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.

Acute exercise and impaired glucose tolerance in obese humans

BACKGROUND: Individuals with impaired glucose tolerance (IGT) have a greater risk of developing diabetes and cardiovascular disease compared with those with normal glycemic control. The aim of this study was to examine the effects of acute aerobic exercise on glycemia, regional arterial stiffness, and oxidative stress in obese subjects with IGT.

Effect of pioglitazone on endothelial function in impaired glucose tolerance

Aim: Flow-mediated dilation (FMD) is a surrogate marker of endothelial function, which has been proposed as a barometer of vascular health. Impaired microvascular response to reactive hyperaemia is thought to be the mechanism behind reduced shear stress and subsequently impaired FMD, which has been associated with cardiovascular events. This study aims to assess the effect of pioglitazone on the vasculature of patients with impaired glucose tolerance (IGT).

Materials and Methods: Forty IGT patients with no cardiovascular disease were compared with 24 healthy age- and sex-matched controls. Endothelial function was assessed using FMD of the brachial artery. Adiponectin (ADN) levels were measured and insulin sensitivity was calculated using homeostasis model assessment of insulin resistance (HOMA-IR). A randomised double-blind placebo-controlled trial of the IGT subjects was then performed, with subjects receiving either pioglitazone 30 mg od or matched placebo for 12 weeks before the measurements were repeated.

Results: The IGT subjects had a significantly impaired FMD compared with the controls (p < 0.001). Diastolic shear stress (DSS) was also significantly reduced in IGT (p = 0.04). High molecular weight (HMW) ADN was significantly lower in the IGT group than in controls (p = 0.03). On analysis of the IGT group after 12 weeks treatment, FMD was significantly increased in the pioglitazone group compared with placebo (p = 0.03) as was endothelium-independent dilation (EID) (p = 0.03). A significant increase in total ADN (p < 0.001), HMW ADN (p < 0.001) and HMW/total ratio (p = 0.001) occurred in the pioglitazone group compared with placebo.

Conclusions: Pioglitazone improved endothelial function in IGT. Treatment with pioglitazone may reduce the risk of cardiovascular disease in this patient group.

Impaired Immune Tolerance to Porphyromonas gingivalis Lipopolysaccharide Promotes Neutrophil Migration and Decreased Apoptosis.

Periodontitis, a chronic inflammatory disease of the tissues supporting the teeth, is characterized by an exaggerated host immune and inflammatory response to periopathogenic bacteria. Toll-like receptor activation, cytokine network induction, and accumulation of neutrophils at the site of inflammation are important in the host defense against infection. At the same time, induction of immune tolerance and the clearance of neutrophils from the site of infection are essential in the control of the immune response, resolution of inflammation, and prevention of tissue destruction. Using a human monocytic cell line, we demonstrate that Porphyromonas gingivalis lipopolysaccharide (LPS), which is a major etiological factor in periodontal disease, induces only partial immune tolerance, with continued high production of interleukin-8 (IL-8) but diminished secretion of tumor necrosis factor alpha (TNF-) after repeated challenge. This cytokine response has functional consequences for other immune cells involved in the response to infection. Primary human neutrophils incubated with P. gingivalis LPS-treated naïve monocyte supernatant displayed a high migration index and increased apoptosis. In contrast, neutrophils treated with P. gingivalis LPS-tolerized monocyte supernatant showed a high migration index but significantly decreased apoptosis. Overall, these findings suggest that induction of an imbalanced immune tolerance in monocytes by P. gingivalis LPS, which favors continued secretion of IL-8 but decreased TNF- production, may be associated with enhanced migration of neutrophils to the site of infection but also with decreased apoptosis and may play a role in the chronic inflammatory state seen in periodontal disease.