Wyniki wyszukiwania - BazTech

1

Neural Network Model for Control of Operating Modes of Crushing and Grinding Complex

Kalinchyk Vasyl, Meita Olexandr, Pobigaylo Vitalii, Borychenko Olena, Kalinchyk Vitalii

Rocznik Ochrona Środowiska

|

2022

|

Tom 24

26--40

EN

This article investigates the application of neural network models to create automated control systems for industrial processes. We reviewed and analysed works on dispatch control and evaluation of equipment operating modes and the use of artificial neural networks to solve problems of this type. It is shown that the main requirements for identification models are the accuracy of estimation and ease of algorithm implementation. It is shown that artificial neural networks meet the requirements for accuracy of classification problems, ease of execution and speed. We considered the structures of neural networks that can be used to recognise the modes of operation of technological equipment. Application of the model and structure of networks with radial basis functions and multilayer perceptrons for identifying the mode of operation of equipment under given conditions is substantiated. The input conditions for constructing neural network models of two types with a given three-layer structure are offered. The results of training neural models on the model of a multilayer perceptron and a network with radial basis functions are presented. The estimation and comparative analysis of models depending on model parameters are made. It is shown that networks with radial basis functions offer greater accuracy in solving identification problems. The structural scheme of the automated process control system with mode identification based on artificial neural networks is offered.

2

A fast neural network learning algorithm with approximate singular value decomposition

Jankowski Norbert, Linowiecki Rafał

International Journal of Applied Mathematics and Computer Science

|

2019

|

Vol. 29, no. 3

581--594

EN

The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given problem, especially in the case of meta-learning. In this article we focus on the construction of a much faster learning algorithm and its modifications, especially for nonlinear versions of neural networks. The main idea of this algorithm lies in the usage of fast approximation of the Moore–Penrose pseudo-inverse matrix. The complexity of the original singular value decomposition algorithm is O(mn2). We consider algorithms with a complexity of O(mnl), where l < n and l is often significantly smaller than n. Such learning algorithms can be applied to the learning of radial basis function networks, extreme learning machines or deep ELMs, principal component analysis or even missing data imputation.

3

Comparison of prototype selection algorithms used in construction of neural networks learned by SVD

Jankowski N.

International Journal of Applied Mathematics and Computer Science

|

2018

|

Vol. 28, no. 4

719--733

EN

Radial basis function networks (RBFNs) or extreme learning machines (ELMs) can be seen as linear combinations of kernel functions (hidden neurons). Kernels can be constructed in random processes like in ELMs, or the positions of kernels can be initialized by a random subset of training vectors, or kernels can be constructed in a (sub-)learning process (sometimes by k-means, for example). We found that kernels constructed using prototype selection algorithms provide very accurate and stable solutions. What is more, prototype selection algorithms automatically choose not only the placement of prototypes, but also their number. Thanks to this advantage, it is no longer necessary to estimate the number of kernels with time-consuming multiple train-test procedures. The best results of learning can be obtained by pseudo-inverse learning with a singular value decomposition (SVD) algorithm. The article presents a comparison of several prototype selection algorithms co-working with singular value decomposition-based learning. The presented comparison clearly shows that the combination of prototype selection and SVD learning of a neural network is significantly better than a random selection of kernels for the RBFN or the ELM, the support vector machine or the kNN. Moreover, the presented learning scheme requires no parameters except for the width of the Gaussian kernel.