• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.287-292
• /
• 2021

In this paper, we propose an efficient CNN application method by analyzing the effect of activation function on the failure diagnosis of the inductive motor stator. Generally, the main purpose of the inductive motor stator failure diagnosis is to prevent the failure by rapidly diagnosing the minute turn short. In the application of activation function, experiments show that the Sigmoid function is 23.23% more useful in accuracy of diagnosis than the ReLu function, although it is shown that ReLu has superiority in overall fixer failure in utilizing the activation function.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.645-650
• /
• 2018

Software stability is the possibility of operating without any malfunction in the operating environment over time. In a finite failure NHPP for software failure analysis, the failure occurrence rate may be constant, monotonically increasing, or monotonically decreasing. In this study, based on the NHPP model and based on the software failure time data, we compared and analyzed the attributes of the software development cost model using the exponential distribution Rayleigh distribution and inverse exponential distribution considering the shape parameter of the Weibull distribution as the life distribution. The results of this study show that the Rayleigh model is the fastest release time and has the economic cost compared to the inverse-exponential model and the Goel-Okumoto model. Using the results of this study, it can be expected that software developers and operators will be able to predict the optimal release time and economic development cost.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.935-944
• /
• 2023

In this study, the Inverse-type (: Inverse-Exponential, Inverse-Rayleigh) life distribution, which is known to be suitable for reliability research, was applied to a software development cost model based on finite failure NHPP(: Nonhomogeneous Poisson Process), and then the attributes that determine the model's performance were analyzed. Additionally, to evaluate the efficiency of the model, it was compared with the Goel-Okumoto basic model. The performance of the model was analyzed using failure time data, and MLE (: Maximum Likelihood Estimation) was applied to calculate the parameters. In conclusion, first, as a result of analyzing m(t), which determines the development cost, the Inverse-Exponential model was efficient due to its small error in the true value. Second, as a result of analyzing the release time along with the development cost, the Inverse-Rayleigh model was confirmed to be the best. Third, as a result of comprehensive evaluation of the attributes (m(t), cost, and release time) of the proposed model, the Inverse-Rayleigh model had the best performance. Therefore, if software developers can effectively utilize this research data in the early process, they will be able to proactively explore and analyze attributes that affect cost.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.7-14
• /
• 2006

The finite failure NHPP models proposed in the literature exhibit either constant, monotonic increasing or monotonic decreasing failure occurrence rates per fault. In this paper, we propose the Erlang reliability model, which can capture the increasing nature of the failure occurrence rate per fault. Equations to estimate the parameters of the Erlang finite failure NHPP model based on failure data collected in the form of inter-failure times are developed. For the sake of proposing shape parameter of the Erlang distribution, we used to the goodness-of-fit test of distribution. Data set, where the underlying failure process could not be adequately described by the existing models, which motivated the development of the Erlang model. Analysis of the failure data set which led us to the Erlang model, using arithmetic and Laplace trend tests, goodness-of-fit test, bias tests is presented.

• Journal of Internet Computing and Services
• /
• v.8 no.5
• /
• pp.21-33
• /
• 2007

An overlay network is a virtual network which is constructed on top of a physical computer network. A node in the overlay network is connected through virtual or logical links, where each link corresponds to a path of the links in the underlying physical network. Overlay networks are suitable for sharing heterogeneous resources in distributed environments, However, overlay networks are limited for achieving reliable communication that failure detection in overlay networks is a very important issue. In this paper, we review conditions of conventional failure detection and propose a new approach to failure detection and resilience which can be applied to HRing (Hierarchical Ring) overlay networks. The proposed method consists of the failure detection and the failure resilience phases. Because it utilizes the characteristics of the HRing overlay network for failure detection, it can reduce unnecessary network traffic and provide better scalability and flexibility. We also analyzed and evaluated the performance of the proposed approach through simulations.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.1
• /
• pp.15-19
• /
• 2022

The radial distribution systems (RDS) commonly used around the world has the following disadvantages. First, when the DL is operated on a radial system, the line utilization rate is usually kept low. Second, if a fault occurs in the radial DL, a power outage of 3 to 5 minutes is occurring depending on the operator's proficiency and fault situation until the fault section is separated and the normal section is replaced. To solve this problem, Various methods have been proposed at domestic and foreign to solve this problem, and in Korea, research is underway on the advanced system of operating multiple linked DL always. A system that is electrically linked always, and that is built to enable high-speed communication during the protection coordination is named networked distribution system (NDS). Because the load shares the DL, the line utilization rate can be improved, and even if the line faults, the normal section does not need to be cut off, so the normal section does not experience a power outage. However, since it is impossible to predict in which direction the fault current will flow when a failure occurs in the NDS, a communication-based protection coordination is used, but there is no backup protection coordination method in case of communication failure. Therefore, in this paper, we propose a protective cooperation method to apply as a backup method when communication fails in NDS. The new method is to change TCC by location of CB using voltage drop in case of fault.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.163-169
• /
• 2020

Recently, research on automation and unmanned operation of machines in the industrial field has been conducted with the advent of AI, Big data, and the IoT, which are the core technologies of the Fourth Industrial Revolution. The machines for these automation processes are controlled based on the data collected from the sensors attached to them, and further, the processes are managed. Conventionally, the abnormalities of sensors are periodically checked and managed. However, due to various environmental factors and situations in the industrial field, there are cases where the inspection due to the failure is not missed or failures are not detected to prevent damage due to sensor failure. In addition, even if a failure occurs, it is not immediately detected, which worsens the process loss. Therefore, in order to prevent damage caused by such a sudden sensor failure, it is necessary to identify the failure of the sensor in an embedded system in real-time and to diagnose the failure and determine the type for a quick response. In this paper, a deep neural network-based fault diagnosis system is designed and implemented using Raspberry Pi to classify typical sensor fault types such as erratic fault, hard-over fault, spike fault, and stuck fault. In order to diagnose sensor failure, the network is constructed using Google's proposed Inverted residual block structure of MobilieNetV2. The proposed scheme reduces memory usage and improves the performance of the conventional CNN technique to classify sensor faults.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.05a
• /
• pp.443-448
• /
• 2003

Ministry of Information and Communication(MIC) requires telecompanys to be base station sharing in order to prevent the duplicated investment and environmental destruction due to indiscreet constructions of a basestations for enlarging its own service area among telecompanys. This paper discussed the troubles of mobile communication services to be generated in common-basestation at the subway, such as factors of power obstacles, communication equipment and establishment obstacles. The content of this paper is helpful in organizing the basestation sharing of IMT-2000 and the 4th generation mobile system, and provides the basic of a higher quality service for common-service communication.

• Journal of the Korean Society for Railway
• /
• v.10 no.1 s.38
• /
• pp.88-95
• /
• 2007

TCN(Train Communication Network) adopts the master/slave protocol to implement real-time communication. In this network, a fault on the master node, cased by either hardware or software failure, makes the entire communication impossible over TCN. To reduce fault detection and recovery time, this paper propose the contention based mastership transfer algorithm. Slave nodes detect the fault of master node and search next master node using the proposed algorithm. This paper also shows the implementation results of a SoC-based Fault-Tolerant MVB Controller(FT-MVBC) which includes the fault-detect-logic as well as the MVB network logic to verify this algorithm.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11S
• /
• pp.3320-3331
• /
• 1999

In this paper, we explore two ways to improve the bandwidth assurance performance of Assured Service(AS). It is well known that AS fails to meet the bandwidth assurance target for large-profile TCP flows competing with many small-profile flows. This flows after the back-offs induced by packet drops. Thus currently proposed solution to this problem naturally focus on modifying TCP's behavior to counter the unfairness in the TCP dynamics. Unfortunately, these proposals lack practicability in terms of the required changes in the incumbent Internet infrastructure. Admitting this difficulty, we instead look to not yet deployed Diff-Serv mechanisms for practical solutions. In particular, we investigate the role of RIO, RED with IN(in-profile) and OUT(out-profile), queue management scheme in the assurance failure for As. Specifically, we identify the inadequacy of RIO that aggravates the bandwidth assurance failure. Then we alleviates the bandwidth assurance failure problem by separately controlling the out-of-profile packet queue length. Through extensive simulations we demonstrate that RI+O extends the regime where AS consistently provides the bandwidth assurance.