• Journal of Advanced Marine Engineering and Technology
• /
• v.23 no.2
• /
• pp.168-175
• /
• 1999

Unlike a general inverted pendulum system which is moved on the cart the proposed inverted pendulum system in this paper has an inverted pendulum which is moved on the two-degree-of-freedom parallelogram link. The dynamic equation of the pendulum system activated by the DD(Direct Drive)motor includes many nonlinear terms and has the high degree of freedoms. The problem is followed hat the exact mathmatical equations can not be analized by a general linear theory However the neural network trained by a simple learning method can control the dynamic system with hard nonlinearities. Learning procedure is the backpropagation algorithm with super-visory signal. The plant inputs obtained by the designed neural network in this paper can stabilize the pendu-lem and get the servo control. Experiment results have proce the effectiveness of the designed neural network controller.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.552-563
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network (WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges the advantages of the neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of the wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of a mobile robot via the gradient descent (GD) method. In addition, an approach that uses adaptive learning rates for training of the WFNN controller is driven via a Lyapunov stability analysis to guarantee fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control results of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2254-2259
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network(WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges advantages of neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of mobile robot using the gradient descent(GD) method. In addition, an approach that uses adaptive learning rates for the training of WFNN controller is driven via a Lyapunov stability analysis to guarantee the fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control performance of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• International Journal of Safety
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2002

It is important to control the high accurate position and force to prevent unexpected accidents by a robot manipulator. Direct-drive robots are suitable to the position and force control with high accuracy, but it is difficult to design a controller because of the system's nonlinearity and link-interactions. This paper is concerned with the study of the stabilization force control of direct-drive robots. The proposed algorithm is consists of the feedback controllers and the neural networks. After the completion of learning, the outputs of feedback controllers are nearly equal to zero, and the neural networks play an important role in the control system. Therefore, the optimum adjustment of control parameters is unnecessary. In other words, the proposed algorithm does not need any knowledge of the controlled system in advance. The effectiveness of the proposed algorithm is demonstrated by the experiment on the force control of a parallelogram link-type robot.

• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.3
• /
• pp.64-71
• /
• 1999

In this paper, two degree of freedom parallelogram link mechanism is used as DD(Direct-drive) robot mechanism. In parallelogram link mechanism, two motors being established in each base frame, the mass of motor itself is not loaded to anther motor; the number of links are increased, the mass of arm being lighter; with the estabilishment of link parameter, nonlinearity such as the centrifugal force disappears; at the same time anti-interference between motors can be realized. And to realize highy-accurate drive of parallelogram link DD robot manipulator, to improve the learning speed through the design of leaning control system using neural network, to raise adapting power to the varied work objects; the learning control algorithm is composed of neural network and feedback controller in this paper.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2687-2698
• /
• 2020

Most of the machine learning-based intrusion detection tools developed for Industrial Control Systems (ICS) are trained on network packet captures, and they rely on monitoring network layer traffic alone for intrusion detection. This approach produces weak intrusion detection systems, as ICS cyber-attacks have a real and significant impact on the process variables. A limited number of researchers consider integrating process measurements. However, in complex systems, process variable changes could result from different combinations of abnormal occurrences. This paper examines recent advances in intrusion detection algorithms, their limitations, challenges and the status of their application in critical infrastructures. We also introduce the discussion on the similarities and conflicts observed in the development of machine learning tools and techniques for fault diagnosis and cybersecurity in the protection of complex systems and the need to establish a clear difference between them. As a case study, we discuss special characteristics in nuclear power control systems and the factors that constraint the direct integration of security algorithms. Moreover, we discuss data reliability issues and present references and direct URL to recent open-source data repositories to aid researchers in developing data-driven ICS intrusion detection systems.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.173-176
• /
• 2003

In this paper, a DLC method is suggested for linear feedback systems to improve the tracking performance when the task of the system is repetitive. DLC can generate the desired control input directly from the previously teamed control inputs corresponding to other output trajectories. It is assumed that all outputs considered in this paper have some relations called "proportionality. " To show the validity and tracking performance of the proposed method, some simulation are performed for the tracking control of a linear system with a PI controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.474-474
• /
• 2000

This paper shows that a system with two-link arm can obtain hand reaching movement to a target object projected on a visual sensor by reinforcement learning using a layered neural network. The reinforcement signal, which is an only signal from the environment, is given to the system only when the hand reaches the target object. The neural network computes two joint torques from visual sensory signals, joint angles, and joint angular velocities considering the urn dynamics. It is known that the trajectory of the voluntary movement o( human hand reaching is almost straight, and the hand velocity changes like bell-shape. Although there are some exceptions, the properties of the trajectories obtained by the reinforcement learning are somewhat similar to the experimental result of the human hand reaching movement.

• School Mathematics
• /
• v.2 no.1
• /
• pp.165-181
• /
• 2000

The teaching-learning methods of figures using computers make loose the difficulties of geometry education from the viewpoint that the abstract figures can be visualized and that by means of this visualization the learning can be accomplished through the direct experience or control. In this thesis, we present a teaching-learning method of figures using Cabri II so that the learners establish their knowledge obtained through their search, investigation, supposition and they accomplish the positive transition to advanced 1earning. So the learners extend their ability of sensuous intuition to their ability of logical reasoning through their logical intuition.