Nonlinear PCA with Local Approach for Diesel Engine Fault Detection and Diagnosis

This brief examines the application of nonlinear statistical process control to the detection and diagnosis of faults in automotive engines. In this statistical framework, the computed score variables may have a complicated nonparametric distri- bution function, which hampers statistical inference, notably for fault detection and diagnosis. This brief shows that introducing the statistical local approach into nonlinear statistical process control produces statistics that follow a normal distribution, thereby enabling a simple statistical inference for fault detection. Further, for fault diagnosis, this brief introduces a compensation scheme that approximates the fault condition signature. Experimental results from a Volkswagen 1.9-L turbo-charged diesel engine are included.

A prospective clinical trial of a real-time polymerase chain reaction assay for the diagnosis of candidemia in nonneutropenic, critically ill adults

Background. Invasive Candida infection among nonneutropenic, critically ill adults is a clinical problem that has received increasing attention in recent years. Poor performance of extant diagnostic modalities has promoted risk-based, preemptive prescribing in view of the poor outcomes associated with inadequate or delayed antifungal therapy; this risks unnecessary overtreatment. A rapid, reliable diagnostic test could have a substantial impact on therapeutic practice in this patient population.

Methods. Three TaqMan-based real-time polymerase chain reaction assays were developed that are capable of detecting the main medically important Candida species, categorized according to the likelihood of fluconazole susceptibility. Assay 1 detected Candida albicans, Candida parapsilosis, Candida tropicalis, and Candida dubliniensis. Assays 2 and 3 detected Candida glabrata and Candida krusei, respectively. The clinical performance of these assays, applied to serum, was evaluated in a prospective trial of nonneutropenic adults in a single intensive care unit.

Results. In all, 527 specimens were obtained from 157 participants. All 3 assays were run in parallel for each specimen; they could be completed within 1 working day. Of these, 23 specimens were obtained from 23 participants categorized as having proven Candida infection at the time of sampling. If a single episode of Candida famata candidemia was excluded, the estimated clinical sensitivity, specificity, and positive and negative predictive values of the assays in this trial were 90.9%, 100%, 100% and 99.8%, respectively.

Conclusions. These data suggest that the described assays perform well in this population for enhancing the diagnosis of candidemia. The extent to which they may affect clinical outcomes, prescribing practice, and cost-effectiveness of care remains to be ascertained.

Proposed wavelet-neurofuzzy combined system for power qualityviolations detection and diagnosis

A system for the identification of power quality violations is proposed. It is a two-stage system that employs the potentials of the wavelet transform and the adaptive neurofuzzy networks. For the first stage, the wavelet multiresolution signal analysis is exploited to denoise and then decompose the monitored signals of the power quality events to extract its detailed information. A new optimal feature-vector is suggested and adopted in learning the neurofuzzy classifier. Thus, the amount of needed training data is extensively reduced. A modified organisation map of the neurofuzzy classifier has significantly improved the diagnosis efficiency. Simulation results confirm the aptness and the capability of the proposed system in power quality violations detection and automatic diagnosis

Improved fault diagnosis in multivariate systems using regression-based reconstruction

Subspace monitoring has recently been proposed as a condition monitoring tool that requires considerably fewer variables to be analysed compared to dynamic principal component analysis (PCA). This paper analyses subspace monitoring in identifying and isolating fault conditions, which reveals that the existing work suffers from inherent limitations if complex fault senarios arise. Based on the assumption that the fault signature is deterministic while the monitored variables are stochastic, the paper introduces a regression-based reconstruction technique to overcome these limitations. The utility of the proposed fault identification and isolation method is shown using a simulation example and the analysis of experimental data from an industrial reactive distillation unit.