Maximum likelihood indentifiering av reaktordynamik från flervariabla experiment

Statistisk signalklassificering utan lärare

This report deals with the problem of learning to classify observations from a mixture of random variables. The distributions of the random variables are of known functional forms but with unknown parameters. This problem is equivalent to that of determining separating hypersurfaces in the range of the random variables. Any rule of classification will be a function of random variables and therefo

En jämförelse mellan olika metoder att införa integrerande återkopplingar i flervariabla system

I detta examensarbete redogörs för tre metoder att införa integratorer vid linjärkvadratisk optimering. För att jämföra metoderna har två system simulerats. Metoderna har i huvudsak jämförts med avseende på snabbhet, maximal amplitud och känslighet.

Granulering - ett dynamiskt betraktelsesätt

In this work mathematical models of a granulating process plant have been determined. The plant is situated at the SUPRA company, Landskrona Sweden. The product studied is a fertilizer NPK. In the process there are oscillations in the material flow. The models will be used an attempt to explain and hopefully control the process better. In the first stage it was tried to obtain a physical model of

SYNPAC - ett interaktivt program för syntes av reglersystem

Jämförelse mellan störningskänsligheten vid direkt mätning och rekonstruktion

Modell av en malkvarn

Optimal styrning av sulfatkokare

Styrning av ljusbåge med tyristorer

Adaptiv styrning av linjära system med hjälp av utvidgat Kalmanfilter

Inkompabilitetslocus: beräkning av allelfrekvenser i en rödklöverpopulation

Dosplanering av läkemedel

Modeller av ekonomiska system

Jämförelse mellan linjära och olinjära modeller för tankreaktorn

Reelltidsidentifiering på Halden-data

Reglering av inloppslåda till en pappersmaskin

Samkörning av motorer

In this report studies have been done on two engines driving a common load via a mechanical gear. The engines are presumed to be linear within their working range. The aim is independently of load variations to get the engines' outgoing angular frequency to be equal to a given reference and to distribute the power between the engines in a given proportion. The report shows that certain arrange

Undersökning av Marsiks adaptiva regulator

Självlärande klassificering

Consider a system recieving signals from a signal-source. The signals describe different input situations. The purpose of the system is to classify the current situation. This can be obtained by means of recursive algorithms. The problem of finding such algorithms can be approached in many different ways. In this report we will assume a minimum of apriori information about the signals and the clas

Utmatning på plotter

The task was to write a program for plotter output on a ink jet plotter built at Inst. för Elmät, LTH. This plotter puts dots of ink on a paper fastened to a rotating drum and it must have, for every x-coordinate in its turn, the y-coordinates in rising order where it shall put a dot. 0