scholarly journals Optimization Analysis Method of New Orthotropic Steel Deck Based on Backpropagation Neural Network-Simulated Annealing Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Xiuli Xu ◽  
Kewei Shi ◽  
Xuehong Li ◽  
Zhijun Li ◽  
Rengui Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Parameter Optimization ◽  
Design Parameter ◽  
Stress Amplitude ◽  
Optimization Method ◽  
Backpropagation Neural Network ◽  
Orthotropic Steel Deck ◽  
Weighting Coefficients ◽  
Steel Deck

To study the effects of the fatigue performance due to the major design parameter of the orthotropic steel deck and to obtain a better design parameter, a construction parameter optimization method based on a backpropagation neural network (BPNN) and simulated annealing (SA) algorithm was proposed. First, the finite element (FE) model was established, and the numerical results were validated against available full-scale fatigue experimental data. Then, by calculating the influence surface of each fatigue detail, the most unfavorable loading position of each fatigue detail was obtained. After that, combined with the data from actual engineering applications, the weight coefficient of each fatigue detail was calculated by an analytic hierarchy process (AHP). Finally, to minimize the comprehensive stress amplitude, a BPNN and SA algorithm were used to optimize the construction parameters, and the optimization results for the conventional weight coefficients were compared with the construction parameters. It can be concluded that compared with the FE method through single-parameter optimization, the BPNN and SA method can synthetically optimize multiple parameters. In addition, compared with the common weighting coefficients, the weighting coefficients proposed in this paper can be better optimized for vulnerable parts. The optimized fatigue detail stress amplitude is minimized, and the optimization results are reliable. For these reasons, the parameter optimization method presented in this paper can be used for other similar applications.

Free Parameter Optimization of DTMDs Based on Improved Hybrid Genetic-Simulated Annealing Algorithm

2020 ◽  
Vol 20 (03) ◽  
pp. 2050031
Author(s):  
Qiang Han ◽  
Xuan Zhang ◽  
Kun Xu ◽  
Xiuli Du
Keyword(s):  
Simulated Annealing ◽  
Parameter Optimization ◽  
Free Parameter ◽  
Simulated Annealing Algorithm ◽  
Optimization Method ◽  
Design Parameters ◽  
Mass Ratio ◽  
Tuned Mass Dampers ◽  
Genetic Simulated Annealing Algorithm ◽  
Annealing Algorithm

The optimum design of distributed tuned mass dampers (DTMDs) is normally based on predefined restrictions, such as the location and/or mass ratio of the tuned mass dampers (TMDs). To further improve the control performance, a free parameter optimization method (FPOM) is proposed. This method only restricts the total mass of the DTMDs system and takes the installation position, mass ratio, stiffness and damping of each TMD as parameters to be optimized. An improved hybrid genetic-simulated annealing algorithm (IHGSA) is adopted to find the optimum values of the design parameters. This algorithm can solve the non-convexity and multimodality problems of the objective function and is quite effective in dealing with the large amount of computations in the free parameter optimization. A numerical benchmark model is adopted to compare the control efficiency of FPOM with conventional control scenarios, such as single TMD, multiple TMDs and DTMDs optimized through conventional methods. The results show that the DTMDs system optimized by using FPOM is superior to the other control scenarios for the same value of mass ratio.

scholarly journals An Improved Neural Network Based on Parasitism – Predation Algorithm for an Automatic Voltage Regulator

2021 ◽  
Vol 19 (2) ◽  
pp. 136-144
Author(s):  
Widi Aribowo ◽  
Bambang Suprianto ◽  
I Gusti Putu Asto Buditjahjanto ◽  
Mahendra Widyartono ◽  
Miftahur Rohman
Keyword(s):  
Neural Network ◽  
Time Delay ◽  
Recurrent Neural Network ◽  
Optimization Method ◽  
Voltage Regulator ◽  
Backpropagation Neural Network ◽  
Automatic Voltage Regulator ◽  
Distributed Time Delay ◽  
Rotor Angle ◽  
Elman Recurrent Neural Network

The parasitism – predation algorithm (PPA) is an optimization method that duplicates the interaction of mutualism between predators (cats), parasites (cuckoos), and hosts (crows). The study employs a combination of the PPA methods using the cascade-forward backpropagation neural network. This hybrid method employs an automatic voltage regulator (AVR) on a single machine system, with the performance measurement focusing on speed and the rotor angle. The performance of the proposed method is compared with the feed-forward backpropagation neural network (FFBNN), cascade-forward backpropagation neural network (CFBNN), Elman recurrent neural network (E-RNN), focused time-delay neural network (FTDNN), and distributed time-delay neural network (DTDNN). The results show that the proposed method exhibits the best speed and rotor angle performance. The PPA-CFBNN method has the ability to reduce the overshoot of the speed by 1.569% and the rotor angle by 0.724%.

scholarly journals Parameter Optimization on FNN/PID Compound Controller for a Three-Axis Inertially Stabilized Platform for Aerial Remote Sensing Applications

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Xiangyang Zhou ◽  
Hao Gao ◽  
Yuan Jia ◽  
Lingling Li ◽  
Libo Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Parameter Optimization ◽  
Fuzzy Neural Network ◽  
Back Propagation ◽  
Optimization Method ◽  
Sensing Applications ◽  
Fuzzy Neural ◽  
Composite Parameter ◽  
Stabilized Platform ◽  
Neural Network Pid

This paper presents a composite parameter optimization method based on the chaos particle swarm optimization and the back propagation algorithms for a fuzzy neural network/proportion integration differentiation compound controller, which is applied for an aerial inertially stabilized platform for aerial remote sensing applications. Firstly, a compound controller combining both the adaptive fuzzy neural network and traditional PID control methods is developed to deal with the contradiction between the control precision and robustness due to disturbances. Then, on the basis of both the chaos particle swarm optimization and the back propagation compound algorithms, the parameters of the fuzzy neural network/PID compound controller are optimized offline and fine-tuned online, respectively. In this way, the compound controller can achieve good adaptive convergence so as to get high stabilization precision under the multisource dynamic disturbance environment. To verify the method, the simulations are carried out. The results show that the composite parameter optimization method can effectively enhance the convergence of the controller, by which the stabilization precision and disturbance rejection capability of the proposed fuzzy neural network/PID compound controller are improved obviously.

Parameter Optimization Method of Screw Axis with Variable Diameters and Different Pitches Based on PSO-BP NN

2014 ◽  
Vol 1006-1007 ◽  
pp. 403-406
Author(s):  
Zhang Ping You ◽  
Wen Hui Zhang ◽  
Xiao Ping Ye
Keyword(s):  
Neural Network ◽  
Parameter Optimization ◽  
Optimization Method ◽  
Bp Algorithm ◽  
The Other ◽  
Optimization Approach ◽  
Screw Axis ◽  
Classic Theory ◽  
Set Up ◽  
The Relationship

Parameter optimization of screw axis with variable diameters and different pitches is very important to improve the performance of material conveying equipment. But it is a trouble thing with classic theory modeling because of the complexity of material fluidity and screw structure. A PSO-trained BP algorithm is applied to establish the screw axis parameter optimization neural network (NN) model.Taking asphalt transfer vehicle as an example, PSO-BP NN is applied to set up the relationship between input parameters and aim parameter. Practical example shows that the PSO-BP NN has faster convergence and higher computational precision than the other three investigated algorithms, and it provides a powerful parameter optimization approach for screw axis with variable diameters and different pitches.

Parameter optimization of a hydraulic engine mount based on a genetic neural network

2009 ◽  
Vol 223 (9) ◽  
pp. 1109-1117 ◽  
Author(s):  
Q Li ◽  
J-C Zhao ◽  
B Zhao ◽  
X-S Zhu
Keyword(s):  
Neural Network ◽  
Parameter Optimization ◽  
Dynamic Characteristics ◽  
Structural Parameters ◽  
Optimal Solution ◽  
Optimization Method ◽  
Test System ◽  
Genetic Neural Network ◽  
Engine Mount ◽  
Optimization Methodology

Hydraulic engine mounts (HEMs) are important vehicle components to isolate the vehicle structure from engine vibration. A parameter optimization methodology for an HEM based on a genetic neural network (NN) model is proposed in this study. Samples of HEMs with different structures and rubber materials are manufactured and their dynamic characteristics are tested on an MTS 831 elastomer test system. Then the test results are used as samples to train the NN model which defines the non-linear global mapping relationship between the HEM's structural parameters and its dynamic characteristics. The fitness values of the population in the genetic algorithm are calculated by the trained NN model, and the optimal solution was acquired with the mutation of population. Finally, experiments are made to validate the reliability of the optimal solution. The proposed optimization method can specify the structures and materials of HEMs to meet the design requirements automatically.

scholarly journals Predicting the Number of COVID-19 Sufferers in Malang City Using the Backpropagation Neural Network with the Fletcher–Reeves Method

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Syaiful Anam ◽  
Mochamad Hakim Akbar Assidiq Maulana ◽  
Noor Hidayat ◽  
Indah Yanti ◽  
Zuraidah Fitriah ◽  
...  
Keyword(s):  
Neural Network ◽  
Convergence Rate ◽  
Gradient Descent ◽  
Infected Individual ◽  
Prediction Method ◽  
Optimization Method ◽  
Descent Method ◽  
Gradient Descent Method ◽  
Backpropagation Neural Network ◽  
Congenital Diseases

COVID-19 is a type of an infectious disease that is caused by the new coronavirus. The spread of COVID-19 needs to be suppressed because COVID-19 can cause death, especially for sufferers with congenital diseases and a weak immune system. COVID-19 spreads through direct contact, wherein the infected individual spreads the COVID-19 virus through cough, sneeze, or close contacts. Predicting the number of COVID-19 sufferers becomes an important task in the effort to curb the spread of COVID-19. Artificial neural network (ANN) is the prediction method that delivers effective results in doing this job. Backpropagation, a type of ANN algorithm, offers predictive problem solving with good performance. However, its performance depends on the optimization method applied during the training process. In general, the optimization method in ANN is the gradient descent method, which is known to have a slow convergence rate. Meanwhile, the Fletcher–Reeves method has a faster convergence rate than the gradient descent method. Based on this hypothesis, this paper proposes a prediction model for the number of COVID-19 sufferers in Malang using the Backpropagation neural network with the Fletcher–Reeves method. The experimental results show that the Backpropagation neural network with the Fletcher–Reeves method has a better performance than the Backpropagation neural network with the gradient descent method. This is shown by the Means Square Error (MSE) resulting from the proposed method which is smaller than the MSE resulting from the Backpropagation neural network with the gradient descent method.

Sign in / Sign up

Export Citation Format

Share Document