• Title/Summary/Keyword: Global Minimum Point

Search Result 70, Processing Time 0.024 seconds

Structure Optimization of a Feedforward Neural Controller using the Genetic Algorithm (유전 알고리즘을 이용한 전방향 신경망 제어기의 구조 최적화)

  • 조철현;공성곤
    • Journal of the Korean Institute of Telematics and Electronics B
    • /
    • v.33B no.12
    • /
    • pp.95-105
    • /
    • 1996
  • This paper presents structure optimization of a feedforward neural netowrk controller using the genetic algorithm. It is important to design the neural network with minimum structure for fast response and learning. To minimize the structure of the feedforward neural network, a genralization of multilayer neural netowrks, the genetic algorithm uses binary coding for the structure and floating-point coding for weights. Local search with an on-line learnign algorithm enhances the search performance and reduce the time for global search of the genetic algorithm. The relative fitness defined as the multiplication of the error and node functions prevents from premature convergence. The feedforward neural controller of smaller size outperformed conventional multilayer perceptron network controller.

  • PDF

Constructing Neural Networks Using Genetic Algorithm and Learning Neural Networks Using Various Learning Algorithms (유전알고리즘을 이용한 신경망의 구성 및 다양한 학습 알고리즘을 이용한 신경망의 학습)

  • 양영순;한상민
    • Proceedings of the Computational Structural Engineering Institute Conference
    • /
    • 1998.04a
    • /
    • pp.216-225
    • /
    • 1998
  • Although artificial neural network based on backpropagation algorithm is an excellent system simulator, it has still unsolved problems of its structure-decision and learning method. That is, we cannot find a general approach to decide the structure of the neural network and cannot train it satisfactorily because of the local optimum point which it frequently falls into. In addition, although there are many successful applications using backpropagation learning algorithm, there are few efforts to improve the learning algorithm itself. In this study, we suggest a general way to construct the hidden layer of the neural network using binary genetic algorithm and also propose the various learning methods by which the global minimum value of the teaming error can be obtained. A XOR problem and line heating problems are investigated as examples.

  • PDF

Some convergence properties of godard's quartic algorithm: 1. The rate of convergence (4차 고다드 알고리즘의 몇 가지 수렴 성질:1. 수렴속도)

  • 최진호;배진수;송익호;박래홍;박정순
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.21 no.9
    • /
    • pp.2349-2354
    • /
    • 1996
  • Convergence analysis on Godard's quartic (GQ) algorithm used forblind equalization is accomplished in this paper. The first main result is an explanation of the lacal behavior of the GQ algorithm around the global minimum point of the average performance functio, from which we can determine the adaptation gain. It is show that the normalized adaptation gain of the GQ algorithm should be smaller than that of the decision directed (DD) algorithm. In addition, it is observed that the GQ algorithm converges faster than the DD equalization algorithm.

  • PDF

Inelastic displacement-based design approach of R/C building structures in seismic regions

  • Rubinstein, Marcelo;Moller, Oscar;Giuliano, Alejandro
    • Structural Engineering and Mechanics
    • /
    • v.12 no.6
    • /
    • pp.573-594
    • /
    • 2001
  • A two-level displacement-based design procedure is developed. To obtain the displacement demands, elastic spectra for occasional earthquakes and inelastic spectra for rare earthquakes are used. Minimum global stiffness and strength to be supplied to the structure are based on specified maximum permissible drift limits and on the condition that the structure responds within the elastic range for occasional earthquakes. The performance of the structure may be assessed by an inelastic push-over analysis to the required displacement and the evaluation of damage indices. The approach is applied to the design of a five-story reinforced concrete coupled wall structure located in the most hazardous seismic region of Argentina. The inelastic dynamic response of the structure subjected to real and artificially generated acceleration time histories is also analyzed. Finally, advantages and limitations of the proposed procedure from the conceptual point of view and practical application are discussed.

An Improved Particle Swarm Optimization Adopting Chaotic Sequences for Nonconvex Economic Dispatch Problems (개선된 PSO 기법을 적용한 전력계통의 경제급전)

  • Jeong, Yun-Won;Park, Jong-Bae;Cho, Ki-Seon;Kim, Hyeong-Jung;Shin, Joong-Rin
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.56 no.6
    • /
    • pp.1023-1030
    • /
    • 2007
  • This paper presents a new and efficient approach for solving the economic dispatch (ED) problems with nonconvex cost functions using particle swarm optimization (PSO). Although the PSO is easy to implement and has been empirically shown to perform well on many optimization problems, it may easily get trapped in a local optimum when solving problems with multiple local optima and heavily constrained. This paper proposes an improved PSO, which combines the conventional PSO with chaotic sequences (CPSO). The chaotic sequences combined with the linearly decreasing inertia weights in PSO are devised to improve the global searching capability and escaping from local minimum. To verify the feasibility of the proposed method, numerical studies have been performed for two different nonconvex ED test systems and its results are compared with those of previous works. The proposed CPSO algorithm outperforms other state-of-the-art algorithms in solving ED problems, which consider valve-point and multi-fuels with valve-point effects.

A Study on Torch Path Generation for Laser Cutting Process (레이저 절단공정에서의 토지경로 생성에 관한 연구)

  • Han, Guk-Chan;Na, Seok-Ju
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.20 no.6
    • /
    • pp.1827-1835
    • /
    • 1996
  • This paper addresses the problem of a torch path generation for the 2D laser cutting of a stock plate nested with resular or irregular parts. Under the constaint of the relative positions of parts enforced by nesting, the developed torch path algorithm generate feasible cutting path. In this paper, the basic object is a polygon( a many-slide figure) with holes. A part may be represented as a number of line segments connected end-to-end in counterclockwise order, and formed a closed contour as requied for cutting paths. The objective is to tranverse this cutting contours with a minimum path length. This paper proposes a simulated annealing based dtorch path algorithm, that is an improved version of previously suggested TSP models. Since everypiercing point of parts is not fixed in advance, the algorithm solves as relazed optimization problem for the constraint, thich is one of the main features of the proposed algorithm. For aolving the torch path optimization problem, an efficient generation mechanism of neighborhood structure and as annealing shedule were introduced. In this way, a global solution can be obtained in a reasonable time. Seveeral examples are represented to ilustrate the method.

Integrated Structure and Controller Design of Single-Link Flexible Arm for Improving the Performance of Position Control (유연 외팔보의 위치제어 성능향상을 위한 형상 및 제어기 통합설계)

  • Lee, Min-U;Park, Jang-Hyeon
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.19 no.10
    • /
    • pp.120-129
    • /
    • 2002
  • An integrated structure and controller design approach for rotating cantilever beam is presented. An optimization method is developed for improving positioning performance considering the elastic deformations during high speed rotation and adopting the beam shape and the control gains as design variables. For this end, a dynamic model is setup by the finite element method according to the shape of the beam. The mass and stiffness of the beam are distributed in such a way that the closed-loop poles of the control system should be located leftmost in the complex s-plane. For optimization method, the simulated annealing method is employed which has higher probability to find the global minimum than the gradient-based down-hill methods. Sequential design and simultaneous design methods are proposed to obtain the optimal shape and controller. Simulations are performed with new designs by the two methods to verify the effectiveness of the approach and the results show that the settling time is improved for point-to-point position controls.

Studying the Ephemeris Effect on Position Accuracy Based on Criteria Applied to Baseline Lengths by New MATLAB Program (NMP)

  • Shimaa Farouk;Mahmoud El-Nokrashy;Ahmed Abd-Elhay;Nasr Saba
    • Journal of Astronomy and Space Sciences
    • /
    • v.40 no.3
    • /
    • pp.113-122
    • /
    • 2023
  • Although the Relative Global Navigation Satellite System (GNSS) positioning technique provides high accuracy, it has several drawbacks. The scarcity of control points, the long baselines, and using of ultra-rabid and rabid products increased position errors. This study has designed a New MATLAB Program that helps users automatically select suitable IGS stations related to the baseline lengths and the azimuth between GNSS points and IGS stations. This study presented criteria for the length of the baselines used in Egypt and an advanced estimated accuracy before starting the project. The experimental test studies the performance of the position accuracy related to the relation between three factors: observation session, final, rabid, and ultrarabid products, and the baseline lengths. Ground control point mediates Egypt was selected as a test point. Nine surrounding IGS stations were selected as reference stations, and the coordinates of the tested point were calculated based on them. Baselines between the tested point and the IGS stations were classified regarding proposal criteria. The coordinates of the tested point were obtained in different observation sessions (0.5, 1, 2, 4, 5, 6, 7, 7.5 h). The results indicated that the lengths of the baseline in Egypt were classified short (less than 600 km), medium (600-1,200 km), and long (greater than 1,200 km) and required a minimum observation time of 4, 5, and 7 h to obtain accuracy 10, 19, 48 mm sequentially. The position accuracy was superior for the rapid and the final than the ultra-rapid products by 16%. A short baseline was at the best case; there was a performance in position accuracy with a 57% deduction in observation time compared with the long baseline.

Minimal Clinically Important Difference of Berg Balance Scale scores in people with acute stroke

  • Song, Min-Jeong;Lee, Jae-Hyoung;Shin, Won-Seob
    • Physical Therapy Rehabilitation Science
    • /
    • v.7 no.3
    • /
    • pp.102-108
    • /
    • 2018
  • Objective: To investigate whether the Minimal Clinically Important Difference (MCID) clinically defines improvement of Berg Balance Scale (BBS) scores in people with acute stroke in response to rehabilitation. Design: Retrospective study. Methods: Seventy-three participants with acute stroke participated in the study. Balance evaluation was performed using the BBS. All patients received rehabilitation with physical therapy for 4 weeks, 5 times a week, for 2 hours and 20 minutes a day. An anchor-based approach using the clinical global impression was used to determine the MCID of the BBS. The MCID was used to define the minimum change in the BBS total score (postintervention-preintervention) that was needed to perceive at least a 3-point improvement on the global rating of change. Receiver operating characteristic (ROC) curves was used to define the cut-off values of the optimal MCID of the BBS in order to discriminate between improvement and no improvement groups. Results: The optimal MCID cut-off point for the BBS change scores was 12.5 points for males with a sensitivity (Sn) of 0.62 and a specificity (Sp) of 0.89, and 12.5 points for females with a Sn of 0.69 and Sp of 0.85. The area under the curve of the ROC curve for all participants were 0.84 (95% confidence interval [CI], 0.72; 0.95, p<0.001), and 0.89 (95% CI, 0.77; 1.00, p<0.001), respectively. Conclusions: The MCID for improvement in balance as measured by the BBS was 13.5 points, indicating that the MCID does clinically detect changes in balance abilities in persons with stroke.

A Study on Minimum Weight Design of Horizontal Corrugated Bulkheads for Chemical Tankers (화학제품 운반선 수평 파형격벽의 최소중량설계에 관한 연구)

  • Shin, Sang-Hoon;Ko, Dae-Eun
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.17 no.9
    • /
    • pp.51-56
    • /
    • 2016
  • Corrugated bulkheads have many advantages compared to stiffened bulkheads, and they have thus been used for the cargo tank bulkheads of commercial vessels, such as bulk carriers, product oil carriers, and chemical tankers. Various studies have been carried out to find the optimum corrugation shape for bulk carriers, but optimum design studies for chemical tankers with bulkheads made of high-priced materials are scarce. The purpose of this study is to develop a minimum weight design method for horizontal corrugated bulkheads for a chemical tanker. An evolution strategy (ES) that searches for a reliable global optimum point was applied as an optimization technique, and the structural safety of the optimum design was verified through structural analysis using the finite element method (FEM). The results were compared with those of an existing ship, which showed a weight reduction of about 14% with equivalent structural strength.