Industrial fault diagnosis: Pneumatic train door case study

Abstract

A practical, robust method of fault detection and diagnosis of a class of pneumatic train door commonly found in rapid transit systems is presented. The methodology followed is intended to be applied within a practical system where computation is distrib uted across a local data network for economic reasons. The health of the system is ascertained by extracting features from the trajectory pro®les of the train door. This is incorporated into a low-level fault detection scheme, which relies upon using simple parity equations. D etailed diagnostics are carried out once a fault has been detected; for this purpose neural network models are utilized. This method of detection and diagnosis is implemented in a distrib uted architecture resulting in a practical, low-cost industria l solution. It is feasible to integrate the results of the diagnosis process directly into an operator's maintenance information system (M IS), thus producing a proactive maintenance regime.

Detection and isolation of actuator failure for actively controlled railway wheelsets

“…(7). i y (7) Where C c can be obtained readily from the system matrix A c , and v c represents the measurement noise vector. In this study, all measurement noises are set to 2% of their absolute maximum values at the vehicle speed of 50(m.sec -1 ).…”

“…Fault detection and isolation techniques have been widely studied, some of which are concerned with the detection of actuator failures in different industrial applications. For example, a neural network has been used to detect and diagnose the malfunction of a pneumatic actuator of a train door [7]; Wolfram and Isermann [8] demonstrated the use of parameter estimation for detecting the electro-mechanical actuator of a textile machine when the electrical part of an ac motor breaks down; and study in [9] used the Extend Kalman Filter (EKF) to detect pump pressure faults in an electrohydraulic actuation system. However, a literature review of the railway vehicle suggests that the majority of condition monitoring tasks are comprehensively considered as the fault identification in dynamic systems [10] such as conicity estimation [11], suspension failure [12], creep force [13] and creep coefficients [14].…”

Research on Urban Rail Train Passenger Door System Fault Diagnosis Using PCA and Rough Set

“…The applications of these methods require a vast amount of prior knowledge which do not make full use of the state data real time train operation, therefore these are not feasible to new train lines or new models of equipment. Migueláñez & Lehrasab [5,6] proposed a dynamic neural network fault diagnosis method for the pneumatic door. Dassanayake [7] proposed a parameter identification method for vehicle door motion state.…”

Fault Diagnostics of Rotating Machinery

“…Each equation is considered to be decoupled and independent because it can be reasonably assumed that under a fault condition the sector jitter can uniquely be affected by the system. This research builds on the work [1], [2], [3], [4] , [5] carried out in the area of Single Throw Mechanical Equipment (STME) in University of Birmingham UK [Lehrasab, 1999] and its application to rotating machines at University of Peshawar [Mahmood, 2007]. STME was formally defined as a system that has two stable states.…”