• Computers and Concrete
• /
• v.7 no.1
• /
• pp.63-81
• /
• 2010

We present the shape determination method of 3-D reinforcement corrosion based on observed temperature on concrete surface. The non-destructive testing for reinforcement corrosion in concrete using a heat image on concrete surface have been proposed by Oshita. The position of the reinforcement of corrosion or the cavity can be found using that method. However, the size of those defects can not be precisely measured based on the heat image. We therefore proposed the numerical determination system of the shape for the reinforcement corrosion using the observed temperature on the concrete surface. The adjoint variable method is introduced to formulate the shape determination problem, and the finite element method is employed to simulate the heat transfer problem. Some numerical experiments and the examination for the number of the observation points are shown in this paper.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.11a
• /
• pp.169-172
• /
• 2006

Wall construction apartment built before 1988 years need internal examination reinforcement according to existing laws ans regulations at remodeling because do not earthquake resistant design. Established newly wall to interest paid back at the same time a the principal direction for wall construction apartment internal examination reinforcement, and satisfied internal examination standard because uses width displacement between floor. This study analyzes displacement value such as latitude and presented position of efficient reinforcement wall and wall quantity at earthquake resistant design of wall construction apartment.

• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.97-105
• /
• 2022

Human casualties from fires are increasing worldwide. The majority of human deaths occur during the evacuation process, as occupants panic and are unaware of the location of the fire and evacuation routes. Using an Internet of Things (IoT) sensor and reinforcement learning, we propose a method to find the safest evacuation route by considering the fire location, flame speed, occupant position, and walking conditions. The first step is detecting the fire with IoT-based devices. The second step is identifying the occupant's position via a beacon connected to the occupant's mobile phone. In the third step, the collected information, flame speed, and walking conditions are input into the reinforcement learning model to derive the optimal evacuation route. This study makes it possible to provide the safest evacuation route for individual occupants in real time. This study is expected to reduce human casualties caused by fires.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2008.10a
• /
• pp.178-182
• /
• 2008

Automotive manufacturers lay their eyes on the new manufacturing technologies because of the strengthened competition. Among them, a simultaneous forming is one of the innovative forming technologies to be able to reduce production time and cost. Several parts can be simultaneous manufactured by process, while the conventional stamping demands the same number of die sets with the number of parts. In this study, the automotive front side member was manufactured by the simultaneous forming. The position and the size of initial blank were determined by forming analysis and try-outs, and the blank movement during the forming was controlled by introducing the pilot pin.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.910-917
• /
• 2020

In fire suppression, continuous delivery of water or foam to the fire source is essential. The present study concerns fire suppression in a ship under sea condition, by introducing reinforcement learning technique to aiming of fire extinguishing nozzle, which works in a ship compartment with six degrees of freedom movement by irregular waves. The physical modeling of the water jet and compartment motion was provided using Unity 3D engine. In the reinforcement learning, the change of the nozzle angle during the scenario was set as the action, while the reward is proportional to the ratio of the water particle delivered to the fire source area. The optimal control of nozzle aiming for continuous delivery of water jet could be derived. Various algorithms of reinforcement learning were tested to select the optimal one, the proximal policy optimization.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.398-403
• /
• 2020

Robot's throwing control is difficult to accurately calculate because of air resistance and rotational inertia, etc. This complexity can be solved by using machine learning. Reinforcement learning using reward function puts limit on adapting to new environment for robots. Therefore, this paper applied deep reinforcement learning using neural network without reward function. Throwing is evaluated as a success or failure. AI network learns by taking the target position and control policy as input and yielding the evaluation as output. Then, the task is carried out by predicting the success probability according to the target location and control policy and searching the policy with the highest probability. Repeating this task can result in performance improvements as data accumulates. And this model can even predict tasks that were not previously attempted which means it is an universally applicable learning model for any new environment. According to the data results from 520 experiments, this learning model guarantees 75% success rate.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1228-1230
• /
• 1996

A neural network(NN) mechanism is proposed to modify the gait of a biped robot that walks on sloping surface using sensory inputs. The robot starts walking on a surface with no priori knowledge of the inclination of the surface. By accumulating experience during walking, the robot improves its walking gait and finally forms a gait that is adapted to the surface inclination. A neural controller is proposed to control the gait which has 72 reciprocally inhibited and excited neurons. PI control is used for position control, and the neurons are trained by a reinforcement learning mechanism. Experiments of static gait learning and pseudo dynamic learning are performed to show the validity of the proposed reinforcement learning mechanism.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.1008-1011
• /
• 2005

It is necessary for the design of lead frame punches in blanking to consider buckling because inner lead pitch of lead frame has been narrowed by miniaturization and high accumulation of semiconductor. In addition, if process variables change in press stamping process, the lift of punches is no longer influenced in wear and punches can be broken suddenly. To prevent the fracture of fine pitch lead frame punches, having considered applying reinforcement to it, this paper verified the design with buckling analysis. This study presents the optimal position and number of reinforcement to be attached to punches. Finally this study presents design rules of attaching reinforcement.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.12
• /
• pp.1379-1387
• /
• 2011

A PID-feedforward controller and Robust Internal-loop Compensator (RIC) based on reinforcement learning using random variable sequences are provided to auto-tune parameters for each controller in the high-precision position control of PMLSM (Permanent Magnet Linear Synchronous Motor). Experiments prove the well-tuned controller could be reduced up to one-fifth level of tracking errors before learning by reinforcement learning. The RIC compared to the PID-feedforward controller showed approximately twice the performance in reducing tracking error and disturbance rejection.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.2
• /
• pp.113-120
• /
• 2021

The Distance Measuring Equipment (DME) is a ground-based aircraft navigation system and is considered as an infrastructure that ensures resilient aircraft navigation capability during the event of a Global Navigation Satellite System (GNSS) outage. The main problem of DME as a GNSS back up is a poor positioning accuracy that often reaches over 100 m. In this paper, a novel approach of applying deep reinforcement learning to a DME pulse design is introduced to improve the DME distance measuring accuracy. This method is designed to develop multipath-resistant DME pulses that comply with current DME specifications. In the research, a Markov Decision Process (MDP) for DME pulse design is set using pulse shape requirements and a timing error. Based on the designed MDP, we created an Environment called PulseEnv, which allows the agent representing a DME pulse shape to explore continuous space using the Soft Actor Critical (SAC) reinforcement learning algorithm.