In-Situ Event Localization for Pipeline Monitoring System Based Wireless Sensor Network Using K-Nearest Neighbors and Support Vector Machine

Abstract

Pipeline Monitoring Systems (PMS) benefits the most of recent developments in wireless remote monitoring since each pipeline would span for long distances which make conventional methods unsuitable. Precise monitoring and detection of damaging events requires moving large amounts of data between sensor nodes and base station for processing which require high bandwidth communication protocol. To overcome this problem, In-Situ processing can be practiced by processing the collected data locally at each node instead of the base station. However, this introduce a challenge to the limited resources available on the nodes. In this paper, a Wireless Sensor Network (WSN) was implemented for In-Situ Pipeline Monitoring System with proposed algorithms for event location estimation. The proposed algorithms include feature extraction (using ANOVA), dimensionality reduction using statistical procedure that is (Principle Component Analysis PCA) and data classification using supervised learning K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). The proposed system was tested on pipelines in Al-Mussaib Gas Turbine Power Plant. During test, knocking events are applied at several distances relative to the nodes locations. Data collected at each node is filtered and processed locally in real time in each two adjacent nodes. The results of the estimation is then sent to the supervisor at base-station for display. The results show the proposed system ability to estimate the location of knocking event.

Simultaneous Fault Diagnostics for Three-Shaft Industrial Gas Turbine

“…Due to this problem, a data-driven (artificial intelligence) method has emerged [51,52], which is also called a performance-based health monitoring approach, which success-fully detects anticipated faults. Data-driven methods include Artificial Neural Network (ANN) [50,[53][54][55][56], Fuzzy Logic (FL) [57][58][59][60], Bayesian Belief Network (BBN) [59,[61][62][63], Deep Learning (DL) [64][65][66][67], Support Vector Machine (SVM) [39,[68][69][70][71], K-Nearest Neighbor (KNN) [72][73][74] and Genetic Algorithm (GA) [75][76][77]. In the data-driven approaches, the data collected from the engine will be utilized to develop a diagnostic model.…”