Monitoring and real-time simulation of power plants: a neural-based environment

Alippi, Cesare; Cori, A.; Piuri, Vincenzo; Pretolani, F.

doi:10.1109/imtc.1996.507288

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model approximation of systems having nonmeasurable states becomes particularly difficult when the neural model must approximate the process or the plant without having access to it on-line during its operational phase. This requirement is of particular interest in all those applications (e.g., what-if applications [12]) which require a model evolving independently from the plant.…”

Section: System Modeling With Noe-based Neural Topologiesmentioning

confidence: 99%

Neural modeling of dynamic systems with nonmeasurable state variables

Alippi

Piuri²

1999

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

The paper studies the ability possessed by recurrent neural networks to model dynamic systems when some relevant state variables are not measurable. Neural architectures based on virtual states-which naturally arise from a space state representation-are introduced and compared with the more traditional neural output error ones. Despite the evident potential model ability possessed by virtual state architectures we experimented that their performances strongly depend on the training efficiency. A novel validation criterion for neural output error architectures is suggested which allows to assess the neural network not only in terms of its approximation accuracy but also with respect to stability issues.

show abstract

Section: System Modeling With Noe-based Neural Topologiesmentioning

confidence: 99%