2.9 KiB
| authors | citekey | publish_date | journal | volume | issue | pages | last_import | |
|---|---|---|---|---|---|---|---|---|
|
agarwalSystematicClassificationNeuralnetworkbased1997 | 1997-04-01 | IEEE Control Systems Magazine | 17 | 2 | 75-93 | 2025-07-21 |
Indexing Information
Published: 1997-04
DOI 10.1109/37.581297 #Control-systems, #Stability-analysis, #Computer-networks, #Concurrent-computing, #Convergence-of-numerical-methods, #Electrical-equipment-industry, #Industrial-control, #Neural-networks, #Proposals, #Taxonomy
#InFirstPass
[!Abstract] Successful industrial applications and favorable comparisons with conventional alternatives have motivated the development of a large number of schemes for neural-network-based control. Each scheme is usually composed of several independent functional features, which makes it difficult to identify precisely what is new in the scheme. Help from available overviews is therefore often inadequate, since they usually discuss only the most important overall schemes. This work breaks the available schemes down to their essential functional features and organizes the latter into a multi-level classification. The classification reveals that similar schemes often get placed in different categories, fundamentally different features often get lumped into a single category, and proposed new schemes are often merely permutations and combinations of the well-established fundamental features. The classification has two main sections: neural network only as an aid; and neural network as controller.>[!seealso] Related Papers
Annotations
Notes
Highlights From Zotero
[!highlight] Highlight rigorous comparisons neural-network controllers have fared better than well- established conventional options when the plant characteristics are poorly known [2-61. 2025-04-15 9:18 am
[!done] Important In order to illus- tr te the unavoidable basic terminology for the unfamiliar re 9 der, a neural network can be regarded simply as a generic 2025-04-15 9:22 am
[!highlight] Highlight mapping, 2025-04-17 4:06 pm
[!highlight] Highlight d also for classifi- cation and optimization tasks. An overview of the proposed classification is shown in Fig. 1. The relatively limited option of using neural networks to merely aid a non-neural controller is further classified in the following section. Of the schemes in which the con 2025-04-17 4:06 pm
[!highlight] Highlight Of the schemes in which the controller itself is a neural network, the section “Train Based on U” classifies the alternative where control-input signals U are available for training the neural controller and the section “Train Based on Goal”classifies the option where the network devises the needed control strategy on its own, based on the ultimate control objective. C 2025-04-17 1:02 pm