The global optimization procedures which simulate the natural evolution are known as Evolutionary Programming or Simulated Evolution. We utilize several concept from natural evolution and construct the global optimization procedure. The features of the proposed method are summarized as follows : 1) Introduction of the concept of temperature to the reproduction process 2) Ajustment of the temperature and metric ; in early stages the generated points can be moved drastically in order to escape from the local minimum and the convergence to the global solution in the final stage should be satisfied. 3) The reproduction and selection processes are simple. The numerical examples including Shekel function type problem are solved and the proposed method hardly misses the global solutions. The identification problem of a nonlinear system by neural networks is also solved successfully. The proposed method is very promising and can be applied to many types of real problems.
Self-tuning control strategies have been considered for systems with unknown parameters. The rapid progress of digital computer enables us to simulate complex and large-scale systems. Many control techniques have been proposed in order to improve the control performance for discrete-time control systems. However, since these control techniques are too complex, it is usually difficult to apply them to real plants and also difficult to understand a physical meaning of control parameters included in these control systems. On the other hand, PID control methods based on the classical control theory have been used widely for real control systems since they have simple control schemes. Therefore, it is necessary to consider control methods with PID control structure in the discrete-time systems. Many literatures with regard to auto-tuning and self-tuning PID control strategies have been reported up to now. But none of them gives us any results for discrete-time systems with time-delay which takes important roles for the stability of the control system and the good control performance. In this paper, we consider a self-tuning PID control algorithm for a system with a time delay element. This control method has four gains, which are proportional, integral, differential gains and a gain for modifying the reference signal. This method enables us to improve a tracking property for a reference signal in the transient state, and also to guarantee the global stability of the control system. Finally, the effectiveness of this control method is shown by applying the method to a temperature control system of a polystrene reactor. In order to show the effectiveness of this method.
A method of delay independent stabilization of a linear system is considered. The state of the system is measured through the output and therefore only a limited part of the state variables is directly measured. In this paper, the delay independent stability of considered systems are proven with the help of the known properties of certain delayed differential equations, without using Lyapunov functions or functionals. Delays contained in the system may vary with time and moreover all delay functions may be different from each other. If the system is observable and statisfies a few additional conditions, the same condition as for the case with all measurable state variables, that has already been published, is obtainable in our case.
Using artificial intelligence techniques, we developed a stepwise method to optimize signal timing parameters, such as splits and offsets, on an urban street. The method is separated into two processes, a training process and an optimization process. In the training process, we used two neural network models ; a multilayer model and Kohonen Feature Map model. The former model builds an input-output relationship between the signal timing parameters and the objective variable. The latter model improves the computational efficiency and the estimation precision. In the optimization process, to avoid the entrapment into a local minimum, we used two artificial intelligence methods ; the Cauchy machine and a genetic algorithm. We adjusted the timing parameters so as to minimize the total weighted sum of delay time and stop frequencies. We compared the solutions by both artificial intelligence methods with those by a conventional method and confirmed that the proposed methods are useful for establishing advanced traffic control systems in the future.