Neural Adaptive PID and Neural Indirect Adaptive Control Switch Controller for Nonlinear MIMO Systems

This paper proposes an adaptive switch controller (ASC) design for the nonlinear multi-input multi-output system (MIMO). In fact, the proposed method is an online switch between the neural network adaptive PID (APID) controller and the neural network indirect adaptive controller (IAC). According to the design of the neural network IAC scheme, the adaptation law has been developed by the gradient descent (GD) method. However, the adaptive PID controller is built based on the neural network combining the PID control and explicit neural structure. The strategy of training consists of online tuning of the neural controller weights using the backpropagation algorithm to select the suitable combination of PID gains such that the error between the reference signal and the actual system output converges to zero. The stability and tracking performance of the neural network ASC, the neural network APID, and the neural network IAC are analyzed and evaluated by the Lyapunov function. Then, the controller results are compared between APID, IAC, and ASC, in this paper, applying to a nonlinear system. From simulations, the proposed adaptive switch controller has better effects both on response time and on tracking performance with smallest MSE.

Adaptive switch to sexually dimorphic movements by partner-seeking termites

How should females and males move to search for partners whose exact location is unknown? Theory predicts that the answer depends on what they know about where targets can be found, raising the question of how actual animals update their mate search patterns to increase encounter probability when conditions change. Here, we show that termites adaptively alternate between sexually monomorphic and dimorphic movements during mate search. When the location of potential mates was completely unpredictable, both sexes moved in straight lines to explore widely. In contrast, when the stray partner was at least nearby, males moved while females paused. Data-based simulations confirmed that these movements increase the rate of successful encounters. The context-dependent switch of search modes is a key to enhance random encounters.

Adaptive Switch Timing Control Law for Optimal Displacement Reduction via SSDI

In the conventional implementation of synchronized switch damping (SSD), the switches are intended to occur at every displacement extrema. However, recent work reveals that switching at the vibration peaks is only optimal for displacement reduction under resonance excitation. In general, the optimal switch timing is dependent on the excitation frequency along with the electromechanical coupling and modal damping of the structure. This work seeks to develop a control framework that searches through the possible switch times to find the optimal switch time for synchronized switch damping on an inductor (SSDI) under steady state excitation. The control law does not need any knowledge of the system, only requiring the voltage of the piezo actuator to develop a displacement estimate that is minimized by adjusting the switch timing. Furthermore, the controller naturally senses changes in the excitation and adapts the switch timing to best reduce displacement under the new excitation.