• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.216-221
• /
• 2022

The 4th industrial revolution is accelerating the transition to digital innovation in various aspects of our daily lives, and efforts for manufacturing innovation are continuing in the manufacturing industry, such as smart factories. The 4th industrial revolution technology in manufacturing can be used based on AI, big data, IoT, cloud, and robots. Through this, it is required to develop a technology to establish a production facility data collection and analysis system that has evolved from the existing automation and to find the cause of defects and minimize the defect rate. In this paper, we implemented a system that collects power, environment, and status data from production facility sites through IoT devices, quantifies them in real-time in a cloud computing environment, and displays them in the form of MQTT-based real-time infographics using widgets. The real-time sensor data transmitted from the IoT device is stored to the cloud server through a Rest API method. In addition, the administrator could remotely monitor the data on the dashboard and analyze it hourly and daily.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.3
• /
• pp.68-76
• /
• 2000

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of conventional techniques such as the pole placement and the optimal control based on the local linearizations have narrow stabilizable regions. At the same time, the fine tunings of their gain parameters are also troublesome. Thus, in this paper, an Evolving Neural Network Controller(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algorithm(RVEGA) was presented for stabilization of an IP system with nonlinearity. This proposed ENNC was described by a simple genetic chromosome. And the deletion of neuron, the according to the various flag types. Therefore, the connection weights, its structure and the neuron types in the given ENNC can be optimized by the proposed evolution strategy. And the proposed ENNC was implemented successfully on the ADA-2310 data acquisition board and the 80586 microprocessor in order to stabilize the IP system. Through the simulation and experimental results, we showed that the finally acquired optimal ENNC was very useful in the stabilization control of IP system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.512-516
• /
• 2004

Context-aware computing has been attracting the attention as an approach to alleviating the inconvenience in human-computer interaction. This paper proposes a context-aware system architecture to be implemented on an SoC(System-on-a-Chip). The proposed architecture supports sensor abstraction, notification mechanism for context changes, modular development, easy service composition using if-then rules, and flexible context-aware service implementation. It consists of the communication unit, the processing unit, the blackboard, and the rule-based system unit, where the first three components reside in the microprocessor part of the SoC and the rule-based system unit is implemented in hardware. For the proposed architecture, an SoC system has been designed and tested in an SoC development platform called SystemC and the feasibility of the behavoir modules for the microprocessor part has been evaluated by implementing software modules on the conventional computer platform. This SoC-based context-aware system architecture has been developed to apply to mobile intelligent robots which would assist old people at home in a context-aware manner.