Novel Adaptive Intelligent Control Scheme with Self-Evolving Genetic Fuzzy BELBIC for Enhancing the Seismic Resilience of Smart Building Structures

Abstract

The most crucial aspect of effective control of civil structures is control algorithms. Under severe earthquake disturbances, the modern semiactively controlled civil structures are highly nonlinear, uncertain, and complex nonstationary systems. These structures require real-time (online) robust control actions to maintain their serviceability and reliability characteristics dynamically toward changing conditions, which the controllers with rigid settings cannot adapt to. Advanced computational methods are needed to develop robust, optimized control to achieve this goal. Adaptive intelligent control algorithms have become a viable substitute for conventional model-based control algorithms. One of the most recent developments, known as the brain emotional learning-based intelligent controller (BELBIC), has caught the attention of scientists as a model-free adaptive control system. It possesses appealing capabilities for dealing with nonlinearities and uncertainties in control frameworks. This paper presents a novel tuning method for the optimum design of a standard brain emotional learning (BEL) controller for smart building structures. The principal contribution of the proposed control scheme is the development of an online self-evolving genetic fuzzy BELBIC (OSEF-BELBIC) that learns an inference (decision-making) system by itself. The proposed control scheme benefits offline and online tuning methods equally: the online self-attuned routines Takagi-Sugeno-Kang-fuzzy inference system and the offline fuzzy inference system tuned by the evolutionary genetic algorithm, also known as the floating fuzzy inference system. In this case, the central control unit BELBIC is based on sensory inputs and emotional cues (reward) signals. Besides, a design methodology is also introduced into the reward signal that combines the classical proportional-integral-derivative (PID) and evolutionary fuzzy logic controller. The proposed control methodology can be a promising model-free adaptive intelligent controller in terms of online and offline BELBIC tuning for the response of each floor in parallel to neutralize nonlinearities. The simulation confirms that the proposed controller, compared with the developed fixed and crisp valued offline tuned genetic PID-based BELBIC (GPID-BELBIC), has superior performance in demonstrating high learning abilities to avoid local minima in attenuating seismic responses of the building. The proposed online self-evolving fuzzy BELBIC control system has great potential to enhance seismic resiliency in smart buildings and other structures. Advanced control techniques like fuzzy logic, genetic algorithms, and brain emotional learning are integrated into the current system to make it adaptive in real time with respect to changing environmental conditions, hence mitigating the effects of earthquakes on buildings. Extending this approach to bigger and more complicated structures like high-rise buildings or bridges will be possible by enhancing their resistance capability against dynamic forces caused by earthquakes or strong winds. The methodology’s flexibility allows for its application in different industries, robotics, machinery control, and flying-craft systems whose operation must correspond with the demands imposed by unpredictable or nonlinear conditions. Such fields will indeed find this capability for real-time, continuous tuning of control parameters that optimizes performance is highly effective for adaptive, power-efficient, low-power-consuming control scenarios. The study forms the base for more robust autonomous systems to enhance safety and improve the performance of different kinds of engineered structures in real-world applications.