Learning event‐triggered control based on evolving data‐driven fuzzy granular models

Cordovil, Luiz A. Q.; Coutinho, Pedro Henrique Silva; Bessa, Iury; Peixoto, Márcia L. C.; Palhares, Reinaldo M.

doi:10.1002/rnc.6024

Cited by 15 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is computed as described in (Cordovil et al, 2022). The total EEFIG performance index is the sum of the data sample contribution index of each granule:…”

Section: Evolving Ellipsoidal Fuzzy Information Granulesmentioning

confidence: 99%

“…As described in (Cordovil et al, 2020;Cordovil et al, 2022), the consequent parameters Θ k are estimated based on Re-cursive Least Squares (RLS) methods. In particular, here we use the Sliding-windowed Fuzzily Weighted Recursive Least Squares (SFWRLS) where the weights are the membership degrees and the data window contains the last φ samples:…”

Section: Eefig-based Degradation Modelling and Rul Estimationmentioning

confidence: 99%

“…The approach in this paper considers a data-based evolving fuzzy model that uses two classes of input features: an interpretable feature as a premise variable and a RUL predictionfriendly counterpart in the autoregressive consequent of the fuzzy model. In particular, the degradation representation is based on the Evolving Ellipsoidal Fuzzy Information Granules (EEFIG), whose has already been applied for clustering (Cordovil, Coutinho, Bessa, D'Angelo, & Palhares, 2020), fault diagnosis (Cordovil et al, 2020), and leaning-based control (Cordovil, Coutinho, Bessa, Peixoto, & Palhares, 2022) approaches. The merit of this methodology over others is that it provides a platform with a dual function mode: (1) Providing a good RUL prediction in conjunction with (2) classifying the different stages of degradation, as shown in Figure 1, enabling interpretability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data-driven Prognostics based on Evolving Fuzzy Degradation Models for Power Semiconductor Devices

et al. 2022

Self Cite

View full text Add to dashboard Cite

The increasing application of power converter systems based on semiconductor devices such as Insulated-Gate Bipolar Transistors (IGBTs) has motivated the investigation of strategies for their prognostics and health management. However, physicsbased degradation modelling for semiconductors is usually complex and depends on uncertain parameters, which motivates the use of data-driven approaches. This paper addresses the problem of data-driven prognostics of IGBTs based on evolving fuzzy models learned from degradation data streams. The model depends on two classes of degradation features: one group of features that are very sensitive to the degradation stages is used as a premise variable of the fuzzy model, and another group that provides good trendability and monotonicity is used for the auto-regressive consequent of the fuzzy model for degradation prediction. This strategy allows obtaining interpretable degradation models, which are improved when more degradation data is obtained from the Unit Under Test (UUT) in real time. Furthermore, the fuzzy-based Remaining Useful Life (RUL) prediction is equipped with an uncertainty quantification mechanism to better aid decisionmakers. The proposed approach is then used for the RUL prediction considering an accelerated aging IGBT dataset from the NASA Ames Research Center.

show abstract

“…is computed as described in (Cordovil et al, 2022). The total EEFIG performance index is the sum of the data sample contribution index of each granule:…”

Section: Evolving Ellipsoidal Fuzzy Information Granulesmentioning

confidence: 99%

Section: Eefig-based Degradation Modelling and Rul Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven Prognostics based on Evolving Fuzzy Degradation Models for Power Semiconductor Devices

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to conventional time-driven control systems, ET mechanisms only update the control signals when a predetermined triggering condition is broken. [27][28][29][30] In recent years, significant advances have been made in both theoretical studies and practical application in the area of ET optimal control problem. 31,32 For CT linear system, a new model-free event-triggered optimal control algorithm was proposed, and a triggering mechanism with guaranteed optimal performance was designed.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning‐based event‐triggered optimal control for unknown nonlinear systems with input delay

Chen,

Sun,

Gao

et al. 2024

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

The optimal control issue of discrete‐time nonlinear unknown systems with time‐delay control input is the focus of this work. In order to reduce communication costs, a reinforcement learning‐based event‐triggered controller is proposed. By applying the proposed control method, closed‐loop system's asymptotic stability is demonstrated, and a maximum upper bound for the infinite‐horizon performance index can be calculated beforehand. The event‐triggered condition requires the next time state information. In an effort to forecast the next state and achieve optimal control, three neural networks (NNs) are introduced and used to approximate system state, value function, and optimal control. Additionally, a M NN is utilized to cope with the time‐delay term of control input. Moreover, taking the estimation errors of NNs into account, the uniformly ultimately boundedness of state and NNs weight estimation errors can be guaranteed. Ultimately, the validity of proposed approach is illustrated by simulations.

show abstract

“…In this regard, evolving systems are effective tools for obtaining incremental models which update their structure and adapt their parameters through autonomous learning from data streams (Angelov, 2012). For this reason, evolving systems have been effectively applied for dealing with complex and time-varying dynamics aiding to solve different problems, such as fault diagnosis (Shah & Wang, 2021), classification (Soares, Angelov, & Gu, 2020), time-series prediction and forecasting (Severiano, de Lima e Silva, Cohen, & Guimarães, 2021), system identification ( Škrjanc, 2021), and learning-based control (Cordovil, Coutinho, Bessa, Peixoto, & Palhares, 2022).…”

Section: Introductionmentioning

confidence: 99%

State of Health and Lifetime Prediction of Lithium-ion Batteries Using Self-learning Incremental Models

Camargos

Angelov²

2022

PHME_CONF

View full text Add to dashboard Cite

Lithium-ion batteries are key energy storage elements in the context of environmental-aware energy systems representing a crucial technology to achieve the goal of zero carbon emission. Therefore, its conditions must be monitored to guarantee the safe and reliable operation of the systems that use these components. Furthermore, lithium-ion batteries’ prognostics and health management policies must cope with the nonlinear and time-varying nature of the complex electrochemical dynamics of battery degradation. This paper proposes an incremental-learning-based algorithm to estimate the State of Health (SoH) and the Remaining Useful Life (RUL) of lithium-ion batteries based on measurement data streams. For this purpose, a two-layer framework is proposed based on incremental modeling of the SoH. In the first layer, a set of representative features are extracted from voltage and current data of partial charging and discharging cycles; these features are then used to train the proposed model in a recursive procedure to estimate the battery’s SoH. The second layer uses the capacity data for incremental learning of an Autoregressive (AR) model for the SoH, which will be used to propagate the battery’s degradation through time to make the RUL prediction. The proposed method was applied to two datasets for experimental evaluation, one from CALCE and another from NASA. The proposed framework was able to estimate the SoH of 8 different lithium-ion cells with an average percentage error below 1.5% for all scenarios, while the lifetime model predicted the cell’s RUL with a maximum average error of 25%.

show abstract

Learning event‐triggered control based on evolving data‐driven fuzzy granular models

Cited by 15 publications

References 42 publications

Data-driven Prognostics based on Evolving Fuzzy Degradation Models for Power Semiconductor Devices

Data-driven Prognostics based on Evolving Fuzzy Degradation Models for Power Semiconductor Devices

Reinforcement learning‐based event‐triggered optimal control for unknown nonlinear systems with input delay

State of Health and Lifetime Prediction of Lithium-ion Batteries Using Self-learning Incremental Models

Contact Info

Product

Resources

About