Design of robotic visual servo control based on neural network and genetic algorithm

Hong-bin, Wang; Liu, Mian

doi:10.1007/s11633-012-0612-x

Cited by 20 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practical engineering applications of the BP neural network method, the numerical optimization performances of the training algorithms used are highly important. 32 Different BP neural networks can be specified in terms of their error backpropagation algorithm; in this paper, the Levenberg–Marquardt (LM) algorithm is adopted and is used to solve for the second derivative of the error to judge the error rate of decline, to adjust the learning rate adaptively and to train the neural network to realize rapid convergence 33–35 .…”

Section: Quality Prediction Methodsmentioning

confidence: 99%

Quality prediction and control of cable harness wiring using extension theory and a backpropagation neural network

Wang

Guo

et al. 2020

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Given that the cable harness wiring quality (CHWQ) of complex mechatronic products is affected by multiple factors and it is difficult to solve the resulting control problems, this paper proposes a quality prediction method for cable harness wiring using extension theory and a backpropagation (BP) neural network. First, a quality prediction framework is designed based on the factors influencing the composition and analysis of the CHWQ. Second, we establish a quality evaluation index system based on five aspects and design a first-level factor set and a second-level factor set. Based on the single factor index for various parameters and evaluation of data after dimensionless parameter processing, we use extension theory and the entropy weight method to determine the membership matrix and the fuzzy weight vector for the first-level evaluation. Additionally, the single factor and the synthetic fuzzy weight vector are determined using the entropy weight method and the analytic hierarchy process (AHP), respectively, and quality grade evaluation based on the fuzzy synthetic evaluation (FSE) method is completed. Finally, we use a three-layer feedforward neural network to predict the quality status of a specific phased array radar system. The results demonstrate that the proposed method can produce increased prediction accuracy.

show abstract

Section: Quality Prediction Methodsmentioning

confidence: 99%

Quality prediction and control of cable harness wiring using extension theory and a backpropagation neural network

Wang

Guo

et al. 2020

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…Then we take the above factors into consideration to limit the result. Finally, we use Genetic Algorithm to solve this problem [2,3].…”

Section: A Main Idea About the Modelmentioning

confidence: 99%

Optimal Design of Crowdsourcing Project Pricing

Lizhi¹,

Chen²,

Zhu³

et al. 2017

Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017)

View full text Add to dashboard Cite

Abstract-Aiming at the problem of the pricing and completion of crowdsourcing project,. we set up a project task pricing design model and solve this model by using genetic algorithm and logistic regression. Meanwhile, we use the differential equation to improve this model. The project task pricing design model is a multi-objective nonlinear programming model. We introduce the concept of company profit to limit the price and regard the profit as our target function. In addition, we consider the members' credit value, the distance between the members to the mission point, the number of members within the mission area and the possibility of members performing tasks to limit target function. In consideration of the possibility of the member performing the task, we used the logistic method to fit it. When considering the integrated reputation of members, we use the entropy weight method to determine the coefficients of each index. Finally, we get the target function values in different cases by using Genetic Algorithm. Meanwhile, we use the differential equation method to set up the price floating model to optimize our existing model. Through the model we established, we can ensure that the tasks issued by the company can be carried out with a higher completion rate in practice, and obtain better profit.

show abstract

“…When the launch energy becomes lower, the region A will shrink to a point and the corresponding trajectory is the optimal one. In this paper, a nominal low energy return orbit is given via the genetic algorithm, because of its advantages on global searching and convergence abilities [15,16] , in which the launch time, initial selenographical longitude and total impulse are the design variables and the weighted sum of launch energy and terminal radius of perigee are the target function. By solving the optimization problem in January of 2020, we can get the optimal nominal return orbit that is shown in Table 1.…”

Section: Nominal Optimal Return Trajectorymentioning

confidence: 99%

Finite thrust transfer strategy designing for low energy moon return based on GPM/VSM

Liu

Jing

Xiao

2015

Int. J. Autom. Comput.

View full text Add to dashboard Cite

In a low energy moon return mission, due to the weak stability of the orbit, it is necessary to implement an accurate orbital maneuver to guarantee a successful return. During the process of getting the optimal thrust control with these two kinds of methods, it is hard to guess the initial value of the co-states in the indirect method while a large amount of calculation is needed to insure the precision in the direct method. To solve the problem, in this paper a combined method is given which has the merit of both direct and indirect methods. In this method, the virtual satellite method (VSM) and the Gauss pseudo-spectral method (GPM) are applied, while the fuel optimal control strategy is computed with GPM to carry out a soft rendezvous between the spacecraft and a hypothetical virtual satellite running on the nominal low energy return orbit so that the spacecraft will enter the return orbit accurately. Compared with the direct and indirect methods, this combined method can avoid guessing the initial value of the co-states and the complexity of calculation is acceptable. According to the simulation results, the spacecraft is inserted to the target return orbit with a high accuracy and also the optimization is very effective.

show abstract

Design of robotic visual servo control based on neural network and genetic algorithm

Cited by 20 publications

References 11 publications

Quality prediction and control of cable harness wiring using extension theory and a backpropagation neural network

Quality prediction and control of cable harness wiring using extension theory and a backpropagation neural network

Optimal Design of Crowdsourcing Project Pricing

Finite thrust transfer strategy designing for low energy moon return based on GPM/VSM

Contact Info

Product

Resources

About