ResNet and PolyNet Based Identification and (MPC) Control of Dynamical Systems: A Promising Way

Many engineering systems can be described by using differential models whose solutions, generally obtained after discretization, can exhibit a noticeable deviation with respect to the response of the physical systems that those models are expected to represent. In those circumstances, one possibility consists of enriching the model in order to reproduce the physical system behavior. The present paper considers a dynamical system and proposes enriching the model solution by learning the dynamical model of the gap between the system response and the model-based prediction while ensuring that the time integration of the learned model remains stable. The proposed methodology was applied in the simulation of the top-oil temperature evolution of a power transformer, for which experimental data provided by the RTE, the French electricity transmission system operator, were used to construct the model enrichment with the hybrid rationale, ensuring more accurate predictions.

show abstract

“…Residual neural networks (ResNets) [29][30][31] aim at emulating the backward integration of a dynamical system. For the dynamical system…”

Section: Residual Netsmentioning

confidence: 99%

Learning Data-Driven Stable Corrections of Dynamical Systems—Application to the Simulation of the Top-Oil Temperature Evolution of a Power Transformer

Ghnatios

Kestelyn

Denis³

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…Finally, the neural network used in this work is residual network (ResNet) [43]. The ResNet network has been assessed to improve the generalizability of the network compared to more conventional neural networks [44,45]. In this work, the state, input, and non-controllable inputs from Eq.…”

Section: Second Level: Dynamic Optimization Via Multi Energy-mpcmentioning

confidence: 99%

“…Table 4 shows the hyper-parameters ranges considered in this work, which were optimized during training using the BlackBoxOptim package [57], according to the methodology proposed in [44]. The hyperparameters selected by the meta-heuristic algorithm can be seen in Table 4.…”

Section: Neural Network Model Identificationmentioning

confidence: 99%

Multi-flow optimization of a greenhouse system: A hierarchical control approach

Blaud,

Haurant,

Chevrel

et al. 2023

Applied Energy

View full text Add to dashboard Cite

“…Residual Neural Networks (ResNet) [2,17,18] aim at emulating the backward integration of a dynamical system. When we consider the dynamical system…”

Section: Residual Netsmentioning

confidence: 99%

Learning Data-Driven Stable Corrections of Dynamical Systems. Application to the Simulation of the Top-Oil Temperature Evolution of a Power Transformer

Ghnatios¹,

Kestelyn²,

Denis³

et al. 2023

Preprint

View full text Add to dashboard Cite

Many engineering systems are described by using differential models whose solutions, generally obtained after discretization, can exhibit a noticeable deviation with respect to the response of the physical systems that those models are expected to represent. In those circumstances one possibility consists of enriching the model in order to reproduce the physical system behavior. The present paper considers a dynamical system, and proposes enriching the model solution by learning the dynamical model of the gap between the system response and the model-based prediction, while ensuring that the time integration of the learnt model remains stable. The proposed methodology is applied on the simulation of the top-oil temperature evolution of a power transformer, whose data is provided by RTE, the French Electricity Transmission System Operator.

show abstract

ResNet and PolyNet Based Identification and (MPC) Control of Dynamical Systems: A Promising Way

Cited by 5 publications

References 75 publications

Learning Data-Driven Stable Corrections of Dynamical Systems—Application to the Simulation of the Top-Oil Temperature Evolution of a Power Transformer

Learning Data-Driven Stable Corrections of Dynamical Systems—Application to the Simulation of the Top-Oil Temperature Evolution of a Power Transformer

Multi-flow optimization of a greenhouse system: A hierarchical control approach

Learning Data-Driven Stable Corrections of Dynamical Systems. Application to the Simulation of the Top-Oil Temperature Evolution of a Power Transformer

Contact Info

Product

Resources

About