Investigating Fault Detection and Diagnosis in a Hydraulic Pitch System Using a State Augmented EKF-Approach

2019 ◽  
Author(s):  
Magnus F. Asmussen ◽  
Henrik C. Pedersen ◽  
Lina Lilleengen ◽  
Andreas Larsen ◽  
Thomas Farsakoglou
Keyword(s):  
Kalman Filter ◽  
Fault Detection ◽  
Extended Kalman Filter ◽  
Fault Detection And Diagnosis ◽  
Sensor Faults ◽  
System Parameters ◽  
Power Regulation ◽  
Pitch System ◽  
Detection And Diagnosis ◽  
Drop Outs

Abstract Pitch systems impose an important part of today’s wind turbines, where they are both used for power regulation and serve as part of a turbines safety system. Any failure on a pitch system is therefore equal to an increase in downtime of the turbine and should hence be avoided. By implementing a Fault Detection and Diagnosis (FDD) scheme faults may be detected and estimated before resulting in a failure, thus increasing the availability and aiding in the maintenance of the wind turbine. The focus of this paper is therefore on the development of a FDD algorithm to detect leakage and sensor faults in a fluid power pitch system. The FDD algorithm is based on a State Augmented Extended Kalman Filter (SAEKF) and a bank of observers, which is designed utilizing an experimentally validated model of a pitch system. The SAEKF is designed to detect and estimate both internal and external leakage faults, while also estimating the unknown external load on the system, and the bank of observers to detect sensor drop-outs. From simulation it is found that the SAEKF may detect both abrupt and evolving internal and external leakages, while being robust towards noise and variation in system parameters. Similar it is found that the scheme is able to detect sensor drop-outs, but is less robust towards this.

scholarly journals Sensor Fault Detection and Diagnosis Method for AHU Using 1-D CNN and Clustering Analysis

2019 ◽  
Vol 2019 ◽  
pp. 1-20 ◽  
Author(s):  
Jingjing Liu ◽  
Min Zhang ◽  
Hai Wang ◽  
Wei Zhao ◽  
Yan Liu
Keyword(s):  
Fault Detection ◽  
Clustering Analysis ◽  
Fault Detection And Diagnosis ◽  
Sensor Faults ◽  
Control Loop ◽  
One Dimensional ◽  
Air Handling Unit ◽  
Sensor Fault Detection ◽  
Diagnosis Method ◽  
Detection And Diagnosis

This paper presents a fault detection and diagnosis (FDD) method, which uses one-dimensional convolutional neural network (1-D CNN) and WaveCluster clustering analysis to detect and diagnose sensor faults in the supply air temperature (Tsup) control loop of the air handling unit. In this approach, 1-D CNN is employed to extract man-guided features from raw data, and the extracted features are analyzed by WaveCluster clustering. The suspicious sensor faults are indicated and categorized by denoting clusters. Moreover, the Tc acquittal procedure is introduced to further improve the accuracy of FDD. In validation, false alarm ratio and missing diagnosis ratio are mainly used to demonstrate the efficiency of the proposed FDD method. Results show that the abrupt sensor faults in Tsup control loop can be efficiently detected and diagnosed, and the proposed method is equipped with good robustness within the noise range of 6 dBm∼13 dBm.

scholarly journals Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating LSTM Autoencoder Detector and Diagnostic Classifiers

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 433
Author(s):  
Ahlam Mallak ◽  
Madjid Fathi
Keyword(s):  
Fault Detection ◽  
Fault Detection And Diagnosis ◽  
Behavioral Changes ◽  
Sensor Faults ◽  
Hydraulic Systems ◽  
Hydraulic Test ◽  
Economic Implications ◽  
Hydraulic Machinery ◽  
Detection And Diagnosis ◽  
Two Phases

Anomaly occurrences in hydraulic machinery might lead to massive system shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications following the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only are the machines and their components prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig was thoroughly achieved. First, we provided a combination of a new architecture of LSTM autoencoders and supervised machine and deep learning methodologies, to perform two separate stages of fault detection and diagnosis. The two phases were condensed by—the detection phase using the LSTM autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework was applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of related work from the past decade, for autoencoders related fault detection and diagnosis in hydraulic systems, was successfully conducted in this study.

Sign in / Sign up

Export Citation Format

Share Document