RESUMEN
This paper proposes an active fault-tolerant control (FTC) approach based on the controller management and virtual actuator idea for linear discrete-time systems subject to unknown L2-bounded disturbances, input constraint, and time-varying additive actuator faults. The closed-loop faulty system, which includes the modified nominal controller, the fault and state estimator, and the virtual actuator, suppresses the effects of disturbances and faults, while ensuring input-constraint satisfaction. The management of the nominal controller is performed through an online optimization method - in the form of a standard quadratic programming problem - by manipulating the reference input and intervening in the nominal controller evolution. The proposed method proves the input-to-state stability (ISS) criterion of the overall closed-loop faulty system. The problem of minimizing the ultimate bound of the ISS criterion is formulated in terms of tractable linear matrix inequality (LMI) conditions that allow the fault and state estimation errors to converge to a small neighborhood of the origin. To illustrate the capabilities and advantages of the proposed control strategy, comparative simulation results are presented for a flexible joint robotic system, tracking control of a DC motor's angular velocity, and the multivariable VTOL aircraft.
RESUMEN
Understanding the pathogenesis of epilepsy including changes in synaptic pathways can improve our knowledge about epilepsy and development of new treatments. In this regard, data-driven models such as artificial neural networks, which are able to capture the effects of synaptic plasticity, can play an important role. This paper proposes long short term memory (LSTM) as the ideal architecture for modeling plasticity changes, and validates this proposal via experimental data. As a special class of recurrent neural networks (RNNs), LSTM is able to track information through time and control its flow via several gating mechanisms, which allow for maintaining the relevant and forgetting the irrelevant information. In our experiments, potentiation and depotentiation of motor circuit and perforant pathway as two forms of plasticity were respectively induced by kindled and kindled + transcranial magnetic stimulation of animal groups. In kindling, both procedure duration and gradual synaptic changes play critical roles. The stimulation of both groups continued for six days. Both after-discharge (AD) and seizure behavior as two biologically measurable effects of plasticity were recorded immediately post each stimulation. Three classes of artificial neural networks-LSTM, RNN, and feedforward neural network (FFNN)-were trained to predict AD and seizure behavior as indicators of plasticity during these six days. Results obtained from the collected data confirm the superiority of LSTM. For seizure behavior, the prediction accuracies achieved by these three models were 0.91 ± 0.01, 0.77 ± 0.02, and 0.59 ± 0.02%, respectively, and for AD, the prediction accuracies were 0.82 ± 0.01, 0.74 ± 0.08 and 0.42 ± 0.1, respectively.