• Journal of the Society of Naval Architects of Korea
• /
• v.28 no.1
• /
• pp.150-168
• /
• 1991

A practical procedure for the ultimate compressive strength-based safety and reliability assessment of the double skin upper deck structure is described. The external compressive stress acting on the upper deck structure which is due to the still water and wave-induced sagging moment is approximately estimated by using the existing rule of classification society. The ultimate compressive stress of double skin structure under the action of sagging moment is analyzed by using idealized structural unit method. Here an idealized plate element subjected to uniaxial load is formulated by idealizing the nonlinear behaviour of the actual element taking account of the initial imperfections in the form of initial deflection and welding residual stress. The interaction effect between the local and global failure in the structure is also taken into consideration. The accuracy of the present method is verified comparing with the present solution and the existing numerical and experimental results for unit member and welded box columns. The safety of the structure is evaluated using the concept of conventional central safety factor and the reliability assessment is made by using Cornel's MVFOSM method. The present procedure is then applied to upper deck structure of double skin product oil carrier. The influence of the initial imperfections and the yield stress of the material on the safety and reliability of the structure is investigated.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.9-14
• /
• 2004

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.

• Journal of Appropriate Technology
• /
• v.6 no.2
• /
• pp.136-145
• /
• 2020

Agriculture is the backbone of the economy of most developing countries. In these countries, agriculture or farming is mostly done manually with little integration of machinery, intelligent systems and data monitoring. Irrigation is an essential process that directly influences crop production. The fluctuating amount of rainfall per year has led to the adoption of irrigation systems in most farms. The absence of smart sensors, monitoring methods and control, has led to low harvests and draining water sources. In this research paper, we introduce a 433 MHz Radio Frequency and 2G based Smart Irrigation Meter System and a water prepayment system for rural areas of Tanzania with no reliable internet coverage. Specifically, Ngurudoto area in Arusha region where it will be used as a case study for data collection. The proposed system is hybrid, comprising of both weather data (evapotranspiration) and soil moisture data. The architecture of the system has on-site weather measurement controllers, soil moisture sensors buried on the ground, water flow sensors, a solenoid valve, and a prepayment system. To achieve high precision in linear and nonlinear regression and to improve classification and prediction, this work cascades a Dynamic Regression Algorithm and Naïve Bayes algorithm.