• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.334-341
• /
• 2003

In this paper, we proposed a recurrent time delayed neural network(RTDNN) controller which compensate a output of neural network controller. Even if learn by neural network controller, it can occur an bad results from disturbance or load variations. So in order to adjust above case, we used the fuzzy compensator to get an expected results. And the weight of main neural network can be changed with the result of learning a inverse model neural network of plant, so a expected dynamic characteristics of plant can be got. As the results of simulation through the second order plant, we confirmed that the proposed recurrent time delayed neural network controller get a good response compare with a time delayed neural network(TDU) controller. We implemented the controller using the DSP processor and applied in a hydraulic servo system. And then we observed an experimental results.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.277-282
• /
• 2006

It is well known that Kalman filtering is an optimal real-time data fusion method for GPS/INS integration. However, it has some limitations in terms of stability, adaptability and observability. A Kalman filter can perform optimally only when its dynamic model is correctly defined and the noise statistics for the measurement and process are completely known. It is found that estimated Kalman filter states could be influenced by several factors, including vehicle dynamic variations, filter tuning results, and environment changes, etc., which are difficult to model. Neural networks can map input-output relationships without apriori knowledge about them; hence a proper designed neural network is capable of learning and extracting these complex relationships with enough training. This paper presents a GPS/INS integrated system that combines Kalman filtering and neural network algorithms to improve navigation solutions during GPS outages. An Extended Kalman filter estimates INS measurement errors, plus position, velocity and attitude errors etc. Kalman filter states, and gives precise navigation solutions while GPS signals are available. At the same time, a multi-layer neural network is trained to map the vehicle dynamics with corresponding Kalman filter states, at the same rate of measurement update. After the output of the neural network meets a similarity threshold, it can be used to correct INS measurements when no GPS measurements are available. Selecting suitable inputs and outputs of the neural network is critical for this hybrid method. Detailed analysis unveils that some Kalman filter states are highly correlated with vehicle dynamic variations. The filter states that heavily impact system navigation solutions are selected as the neural network outputs. The principle of this hybrid method and the neural network design are presented. Field test data are processed to evaluate the performance of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.865-870
• /
• 2003

A motion controller has been used variously in industry such as semiconductor manufacture equipment, industrial robot, assembly/conveyor line applications and CNC equipment. There are several types of controller in motion control. One of these is a PC-based motion controller such as PCI or ISA, and another is stand-alone motion controller. The PC bus-based motion controller is popular because of improving bus architectures and GUI (Graphic User Interface) that offer convenience of use to user. There are some problems in this. The PC bus-based solution allows for only one of the form factors, so it has a poor flexibility. The overall system package size is bigger than other motion control system. And also, additional axes of control require additional slot, however the number of slots is limited. Furthermore, unwieldy and many wirings come to connect plants or I/O. The stand-alone motion controller has also this limit of axes of control and wiring problems. To resolve these problems, controller must have capability of operating as stand-alone devices that resides outside the computer and it needs network capability to communicate to each motion device. In this paper, a network-based stand-alone motion system is proposed. This system integrates PC and motion controller into one stand-alone motion system, and uses CAN (Controller Area Network) as network protocol. Single board computer that is type of 3.5" FDD form factor is used to reduce the system size and cost. It works with Windows XP Embedded as operating system. This motion system operates by itself or serves as master motion controller that communicates to slave motion controller. The Slave motion controllers can easily connect to master motion system through CAN-network.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.1
• /
• pp.25-38
• /
• 2017

Many security threats are occurring around the world due to the characteristics of industrial control systems that can cause serious damage in the event of a security incident including major national infrastructure. Therefore, the industrial control system network traffic should be analyzed so that it can identify the attack in advance or perform incident response after the accident. In this paper, we research the visualization technique as network forensics to enable reasonable suspicion of all possible attacks on DNP3 control system protocol, and define normal action based rules and derive visualization requirements. As a result, we developed a visualization tool that can detect sudden network traffic changes such as DDoS and attacks that contain anormal behavior from captured packet files on industrial control system network. The suspicious behavior in the industrial control system network can be found using visualization tool with Digital Bond packet.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.632-637
• /
• 2019

Recent researches on autonomous driving of vehicles are becoming very active, and it is a trend to assist safe driving and improve driver's convenience. Autonomous vehicles are required to combine artificial intelligence, image recognition capability, and Internet communication between objects. Because mobile telecommunication networks have limitations in their processing, they can be easily implemented and scale using an easily expandable Wi-Fi network. We propose a wireless design method to construct such a vehicle control network. We propose the arrangement of AP and the software configuration method to minimize loss of data transmission / reception of mobile terminal. Through the design of the proposed network system, the communication performance of the moving vehicle can be dramatically increased. We also verify the packet structure of GPS, video, voice, and data communication that can be used for the vehicle through experiments on the movement of various terminal devices. This wireless design technology can be extended to various general purpose wireless networks such as 2.4GHz, 5GHz and 10GHz Wi-Fi. It is also possible to link wireless intelligent road network with autonomous driving.

• Journal of the Korean Institute of Educational Facilities
• /
• v.25 no.6
• /
• pp.35-44
• /
• 2018

The purpose of this study is to predict more accurate construction costs and to support efficient decision making in the planning and design stages of smart education facilities. The higher the error in the projected cost, the more risk a project manager takes. If the manager can predict a more accurate construction cost in the early stages of a project, he/she can secure a decision period and support a more rational decision. During the planning and design stages, there is a limited amount of variables that can be selected for the estimating model. Moreover, since the number of completed smart schools is limited, there is little data. In this study, various artificial intelligence models were used to accurately predict the construction cost in the planning and design phase with limited variables and lack of performance data. A theoretical study on an artificial neural network and deep learning was carried out. As the artificial neural network has frequent problems of overfitting, it is found that there is a problem in practical application. In order to overcome the problem, this study suggests that the improved models of Deep Neural Network and Deep Belief Network are more effective in making accurate predictions. Deep Neural Network (DNN) and Deep Belief Network (DBN) models were constructed for the prediction of construction cost. Average Error Rate and Root Mean Square Error (RMSE) were calculated to compare the error and accuracy of those models. This study proposes a cost prediction model that can be used practically in the planning and design stages.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.6
• /
• pp.517-531
• /
• 2021

The water supply facilities of Korea have achieved a rapid growth, along with the other social infrastructures consisting a city, due to the phenomenon of urbanization according to economic development. Meanwhile, the level of water supply service demanded by consumer is also steadily getting higher in keeping with economic growth. However, as an adverse effect of rapid growth, the quantity of aged water supply pipes are increasing rapidly, Bursts caused by pipe aging brought about an enormous economic loss of about 6,161 billion won as of 2019. These problems are not only worsening water supply management, also increasing the regional gap in water supply services. The purpose of this study is to classify hazard evaluation indicators and to rank the water distribution network hazard by cluster using the TOPSIS method. In conclusion, in this study, the entropy-based multi-criteria decision-making methods was applied to rank the hazard management of the water distribution network, and the hazard management ranking for each cluster according to the water supply conditions of the county-level municipalities was determined according to the evaluation indicators of water outage, water leakage, and pipe aging. As such, the hazard ranking method proposed in this study can consider various factors that can impede the tap water supply service in the water distribution network from a macroscopic point of view, and it can be reflected in evaluating the degree of hazard management of the water distribution network from a preventive point of view. Also, it can be utilized in the implementation of the maintenance plan and water distribution network management project considering the equity of water supply service and the stability of service supply.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.235-238
• /
• 1996

In this paper, a new optimization method which is a kind of random searching is presented. The proposed method is called RasVal which is an abbreviation of Random Search Method with Variable Seaxch Length and it can search for a global minimum based on the probability density functions of searching, which can be modified using informations on success or failure of the past searching in order to execute intensified and diversified searching. By applying the proposed method to a nonlinear crane control system which can be controlled by the Universal Learning Network with radial basis function(R.B.P.), it has been proved that RasVal is superior in performance to the commonly used back propagation learning algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2101-2105
• /
• 2003

Recently the number of Internet users has very sharply increased, and the number of intrusions has also increased very much. Consequently, security products are being developed and adapted to prevent systems and networks from being hacked and intruded. Even if security products are adapted, however, hackers can still attack a system and get a special authorization because the security products cannot prevent a system and network from every instance of hacking and intrusion. Therefore, the researchers have focused on an active hacking prevention method, and they have tried to develop a traceback system that can find the real location of an attacker. At present, however, because of the characteristics of Internet - diversity, anonymity - the real-time traceback is very difficult. To over-come this problem the Network-based Real-Time Connection Traceback System (NRCTS) was proposed. But there is a security problem that the victim system can be hacked during the traceback. So, in this paper, we propose modified NRCTS with connection redirection technique. We call this traceback system as Connection Redirected Network-based Real-Time Connection Traceback System (CR-NRCTS).

• International journal of advanced smart convergence
• /
• v.6 no.4
• /
• pp.67-72
• /
• 2017

Deep learning neural network becomes very popular nowadays due to the reason that it can learn a very complex dataset such as the image dataset. Although deep learning neural network can produce high accuracy on the image dataset, it needs a lot of time to reach the convergence stage. To solve the issue, we have proposed a scaling method to improve the neural network to achieve the convergence stage in a shorter time than the original method. From the result, we can observe that our algorithm has higher performance than the other previous work.