Ohutlevytuotteenvalmistusteknisten piirteiden tunnistaminen ja käyttö suunnittelun apuna

Suunnittelu- ja valmistustoiminnot ovat eriytymässä myös ohutlevyteollisuudessa. Kilpailukyvyn parantamiseksi, valmistusta siirretään alihankkijoille maihin, jossa työvoima on halpaa ja suuret markkinat lähellä, tuotekehityksen ja suunnittelun jäädessä Suomeen tai muualle Länsi-Eurooppaan. Tällöin vanhan lokaalin toimintamallin synergiaedut eivät ole enää mahdollisia ja tuotteen valmistettavuuden arviointi, laadunhallinta ja komponenttien yhteensopivuuden varmistaminen on erittäin haasteellista. Tässä tutkimuksessa etsittiin uuden toimintamallin tuomiin haasteisiin vastauksia piirrepohjaisesta mallintamisesta. Tavoitteen mukaisesti, tutkimuksessa tunnistettiin ohutlevytuotteen valmistusteknilliset piirteet ja luotiin niiden mukainen piirrekaavio. Piirteiden tunnistus vaati tutkimustyötä sekä nykyaikaisten suunnittelumetodien että valmistusmenetelmien ja ohutlevymateriaalien parissa. Lisäksitarkasteltiin, millaisia vaikutuksia piirteillä on tuotteen valmistettavuuteen ja miten nämä tulee huomioida tuotteen suunnittelussa.

New Distance Transforms for Gray Level Image Compression

This thesis deals with distance transforms which are a fundamental issue in image processing and computer vision. In this thesis, two new distance transforms for gray level images are presented. As a new application for distance transforms, they are applied to gray level image compression. The new distance transforms are both new extensions of the well known distance transform algorithm developed by Rosenfeld, Pfaltz and Lay. With some modification their algorithm which calculates a distance transform on binary images with a chosen kernel has been made to calculate a chessboard like distance transform with integer numbers (DTOCS) and a real value distance transform (EDTOCS) on gray level images. Both distance transforms, the DTOCS and EDTOCS, require only two passes over the graylevel image and are extremely simple to implement. Only two image buffers are needed: The original gray level image and the binary image which defines the region(s) of calculation. No other image buffers are needed even if more than one iteration round is performed. For large neighborhoods and complicated images the two pass distance algorithm has to be applied to the image more than once, typically 3 10 times. Different types of kernels can be adopted. It is important to notice that no other existing transform calculates the same kind of distance map as the DTOCS. All the other gray weighted distance function, GRAYMAT etc. algorithms find the minimum path joining two points by the smallest sum of gray levels or weighting the distance values directly by the gray levels in some manner. The DTOCS does not weight them that way. The DTOCS gives a weighted version of the chessboard distance map. The weights are not constant, but gray value differences of the original image. The difference between the DTOCS map and other distance transforms for gray level images is shown. The difference between the DTOCS and EDTOCS is that the EDTOCS calculates these gray level differences in a different way. It propagates local Euclidean distances inside a kernel. Analytical derivations of some results concerning the DTOCS and the EDTOCS are presented. Commonly distance transforms are used for feature extraction in pattern recognition and learning. Their use in image compression is very rare. This thesis introduces a new application area for distance transforms. Three new image compression algorithms based on the DTOCS and one based on the EDTOCS are presented. Control points, i.e. points that are considered fundamental for the reconstruction of the image, are selected from the gray level image using the DTOCS and the EDTOCS. The first group of methods select the maximas of the distance image to new control points and the second group of methods compare the DTOCS distance to binary image chessboard distance. The effect of applying threshold masks of different sizes along the threshold boundaries is studied. The time complexity of the compression algorithms is analyzed both analytically and experimentally. It is shown that the time complexity of the algorithms is independent of the number of control points, i.e. the compression ratio. Also a new morphological image decompression scheme is presented, the 8 kernels' method. Several decompressed images are presented. The best results are obtained using the Delaunay triangulation. The obtained image quality equals that of the DCT images with a 4 x 4

Modelling of combustion and sorbent reactions in three-dimensional flow environment of a circulating fluidized bed furnace

This thesis presents a three-dimensional, semi-empirical, steady state model for simulating the combustion, gasification, and formation of emissions in circulating fluidized bed (CFB) processes. In a large-scale CFB furnace, the local feeding of fuel, air, and other input materials, as well as the limited mixing rate of different reactants produce inhomogeneous process conditions. To simulate the real conditions, the furnace should be modelled three-dimensionally or the three-dimensional effects should be taken into account. The only available methods for simulating the large CFB furnaces three-dimensionally are semi-empirical models, which apply a relatively coarse calculation mesh and a combination of fundamental conservation equations, theoretical models and empirical correlations. The number of such models is extremely small. The main objective of this work was to achieve a model which can be applied to calculating industrial scale CFB boilers and which can simulate all the essential sub-phenomena: fluid dynamics, reactions, the attrition of particles, and heat transfer. The core of the work was to develop the model frame and the required sub-models for determining the combustion and sorbent reactions. The objective was reached, and the developed model was successfully used for studying various industrial scale CFB boilers combusting different types of fuel. The model for sorbent reactions, which includes the main reactions for calcitic limestones, was applied for studying the new possible phenomena occurring in the oxygen-fired combustion. The presented combustion and sorbent models and principles can be utilized in other model approaches as well, including other empirical and semi-empirical model approaches, and CFD based simulations. The main achievement is the overall model frame which can be utilized for the further development and testing of new sub-models and theories, and for concentrating the knowledge gathered from the experimental work carried out at bench scale, pilot scale and industrial scale apparatus, and from the computational work performed by other modelling methods.

Evaluation of Bubble Formation and Break Up in Suppression Pools by Using Pattern Recognition Methods

During a possible loss of coolant accident in BWRs, a large amount of steam will be released from the reactor pressure vessel to the suppression pool. Steam will be condensed into the suppression pool causing dynamic and structural loads to the pool. The formation and break up of bubbles can be measured by visual observation using a suitable pattern recognition algorithm. The aim of this study was to improve the preliminary pattern recognition algorithm, developed by Vesa Tanskanen in his doctoral dissertation, by using MATLAB. Video material from the PPOOLEX test facility, recorded during thermal stratification and mixing experiments, was used as a reference in the development of the algorithm. The developed algorithm consists of two parts: the pattern recognition of the bubbles and the analysis of recognized bubble images. The bubble recognition works well, but some errors will appear due to the complex structure of the pool. The results of the image analysis were reasonable. The volume and the surface area of the bubbles were not evaluated. Chugging frequencies calculated by using FFT fitted well into the results of oscillation frequencies measured in the experiments. The pattern recognition algorithm works in the conditions it is designed for. If the measurement configuration will be changed, some modifications have to be done. Numerous improvements are proposed for the future 3D equipment.

Supervised localimage feature detection

This thesis is about detection of local image features. The research topic belongs to the wider area of object detection, which is a machine vision and pattern recognition problem where an object must be detected (located) in an image. State-of-the-art object detection methods often divide the problem into separate interest point detection and local image description steps, but in this thesis a different technique is used, leading to higher quality image features which enable more precise localization. Instead of using interest point detection the landmark positions are marked manually. Therefore, the quality of the image features is not limited by the interest point detection phase and the learning of image features is simplified. The approach combines both interest point detection and local description into one phase for detection. Computational efficiency of the descriptor is therefore important, leaving out many of the commonly used descriptors as unsuitably heavy. Multiresolution Gabor features has been the main descriptor in this thesis and improving their efficiency is a significant part. Actual image features are formed from descriptors by using a classifierwhich can then recognize similar looking patches in new images. The main classifier is based on Gaussian mixture models. Classifiers are used in one-class classifier configuration where there are only positive training samples without explicit background class. The local image feature detection method has been tested with two freely available face detection databases and a proprietary license plate database. The localization performance was very good in these experiments. Other applications applying the same under-lying techniques are also presented, including object categorization and fault detection.

Local and Global Feature Extraction for Invariant Object Recognition

Perceiving the world visually is a basic act for humans, but for computers it is still an unsolved problem. The variability present innatural environments is an obstacle for effective computer vision. The goal of invariant object recognition is to recognise objects in a digital image despite variations in, for example, pose, lighting or occlusion. In this study, invariant object recognition is considered from the viewpoint of feature extraction. Thedifferences between local and global features are studied with emphasis on Hough transform and Gabor filtering based feature extraction. The methods are examined with respect to four capabilities: generality, invariance, stability, and efficiency. Invariant features are presented using both Hough transform and Gabor filtering. A modified Hough transform technique is also presented where the distortion tolerance is increased by incorporating local information. In addition, methods for decreasing the computational costs of the Hough transform employing parallel processing and local information are introduced.

CFD Modelling of Direct Contact Condensation in Suppression Pools by Applying Condensation Models of Separated Flow

The condensation rate has to be high in the safety pressure suppression pool systems of Boiling Water Reactors (BWR) in order to fulfill their safety function. The phenomena due to such a high direct contact condensation (DCC) rate turn out to be very challenging to be analysed either with experiments or numerical simulations. In this thesis, the suppression pool experiments carried out in the POOLEX facility of Lappeenranta University of Technology were simulated. Two different condensation modes were modelled by using the 2-phase CFD codes NEPTUNE CFD and TransAT. The DCC models applied were the typical ones to be used for separated flows in channels, and their applicability to the rapidly condensing flow in the condensation pool context had not been tested earlier. A low Reynolds number case was the first to be simulated. The POOLEX experiment STB-31 was operated near the conditions between the ’quasi-steady oscillatory interface condensation’ mode and the ’condensation within the blowdown pipe’ mode. The condensation models of Lakehal et al. and Coste & Lavi´eville predicted the condensation rate quite accurately, while the other tested ones overestimated it. It was possible to get the direct phase change solution to settle near to the measured values, but a very high resolution of calculation grid was needed. Secondly, a high Reynolds number case corresponding to the ’chugging’ mode was simulated. The POOLEX experiment STB-28 was chosen, because various standard and highspeed video samples of bubbles were recorded during it. In order to extract numerical information from the video material, a pattern recognition procedure was programmed. The bubble size distributions and the frequencies of chugging were calculated with this procedure. With the statistical data of the bubble sizes and temporal data of the bubble/jet appearance, it was possible to compare the condensation rates between the experiment and the CFD simulations. In the chugging simulations, a spherically curvilinear calculation grid at the blowdown pipe exit improved the convergence and decreased the required cell count. The compressible flow solver with complete steam-tables was beneficial for the numerical success of the simulations. The Hughes-Duffey model and, to some extent, the Coste & Lavi´eville model produced realistic chugging behavior. The initial level of the steam/water interface was an important factor to determine the initiation of the chugging. If the interface was initialized with a water level high enough inside the blowdown pipe, the vigorous penetration of a water plug into the pool created a turbulent wake which invoked the chugging that was self-sustaining. A 3D simulation with a suitable DCC model produced qualitatively very realistic shapes of the chugging bubbles and jets. The comparative FFT analysis of the bubble size data and the pool bottom pressure data gave useful information to distinguish the eigenmodes of chugging, bubbling, and pool structure oscillations.

Semantic and fuzzy modelling for human behaviour recognition in smart spaces : a case study on ambient assisted living.

Human activity recognition in everyday environments is a critical, but challenging task in Ambient Intelligence applications to achieve proper Ambient Assisted Living, and key challenges still remain to be dealt with to realize robust methods. One of the major limitations of the Ambient Intelligence systems today is the lack of semantic models of those activities on the environment, so that the system can recognize the speci c activity being performed by the user(s) and act accordingly. In this context, this thesis addresses the general problem of knowledge representation in Smart Spaces. The main objective is to develop knowledge-based models, equipped with semantics to learn, infer and monitor human behaviours in Smart Spaces. Moreover, it is easy to recognize that some aspects of this problem have a high degree of uncertainty, and therefore, the developed models must be equipped with mechanisms to manage this type of information. A fuzzy ontology and a semantic hybrid system are presented to allow modelling and recognition of a set of complex real-life scenarios where vagueness and uncertainty are inherent to the human nature of the users that perform it. The handling of uncertain, incomplete and vague data (i.e., missing sensor readings and activity execution variations, since human behaviour is non-deterministic) is approached for the rst time through a fuzzy ontology validated on real-time settings within a hybrid data-driven and knowledgebased architecture. The semantics of activities, sub-activities and real-time object interaction are taken into consideration. The proposed framework consists of two main modules: the low-level sub-activity recognizer and the high-level activity recognizer. The rst module detects sub-activities (i.e., actions or basic activities) that take input data directly from a depth sensor (Kinect). The main contribution of this thesis tackles the second component of the hybrid system, which lays on top of the previous one, in a superior level of abstraction, and acquires the input data from the rst module's output, and executes ontological inference to provide users, activities and their in uence in the environment, with semantics. This component is thus knowledge-based, and a fuzzy ontology was designed to model the high-level activities. Since activity recognition requires context-awareness and the ability to discriminate among activities in di erent environments, the semantic framework allows for modelling common-sense knowledge in the form of a rule-based system that supports expressions close to natural language in the form of fuzzy linguistic labels. The framework advantages have been evaluated with a challenging and new public dataset, CAD-120, achieving an accuracy of 90.1% and 91.1% respectively for low and high-level activities. This entails an improvement over both, entirely data-driven approaches, and merely ontology-based approaches. As an added value, for the system to be su ciently simple and exible to be managed by non-expert users, and thus, facilitate the transfer of research to industry, a development framework composed by a programming toolbox, a hybrid crisp and fuzzy architecture, and graphical models to represent and con gure human behaviour in Smart Spaces, were developed in order to provide the framework with more usability in the nal application. As a result, human behaviour recognition can help assisting people with special needs such as in healthcare, independent elderly living, in remote rehabilitation monitoring, industrial process guideline control, and many other cases. This thesis shows use cases in these areas.

Optical Character Recognition for Symbian OS

This Master's thesis addresses the design and implementation of the optical character recognition (OCR) system for a mobile device working on the Symbian operating system. The developed OCR system, named OCRCapriccio, emphasizes the modularity, effective extensibility and reuse. The system consists of two parts which are the graphical user interface and the OCR engine that was implemented as a plug-in. In fact, the plug-in includes two implementations of the OCR engine for enabling two types of recognition: the bitmap comparison based recognition and statistical recognition. The implementation results have shown that the approach based on bitmap comparison is more suitable for the Symbian environment because of its nature. Although the current implementation of bitmap comparison is lacking in accuracy, further development should be done in its direction. The biggest challenges of this work were related to developing an OCR scheme that would be suitable for Symbian OS Smartphones that have limited computational power and restricted resources.

Physical Realization of an Optical Automatic Target Recognition System

In the modern warfare there is an active development of a new trend connected with a robotic warfare. One of the critical elements of robotics warfare systems is an automatic target recognition system, allowing to recognize objects, based on the data received from sensors. This work considers aspects of optical realization of such a system by means of NIR target scanning at fixed wavelengths. An algorithm was designed, an experimental setup was built and samples of various modern gear and apparel materials were tested. For pattern testing the samples of actively arm engaged armies camouflages were chosen. Tests were performed both in clear atmosphere and in the artificial extremely humid and hot atmosphere to simulate field conditions.

Local Binary Patterns in Focal-Plane Processing. Analysis and Applications

Feature extraction is the part of pattern recognition, where the sensor data is transformed into a more suitable form for the machine to interpret. The purpose of this step is also to reduce the amount of information passed to the next stages of the system, and to preserve the essential information in the view of discriminating the data into different classes. For instance, in the case of image analysis the actual image intensities are vulnerable to various environmental effects, such as lighting changes and the feature extraction can be used as means for detecting features, which are invariant to certain types of illumination changes. Finally, classification tries to make decisions based on the previously transformed data. The main focus of this thesis is on developing new methods for the embedded feature extraction based on local non-parametric image descriptors. Also, feature analysis is carried out for the selected image features. Low-level Local Binary Pattern (LBP) based features are in a main role in the analysis. In the embedded domain, the pattern recognition system must usually meet strict performance constraints, such as high speed, compact size and low power consumption. The characteristics of the final system can be seen as a trade-off between these metrics, which is largely affected by the decisions made during the implementation phase. The implementation alternatives of the LBP based feature extraction are explored in the embedded domain in the context of focal-plane vision processors. In particular, the thesis demonstrates the LBP extraction with MIPA4k massively parallel focal-plane processor IC. Also higher level processing is incorporated to this framework, by means of a framework for implementing a single chip face recognition system. Furthermore, a new method for determining optical flow based on LBPs, designed in particular to the embedded domain is presented. Inspired by some of the principles observed through the feature analysis of the Local Binary Patterns, an extension to the well known non-parametric rank transform is proposed, and its performance is evaluated in face recognition experiments with a standard dataset. Finally, an a priori model where the LBPs are seen as combinations of n-tuples is also presented

Automatic recognition of fish from video sequences

The problem of automatic recognition of the fish from the video sequences is discussed in this Master’s Thesis. This is a very urgent issue for many organizations engaged in fish farming in Finland and Russia because the process of automation control and counting of individual species is turning point in the industry. The difficulties and the specific features of the problem have been identified in order to find a solution and propose some recommendations for the components of the automated fish recognition system. Methods such as background subtraction, Kalman filtering and Viola-Jones method were implemented during this work for detection, tracking and estimation of fish parameters. Both the results of the experiments and the choice of the appropriate methods strongly depend on the quality and the type of a video which is used as an input data. Practical experiments have demonstrated that not all methods can produce good results for real data, whereas on synthetic data they operate satisfactorily.

Modelling of changes in electricity end-use and their impacts on electricity distribution

The electricity distribution sector will face significant changes in the future. Increasing reliability demands will call for major network investments. At the same time, electricity end-use is undergoing profound changes. The changes include future energy technologies and other advances in the field. New technologies such as microgeneration and electric vehicles will have different kinds of impacts on electricity distribution network loads. In addition, smart metering provides more accurate electricity consumption data and opportunities to develop sophisticated load modelling and forecasting approaches. Thus, there are both demands and opportunities to develop a new type of long-term forecasting methodology for electricity distribution. The work concentrates on the technical and economic perspectives of electricity distribution. The doctoral dissertation proposes a methodology to forecast electricity consumption in the distribution networks. The forecasting process consists of a spatial analysis, clustering, end-use modelling, scenarios and simulation methods, and the load forecasts are based on the application of automatic meter reading (AMR) data. The developed long-term forecasting process produces power-based load forecasts. By applying these results, it is possible to forecast the impacts of changes on electrical energy in the network, and further, on the distribution system operator’s revenue. These results are applicable to distribution network and business planning. This doctoral dissertation includes a case study, which tests the forecasting process in practice. For the case study, the most prominent future energy technologies are chosen, and their impacts on the electrical energy and power on the network are analysed. The most relevant topics related to changes in the operating environment, namely energy efficiency, microgeneration, electric vehicles, energy storages and demand response, are discussed in more detail. The study shows that changes in electricity end-use may have radical impacts both on electrical energy and power in the distribution networks and on the distribution revenue. These changes will probably pose challenges for distribution system operators. The study suggests solutions for the distribution system operators on how they can prepare for the changing conditions. It is concluded that a new type of load forecasting methodology is needed, because the previous methods are no longer able to produce adequate forecasts.

Pretraining Convolutional Neural Networks for Visual Recognition

Convolutional Neural Networks (CNN) have become the state-of-the-art methods on many large scale visual recognition tasks. For a lot of practical applications, CNN architectures have a restrictive requirement: A huge amount of labeled data are needed for training. The idea of generative pretraining is to obtain initial weights of the network by training the network in a completely unsupervised way and then fine-tune the weights for the task at hand using supervised learning. In this thesis, a general introduction to Deep Neural Networks and algorithms are given and these methods are applied to classification tasks of handwritten digits and natural images for developing unsupervised feature learning. The goal of this thesis is to find out if the effect of pretraining is damped by recent practical advances in optimization and regularization of CNN. The experimental results show that pretraining is still a substantial regularizer, however, not a necessary step in training Convolutional Neural Networks with rectified activations. On handwritten digits, the proposed pretraining model achieved a classification accuracy comparable to the state-of-the-art methods.