Application of auto-associative neural networks to transient fault detection in an IC engine

The tailpipe emissions from automotive engines have been subject to steadily reducing legislative limits. This reduction has been achieved through the addition of sub-systems to the basic four-stroke engine which thereby increases its complexity. To ensure the entire system functions correctly, each system and / or sub-systems needs to be continuously monitored for the presence of any faults or malfunctions. This is a requirement detailed within the On-Board Diagnostic (OBD) legislation. To date, a physical model approach has been adopted by me automotive industry for the monitoring requirement of OBD legislation. However, this approach has restrictions from the available knowledge base and computational load required. A neural network technique incorporating Multivariant Statistical Process Control (MSPC) has been proposed as an alternative method of building interrelationships between the measured variables and monitoring the correct operation of the engine. Building upon earlier work for steady state fault detection, this paper details the use of non-linear models based on an Auto-associate Neural Network (ANN) for fault detection under transient engine operation. The theory and use of the technique is shown in this paper with the application to the detection of air leaks within the inlet manifold system of a modern gasoline engine whilst operated on a pseudo-drive cycle. Copyright © 2007 by ASME.

PLS modelling and fault detection on the Tennessee Eastman benchmark

This paper describes the application of multivariate regression techniques to the Tennessee Eastman benchmark process for modelling and fault detection. Two methods are applied : linear partial least squares, and a nonlinear variant of this procedure using a radial basis function inner relation. The performance of the RBF networks is enhanced through the use of a recently developed training algorithm which uses quasi-Newton optimization to ensure an efficient and parsimonious network; details of this algorithm can be found in this paper. The PLS and PLS/RBF methods are then used to create on-line inferential models of delayed process measurements. As these measurements relate to the final product composition, these models suggest that on-line statistical quality control analysis should be possible for this plant. The generation of `soft sensors' for these measurements has the further effect of introducing a redundant element into the system, redundancy which can then be used to generate a fault detection and isolation scheme for these sensors. This is achieved by arranging the sensors and models in a manner comparable to the dedicated estimator scheme of Clarke et al. 1975, IEEE Trans. Pero. Elect. Sys., AES-14R, 465-473. The effectiveness of this scheme is demonstrated on a series of simulated sensor and process faults, with full detection and isolation shown to be possible for sensor malfunctions, and detection feasible in the case of process faults. Suggestions for enhancing the diagnostic capacity in the latter case are covered towards the end of the paper.

Numerical Investigation of Optimal Pin Actuator Location on a Supersonic Projectile

The flowfield around a supersonic projectile using a pin actuator control method has been predicted using computational fluid dynamics. It has been predicted using both viscous and inviscid methods for a number of positions. Both methods showed that an optimal longitudinal position exists. However, the inviscid model over-predicted the lateral acceleration due to the difference in shock formation around the pin between the two approaches. The optimal location was predicted independent of solver, however the higher-fidelity solver predicted lower achievable lateral accelerations. This is due to the viscous interactions caused by the pin. The effect of projectile orientation has shown that shielding the pin leads to reduced effectiveness due to the wake of the fin enveloping the pin. When the pin is exposed to onset flow, the forces achieved are increased. There is also an increase in the achievable forces and moments with increasing Mach number.

Ginkgolide B and bilobalide block the pore of the 5-HT3 receptor at a location that overlaps the picrotoxin binding site

Extracts from the Ginkgo biloba tree are widely used as herbal medicines, and include bilobalide (BB) and ginkgolides A and B (GA and GB). Here we examine their effects on human 5-HT(3)A and 5-HT(3)AB receptors, and compare these to the effects of the structurally related compounds picrotin (PTN) and picrotoxinin (PXN), the two components of picrotoxin (PTX), a known channel blocker of 5-HT3, nACh and GABA(A) receptors. The compounds inhibited 5-HT-induced responses of 5-HT3 receptors expressed in Xenopus oocytes, with IC50 values of 470 mu M (BB), 730 mu M (GB), 470 mu M (PTN), 11 mu M (PXN) and > 1 mM (GA) in 5-HT(3)A receptors, and 3.1 mM (BB), 3.9 mM (GB), 2.7 mM (PTN), 62 mu M (PXN) and > 1 mM (GA) in 5-HT(3)AB receptors. Radioligand binding on receptors expressed in HEK 293 cells showed none of the compounds displaced the specific 5-HT3 receptor antagonist [H-3]granisetron, confirming that they do not act at the agonist binding site. Inhibition by GB at 5-HT(3)A receptors is weakly use-dependent, and recovery is activity dependent, indicating channel block. To further probe their site of action at 5-HT(3)A receptors, BB and GB were applied alone or in combination with PXN, and the results fitted to a mathematical model; the data revealed partially overlapping sites of action. We conclude that BB and GB block the channel of the 5-HT(3)A receptor. Thus these compounds have comparable, although less potent, behaviour than at some other Cys-loop receptors, demonstrating their actions are conserved across the family. (C) 2010 Published by Elsevier Ltd.

Application of Nonlinear PCA for Fault Detection in Polymer Extrusion Processes

This paper describes the application of an improved nonlinear principal component analysis (PCA) to the detection of faults in polymer extrusion processes. Since the processes are complex in nature and nonlinear relationships exist between the recorded variables, an improved nonlinear PCA, which incorporates the radial basis function (RBF) networks and principal curves, is proposed. This algorithm comprises two stages. The first stage involves the use of the serial principal curve to obtain the nonlinear scores and approximated data. The second stage is to construct two RBF networks using a fast recursive algorithm to solve the topology problem in traditional nonlinear PCA. The benefits of this improvement are demonstrated in the practical application to a polymer extrusion process.