Characterisation of modern complex powertrains is a time consuming and expensive process. Little effort has been made to improve the efficiency of testing methodologies used to obtain data for this purpose. Steady-state engine testing is still regarded as the golden standard, where approximately 90% of testing time is wasted waiting for the engine to stabilize. Rapid dynamic engine testing, as a replacement for the conventional steady-state method, has the potential to significantly reduce the time required for characterisation. However, even by using state of the art measurement equipment, dynamic engine testing introduces the problem that certain variables are not directly measurable due to the excitation of the system dynamics. Consequently, it is necessary to develop methods that allow the observation of not directly measurable quantities during transient engine testing. Engine testing for the characterisation of the engine air-path is specifically affected by this problem since the air mass flow entering the cylinder is not directly measurable by any sensor during transient operation. This dissertation presents a comprehensive methodology for engine air charge characterisation using dynamic test data. An observer is developed, which allows observation of the actual air mass flow into the engine during transient operation. The observer is integrated into a dual-ramp testing procedure, which allows the elimination of unaccounted dynamic effects by averaging over the resulting hysteresis. A simulation study on a 1-D gas dynamic engine model investigates the accuracy of the developed methodology. The simulation results show a trade-off between time saving and accuracy. Experimental test result confirm a time saving of 95% compared to conventional steady-state testing and at least 65% compared to quasi steady-state testing while maintaining the accuracy and repeatability of conventional steady-state testing.

The diploma thesis is written with a view to illustrate application of statistical methods describing progress of economical processes in company. The thesis is divided into two separated parts. First part focuses on theoretical pieces of knowledge about control charts and time series. Second part is composed from chapters that are focused on its practical usage. As simple application for control chart making is enclosed.

Chromosome classification is one of the essential tasks in karyotyping to diagnose genetic abnormalities like some types of cancers and Down syndrome. Deep convolutional neural networks have been widely used in this task, and the accuracy of classification models is exceptionally critical to such sensitive medical diagnoses. However, it is not always possible to meet the expected accuracy rates for diagnosis. So, it is vital to tell how certain or uncertain a model is with its decision. In our work, we use two metrics, entropy and variance, as uncertainty measurements. Moreover, three additional metrics, fail rate, workload, and tolerance range, are used to measure uncertainty metrics’ quality. Four different non-Bayesian methods: deep ensembles, snapshot ensembles, Test Time Augmentation, and Test Time Dropout, are used in experiments. A negative correlation is observed between the accuracy and the uncertainty estimation; the higher the accuracy of the model, the lower the uncertainty. Densenet121 with deep ensembles as the uncertainty evaluation method and variance as the uncertainty metric gives the best outcomes. Densenet121 provides a wider tolerance range and better separation between uncertain and certain predictions. / Kromosomklassificering är en av de viktigaste uppgifterna i Karyotyping för att diagnostisera genetiska abnormiteter som vissa typer av cancer och Downs syndrom. Deep Convolutional Neural Networks har använts i stor utsträckning i denna uppgift, och noggrannheten hos klassificeringsmodeller är exceptionellt kritisk för sådana känsliga medicinska diagnoser. Det är dock inte alltid möjligt att uppfylla de förväntade noggrannhetsgraderna för diagnos. Så det är viktigt att berätta hur säker eller osäker en modell är med sitt beslut. Forskning har gjorts för att uppskatta osäkerheten med bayesiska metoder och icke-bayesiska neurala nätverk, medan lite är känt om kvaliteten på osäkerhetsuppskattningar. I vårt arbete använder vi två mått, entropi och varians, som osäkerhetsmätningar. Dessutom används ytterligare tre mätvärden, felfrekvens, arbetsbelastning och toleransintervall för att mäta osäkerhetsmätarnas kvalitet. Fyra olika icke-bayesiska metoder: djupa ensembler, ögonblicksbilder, Test Time Augmentation (TTA) och Test Time Dropout (TTD) används i experiment. En negativ korrelation observeras mellan noggrannheten och osäkerhetsuppskattningen; ju högre noggrannhet modellen är, desto lägre är osäkerheten. Densenet121 med djupa ensembler som osäkerhetsutvärderingsmetod och varians som osäkerhetsmätvärdet ger de bästa resultaten. De ger ett bredare toleransintervall och bättre separation mellan osäkra och vissa förutsägelser.