Skip to main content

Über dieses Buch

Micromechanical manufacturing based on microequipment creates new possibi- ties in goods production. If microequipment sizes are comparable to the sizes of the microdevices to be produced, it is possible to decrease the cost of production drastically. The main components of the production cost - material, energy, space consumption, equipment, and maintenance - decrease with the scaling down of equipment sizes. To obtain really inexpensive production, labor costs must be reduced to almost zero. For this purpose, fully automated microfactories will be developed. To create fully automated microfactories, we propose using arti?cial neural networks having different structures. The simplest perceptron-like neural network can be used at the lowest levels of microfactory control systems. Adaptive Critic Design, based on neural network models of the microfactory objects, can be used for manufacturing process optimization, while associative-projective neural n- works and networks like ART could be used for the highest levels of control systems. We have examined the performance of different neural networks in traditional image recognition tasks and in problems that appear in micromechanical manufacturing. We and our colleagues also have developed an approach to mic- equipment creation in the form of sequential generations. Each subsequent gene- tion must be of a smaller size than the previous ones and must be made by previous generations. Prototypes of ?rst-generation microequipment have been developed and assessed.



Chapter 1. Introduction

The title of the book, “Neural Networks and Micromechanics,” seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 2. Classical Neural Networks

Dring the last few decades, neural networks have moved from theory to offering solutions for industrial and commercial problems. Many people are interested in neural networks from many different perspectives. Engineers use them to build practical systems to solve industrial problems. For example, neural networks can be used for the control of industrial processes. There are many publications that relate to the neural network theme. Every year, tens or even hundreds of international conferences, symposiums, congresses, and seminars take place in the world. As an introduction to this theme we can recommend the books of Robert Hecht-Nielsen [1], Teuvo Kohonen [2], and Philip Wasserman [3], and a more advanced book that is oriented on the applications of neural networks and is edited by A. Browne [4]. In this book it is assumed that the reader has some previous knowledge of neural networks and an understanding of their basic mechanisms. In this section we want to present a very short introduction to neural networks and to highlight the most important moments in neural network development.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 3. Neural Classifiers

In this chapter we shall describe the neural classifiers. One of the important tasks in micromechanics for process automation is pattern recognition. For this purpose we developed different neural classifiers. Below, we will describe the Random Threshold Classifier (RTC classifier), Random Subspace Classifier (RSC classifier), and LIRA classifier (LImited Receptive Area). We will describe the structure and functions of these classifiers and how we use them. The first problem is the texture recognition problem. The task of classification in recognition systems is a more important issue than clustering or unsupervised segmentation in a vast majority of applications [1]. Texture classification plays an important role in outdoor scene images recognition, surface visual inspection systems, and so on. Despite its potential importance, there is no formal definition of texture due to an infinite diversity of texture samples. There exists a large number of texture analysis methods in the literature.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 4. Permutation Coding Technique for Image Recognition System

A feature extractor and neural classifier for a face image recognition system are proposed. They are based on the Permutation Coding technique, which continues our investigation of neural networks. The permutation coding technique makes it possible to take into account not only detected features, but also the position of each feature in the image. It permits us to obtain a sufficiently general description of the image to be recognized. Different types of images were used to test the proposed image recognition system. It was tested on the handwritten digit recognition problem and the face recognition problem. The results of this test are very promising. The error rate for the MNIST database is 0.44%, and for the ORL database it is 0.1%. In the last section, which is devoted to micromechanics applications, we will describe the application of the permutation coding technique to the micro-object shape recognition problem.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 5. Associative-Projective Neural Networks (APNNs)

Associative-projective neural networks (APNNs) were proposed by E. M. Kussul [1] and were developed with the participation of T. N. Baidyk and D. A. Rachkovskij [2–10]. These networks relate to those with distributed coding methods [11]. Later we shall discuss them in detail. APNNs make it possible to construct hierarchical systems for information processing. Before examining the structure and the properties of the associative-projective neural networks, let us describe the model of the neuron and the model of the associative neural field, which is the base block of this neural network architecture. Para>Before examining the structure and the properties of the associative-projective neural networks, let us describe the model of the neuron and the model of the associative neural field, which is the base block of this neural network architecture.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 6. Recognition of Textures, Object Shapes, and Handwritten Words

Neural networks are widely used for solving pattern recognition problems [1–5]. Let us examine the following stages in the recognition of visual patterns: extraction of textural features; recognition of textures; extraction on the image of the regions with uniform texture; and the recognition of the shape of these regions. All these stages can be realized effectively on neurocomputers. Some statistical characteristics of the local sections of images usually are understood by textural features [6, 7]. We understand under the texture a property of the local section of the image, which is fixed in a certain extensive section of the image. The foliage of the trees, grass, asphalt coating, and so on can serve as examples of sections of images having identical texture.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 7. Hardware for Neural Networks

The simulation of neural networks on conventional computers is time-consuming because parallel structures and processes are transferred to a sequential machine. New computational means oriented to the realization of neural network paradigms were developed, these are called neurocomputers. Universal and specialized neurocomputers [1–7] were created. In this chapter, several versions of hardware for the proposed neural networks will be considered. The purpose of creating the neurocomputer was to increase the speed and expansion of simulated neural networks. At the Institute of Cybernetics of the National Academy of Sciences, Ukraine, under the management of the Doctor of Sciences E. M. Kussul, the first neurocomputer for associative-projective neural networks was developed and tested. The block diagram of the neurocomputer, named NIC, is given in Fig. 7.1. The model consists of two basic blocks: the block of processing modules and the control unit. The former contains the random access memory (RAM), arithmetic-logical unit (ALU), multiplexer (MUX1), shift register (SRG1) and unit of binary counters (St1). The latter contains the high-speed memory unit (CM), arithmetic-logical unit (ALU2), shift registers (SRG2 and SRG3), multiplexer (MUX2), binary counter (Ct2), training address register (IRG), and synchronizing circuit (not shown in the figure).
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 8. Micromechanics

We suggest a new technology for the production of low-cost micromechanical devices that is based on the application of microequipment, similar to conventional mechanical equipment, but much smaller. It permits us to use the conventional technology for the mechanical treatment of materials and for the automatic assembly of mechanical and electronic devices for manufacturing micromechanical and microelectromechanical devices of submillimeter sizes. We call it “Microequipment Technology” (MET). MET will use microequipment for manufacturing commercial products and in turn will produce the necessary microequipment units. The decrease in manufacturing costs of microdevices will be achieved on the basis of mass parallel production processes used in MET [1], instead of the batch processes used in Microelectromechanical Systems (MEMS) [2–4]. In accordance with MET, sequential generations of microequipment are to be created (Fig. 8.1) [5, 6].
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 9. Applications of Neural Networks in Micromechanics

A computer vision system permits one to provide feedback, which increases the precision of the manufacturing process. It could be used in low-cost micromachine tools and micromanipulators for microdevice production. A method of sequential generations was proposed to create such microequipment [1]. According to this method, the microequipment of each new generation is smaller than the equipment of the previous generations. This approach would allow us to use low-cost components for each microequipment generation and to create microfactories capable of producing low-cost microdevices [2]. To preserve high precision of the microequipment, it is necessary to use adaptive algorithms of micropiece production. Algorithms based on contact sensors were proved and showed good results [2]. The neural-network-based vision system could provide much more extensive possibilities to improve the manufacturing process.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 10. Texture Recognition in Micromechanics

The main approaches to microdevice production are microelectromechanical systems (MEMS) [1, 2] and microequipment technology (MET) [3–7]. To get the most out of these technologies, it is important to have advanced image recognition systems. In this chapter, we propose the Random Subspace Neural Classifier (RSC) for metal surface texture recognition. Examples of metal surfaces are presented in Fig. 10.1. Due to changes in viewpoint and illumination, the visual appearance of different surfaces can vary greatly, making recognition very difficult [8]. Different lighting conditions and viewing angles greatly affect the grayscale properties of an image due to such effects as shading, shadowing, and local occlusions. The real surface images, which it is necessary to recognize in industrial environments, have all these problems and more, such as dust on the surface.
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch

Chapter 11. Adaptive Algorithms Based on Technical Vision

One problem with the microassembly process is that the workpiece sticks to the micromanipulator gripper, and it is difficult to release the gripper from the workpiece. To resolve this problem, we propose the following assembly process sequence [1] (Fig. 11.1). The gripper of the assembly device is the needle (1) in the tube (2). The microring is put on the needle and is introduced with the needle into the hole (Fig. 11.1a, b). After that, the needle is removed, and the microring is held in the hole with the tube (Fig. 11.1c). In the next step, the tube with the needle is moved aside, and the microring is held in the hole and cannot follow the tube (Fig. 11.1d). The tube then is moved up and liberates the end of the needle for the next operation (Fig. 11.1e).
Ernst Kussul, Tatiana Baidyk, Donald C. Wunsch


Weitere Informationen

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Globales Erdungssystem in urbanen Kabelnetzen

Bedingt durch die Altersstruktur vieler Kabelverteilnetze mit der damit verbundenen verminderten Isolationsfestigkeit oder durch fortschreitenden Kabelausbau ist es immer häufiger erforderlich, anstelle der Resonanz-Sternpunktserdung alternative Konzepte für die Sternpunktsbehandlung umzusetzen. Die damit verbundenen Fehlerortungskonzepte bzw. die Erhöhung der Restströme im Erdschlussfall führen jedoch aufgrund der hohen Fehlerströme zu neuen Anforderungen an die Erdungs- und Fehlerstromrückleitungs-Systeme. Lesen Sie hier über die Auswirkung von leitfähigen Strukturen auf die Stromaufteilung sowie die Potentialverhältnisse in urbanen Kabelnetzen bei stromstarken Erdschlüssen. Jetzt gratis downloaden!