|
11. |
Integral equation models for continuous dynamical systems |
|
International Journal of Systems Science,
Volume 24,
Issue 8,
1993,
Page 1589-1599
S. MUKHOPADHYAY,
A. PATRA,
GANTIPRASADA RAO,
Preview
|
PDF (303KB)
|
|
摘要:
Two types of integral equations have been used in the literature to estimate the parameters of a continuous-time model of a linear system. This paper reveals the relationships between them and outlines the method of removing initial conditions. It then considers discrete approximations of signals and multiple integrals occurring in these equations. New recursive formulae are given for integrals of both types with samples and the so-called ‘block-pulse coefficients’ or averaged measurements. This implies that the methods developed using the block-pulse function approach with integral equation models can be extended easily with samples and vice versa.
ISSN:0020-7721
DOI:10.1080/00207729308949582
出版商:Taylor & Francis Group
年代:1993
数据来源: Taylor
|
12. |
Application of a multi-layered neural network to system identification |
|
International Journal of Systems Science,
Volume 24,
Issue 8,
1993,
Page 1601-1609
C. S. FU,
M. POCH,
Preview
|
PDF (271KB)
|
|
摘要:
A study on the application of the neural network method to estimate chemical oxygen demand (COD) in a wastewater treatment process is introduced after presenting the back propagation algorithm, one of the most typical algorithms of neural networks, in detail. Several types of simulation have been tried in order to select suitable neural network parameters. The results of simulation to estimate real sampling COD data for a specific real-world wastewater treatment process shows that our method is promising.
ISSN:0020-7721
DOI:10.1080/00207729308949583
出版商:Taylor & Francis Group
年代:1993
数据来源: Taylor
|
13. |
Optimal testing policy for a computer system with fault margin |
|
International Journal of Systems Science,
Volume 24,
Issue 8,
1993,
Page 1611-1620
SHEY-HUEI SHEU,
Preview
|
PDF (220KB)
|
|
摘要:
The periodic testing policy is considered, for a computer system which fails when the total number of hidden faults exceeds a threshold levelNof tolerence. Periodic tests are scheduled at timeskT(k= 1,2, ⃛) to detect hidden faults. A fault occurs according to a non-homogeneous Poisson processes. When theith fault occurs at ageSi<T, (i) it causes a system failure with probabilityp1(Si), (ii) it becomes a hidden fault with probabilityp2(Si)and is accumulated, or (iii) it is removed with probabilityp3(Si). The expected cost rate is derived. The aim of the paper is to find the optimalTwhich minimizes the expected cost rate per unit time of the policy. Various special cases are considered.
ISSN:0020-7721
DOI:10.1080/00207729308949584
出版商:Taylor & Francis Group
年代:1993
数据来源: Taylor
|
|