The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In the traditional flatness pattern recognition neural network, the topologic configurations need to be rebuilt with a changing width of cold strip. Furthermore, the large learn assignment, slow convergence, and local minimal in the network are observed. Moreover, going by the structure of the traditional neural network, according to experience, it has been proved that the model is time-consuming...
In order to further improve the accuracy of short-term load forecasting, a selective neural network ensemble method using discrete differential evolution algorithm is proposed. Firstly, the individual vectors in differential evolution algorithm are dispersed. Secondly, a group of RBF neural networks with larger difference are trained independently and a binary bit string in multi-dimensional space...
Reseeding is an effective method to reduce test redundancy, i.e., to reduce test length in Built-in Self-test (BIST) design. In general reseeding method, the seeds were saved in a ROM, however, bringing about higher hardware overhead. Managed by Test Access Port (TAP) controller, an improved resseding method proposed in this paper adopts boundary scan architecture to reseed the test pattern generation...
A discrete time neural network adaptive inversion controller design for a supermaneuverable aircraft nonlinear model is presented. The singular perturbation theory is used to separate the nonlinear dynamics into fast and slow sub-systems; The dynamic inversion is applied to design the control laws for the two sub-systems separately; The neural network adaptive control is based on the dynamic inversion,...
When combining grey system with RBF neural network, local optimization and convergence problems are still existed, so genetic algorithm is introduced to assist the modeling of grey neural network in this paper. Firstly, genetic algorithm is employed to solve the parameters of improved GM(1,1) with Lagrange's value theorem, and then RBF neural network is parallel connected to compensate errors. A new...
This paper discusses the classification on the grade of likelihood of accident occurrence in prediction and severity of the consequences of accidents, based on construction characteristics of large and medium-sized projects and questions put forward in site safety management. Practically, the likelihood of accident occurrence is classified into five fuzzy grades. Under the premise conditions of probable...
In this article, an analytic hierarchy process (AHP) approach is described and applied to a fuzzy synthetic evaluation on customer loyalty of commercial banking industries. Results of the AHP show that the customer loyalty coefficient of certain commercial banking enterprise is within the "very promising" range. In addition, the results also show that repeat purchase intention, referral...
During the product planning phase in QFD (Quality Function Deployment), the final importance of the technical requirements is key to optimize the whole HoQ (House of Quality) and to make deployment decision for the next stage. In the paper, the limitations of traditional methods are analyzed; by using the built product planning HoQ and the available linguistic terms based experts' knowledge, and with...
After analyzing the bidding tactics decision-making index system for BOT projects, the bidding tactics decision-making method is presented by wavelet network learning algorithm based on conjugate gradient method, the decision-making model is set up. The paper bring forward the problem solving method to the above model by optimizing and select the hidden units of wavelet network. An instance is given...
An intelligent model of relative words that concerns semantic similarity is discussed in this paper. Based on this model, a knowledge system capable of semantically calculating and associating has been developed, which enables adapting and/or extending keywords in search process. This paper aims to make information retrieval with semantic ability; as a result, the precision of information retrieval...
Parallel robots have very good performance in terms of rigidity, strength-to-weight ratios and positioning accuracy. A 2-DOF redundantly actuated parallel robot is taken as the object of study in this paper. As far as trajectory tracking performance, controller is essential. In order to improve the trajectory tracking performance, a neural network PID (proportion integral differential) controller...
It is a key problem to represent properly the knowledge in space decision support system. The knowledge has the character of multi-dimension, fuzzy and randomcity in uncertain problems on space decision. In order to improve the ability of dealing with uncertain problems in space decision support system the representation and induction based on cloud model is proposed in this article. Firstly the multi-dimension...
In this paper, the algebraic structure for a class of point fuzzy numbers are investigated that new algebraic operations about point fuzzy numbers are presented, such that point fuzzy numbers set F(R) are F-Abel group, F-linear space, and F-commutative algebra, respectively. Example is also given to illustrate our results.
With the improvement of machining automatization, tool condition on-line monitoring has been a crucial problem and paid more attention. The image processing technology is introduced into the condition monitoring of cutting tool wear. The experimental system on the state of cutting tool condition monitor is designed. Through collecting the online images of cutting tool and machined surface, the pulse-couple...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.