• Journal of the Korean Society of Safety
• /
• v.38 no.1
• /
• pp.1-8
• /
• 2023

It is extremely important to design safety-guaranteed industrial processes because such process determine the ultimate outcomes of industrial activities, including worker safety. Application of artificial intelligence (AI) in industrial safety involves modeling industrial safety systems by using vast amounts of safety-related data, accident prediction, and accident prevention based on predictions. As a preliminary step toward realizing AI-based industrial safety in Korea, this study discusses neural network-based modeling of industrial safety systems. The input variables that are the most discriminatory relative to the output variables of industrial safety processes are selected using two information-theoretic measures, namely entropy and cross entropy. Normalized frequency and severity of industrial accidents are selected as the output variables. Our simulation results confirm the effectiveness of the proposed neural network model and, therefore, the feasibility of extending the model to include more input and output variables.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.4
• /
• pp.84-92
• /
• 1997

Among the various sources of vehicle interior noise, this paper concerns the road induced noise ; the identification of its transfer path by using experimental method. Multiple input and single output model is taken as a noise generation model. Because it is impossible to measure the road imput forces directly, the acceleration signals are measured on four axle;three directions for each point. By considering the cross correlations of input signals, four uncorrelated source groups are taken. Multiple coherence function is employed to investigate the contribution of each group. In addtion, to identify the detailed path through the suspension systems, the contributions of all possible paths are ranked by using the coherence functions between interior noise and the relative accelerations of connections such as bushings and mountings. Measurements are performed with passenger vehicle traveling on concrete and asphalt roads at 60㎞/h.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.58-60
• /
• 2017

In the offshore crane system, the requirements on the operating safety are extremely high due to many external factors. This paper describes a model for studying the dynamic behavior of the offshore crane system. The obtained model allows to evaluate the fluctuations of the load arising from the elasticity of the rope. Especially, in this paper, the authors design control system in which just winch rotation angle and rope tension are used without load position information. The controller design based on input-output feedback linearization theory is presented which can handle the effect of the elasticity of the rope and track the load target trajectory input. Besides that, a full order observer is designed to estimate unknown states. Finally, By the experiment results, the effectiveness of proposed control method is evaluated and verified.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.185-188
• /
• 1997

In this paper, we execute identification, linearization, and control of a nonlinear system using recurrent neural networks. In general nonlinear control system become complex because of nonlinearity and uncertainty. And though we compose nonlinear control system based on the model, it is difficult to get good control ability. So we identify the nonlinear control system using the recurrent neural networks and execute feedback linearization of identified model, In this process we choose the optional linear system, and the system which will have to be feedback linearized if trained to follow the linearity between input and output of the system we choose. We the feedback linearized system by applying standard linear control strategy and simulation. And we evaluate the effectiveness by comparing the result which is linearized theoretically.

• Computers and Concrete
• /
• v.29 no.3
• /
• pp.145-159
• /
• 2022

In this study, the extreme learning machine and deep learning models were devised to estimate the bond strength of corroded reinforcement in concrete. The six inputs and one output were used in this study. The compressive strength, concrete cover, bond length, steel type, diameter of steel bar, and corrosion level were selected as the input variables. The results of bond strength were used as the output variable. Moreover, the Analysis of variance (Anova) was used to find the effect of input variables on the bond strength of corroded reinforcement in concrete. The prediction results were compared to the experimental results and each other. The extreme learning machine and the deep learning models estimated the bond strength by 99.81% and 99.99% accuracy, respectively. This study found that the deep learning model can be estimated the bond strength of corroded reinforcement with higher accuracy than the extreme learning machine model. The Anova results found that the corrosion level was found to be the input variable that most affects the bond strength of corroded reinforcement in concrete.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.4 no.2
• /
• pp.175-183
• /
• 1999

For fast response of the dc output voltage in P\hi1'v1 converter, it is desirable that the relation of power balance of the i input and output terminals is introduced to the system modeling. In this case, controller desi밍1 is not easy since the m model is nonlinear. In this paper, a nonlinear control them${\gamma}$ using input-output feedback linearization is used to solve t the nonlinear problem of the system. By nonlinear control. the voltage transient response can be faster, and it is also p possible to control the output voltage to be constant with smaller output filter capacitance for load disturbance.

• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.47-58
• /
• 2018

In this study, we define Fintech services as review previous literatures and identify the traditional Fintech service market for analysing the economic effects of the Fintech Industry by using the 2014 Input-Output Table. We can identify the current market of Fintech industry which consists of VAN, PG, financial SW, mobile banking and Fintech R&D and we conduct Input-Output analysis by using non-competitive import model. The Input-Output analysis results show that production inducement effect and front/rear chain effect of the Fintech Industry are below average of other industries. This is because the Fintech technology and industry were emerging in Korea at that time (2014), and thus the ripple effects are not significant. Especially, due to the existing white risk financial regulation, new business opportunities have not been open to adapt new ICT-financial technologies. Therefore, when the business ecosystem is build through deregulation and platforms of the financial sector, it is expected that the Fintech Industry will have a high ripple effect. In this study, we identify the current market of Fintech industry from ICT indusries and conduct Input-Output analysis. The economic effects of the Fintech industry are not remarkable, but it is significant to identify the emerging market and present the basic analysis of issued research field.

• Journal of Advanced Navigation Technology
• /
• v.16 no.4
• /
• pp.586-592
• /
• 2012

One approach of the control of a nonlinear system that has gained some success employs a fuzzy structure in cooperation with a neural network(ANFIS). The traditional ANFIS can only model and control the process in single-dimensional output nature in spite of multi-dimensional input. The membership function parameters are tuned using a combination of least squares estimation and back-propagation algorithm. In the case of a mobile robot, we need to drive left and right wheel respectively. In this paper, we proposed the control system architecture for a mobile robotic system that employs the 2-input 2-output ANFIS controller for trajectory tracking. Simulation results and preliminary evaluation show that the proposed architecture is a feasible one for mobile robotic systems.

• Proceedings of the IEEK Conference
• /
• 2000.11a
• /
• pp.303-306
• /
• 2000

In this paper, we propose VC merge capable hardware architecture for scalability based on ATM switching fabric. We implemented a scheduler for configuring crossbars in input-queued switches which support virtual output queues at the input ports. Also, we implemented VC merge capable scheduler at the output ports. We verified the proposed model by using C language, and designed with VHDL language. Then, we simulated and synthesized it with software of the SYNOPSYS corporation.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.31-33
• /
• 1991

A passive power converter operating on the principle of parametric excitation, called Parametric transformer, is analyzed. The energy transfer from the input to the output is achieved through the double frequency variation of magnetic path reluctance to the input frequency without mutual flux coupling between two windings. Thus, output becomes available which is essentially independant of waveform of excitation. The mathmatical model of the device is developed and its solution is obtained. The outstanding characteristics of the device is explained from the analysis.