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.

Parameter Optimization of High Deposition Rate Laser Cladding Based on the Response Surface Method and Genetic Neural Network Model

2021 ◽  
Vol 48 (6) ◽  
pp. 0602112
Author(s):  
庞祎帆 Pang Yifan ◽  
傅戈雁 Fu Geyan ◽  
王明雨 Wang Mingyu ◽  
龚燕琪 Gong Yanqi ◽  
余司琪 Yu Siqi ◽  
...  
Keyword(s):  
Neural Network ◽  
Response Surface ◽  
Response Surface Method ◽  
Deposition Rate ◽  
Network Model ◽  
Parameter Optimization ◽  
Neural Network Model ◽  
High Deposition Rate ◽  
Surface Method ◽  
Genetic Neural Network

scholarly journals Optimum Design of Structural Parameters for Thin-walled Metal Container

2019 ◽  
Vol 288 ◽  
pp. 01007
Author(s):  
Liao Hongbo ◽  
Yang Dan ◽  
Yin Fenglong ◽  
Liang Xiaodong ◽  
Li Erkang ◽  
...  
Keyword(s):  
Structural Parameters ◽  
Optimization Method ◽  
External Pressure ◽  
Test System ◽  
Manufacturing Cost ◽  
Thin Wall ◽  
Pressure Test ◽  
Critical Instability ◽  
Thin Walled ◽  
Better Than

In order to further increase the volume, reduce the weight and manufacturing cost, the key structural parameters of thin-walled metal packing container are optimized. The instability conditions under circumferential external pressure and axial load are analyzed, a mathematical model with the constraint of critical instability strength, the maximum volume and minimum mass as the objective is constructed. Multi-objective optimization method with nonlinear constraints is used to solve the key structural parameters, such as wall thickness, diameter and height, and the optimization result is calculated by fgoalattain() function in the Matlab optimization toolbox. The instability pressure test system is constructed, the instability pressure of the optimized thin-wall metal packing container is tested. The results show that the unstable pressure is higher than 120kPa, which are better than the design index.

Parameter Optimization of Laser Scribing Technics of 30Q130 Grain-Oriented Silicon Steel Based on Genetic Neural Network

2010 ◽  
Vol 37-38 ◽  
pp. 844-848
Author(s):  
Yu Huang ◽  
Yong Liu ◽  
Guo Li Zhu
Keyword(s):  
Neural Network ◽  
Orthogonal Experiment ◽  
Core Loss ◽  
Optimization Method ◽  
Silicon Steel ◽  
Laser Scribing ◽  
Cold Rolling And Annealing ◽  
Neural Network Prediction ◽  
Genetic Neural Network ◽  
Network Prediction

A laser is often considered to scribe the grain-oriented silicon steel surfaces after cold-rolling and annealing to reduce the core loss. It is necessary to select the best scribing parameters to maximize the reduction in this process. This paper proposed an optimization method of genetic algorithm during laser scribing of 30Q130 steel, by developing an artificial neural network prediction model using a database form a designed orthogonal experiment. The objective was to determine the best combination values of three important scribing parameters, namely scribing velocity, pulse energy and scanning spacing, that can get the largest core loss reduction. An optimized combination of parameters was obtained by this method and then validated by an adding experiment. The result indicates that the optimization model is reliable.

Force Analyzing and Parameter Optimization of the Telescopic In-Pipe Robot

2015 ◽  
Vol 738-739 ◽  
pp. 941-945
Author(s):  
Di Qu ◽  
Hua Song ◽  
Jing Sun
Keyword(s):  
Structural Parameters ◽  
Small Diameter ◽  
Optimal Solution ◽  
Basic Structure ◽  
Optimization Method ◽  
Multi Objective Optimization ◽  
Trenchless Technology ◽  
Motor Torque ◽  
Underground Pipelines ◽  
Locking Mechanism

Typical wheeled or tracked robot could hardly apply to middle or small diameter underground pipelines laid by trenchless technology. Aiming at this kind of pipeline’s characteristics, this paper puts forward a basic structure of telescopic in-pipe robot. To provide necessary theoretical basis for the device selection, the mechanical model and force analyzing are given in detail. The speed of robot, as well as the motor torque of locking mechanism, could be expressed as the function of the robot’s structural parameters. As a result, the robot’s structural parameters take influence on its performance. In order to achieve the best performance, it is necessary to use the multi-objective optimization method to select these parameters. Using the genetic algorithm toolbox, the optimal solution of these parameters was obtained. Based on this, the motor torque of locking mechanism is minimum while the speed of the robot is maximum.

Genetic Neural Network Based Financial Distress Prediction

2014 ◽  
Vol 933 ◽  
pp. 921-925
Author(s):  
Xin Yun Liu ◽  
Heng Jun Liu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Financial Distress ◽  
Structural Parameters ◽  
Optimal Structure ◽  
Structure Parameters ◽  
Financial Distress Prediction ◽  
Distress Prediction ◽  
Genetic Neural Network

Enterprise financial distress prediction based on neural network has some disadvantages, such as complex structure, slow convergence rate and easily falling into local minimum points. The paper presents the genetic neural network based enterprise financial distress prediction. Firstly, the structural parameters of neural network model are encoded and connected into gene sequence to obtain an individual. A certain number of individuals make up a population. Secondly, after the reproduction, crossover and mutation operations upon the population, the best individual, that is the optimal structure parameters of neural network model, is obtained. Finally, the neural network model with the optimal structure parameters is trained by the training samples and the trained neural network model can realize enterprise financial distress prediction. The testing results show that the method achieves higher training speed and lower error rate.

Direct Torque Control of the Genetic Neural Network under the Low-Speed

2012 ◽  
Vol 466-467 ◽  
pp. 694-697
Author(s):  
Lian Zhang ◽  
Wei Lai ◽  
Jie Li
Keyword(s):  
Neural Network ◽  
Structure Learning ◽  
Dynamic Performance ◽  
Asynchronous Motor ◽  
Direct Torque Control ◽  
Optimal Solution ◽  
Torque Control ◽  
Bp Network ◽  
Low Speed ◽  
Genetic Neural Network

For the direct torque control of asynchronous motor rapid response and speed ripple, this article proposes the genetic neural network algorithm based on the model of stator flux, to achieve the selecting of switch state under the low-speed. Using the global optimization and search method of genetic algorithm obtains global optimal solution, while the connection weights and network structure learning improve the training effectiveness of neural network, so that the BP network has better adaptive characteristic. The effectiveness of the design is verified by the simulation, and it shows that the speed control system has good dynamic performance and steady state performance under the low-speed.

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.

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.

Sign in / Sign up

Export Citation Format

Share Document