Chemical plant fault diagnosis by neural networks
Dijagnostika kvara hemijskog postrojenja pomoću neuronskih mreža
Само за регистроване кориснике
2000
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
An analysis of learning and generalization characteristics of neural networks for diagnosing process failures was presented. Various feedforward neural network topologies were tested and compared. The single fault assumption was relaxed to include multiple causal origins of the symptoms. A chemical plant composed of a reactor and a distillation column was used as a case study. The performance during recall improves at first with an increase in the number of hidden units and with the amount of training, and then attains convergence. The algorithm of the Generalized Delta Rule (GDR) was used to train the networks by minimizing the sum of squares of residual according to the given convergence criterion. The obtained results show the applicability of the neural networks structure with hidden layers for process fault diagnosing. These results illustrate the feasibility of using neural networks for fault recognition and location.
Извор:
Chemical Industry and Chemical Engineering Quarterly, 2000, 6, 3, 372-377Издавач:
- CI and CEQ
Институција/група
Tehnološko-metalurški fakultetTY - JOUR AU - Savkovic-Stevanovic, Jelenka B. PY - 2000 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/5308 AB - An analysis of learning and generalization characteristics of neural networks for diagnosing process failures was presented. Various feedforward neural network topologies were tested and compared. The single fault assumption was relaxed to include multiple causal origins of the symptoms. A chemical plant composed of a reactor and a distillation column was used as a case study. The performance during recall improves at first with an increase in the number of hidden units and with the amount of training, and then attains convergence. The algorithm of the Generalized Delta Rule (GDR) was used to train the networks by minimizing the sum of squares of residual according to the given convergence criterion. The obtained results show the applicability of the neural networks structure with hidden layers for process fault diagnosing. These results illustrate the feasibility of using neural networks for fault recognition and location. PB - CI and CEQ T2 - Chemical Industry and Chemical Engineering Quarterly T1 - Chemical plant fault diagnosis by neural networks T1 - Dijagnostika kvara hemijskog postrojenja pomoću neuronskih mreža EP - 377 IS - 3 SP - 372 VL - 6 UR - https://hdl.handle.net/21.15107/rcub_technorep_5308 ER -
@article{ author = "Savkovic-Stevanovic, Jelenka B.", year = "2000", abstract = "An analysis of learning and generalization characteristics of neural networks for diagnosing process failures was presented. Various feedforward neural network topologies were tested and compared. The single fault assumption was relaxed to include multiple causal origins of the symptoms. A chemical plant composed of a reactor and a distillation column was used as a case study. The performance during recall improves at first with an increase in the number of hidden units and with the amount of training, and then attains convergence. The algorithm of the Generalized Delta Rule (GDR) was used to train the networks by minimizing the sum of squares of residual according to the given convergence criterion. The obtained results show the applicability of the neural networks structure with hidden layers for process fault diagnosing. These results illustrate the feasibility of using neural networks for fault recognition and location.", publisher = "CI and CEQ", journal = "Chemical Industry and Chemical Engineering Quarterly", title = "Chemical plant fault diagnosis by neural networks, Dijagnostika kvara hemijskog postrojenja pomoću neuronskih mreža", pages = "377-372", number = "3", volume = "6", url = "https://hdl.handle.net/21.15107/rcub_technorep_5308" }
Savkovic-Stevanovic, J. B.. (2000). Chemical plant fault diagnosis by neural networks. in Chemical Industry and Chemical Engineering Quarterly CI and CEQ., 6(3), 372-377. https://hdl.handle.net/21.15107/rcub_technorep_5308
Savkovic-Stevanovic JB. Chemical plant fault diagnosis by neural networks. in Chemical Industry and Chemical Engineering Quarterly. 2000;6(3):372-377. https://hdl.handle.net/21.15107/rcub_technorep_5308 .
Savkovic-Stevanovic, Jelenka B., "Chemical plant fault diagnosis by neural networks" in Chemical Industry and Chemical Engineering Quarterly, 6, no. 3 (2000):372-377, https://hdl.handle.net/21.15107/rcub_technorep_5308 .