Broadband excitation in the system identification of active magnetic bearing rotor systems

One of the targets of the climate and energy package of the European Union is to increase the energy efficiency in order to achieve a 20 percent reduction in primary energy use compared with the projected level by 2020. The energy efficiency can be improved for example by increasing the rotational speed of large electrical drives, because this enables the elimination of gearboxes leading to a compact design with lower losses. The rotational speeds of traditional bearings, such as roller bearings, are limited by mechanical friction. Active magnetic bearings (AMBs), on the other hand, allow very high rotational speeds. Consequently, their use in large medium- and high-speed machines has rapidly increased. An active magnetic bearing rotor system is an inherently unstable, nonlinear multiple-input, multiple-output system. Model-based controller design of AMBs requires an accurate system model. Finite element modeling (FEM) together with the experimental modal analysis provides a very accurate model for the rotor, and a linearized model of the magneticactuators has proven to work well in normal conditions. However, the overall system may suffer from unmodeled dynamics, such as dynamics of foundation or shrink fits. This dynamics can be modeled by system identification. System identification can also be used for on-line diagnostics. In this study, broadband excitation signals are adopted to the identification of an active magnetic bearing rotor system. The broadband excitation enables faster frequency response function measurements when compared with the widely used stepped sine and swept sine excitations. Different broadband excitations are reviewed, and the random phase multisine excitation is chosen for further study. The measurement times using the multisine excitation and the stepped sine excitation are compared. An excitation signal design with an analysis of the harmonics produced by the nonlinear system is presented. The suitability of different frequency response function estimators for an AMB rotor system are also compared. Additionally, analytical modeling of an AMB rotor system, obtaining a parametric model from the nonparametric frequency response functions, and model updating are discussed in brief, as they are key elements in the modeling for a control design. Theoretical methods are tested with a laboratory test rig. The results conclude that an appropriately designed random phase multisine excitation is suitable for the identification of AMB rotor systems.

Active Magnetic Bearing System Identification Methods and Rotor Model Updating

Active magnetic bearing is a type of bearing which uses magnetic field to levitate the rotor. These bearings require continuous control of the currents in electromagnets and data from position of the rotor and the measured current from electromagnets. Because of this different identification methods can be implemented with no additional hardware. In this thesis the focus was to implement and test identification methods for active magnetic bearing system and to update the rotor model. Magnetic center calibration is a method used to locate the magnetic center of the rotor. Rotor model identification is an identification method used to identify the rotor model. Rotor model update is a method used to update the rotor model based on identification data. These methods were implemented and tested with a real machine where rotor was levitated with active magnetic bearings and the functionality of the methods was ensured. Methods were developed with further extension in mind and also with the possibility to apply them for different machines with ease.

Tuotekustannuslaskentamallin kehittäminen elintarvikealan yritykseen

Työn tavoitteena oli kehittää tuotekustannuslaskentamalli elintarvikealan yritykseen. Laskentamallin avulla halutaan saada tarkempaa tietoa tuotteiden kustannuksista ja kannattavuuksista. Työ muodostuu teoreettisesta kirjallisuusselvityksestä sekä empiirisestä case-tutkimuksesta. Aineiston perusteella kohdeyritykselle saatiin kehitettyä tuotekustannuslaskentamalli. Työn tutkimusote on konstruktiivinen. Laskentamallin kehittäminen edellytti välillisten kustannusten kohdistamisperiaatteiden määrittämistä. Välilliset kustannukset kohdistetaan perinteisellä kaksivaiheisella menetelmällä. Kustannukset kohdistetaan ensin niille kuuluville kustannuspaikoille. Kustannuspaikoilta kustannukset kohdistetaan edelleen tuoteryhmille ja tuotteille. Kohdeyrityksen tuotekustannuslaskenta on aikaisemmin perustunut ainoastaan standardikustannuslaskentaan. Kehitetyn kustannuslaskentamallin avulla tuotteiden kustannuksista ja kannattavuudesta saadaan tarkempaa tietoa, koska välillisten kustannusten kohdistamiseen luotiin selkeät menetelmät. Parantunutta kus-tannustietoa voidaan hyödyntää tuotteita koskevissa päätöksentekotilanteissa.

Practical Framework for Monitoring the Performance of Agile IT Projects in an Output-Based Outsourcing Context

Over the past decade, organizations worldwide have begun to widely adopt agile software development practices, which offer greater flexibility to frequently changing business requirements, better cost effectiveness due to minimization of waste, faster time-to-market, and closer collaboration between business and IT. At the same time, IT services are continuing to be increasingly outsourced to third parties providing the organizations with the ability to focus on their core capabilities as well as to take advantage of better demand scalability, access to specialized skills, and cost benefits. An output-based pricing model, where the customers pay directly for the functionality that was delivered rather than the effort spent, is quickly becoming a new trend in IT outsourcing allowing to transfer the risk away from the customer while at the same time offering much better incentives for the supplier to optimize processes and improve efficiency, and consequently producing a true win-win outcome. Despite the widespread adoption of both agile practices and output-based outsourcing, there is little formal research available on how the two can be effectively combined in practice. Moreover, little practical guidance exists on how companies can measure the performance of their agile projects, which are being delivered in an output-based outsourced environment. This research attempted to shed light on this issue by developing a practical project monitoring framework which may be readily applied by organizations to monitor the performance of agile projects in an output-based outsourcing context, thus taking advantage of the combined benefits of such an arrangement Modified from action research approach, this research was divided into two cycles, each consisting of the Identification, Analysis, Verification, and Conclusion phases. During Cycle 1, a list of six Key Performance Indicators (KPIs) was proposed and accepted by the professionals in the studied multinational organization, which formed the core of the proposed framework and answered the first research sub-question of what needs to be measured. In Cycle 2, a more in-depth analysis was provided for each of the suggested Key Performance Indicators including the techniques for capturing, calculating, and evaluating the information provided by each KPI. In the course of Cycle 2, the second research sub-question was answered, clarifying how the data for each KPI needed to be measured, interpreted, and acted upon. Consequently, after two incremental research cycles, the primary research question was answered describing the practical framework that may be used for monitoring the performance of agile IT projects delivered in an output-based outsourcing context. This framework was evaluated by the professionals within the context of the studied organization and received positive feedback across all four evaluation criteria set forth in this research, including the low overhead of data collection, high value of provided information, ease of understandability of the metric dashboard, and high generalizability of the proposed framework.

Converter-flux-based current control of voltage source PWM rectifiers - analysis and implementation

Pulsewidth-modulated (PWM) rectifier technology is increasingly used in industrial applications like variable-speed motor drives, since it offers several desired features such as sinusoidal input currents, controllable power factor, bidirectional power flow and high quality DC output voltage. To achieve these features,however, an effective control system with fast and accurate current and DC voltage responses is required. From various control strategies proposed to meet these control objectives, in most cases the commonly known principle of the synchronous-frame current vector control along with some space-vector PWM scheme have been applied. Recently, however, new control approaches analogous to the well-established direct torque control (DTC) method for electrical machines have also emerged to implement a high-performance PWM rectifier. In this thesis the concepts of classical synchronous-frame current control and DTC-based PWM rectifier control are combined and a new converter-flux-based current control (CFCC) scheme is introduced. To achieve sufficient dynamic performance and to ensure a stable operation, the proposed control system is thoroughly analysed and simple rules for the controller design are suggested. Special attention is paid to the estimationof the converter flux, which is the key element of converter-flux-based control. Discrete-time implementation is also discussed. Line-voltage-sensorless reactive reactive power control methods for the L- and LCL-type line filters are presented. For the L-filter an open-loop control law for the d-axis current referenceis proposed. In the case of the LCL-filter the combined open-loop control and feedback control is proposed. The influence of the erroneous filter parameter estimates on the accuracy of the developed control schemes is also discussed. A newzero vector selection rule for suppressing the zero-sequence current in parallel-connected PWM rectifiers is proposed. With this method a truly standalone and independent control of the converter units is allowed and traditional transformer isolation and synchronised-control-based solutions are avoided. The implementation requires only one additional current sensor. The proposed schemes are evaluated by the simulations and laboratory experiments. A satisfactory performance and good agreement between the theory and practice are demonstrated.

Learning Preferences with Kernel-Based Methods

Learning of preference relations has recently received significant attention in machine learning community. It is closely related to the classification and regression analysis and can be reduced to these tasks. However, preference learning involves prediction of ordering of the data points rather than prediction of a single numerical value as in case of regression or a class label as in case of classification. Therefore, studying preference relations within a separate framework facilitates not only better theoretical understanding of the problem, but also motivates development of the efficient algorithms for the task. Preference learning has many applications in domains such as information retrieval, bioinformatics, natural language processing, etc. For example, algorithms that learn to rank are frequently used in search engines for ordering documents retrieved by the query. Preference learning methods have been also applied to collaborative filtering problems for predicting individual customer choices from the vast amount of user generated feedback. In this thesis we propose several algorithms for learning preference relations. These algorithms stem from well founded and robust class of regularized least-squares methods and have many attractive computational properties. In order to improve the performance of our methods, we introduce several non-linear kernel functions. Thus, contribution of this thesis is twofold: kernel functions for structured data that are used to take advantage of various non-vectorial data representations and the preference learning algorithms that are suitable for different tasks, namely efficient learning of preference relations, learning with large amount of training data, and semi-supervised preference learning. Proposed kernel-based algorithms and kernels are applied to the parse ranking task in natural language processing, document ranking in information retrieval, and remote homology detection in bioinformatics domain. Training of kernel-based ranking algorithms can be infeasible when the size of the training set is large. This problem is addressed by proposing a preference learning algorithm whose computation complexity scales linearly with the number of training data points. We also introduce sparse approximation of the algorithm that can be efficiently trained with large amount of data. For situations when small amount of labeled data but a large amount of unlabeled data is available, we propose a co-regularized preference learning algorithm. To conclude, the methods presented in this thesis address not only the problem of the efficient training of the algorithms but also fast regularization parameter selection, multiple output prediction, and cross-validation. Furthermore, proposed algorithms lead to notably better performance in many preference learning tasks considered.

Identification and characterization of new genes and pathways regulating spermatogonial cell fate

Spermatogenesis, i.e sperm production in the seminiferous tubules of the testis, is a complex process that takes over one month to complete. Life-long ability of sperm production ultimately lies in a small population of undifferentiated cells, called spermatogonial stem cells (SSCs). These cells give rise to differentiating spermatogonia, which are committed to mature into spermatozoa. SSCs represent a heterogeneous population of cells and many aspects of their basic biology are still unknown. Understanding the mechanisms behind the cell fate decision of these cells is important to gain more insights into the causes of infertility and testis cancer. In addition, an interesting new aspect is the use of testis-derived stem cells in regenerative medicine. Our data demonstrated that adult mouse testis houses a population of Nanog-expressing spermatogonia. Based on mRNA and protein analysis these cells are enriched in stage XII of the mouse seminiferous epithelial cycle. The cells derived from this stage have the highest capacity to give rise to ES cell-like cells which express Oct4 and Nanog. These cells are under tight non- GDNF regulation but their fate can be dictated by activating p21 signalling. Comparative studies suggested that these cells are regulated like ES cells. Taken together these data imply that pluripotent cells are present in the adult mammalian testis. CIP2A (cancerous inhibitor of PP2A) has been associated with tumour aggressiveness and poor prognosis. In the testis it is expressed by the descendants of stem cells, i.e. the spermatogonial progenitor cells. Our data suggest that CIP2A acts upstream of PLZF and is needed for quantitatively normal spermatogenesis. Classification of CIP2A as a cancer/testis gene makes it an attractive target for cancer therapy. Study on the CIP2A deficient mouse model demonstrates that systemic inhibition of CIP2A does not severely interfere with growth and development or tissue or organ function, except for the spermatogenic output. These data demonstrate that CIP2A is required for quantitatively normal spermatogenesis. Hedgehog (Hh) signalling is involved in the development and maintenance of many different tissues and organs. According to our data, Hh signalling is active at many different levels during rat spermatogenesis: in spermatogonia, spermatocytes and late elongating spermatids. Localization of Suppressor of Fused (SuFu), the negative regulator of the pathway, specifically in early elongating spermatids suggests that Hh signalling needs to be shut down in these cells. Introduction of Hh signalling inhibitor resulted in an increase in germ cell apoptosis. Follicle-stimulating hormone (FSH) and inhibition of receptor tyrosine kinases resulted in down-regulation of Hh signalling. These data show that Hh signalling is under endocrine and paracrine control and it promotes germ cell survival.

Simulation of structural stress history based on dynamic analysis

Modern machine structures are often fabricated by welding. From a fatigue point of view, the structural details and especially, the welded details are the most prone to fatigue damage and failure. Design against fatigue requires information on the fatigue resistance of a structure’s critical details and the stress loads that act on each detail. Even though, dynamic simulation of flexible bodies is already current method for analyzing structures, obtaining the stress history of a structural detail during dynamic simulation is a challenging task; especially when the detail has a complex geometry. In particular, analyzing the stress history of every structural detail within a single finite element model can be overwhelming since the amount of nodal degrees of freedom needed in the model may require an impractical amount of computational effort. The purpose of computer simulation is to reduce amount of prototypes and speed up the product development process. Also, to take operator influence into account, real time models, i.e. simplified and computationally efficient models are required. This in turn, requires stress computation to be efficient if it will be performed during dynamic simulation. The research looks back at the theoretical background of multibody dynamic simulation and finite element method to find suitable parts to form a new approach for efficient stress calculation. This study proposes that, the problem of stress calculation during dynamic simulation can be greatly simplified by using a combination of floating frame of reference formulation with modal superposition and a sub-modeling approach. In practice, the proposed approach can be used to efficiently generate the relevant fatigue assessment stress history for a structural detail during or after dynamic simulation. In this work numerical examples are presented to demonstrate the proposed approach in practice. The results show that approach is applicable and can be used as proposed.

Wind Turbine Direct-Drive Permanent-Magnet Generator with Direct Liquid Cooling for Mass Reduction

Today’s electrical machine technology allows increasing the wind turbine output power by an order of magnitude from the technology that existed only ten years ago. However, it is sometimes argued that high-power direct-drive wind turbine generators will prove to be of limited practical importance because of their relatively large size and weight. The limited space for the generator in a wind turbine application together with the growing use of wind energy pose a challenge for the design engineers who are trying to increase torque without making the generator larger. When it comes to high torque density, the limiting factor in every electrical machine is heat, and if the electrical machine parts exceed their maximum allowable continuous operating temperature, even for a short time, they can suffer permanent damage. Therefore, highly efficient thermal design or cooling methods is needed. One of the promising solutions to enhance heat transfer performances of high-power, low-speed electrical machines is the direct cooling of the windings. This doctoral dissertation proposes a rotor-surface-magnet synchronous generator with a fractional slot nonoverlapping stator winding made of hollow conductors, through which liquid coolant can be passed directly during the application of current in order to increase the convective heat transfer capabilities and reduce the generator mass. This doctoral dissertation focuses on the electromagnetic design of a liquid-cooled direct-drive permanent-magnet synchronous generator (LC DD-PMSG) for a directdrive wind turbine application. The analytical calculation of the magnetic field distribution is carried out with the ambition of fast and accurate predicting of the main dimensions of the machine and especially the thickness of the permanent magnets; the generator electromagnetic parameters as well as the design optimization. The focus is on the generator design with a fractional slot non-overlapping winding placed into open stator slots. This is an a priori selection to guarantee easy manufacturing of the LC winding. A thermal analysis of the LC DD-PMSG based on a lumped parameter thermal model takes place with the ambition of evaluating the generator thermal performance. The thermal model was adapted to take into account the uneven copper loss distribution resulting from the skin effect as well as the effect of temperature on the copper winding resistance and the thermophysical properties of the coolant. The developed lumpedparameter thermal model and the analytical calculation of the magnetic field distribution can both be integrated with the presented algorithm to optimize an LC DD-PMSG design. Based on an instrumented small prototype with liquid-cooled tooth-coils, the following targets have been achieved: experimental determination of the performance of the direct liquid cooling of the stator winding and validating the temperatures predicted by an analytical thermal model; proving the feasibility of manufacturing the liquid-cooled tooth-coil winding; moreover, demonstration of the objectives of the project to potential customers.

Stiffness based trajectory planning and feedforward based vibration suppression control of parallel robot machines

The dissertation proposes two control strategies, which include the trajectory planning and vibration suppression, for a kinematic redundant serial-parallel robot machine, with the aim of attaining the satisfactory machining performance. For a given prescribed trajectory of the robot's end-effector in the Cartesian space, a set of trajectories in the robot's joint space are generated based on the best stiffness performance of the robot along the prescribed trajectory. To construct the required system-wide analytical stiffness model for the serial-parallel robot machine, a variant of the virtual joint method (VJM) is proposed in the dissertation. The modified method is an evolution of Gosselin's lumped model that can account for the deformations of a flexible link in more directions. The effectiveness of this VJM variant is validated by comparing the computed stiffness results of a flexible link with the those of a matrix structural analysis (MSA) method. The comparison shows that the numerical results from both methods on an individual flexible beam are almost identical, which, in some sense, provides mutual validation. The most prominent advantage of the presented VJM variant compared with the MSA method is that it can be applied in a flexible structure system with complicated kinematics formed in terms of flexible serial links and joints. Moreover, by combining the VJM variant and the virtual work principle, a systemwide analytical stiffness model can be easily obtained for mechanisms with both serial kinematics and parallel kinematics. In the dissertation, a system-wide stiffness model of a kinematic redundant serial-parallel robot machine is constructed based on integration of the VJM variant and the virtual work principle. Numerical results of its stiffness performance are reported. For a kinematic redundant robot, to generate a set of feasible joints' trajectories for a prescribed trajectory of its end-effector, its system-wide stiffness performance is taken as the constraint in the joints trajectory planning in the dissertation. For a prescribed location of the end-effector, the robot permits an infinite number of inverse solutions, which consequently yields infinite kinds of stiffness performance. Therefore, a differential evolution (DE) algorithm in which the positions of redundant joints in the kinematics are taken as input variables was employed to search for the best stiffness performance of the robot. Numerical results of the generated joint trajectories are given for a kinematic redundant serial-parallel robot machine, IWR (Intersector Welding/Cutting Robot), when a particular trajectory of its end-effector has been prescribed. The numerical results show that the joint trajectories generated based on the stiffness optimization are feasible for realization in the control system since they are acceptably smooth. The results imply that the stiffness performance of the robot machine deviates smoothly with respect to the kinematic configuration in the adjacent domain of its best stiffness performance. To suppress the vibration of the robot machine due to varying cutting force during the machining process, this dissertation proposed a feedforward control strategy, which is constructed based on the derived inverse dynamics model of target system. The effectiveness of applying such a feedforward control in the vibration suppression has been validated in a parallel manipulator in the software environment. The experimental study of such a feedforward control has also been included in the dissertation. The difficulties of modelling the actual system due to the unknown components in its dynamics is noticed. As a solution, a back propagation (BP) neural network is proposed for identification of the unknown components of the dynamics model of the target system. To train such a BP neural network, a modified Levenberg-Marquardt algorithm that can utilize an experimental input-output data set of the entire dynamic system is introduced in the dissertation. Validation of the BP neural network and the modified Levenberg- Marquardt algorithm is done, respectively, by a sinusoidal output approximation, a second order system parameters estimation, and a friction model estimation of a parallel manipulator, which represent three different application aspects of this method.

Automatic image-based identification of Saimaa ringed seals

The Saimaa ringed seal is one of the most endangered seals in the world. It is a symbol of Lake Saimaa and a lot of effort have been applied to save it. Traditional methods of seal monitoring include capturing the animals and installing sensors on their bodies. These invasive methods for identifying can be painful and affect the behavior of the animals. Automatic identification of seals using computer vision provides a more humane method for the monitoring. This Master's thesis focuses on automatic image-based identification of the Saimaa ringed seals. This consists of detection and segmentation of a seal in an image, analysis of its ring patterns, and identification of the detected seal based on the features of the ring patterns. The proposed algorithm is evaluated with a dataset of 131 individual seals. Based on the experiments with 363 images, 81\% of the images were successfully segmented automatically. Furthermore, a new approach for interactive identification of Saimaa ringed seals is proposed. The results of this research are a starting point for future research in the topic of seal photo-identification.

Identification of characteristics for successful university-company partnership development

The importance of university-company collaboration has increased during the last decades. The drivers for that are, on the one hand, changes in business logic of companies and on the other hand the decreased state funding of universities. Many companies emphasize joint research with universities as an enabling input to their development processes, which aim at creating new innovations, products and wealth. These factors have changed universities’ operations and they have adopted several practices of dynamic business organizations, such as strategic planning, monitoring and controlling methods of internal processes etc. The objective of this thesis is to combine different characteristics of successful university-company partnership and its development. The development process starts with identifying potential partners in the university’s interest group, which requires understanding the role of different partners in the innovation system. Next, in order to find a common development basis, matching the policy and strategy between partners is needed. The third phase is to combine the academic and industrial objectives of a joint project, which is a typical form of university-company collaboration. The optimum is a win-win situation where both partners, universities and companies, can get addedvalue. For the companies added value typically means access to new research results before their competitors. For the universities added value offers a possibility to carry on high level scientific work. The research output in the form of published scientific articles is evaluated by the international science community. Because the university-company partnership is often executed by joint projects, the different forms of this kind of projects is discussed in this study. The most challenging form of collaboration is a semi-open project model, which is not based on bilateral activities between universities and companies but on a consortium of several universities, research institutes and companies. The universities and companies are core actors in the innovation system. Thus the discussion of their roles and relations to public operators like publicly funded financiers is important. In the Finnish innovation system there are at least the following doers executing strategies and policies: EU, Academy of Finland and TEKES. In addition to these, Strategic Centres for Science, Technology and Innovation which are owned jointly by companies, universities and research organizations have a very important role in their fields of business. They transfer research results into commercial actions to generate wealth. The thesis comprises two parts. The first part consists of an overview of the study including introduction, literature review, research design, synthesis of findings and conclusions. The second part introduces four original research publications.

Model-based testing of software systems : functionality and performance

Software is a key component in many of our devices and products that we use every day. Most customers demand not only that their devices should function as expected but also that the software should be of high quality, reliable, fault tolerant, efficient, etc. In short, it is not enough that a calculator gives the correct result of a calculation, we want the result instantly, in the right form, with minimal use of battery, etc. One of the key aspects for succeeding in today's industry is delivering high quality. In most software development projects, high-quality software is achieved by rigorous testing and good quality assurance practices. However, today, customers are asking for these high quality software products at an ever-increasing pace. This leaves the companies with less time for development. Software testing is an expensive activity, because it requires much manual work. Testing, debugging, and verification are estimated to consume 50 to 75 per cent of the total development cost of complex software projects. Further, the most expensive software defects are those which have to be fixed after the product is released. One of the main challenges in software development is reducing the associated cost and time of software testing without sacrificing the quality of the developed software. It is often not enough to only demonstrate that a piece of software is functioning correctly. Usually, many other aspects of the software, such as performance, security, scalability, usability, etc., need also to be verified. Testing these aspects of the software is traditionally referred to as nonfunctional testing. One of the major challenges with non-functional testing is that it is usually carried out at the end of the software development process when most of the functionality is implemented. This is due to the fact that non-functional aspects, such as performance or security, apply to the software as a whole. In this thesis, we study the use of model-based testing. We present approaches to automatically generate tests from behavioral models for solving some of these challenges. We show that model-based testing is not only applicable to functional testing but also to non-functional testing. In its simplest form, performance testing is performed by executing multiple test sequences at once while observing the software in terms of responsiveness and stability, rather than the output. The main contribution of the thesis is a coherent model-based testing approach for testing functional and performance related issues in software systems. We show how we go from system models, expressed in the Unified Modeling Language, to test cases and back to models again. The system requirements are traced throughout the entire testing process. Requirements traceability facilitates finding faults in the design and implementation of the software. In the research field of model-based testing, many new proposed approaches suffer from poor or the lack of tool support. Therefore, the second contribution of this thesis is proper tool support for the proposed approach that is integrated with leading industry tools. We o er independent tools, tools that are integrated with other industry leading tools, and complete tool-chains when necessary. Many model-based testing approaches proposed by the research community suffer from poor empirical validation in an industrial context. In order to demonstrate the applicability of our proposed approach, we apply our research to several systems, including industrial ones.

Determining vehicle drivetrain dynamics using system identification

Target of this book is to propose an approach for modelling drivetrain dynamics in order to design further a vibration control system of a hybrid bus. In this thesis two approaches are examined and compared. First model is obtained by theoretical means: drivetrain is represented as a system of rotating masses, which motion is described with differential equations. Second model is obtained using system identification method: mathematical description of the dynamic behavior of a system is formed based on measured input (torque) and output (speed) data. Then two models are compared and an optimal approach is suggested.

Wood species identification by visual characterization of fibers

Kandidaatintyö tehtiin osana PulpVision-tutkimusprojektia, jonka tarkoituksena on kehittää kuvapohjaisia laskenta- ja luokittelumetodeja sellun laaduntarkkailuun paperin valmistuksessa. Tämän tutkimusprojektin osana on aiemmin kehitetty metodi, jolla etsittiin kaarevia rakenteita kuvista, ja tätä metodia hyödynnettiin kuitujen etsintään kuvista. Tätä metodia käytettiin lähtökohtana kandidaatintyölle. Työn tarkoituksena oli tutkia, voidaanko erilaisista kuitukuvista laskettujen piirteiden avulla tunnistaa kuvassa olevien kuitujen laji. Näissä kuitukuvissa oli kuituja neljästä eri puulajista ja yhdestä kasvista. Nämä lajit olivat akasia, koivu, mänty, eukalyptus ja vehnä. Jokaisesta lajista valittiin 100 kuitukuvaa ja nämä kuvat jaettiin kahteen ryhmään, joista ensimmäistä käytettiin opetusryhmänä ja toista testausryhmänä. Opetusryhmän avulla jokaiselle kuitulajille laskettiin näitä kuvaavia piirteitä, joiden avulla pyrittiin tunnistamaan testausryhmän kuvissa olevat kuitulajit. Nämä kuvat oli tuottanut CEMIS-Oulu (Center for Measurement and Information Systems), joka on mittaustekniikkaan keskittynyt yksikkö Oulun yliopistossa. Yksittäiselle opetusryhmän kuitukuvalle laskettiin keskiarvot ja keskihajonnat kolmesta eri piirteestä, jotka olivat pituus, leveys ja kaarevuus. Lisäksi laskettiin, kuinka monta kuitua kuvasta löydettiin. Näiden piirteiden eri yhdistelmien avulla testattiin tunnistamisen tarkkuutta käyttämällä k:n lähimmän naapurin menetelmää ja Naiivi Bayes -luokitinta testausryhmän kuville. Testeistä saatiin lupaavia tuloksia muun muassa pituuden ja leveyden keskiarvoja käytettäessä saavutettiin jopa noin 98 %:n tarkkuus molemmilla algoritmeilla. Tunnistuksessa kuitujen keskimäärinen pituus vaikutti olevan kuitukuvia parhaiten kuvaava piirre. Käytettyjen algoritmien välillä ei ollut suurta vaihtelua tarkkuudessa. Testeissä saatujen tulosten perusteella voidaan todeta, että kuitukuvien tunnistaminen on mahdollista. Testien perusteella kuitukuvista tarvitsee laskea vain kaksi piirrettä, joilla kuidut voidaan tunnistaa tarkasti. Käytetyt lajittelualgoritmit olivat hyvin yksinkertaisia, mutta ne toimivat testeissä hyvin.