Genetic Algorithms in Intelligent Control Systems Design

This paper presents a rigorous mathematical development for the design of robust intelligent type-2 fuzzy control systems with regards to the disturbance rejection problem. The majority of the papers in the literature uses only type-1 fuzzy systems for the modeling of both plant ant controller. In the control structure presented in this paper, we use type-2 fuzzy systems, which are more generalized than their type-1 counterparts and particularly known for handling uncertainties. This work extends and generalizes the previous results for the design of robust intelligent control systems. The final robust criteria are given based on linear matrix inequalities (LMIs), and two examples are provided to demonstrate the developed methodologies. The simulation results also show the potential of type-2 fuzzy controllers in improving robustness compared to type-1. The mathematically-sound general framework proposed in this paper provides a systematic tool for the design of robust intelligent controllers, and hence it is expected to widen their applications.

This report presents a generalized design strategy of intelligent robust control systems based on quantum/soft computing technologies that enhance robustness of fuzzy controllers by supplying a self-organizing capability. It is demonstrated that fuzzy controllers prepared to maintain control object in the prescribed conditions are often fail to control when such a conditions are dramatically changed. We propose the solution of such kind of problems by introducing a generalization of strategies in fuzzy inference from a set of pre-defined fuzzy controllers by new quantum fuzzy inference based systems (prototype of intelligent system of systems engineering). We stress our attention on the robustness features of intelligent control systems.

This study delves into the dynamic coupling and intelligent control of offshore floating wind power platforms, leveraging a synergistic approach of field measurements and numerical simulations. Data were sourced from an operational platform in the North Sea and augmented with high-fidelity computational models developed using ANSYS AQWA. The research methodology encompassed data preprocessing, dynamic coupling analysis, intelligent control system design, and performance evaluation. The interaction between environmental forces (wind, waves, and currents) and the platform’s response (heave, pitch, and roll) was scrutinized through a coupled dynamic model. An intelligent control system, integrating a Proportional-Integral-Derivative (PID) controller with a fuzzy logic system, was devised to mitigate the platform’s motion. Performance metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Stability Index (SI), revealed substantial enhancements with the intelligent control system, achieving reductions in RMSE and MAE by up to 50% and an increase in SI by up to 25%. These findings highlight the efficacy of the proposed control strategy in bolstering stability and diminishing the dynamic response of offshore floating wind power platforms under diverse environmental conditions.

In this paper, we propose a new generalized design methodology of intelligent robust fuzzy control systems based on quantum genetic algorithm (QGA) called quantum fuzzy model that enhance robustness of fuzzy logic controllers. The QGA is adopted because of their capabilities of directed random search for global optimization to find the parameters of the shape and width of membership functions and rule set of the FLC to obtain the optimal fuzzy controller simultaneously. We test the optimal FLC obtained by the quantum computing applied on the control of dynamic balance and motion of cart-pole balancing system. We compare the proposed technique with existing mamdani fuzzy logic controller which is designed through conventional genetic algorithm. Simulation results reveal that QGA performs better than conventional GA in terms of running speed and optimizing capability.

With the worsening of the global environment and the strengthening of people's awareness of environmental protection, the air pollution caused by the exhaust emissions of marine diesel engines has attracted extensive attention from the international community. Because the exhaust post-treatment technology does not need to be reformed for diesel engine, and the quality requirement of fuel is relatively low, domestic and foreign research and development institutions all attach great importance to the research of exhaust post-treatment technology. By analyzing the mechanism and main chemical reaction of SCR reaction, the overall design scheme of marine diesel engine exhaust intelligent emission reduction control system was completed in order to reduce the nitrogen oxides and solid particles in the exhaust of marine diesel engine. According to TierIII emission regulation and marine diesel engine exhaust, the hardware structure design and model selection of marine diesel engine exhaust intelligent emission control system are completed. In order to ensure that the emission of the control system can meet the requirements of nitrogen oxide conversion rate and ammonia gas escape quantity at the same time, the corresponding model prediction algorithm is designed in this paper. Through the analysis of experimental results, it is proved that the control system established in this paper can well meet the emission requirements of TierIII regulations. The research content of this paper can be applied in the field of shipping to meet the requirements of TierIII regulations and prepare for more stringent emission regulations.

This paper developed a fuzzy logic controller with a genetic algorithm control system for sensor based pipeline robot navigation in pipe environment. The fuzzy controller creates initial membership functions and fuzzy logic rules. the genetic algorithm, which automatically designs a fuzzy logic controller by modifying the position of controller membership functions and the commands given to the pipeline robot, optimizes the fuzzy controller. This GA-fuzzy system is used to control the mobile pipeline robot, which is equipped with an array of ultrasonic sensors to acquire the distance between the pipeline robot and obstacle. On the basis of this system, a strategy for combining local behavior control with global behavior control planning was proposed in this paper. Finally a pipeline robot runs in simulation environment. The experimental results show that appropriate control mechanisms of the fuzzy controller are obtained by evolution. The controller has evolved well enough to smoothly drive the pipeline robot in different pipe environment.

As road traffic develops, energy-saving and efficient street lights have become a key research field for relevant professionals. To reduce street lights energy consumption, a fireworks algorithm is used to optimize the membership function parameters of fuzzy control and the initial parameters of PI control. A fireworks algorithm improved adaptive fuzzy PI solar LED street light control system is designed. The results showed that in the calculation of Root-mean-square deviation and Mean absolute error, the Root-mean-square deviation of the adaptive fuzzy PI control system improved by the fireworks algorithm was 0.213, 0.258, 0.243, 0.220, and the Mean absolute error was 0.143, 0.152, 0.154, 0.139, respectively, which proved that the prediction accuracy was high and the stability was good. In the calculation of the 1-day power consumption of the solar LED intelligent control system, the average power consumption of the designed solar LED intelligent control system was about 2000W, which was 25.9%, 47.4%, and 42.9% lower than the other three control methods, respectively. This proves that its energy consumption is low, and its heat generation is low, and the battery service life is long. The research and design of an adaptive fuzzy PI control solar LED street light intelligent control system has good performance, which can effectively achieve intelligent management and energy conservation and emission reduction in smart cities.

In recent years, the quest has been focused on energy efficient building design. To achieve this in terms of high efficiency air conditioning schemes for hot climate cooling, the combination of variable refrigerant volume (VRV) with variable air volume (VAV) systems have become popular. In this paper, attention is focused on achieving good thermal comfort and indoor air quality (IAQ) combined with energy savings by using multi-zone VAV air conditioning (A/C) that incorporates a genetic based fuzzy logic controller (FLC). Experimental analysis based on a combined demand controlled ventilation (DCV) with economizer cycle (EC) was performed on an inverter driven multi-zone direct expansion (DX) VAV A/C system integrated with a fuzzy logic controller and optimized by a genetic algorithm (GA). The opening of the VAV box damper was controlled using the fuzzy logic controller. Based on the test results, the proposed fuzzy logic operated system maintained supply air temperature close to 13°C and an occupant zone at a consistent temperature of around 24 °C. In DCV mode, the concentration of CO2 was maintained between 950 ppm and 1040 ppm while, when the system was operated under a combined DCV-EC ventilation scheme, the CO2 concentration was maintained at between 350 ppm and 970 ppm. The experimental results suggested that CO2 concentration obtained experimentally was well within the permissible limit for the varying load conditions. Under the combined DCV-EC mode of ventilation, using a fuzzy-genetic algorithm, the maximum power obtained for the supply air fan and variable speed compressor was 415 W and 3.4 kW respectively. The compressor was totally turned OFF during the economizer cycle thus contributing to total power savings. The energy savings potential of the proposed fuzzy controlled multi-zone DX VAV A/C system yielded 70% and 89% under DCV and combined DCV economizer cycle ventilation modes respectively when compared with a constant air volume (CAV) A/C system operated under the DCV technique. The test results suggested that it was feasible for this fuzzy control methodology, integrated with the developed genetic algorithm, to provide a proper control of IAQ, thermal comfort and energy conservation.

In this paper mathematical models of Mamdani type fuzzy PI or PD controllers via Center of Gravity (CoG) defuzzification are obtained. These controllers are called the simplest fuzzy PI or PD controllers as minimal number of fuzzy sets (two fuzzy sets on each of the two-input variables and three fuzzy sets on the output variable) are employed. The basic components of these models are L-type and Y-type membership functions on each input variable, trapezoidal or triangular membership functions on output variable, minimum / algebraic product t-norm, maximum OR operator, three linear fuzzy control rules, minimum / algebraic product inference and CoG defuzzification. Mathematical models of fuzzy controller via CoG defuzzification were not reported in the literature and are therefore presented for the first time in this paper.

Although fuzzy logic controllers and expert systems have been successfully applied in many complex industrial processes, they experience a deficiency in knowledge acquisition and rely to a great extent on empirical and heuristic knowledge which, in many cases, cannot be objectively elicited. Among the problems to be resolved in fuzzy controller design are the determination of the linguistic state space, definition of the membership functions of each linguistic term and the derivation of the control rules. Some of these problems can be solved by application of machine learning. First, it is desirable to simplify and automate the specification of linguistic rules. Secondly, it is also desirable that modification of control rules is possible in order to cope with previously unknown or changes in process dynamics. Machine learning methods have, in recent years, emerged from the use of learning algorithms modelled on natural and biological systems. These methods attempt to abstract the advanced mechanisms of learning exhibited by such systems, which can consequently be applied to intelligent control. One of these new algorithms is the genetic algorithm which is modelled on the processes of natural evolution. The paper develops the application of genetic algorithm techniques for fuzzy controller design. Genetic algorithms are used to automate and introduce objective criteria in defining fuzzy controller parameters.

The nuclear steam generator is a nonminimum-phase system, which is caused by the swell and shrink effects. Since its inverse system has unstable dynamics, it is difficult to train the fuzzy controller via the conventional backpropagation of the system output errors. In this paper, a genetic algorithm is applied for the simultaneous design of membership functions and rule sets for a fuzzy control method for a steam generator water level. The genetic fuzzy controller for the steam generator is a fuzzy logic controller which is tuned offline by the genetic algorithm using the water level, feedwater flowrate, and steam flowrate signals of the steam generator. The symmetric Gaussian membership functions based on the flowrate and water level errors are applied. The proposed genetic fuzzy controller has a generalized and simplified rule base. The same genetic algorithm that is used to optimize the genetic fuzzy controller tunes a conventional proportional-integral (P-I) controller, and the performance of two controllers is compared. The genetic fuzzy controller shows good response that its swell and shrink phenomena are smaller and its response is faster than those of a well-tuned P-I controller are.

Fuzzy logic controllers are designed for spacecraft hovering flight in a binary asteroid system. The binary asteroid system is modeled as an ellipsoid-sphere system where the spherical harmonics method is adopted to represent the gravitational field of the asteroids. The method to design the fuzzy logic controllers is introduced in detail. Hovering flight about the inner collinear equilibrium point L 1 of binary asteroid Didymos is numerically presented. Detailed steps on roughly estimating the scaling gains of fuzzy logic controllers are also summarized. Numerical simulations are performed to show the effectiveness of the proposed method. Moreover, the aforementioned fuzzy logic controllers can be used for both continuous and impulsive thrusters. The fuzzy controllers with continuous thrust, the fuzzy controllers with fixed thrust, and the other two kinds of sliding-mode controllers are optimized in the same way and compared in the same simulation environment together, to show tremendous advantages of fuzzy logic controllers and continuous thrusters on both control performance and propellant consumption.

The integration of fuzzy logic controllers in automatic vehicle navigation systems represents a significant advancement in intelligent transportation systems, especially when paired with Internet of Things (IoT) functionalities and optimized through genetic algorithms. This innovative fusion harnesses the precision of fuzzy logic, the connectivity of IoT, and the optimization capabilities of genetic algorithms to transform automatic vehicle navigation. Fuzzy logic controllers excel in managing uncertainty and imprecision, providing decision-making capabilities akin to human reasoning. By simultaneously assessing multiple inputs and determining actions based on degrees of truth, fuzzy logic enables safe and efficient navigation in dynamic driving environments with fluctuating variables like obstacle proximity and traffic flow. IoT integration enhances navigation systems by enabling real-time data collection and sharing among vehicles and infrastructure, fostering adaptive route planning and improving the overall navigation experience. Genetic algorithms further optimize system performance by iteratively adjusting fuzzy logic controller parameters, ensuring efficient decision-making tailored to specific performance criteria such as travel time and fuel consumption. This collaborative integration of fuzzy logic controllers, IoT, and genetic algorithms offers a holistic solution to the challenges of automatic vehicle navigation, enhancing safety, efficiency, and adaptability in complex driving scenarios. Beyond enhancing individual vehicle performance, this approach contributes to overall transportation system efficiency and safety by mitigating traffic congestion, reducing emissions, and minimizing accidents. Consequently, these integrated systems address crucial societal challenges and pave the way for widespread adoption of autonomous vehicles in the future.

10 - Robust design of intelligent control systems to mitigate earthquake-induced vibrations under uncertain conditions

The article discusses the information technology of a robust intelligent control system design based on quantum fuzzy inference. The application of the developed design methodology is based on the quantum self-organization of fuzzy controller’s imperfect knowledge bases and leads to an increase in the robustness of intelligent control systems in unpredicted situations. The results of mathematical modeling and physical experiment are compared using the example of an autonomous robot in the form of a “cart – pole” system. Experimental confirmation of the synergetic effect existence in the robust self-organized fuzzy controller formation from a finite number of non-robust fuzzy controllers in on-line has been demonstrated. The resulting effect is based on the existence of hidden quantum information extracted from the classical states of the controller’s time-varying gain coefficients processes schedule. The derived law of quantum information thermodynamics establishes the possibility to forming a thermodynamic control force due to the extracted amount of hidden quantum information and performing additional useful work, that guarantees the achievement of the control goal based on increasing the robustness of a self-organized quantum controller. At the same time, the amount of useful work performed by the control object (at the macro level) exceeds the amount of work spent (at the micro level) by a quantum self-organized controller to extract the quantum information hidden in the responses of imperfect knowledge bases without violating the second thermodynamics information law for open quantum systems with information exchange of entangled super correlated states. A concrete example of an autonomous robot is given, demonstrating the existence of a quantum self-organization synergetic effect to imperfect knowledge bases.