• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.503-506
• /
• 2005

In this study, optimization design technique for control of solid-fluid coupled force (sloshing) using evolutionary method is suggested. Artificial neural networks(ANN) and genetic algorithm(GA) is employed as evolutionary optimization method. The ANN is used to analysis of the sloshing and the genetic algorithm is adopted as an optimization algorithm. In the creation of ANN learning data, the design of experiments is adopted to higher performance of the ANN learning using minimum learning data and ALE(Arbitrary Lagrangian Eulerian) numerical method is used to obtain the sloshing analysis results. The proposed optimization technique is applied to the minimization of sloshing of the water in the tank lorry with baffles under 2 second lane change.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.1
• /
• pp.42-50
• /
• 1997

Vector quantization has shown to be useful for compressing data related with a wide rnage of applications such as image processing, speech processing, and weather satellite. Neural networks of images this paper propses a efficient neural network learning algorithm, called learning count control algorithm based on the frquency sensitive learning algorithm. This algorithm can train a results more codewords can be assigned to the sensitive region of the human visual system and the quality of the reconstructed imate can be improved. We use a human visual systrem model that is a cascade of a nonlinear intensity mapping function and a modulation transfer function with a bandpass characteristic.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.2
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.95-98
• /
• 1996

Universal Learning Network(U.L.N.), which can model and control the large scale complicated systems naturally, consists of nonlinearly operated nodes and multi-branches that may have arbitrary time delays including zero or minus ones. Therefore, U.L.N. can be applied to many kinds of systems which are difficult to be expressed by ordinary first order difference equations with one sampling time delay. It has been already reported that learning algorithm of parameter variables in U.L.N. by forward and backward propagation is useful for modeling, managing and controlling of the large scale complicated systems such as industrial plants, economic, social and life phenomena. But, in the previous learning algorithm of U.L.N., time delays between the nodes were fixed, in other words, criterion function of U.L.N. was improved by adjusting only parameter variables. In this paper, a new learning algorithm is proposed, where not only parameter variables but also time delays between the nodes can be adjusted. Because time delays are integral numbers, adjustment of time delays can be carried out by a kind of random search procedure which executes intensified and diversified search in a single framework.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.721-736
• /
• 2021

For the mobile edge computing (MEC) system supporting dense network, a joint allocation algorithm of computing and communication resources based on reinforcement learning is proposed. The energy consumption of task execution is defined as the maximum energy consumption of each user's task execution in the system. Considering the constraints of task unloading, power allocation, transmission rate and calculation resource allocation, the problem of joint task unloading and resource allocation is modeled as a problem of maximum task execution energy consumption minimization. As a mixed integer nonlinear programming problem, it is difficult to be directly solve by traditional optimization methods. This paper uses reinforcement learning algorithm to solve this problem. Then, the Markov decision-making process and the theoretical basis of reinforcement learning are introduced to provide a theoretical basis for the algorithm simulation experiment. Based on the algorithm of reinforcement learning and joint allocation of communication resources, the joint optimization of data task unloading and power control strategy is carried out for each terminal device, and the local computing model and task unloading model are built. The simulation results show that the total task computation cost of the proposed algorithm is 5%-10% less than that of the two comparison algorithms under the same task input. At the same time, the total task computation cost of the proposed algorithm is more than 5% less than that of the two new comparison algorithms.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.6
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.

• Journal of Mechanical Science and Technology
• /
• v.19 no.2
• /
• pp.529-539
• /
• 2005

The development of a fast, accurate, and inexpensive position-controlled pneumatic actuator that may be applied to various practical positioning applications with various external loads is described in this paper. A novel modified pulse-width modulation (MPWM) valve pulsing algorithm allows on/off solenoid valves to be used in place of costly servo valves. A comparison between the system response of the standard PWM technique and that of the modified PWM technique shows that the performance of the proposed technique was significantly increased. A state-feedback controller with position, velocity and acceleration feedback was successfully implemented as a continuous controller. A switching algorithm for control parameters using a learning vector quantization neural network (LVQNN) has newly proposed, which classifies the external load of the pneumatic actuator. The effectiveness of this proposed control algorithm with smooth switching control has been demonstrated through experiments with various external loads.

• International Journal of Precision Engineering and Manufacturing
• /
• v.3 no.1
• /
• pp.33-42
• /
• 2002

Recently, various experiments to apply reinforcement learning method to the self-learning intelligent control of continuous dynamic system have been reported in the machine learning related research community. The reports have produced mixed results of some successes and some failures, and show that the success of reinforcement learning method in application to the intelligent control of continuous control systems depends on the ability to combine proper function approximation method with temporal difference methods such as Q-learning and value iteration. One of the difficulties in using function approximation method in connection with temporal difference method is the absence of guarantee for the convergence of the algorithm. This paper provides a proof of convergence of a particular function approximation method based on \"barycentric interpolator\" which is known to be computationally more efficient than multilinear interpolation .

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.339-344
• /
• 1993

A study for a lathe to machine workpieces with noncircular corss-sections is presented. The noncircular cutting is accomplished by controlling the radial tool position synchronized with the revolution angle of spindle. A learning control algorithm is suggested for the toll positioning, of which the control performances are analyzed and simulated on a numerical computer that the effectiveness of the control is convinced. The learning control is tested on a NC-lathe which shows successful results.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10b
• /
• pp.734-739
• /
• 1988

For the trajectory control of dynamic systems with unidentified parameters a second-order iterative learning control method is presented. In contrast to other known methods, the proposed learning control scheme can utilize more than one error history contained in the trajectories generated at prior iterations. A convergency proof is given and it is also shown that the convergence speed can be improved in compared to conventional methods. Examples are provided to show effectiveness of the algorithm, and, via simulation, it is demonstrated that the method yields a good performance even in the presence of distubances.