmission Systems ◽  
Original Algorithm ◽  
Tropical Conditions ◽  
Natural Gas Transmission

Natural gas transmission infrastructure is a large-scale complex system often exhibiting a considerable operating states not only due to natural, slow and normal process changes related to aging but also to a dynamic interaction with multiple agents overall having different functional parameters, an irregular demand trend adjusted by the hour, and sometimes affected by external conditions as severe climate periods. As traditional fault detection relies in alarm management system and operator’s expertise, it is paramount to deploy a strategy being able to update its underlying structure and effectively adapting to such process shifts. This feature would allow operators and engineers to have a better framework to address the online data being gathered in dynamic on transient conditions. This paper presents an extended analysis on WARP technique to address the abnormal condition management activities of multiple-state processes deployed in critical natural gas transmission infrastructure. Special emphasis is made on the updating activity to incorporate effectively the operating shifts exhibited by a new operating condition implemented on a fault detection strategy. This analysis broadens the authors’ original algorithm scope to include multi-state systems in addition to process drifting behavior. The strategy is assessed under two different scenarios rendering a major shift in process’ operating conditions related to natural gas transmission systems: A transition between low and high natural gas demand to support hydroelectric generation matrix on severe tropical conditions. Performance evaluation of fault detection algorithm is carried out based on false alarm rate, detection time and misdetection rate estimated around the model update.

Data Segmentation Criteria Assessment for Fault Detection Techniques Based on Principal Component Analysis for Natural Gas Transmission System

2018 ◽  
Author(s):  
Cinthia Audivet ◽  
Horacio Pinzón ◽  
Jesus García ◽  
Marlon Consuegra ◽  
Javier Alexander ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Natural Gas ◽  
Fault Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Principal Component ◽  
Detection Time ◽  
Case Scenario ◽  
Data Segmentation ◽  
Natural Gas Transmission

Statistical analytics, as a data extraction and fault detection strategy, may incorporate segmentation techniques to overcome its underlying limitations and drawbacks. Merging both techniques shall provide a more robust monitoring structure to address the proper identification of normal and abnormal conditions, to improve the extraction of fundamental correlation among variables, and to improve the separation of both main variation and natural variation (noise) subspaces. This additional feature is key to limit the false alarm rate and to optimize the fault detection time when it is implemented on industrial applications. This paper presents an analysis to determine whether a segmentation approach, as a previous step of detection, enhances the fault detection strategies, specifically the principal component analysis performance. The data segmentation criteria assessed in this study includes two approaches: a) Sources (well) of the transmitted natural gas and b) Promigas’ natural gas pipeline division defined by the Energy and Gas Regulation Commission (CREG in Spanish). The performance assessment of segmentation criteria was carried out evaluating the false alarm rate and detection time when the natural gas transmission network presents faults of different magnitude. The results show that the implementation of a segmentation criteria provides an advantage in terms of the detection time, but it depends of the fault magnitude and the number of clusters. The detection time is improved by 25% in the case scenario I, when transition zones are considered. On the other hand, the detection time is slightly better with less than 10% in the case scenario II, where the segmentation is geographical.

Fault detection algorithms for real-time diagnosis in large-scale systems

2001 ◽  
Author(s):  
Thiagalingam Kirubarajan ◽  
Venkatesh N. Malepati ◽  
Somnath Deb ◽  
Jie Ying
Keyword(s):  
Fault Detection ◽  
Real Time ◽  
Large Scale ◽  
Large Scale Systems ◽  
Detection Algorithms ◽  
Time Diagnosis

scholarly journals Development and Field Evaluation of Data-driven Whole Building Fault Detection and Diagnosis Strategy

2018 ◽  
Vol 10 (1) ◽  
Author(s):  
Yimin Chen ◽  
Jin Wen
Keyword(s):  
Fault Detection ◽  
Principal Component ◽  
Field Evaluation ◽  
Fault Detection And Diagnosis ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Component Level ◽  
Automation Systems ◽  
Tightly Coupled ◽  
Detection And Diagnosis

Faults, i.e., malfunctioned sensors, components, control, and systems, in a building have significantly adverse impacts on the building’s energy consumption and indoor environment. To date, extensive research has been conducted on the development of component level fault detection and diagnosis (FDD) for building systems, especially the Heating, Ventilating, and Air Conditioning (HVAC) system. However, for faults that have multi-system impacts, component level FDD tools may encounter high false alarm rate due to the fact that HVAC subsystems are often tightly coupled together. Hence, the detection and diagnosis of whole building faults is the focus of this study. Here, a whole building fault refers to a fault that occurs in one subsystem but triggers abnormalities in other subsystems and have significant adverse whole building energy impact. The wide adoption of building automation systems (BAS) and the development of machine learning techniques make it possible and cost-efficient to detect and diagnose whole building faults using data-driven methods. In this study, a whole building FDD strategy which adopts weather and schedule information based pattern matching (WPM) method and feature based Principal Component Analysis (FPCA) for fault detection, as well as Bayesian Networks (BNs) based method for fault diagnosis is developed. Fault tests are implemented in a real campus building. The collected data are used to evaluate the performance of the proposed whole building FDD strategies.

scholarly journals Metric Learning Method Aided Data-Driven Design of Fault Detection Systems

2014 ◽  
Vol 2014 ◽  
pp. 1-9
Author(s):  
Guoyang Yan ◽  
Jiangyuan Mei ◽  
Shen Yin ◽  
Hamid Reza Karimi
Keyword(s):  
Fault Detection ◽  
Feature Vector ◽  
Metric Learning ◽  
Principal Component ◽  
Industrial Applications ◽  
Data Driven ◽  
Detection Methods ◽  
Feature Extraction Method ◽  
Detection Systems ◽  
The Relationship

Fault detection is fundamental to many industrial applications. With the development of system complexity, the number of sensors is increasing, which makes traditional fault detection methods lose efficiency. Metric learning is an efficient way to build the relationship between feature vectors with the categories of instances. In this paper, we firstly propose a metric learning-based fault detection framework in fault detection. Meanwhile, a novel feature extraction method based on wavelet transform is used to obtain the feature vector from detection signals. Experiments on Tennessee Eastman (TE) chemical process datasets demonstrate that the proposed method has a better performance when comparing with existing methods, for example, principal component analysis (PCA) and fisher discriminate analysis (FDA).

Sign in / Sign up

Export Citation Format

Share Document