Hybrid system identification using a mixture of NARX experts with LASSO-based feature selection

Brusaferri, Alessandro; Matteucci, Matteo; Portolani, Pietro; Spinelli, Stefano; Vitali, Andrea

doi:10.1109/codit49905.2020.9263962

Cited by 2 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed method, we will use different ANN classes [22,23] to design a hybrid real-time system with continuous and discrete components. We use a typical design of a neural network, in which we define training, testing, and validation (Figure 10).…”

Section: Modeling Methodsmentioning

confidence: 99%

Artificial Neuron-based Model for a Hybrid Real-Time System: Induction Motor Case Study

Capel¹

2022

Preprint

View full text Add to dashboard Cite

A correct system design can be systematically obtained from a specification model of a real-time system that integrates hybrid measurements in a realistic industrial environment, this has been carried out through complete Matlab / Simulink / Stateflow models. However, there is a widespread interest in carrying out that modeling by resorting to Machine Learning models, which can be understood as Automated Machine Learning for Real-time systems that present some degree of hybridization. An induction motor controller which must be able to maintain a constant air flow through a filter is one of these systems and it is discussed in the paper as a study case of closed-loop control system. The article discusses a practical application of ML methods that demonstrates how to replace such closed loop in industrial control systems with a Simulink block generated from neural networks to show how the proposed procedure can be applied to derive complete hybrid system designs with artificial neural networks (ANN). In the proposed ANN-based method to design a real-time hybrid system with continuous and discrete components, we use a typical design of a neural network, in which we define the usual phases: training, validation, and testing. The generated output of the model is made up of reference variables values of the cyber-physical system, which represent the functional and dynamic aspects of model. They are used to feed Simulink/Stateflow blocks in the real target system.

show abstract

Section: Modeling Methodsmentioning

confidence: 99%