• The Journal of Korea Robotics Society
• /
• 제19권3호
• /
• pp.266-273
• /
• 2024

With the rising interaction between robots and humans, detecting collisions has become increasingly vital for ensuring safety. In this paper, we propose a novel approach for detecting collisions without using force torque sensors or tactile sensors, utilizing a Transformer-based neural network architecture. The proposed collision detection approach comprises a torque estimator network that predicts the joint torque in a free-motion state using Synchronous time-step encoding, and a collision discriminator network that predicts collisions by leveraging the difference between estimated and actual torques. The collision discriminator finally creates a binary tensor that predicts collisions frame by frame. In simulations, the proposed network exhibited enhanced collision detection performance relative to the other kinds of networks both in terms of prediction speed and accuracy. This underscores the benefits of using Transformer networks for collision detection tasks, where rapid decision-making is essential.

• Journal of Welding and Joining
• /
• 제11권4호
• /
• pp.44-56
• /
• 1993

The arc welding processes are substantially nonlinear, in addition to being highly coupled multivariable systems, Frequently, not all the variables affecting the welding quality are known, nor may they be easily quantified. From this point of view, decoupling between the welding parameters from the welding quality is very difficult, which makes it also difficult to control the welding parameters for obtaining the desired welding quality. In this study, a neural network based on the backpropagation algorithm was implemented and adopted for the selection of gas metal arc welding parameters of the fillet joint, that is, welding current, arc voltage and welding speed. The performance of the neural network for modeling the relationship between the welding quality and welding parameters was presented and evaluated by using the actual welding data. To obtain the optimal neural network structure, various types of the neural network structures were tested with the experimental data. It was revealed that the neural network can be effectively adopted to select the appropriate gas metal arc welding parameter of fillet joints for a given weld quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권5호
• /
• pp.799-818
• /
• 2010

In traditional unstructured P2P file sharing network, each peer establishes connections with a certain number of randomly chosen other peers. This would lead to redundant traffic and P2P network partition in mobile ad hoc network (MANET). We propose an approach to construct an efficient unstructured P2P overlay over MANET using underlying cluster-based routing (CBRP). One of the peers in the P2P network is used as a root-peer to connect all peers. Each peer maintains connection with physically closer peers such that it can reach the root-peer. The peer constructs a minimum-spanning tree consisting of itself, its directly connected neighbor peers and 2-hop away neighbor peers to remove far away redundant links and to build an overlay closer to the physical network. Due to on-demand nature of inter-cluster routing of CBRP, the positioning algorithm for MANET is used to retrieve the file by a peer from the source peer via shorter path in the physical network. We can show by simulation that our approach performs better in comparison with the existing approach.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.227-228
• /
• 2008

• Journal of the Economic Geographical Society of Korea
• /
• 제15권4호
• /
• pp.550-569
• /
• 2012

This paper studies the R&D network of the Zhongguancun Cluster, the most representative innovative cluster of the high-tech industry in China at present. For this study, Zhongguancun Cluster was the first high-tech cluster to have been created in China, the current Zhongguancun Cluster has played a leading role in the development of the high-tech industry in China. In addition, the Zhongguancun Cluster has at helped elevate China as a key region in terms of research development in relation to the high-tech industry. In particular, companies evaluate the research development network culture of Zhongguancun cluster positively and this increases their tendency to approach the research development network with an open mind. The main contents in research development network are as follows; (1) joint or consigned research development and technology transfer in the case of research development network between companies, (2) joint or consigned research development, human resource support and employment, technical advice and consultant and technology transfer in the case of industrial-educational relationships (3) joint or consigned research development, technical advice and consultant and technology transfer in the case of industrial-research relationships, (4) financial support and participation in joint research development project held by government in the case of industrial and governmental relationships (5) financing for research development, utilization of research human resources, purchase of research development and use of research development equipment for mediators. The main difficulties in creating a research development network are 'lack of mutual trust', 'financial problems of companies' and 'lack of information'. Especially, the main key obstacles for the most important research development network between industry and government in the case of the Zhongguancun Cluster are 'complicated and strict procedures. Therefore, more accurate and detailed understanding of the conditions and the following institutional measures from government are required for research development among companies.

• Journal of Information Technology and Architecture
• /
• 제11권1호
• /
• pp.11-23
• /
• 2014

Kill Chain is getting attention due to North Korea's recent nuclear test and missile launches and has emerged the need for an early build up. In order to build a materialized kill chain, you should review the unique kill chain to support operations effectively using various sensors and striking weapon system. Especially, you need a suitable network to reduce a reaction time against the enemy attack under joint operations environment etc. Currently there are many communication ways(e.g. data link, voice, video and text message) used in operations through satellite, wired and wireless and so on. Now, this paper contains analysis on various means for target information exchange which are used in the kill chain. And appropriate network of the kill chain for target information transmission is addressed to confirm feasibility of its alternatives, which is developed using AHP(Analytic Hierarchy Process). Finally, this paper is suggesting network and means of its building up for target information transmission of kill chain which can be implemented under the situation of joint battle field.

• Journal of Institute of Control, Robotics and Systems
• /
• 제16권3호
• /
• pp.305-312
• /
• 2010

The aim of this study is to find an analytic solution to the problem of determining the optimal capacity of a batch-storage network to meet demand for finished products in a system undergoing joint random variations of operating time and batch material loss. The superstructure of the plant considered here consists of a network of serially and/or parallel interlinked batch processes and storage units. The production processes transform a set of feedstock materials into another set of products with constant conversion factors. The final product demand flow is susceptible to joint random variations in the cycle time and batch size. The production processes have also joint random variations in cycle time and product quantity. The spoiled materials are treated through regeneration or waste disposal processes. The objective function of the optimization is minimizing the total cost, which is composed of setup and inventory holding costs as well as the capital costs of constructing processes and storage units. A novel production and inventory analysis the PSW (Periodic Square Wave) model, provides a judicious graphical method to find the upper and lower bounds of random flows. The advantage of this model is that it provides a set of simple analytic solutions while also maintaining a realistic description of the random material flows between processes and storage units; as a consequence of these analytic solutions, the computation burden is significantly reduced. The proposed method has the potential to rapidly provide very useful data on which to base investment decisions during the early plant design stage. It should be of particular use when these decisions must be made in a highly uncertain business environment.

• The Journal of Bigdata
• /
• 제6권2호
• /
• pp.109-124
• /
• 2021

In this paper, the structural characteristics of Industry-University cooperation networks are analyzed using network analysis. Recent studies have shown that technological cooperation and joint research has a positive effect on R&D performance. In order to boost innovation performance, various types of cooperative activities and governmental policy supports for major R&D stakeholders(i.e. universities, laboratories, etc.) are provided. However, despite these efforts, the outcome is still insufficient, so it is time to prepare for a plan to build an innovative network to strengthen university-centered Industry-University cooperation activities. Specifically, this study builds the networks according to the form of Industry-University cooperations(i.e. patent, paper, joint research, and technology transfer), and different types of Industry-University cooperation networks are analyzed from a statistical viewpoint by using QAP correlation and regression analyses. The analysis results show that joint research network is closely related to paper network, and is related to other Industry-University cooperation networks. This study is expected to shed a light on supporting innovation activities such as establishing Industry-University cooperation strategies and discovering cooperative partners necessary for creating new growth engines for universities.

• Journal of Communications and Networks
• /
• 제14권3호
• /
• pp.257-266
• /
• 2012

A decode-and-forward two-way relay system benefits from orthogonal frequency division multiplexing (OFDM) and relay transmission. In this paper, we consider a decode-and-forward two-way relay system over OFDMwith two strategies: A joint subcarrier matching algorithm and a power allocation algorithm operating with a total power constraint for all subcarriers. The two strategies are studied based on average capacity using numerical analysis by uniformly allocating power constraints for each subcarrier matching group. An optimal subcarrier matching algorithm is proposed to match subcarriers in order of channel power gain for both transmission sides. Power allocation is defined based on equally distributing the capacity of each hop in each matching group. Afterward, a modified water-filling algorithm is also considered to allocate the power among all matching groups in order to increase the overall capacity of the network. Finally, Monte Carlo simulations are completed to confirm the numerical results and show the advantages of the joint subcarrier matching, power allocation and water filling algorithms, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제20권6호
• /
• pp.843-847
• /
• 2010

Recently, one of the most interesting issue in the intelligent robot and the industrial robot area is the design and an implementation of servo driver module based on motion network for hollow type joint module of all-in-one structure. In this paper, we designed and implemented for hollow type driver, and also verified the performance of the developed module through the experiment.