• Industrial Engineering and Management Systems
• /
• 제15권4호
• /
• pp.364-373
• /
• 2016

Disassembly is one of the important activities in treating with the product at the End of Life time (EOL). Disassembly is defined as a systematic technique in dividing the products into its constituent elements, segments, sub-assemblies, and other groups. We concern with a Fuzzy Disassembly Line Balancing Problem (FDLBP) with multiple objectives in this article that it needs to allocation of disassembly tasks to the ordered group of disassembly Work Stations. Tasks-processing times are fuzzy numbers with triangular membership functions. Four objectives are acquired that include: (1) Minimization of number of disassembly work stations; (2) Minimization of sum of idle time periods from all work stations by ensuring from similar idle time at any work-station; (3) Maximization of preference in removal the hazardous parts at the shortest possible time; and (4) Maximization of preference in removal the high-demand parts before low-demand parts. This suggested model was initially solved by GAMS software and then using Genetic Algorithm (GA) in MATLAB software. This model has been utilized to balance automotive engine disassembly line in fuzzy environment. The fuzzy results derived from two software programs have been compared by ranking technique using mean and fuzzy dispersion with each other. The result of this comparison shows that genetic algorithm and solving it by MATLAB may be assumed as an efficient solution and effective algorithm to solve FDLBP in terms of quality of solution and determination of optimal sequence.

• 로봇학회논문지
• /
• 제1권1호
• /
• pp.9-16
• /
• 2006

The Mobile robots are increasingly being used to perform tasks in unknown environments. The potential of robots to undertake such tasks lies in their ability to intelligently and efficiently search in an environment. An algorithm has been developed for robots which explore the environment to measure the physical properties (dust in this paper). While the robot is moving, it measures the amount of dust and registers the value in the corresponding grid cell. The robot moves from local maximum to local minimum, then to another local maximum, and repeats. To reach the local maximum or minimum, simple gradient following is used. Robust estimation of the gradient using perturbation/correlation, which is very effective when analytical solution is not available, is described. By introducing the probability of each grid cell, and considering the probability distribution, the robot doesn't have to visit all the grid cells in the environment still providing fast and efficient sensing. The extended algorithm to coordinate multiple robots is presented with simulation results.

• 정보처리학회논문지A
• /
• 제11A권1호
• /
• pp.67-74
• /
• 2004

대부분의 병렬 알고리즘은 동기 알고리즘으로, 올바른 계산을 위해 작업을 일찍 끝낸 빠른 프로세서들은 동기점에서 느린 프로세서를 기다려야 하는데, 프로세서들의 성능이 다를 경우 연산 속도는 가장 느린 프로세서에 의해 결정된다. 본 논문에서는 거대 고유치 문제의 주요 고유쌍을 구하는 문제에 있어서 빠른 프로세서의 유휴 시간을 줄여 수렴 속도를 가속한 수 있는 동기/비동기 혼합 알고리즘을 고안하고 이를 MPMD 프로그래밍 방식을 사용하여 구현하였다.

• International Journal of Control, Automation, and Systems
• /
• 제4권5호
• /
• pp.601-614
• /
• 2006

In this paper, a study on task assignment strategies for a complex real-time network system is presented. Firstly, two task assignment strategies are proposed to improve previous strategies. The proposed strategies assign tasks with meeting end-to-end real-time constraints, and also with optimizing system utilization through period modulation of the tasks. Consequently, the strategies aim at the optimizationto optimize of system performance with while still meeting real-time constraints. The proposed task assignment strategies are devised using the genetic algorithmswith heuristic real-time constraints in the generation of new populations. The strategies are differentiated by the optimization method of the two objectives-meeting end-to-end real-time constraints and optimizing system utilization: the first one has sequential genetic algorithm routines for the objectives, and the second one has one multiple objective genetic algorithm routine to find a Pareto solution. Secondly, the performances of the proposed strategies and a well-known existing task assignment strategy using the BnB(Branch and Bound) optimization are compared with one other through some simulation tests. Through the comparison of the simulation results, the most adequate task assignment strategies are proposed for some as system requirements-: the optimization of system utilization, the maximization of running tasktasks, and the minimization of the number of network node nodesnumber for a network system.

• 항공우주시스템공학회지
• /
• 제17권2호
• /
• pp.78-85
• /
• 2023

다수 무인기 체계에서 임무할당은 임무 수행 능력을 결정하는 중요한 요인이다. 본 논문은 유전 알고리즘에 기반한 임무계획기법을 제안한다. 본 기법을 통해 제한 조건을 만족하면서, 임무 완료 시간을 최소화하는 해를 구할 수 있다. 임무 할당 문제의 최적해를 구하기 위해서는 계산량이 많이 필요하므로 본 기법이 해를 구하는 대안이 될 수 있다. 본 기법은 현실 세계의 다양한 종류의 무인기, 임무, 제한 조건을 고려하였다. 제안된 기법은 각 무인기의 임무 시퀀스와 제한 조건 만족을 위한 임무 별 대기 시간을 도출한다. 다양한 수치적 시뮬레이션 결과를 통해 임무 종료 시간을 최소화하는 임무계획 기법의 성능을 확인하였다.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.13-23
• /
• 2018

Deep learning is a promising solution to a number of complex problems based on its inherent capability to approximate almost all types of functions without the demand for handcrafted feature extraction. New wireless transmission and access schemes based on deep learning are being increasingly proposed as substitutes for existing approaches, providing a lower complexity and better performance gain. Among such schemes, a communications system is viewed as an end-to-end autoencoder. The learning process applied in autoencoders can automatically deal with some nonlinear or unknown properties in communications systems. Deep learning can also be used to optimize each processing block for required tasks such as channel decoding, signal detection, and multiple access. On top of recent related research trends, we suggest appropriate research approaches for communications systems to adopt deep learning.

• 산업경영시스템학회지
• /
• 제23권54호
• /
• pp.13-26
• /
• 2000

Machining route selection to produce parts should be based on shop flow information because of input data at scheduling tasks and is one of the main problem in process planning. This paper addresses the problem of machining route selection in multi-stage process with machine group included a similar function. The model proposed is formulated as 0-1 integer programing considering the relation of parts and machine table size, avaliable time of each machine for planning period, and delivery date. The objective of the model is to minimize the sum of processing, transportation, and setup time for all parts. Genetic algorithm approach is developed to solve this model. The efficiency of the approach is examined in comparison with the method of branch and bound technique for the same problem. Also, this paper is to solve large problem scale and provide it if the multiple machining routes are existed an optimal solution.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• 로봇학회논문지
• /
• 제17권1호
• /
• pp.16-24
• /
• 2022

This paper presents a method that can reduce the computational cost of the hierarchical quadratic programming (HQP)-based robot controller. Hierarchical controllers can effectively manage articulated robots with many degrees of freedom (DoFs) to perform multiple tasks. The HQP-based controller is one of the generic hierarchical controllers that can provide a control solution guaranteeing strict task priority while handling numerous equality and inequality constraints. However, according to a large amount of computation, it can be a burden to use it for real-time control. Therefore, for practical use of the HQP, we propose a method to reduce the computational cost by decreasing the size of the decision variable. The computation time and control performance of the proposed method are evaluated by real robot experiments with a 15 DoFs dual-arm manipulator.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.