• Citations Per Year
Learn More
BP neural network is easily trapped into the local minimum during the training process, which results that it can't get the optimal solution, even misjudging in device fault diagnosis. Directing to the above problems, a Hopfield-BP neural network fault diagnosis method was proposed, which combined Hopfield neural network, having the global optimal neural(More)
Directing to the inconsistency of the fault diagnosis information, a method of the rules extraction for fault diagnosis based on rough set theory and decision network is proposed. The fault diagnosis decision system attributes are reduced through discernibility matrix and discernibility function firstly, and then a decision network with different reduced(More)
SQL injection is an attack technique used to exploit code by altering back-end SQL statements through manipulating input. This paper proposes a novel methodology of preventing SQL injection attacks by building a protective adaptive shell. The protective shell is located between the application and the back-end database and has three layers to block illegal(More)
Hydraulic control system is a typical highly nonlinear system, the loops of the system are coupled each other, so that the failure modes, failure mechanism of the hydraulic control system is very complex and diverse. Fault diagnosis of hydraulic control system is a uncertainty, incomplete information systems, which makes wrong diagnosis. Directing to the(More)
The paper combined the advantage of Particle Swarm Optimization algorithm (PSO), the global optimizing ability of Hopfield Neural Network, and the teacher supervising features of BP neural network to construct a new equipment fault diagnosis method with higher diagnosis precision, compared with the traditional single BP neural network.
In order to evaluate the bilingual instructing process and help the university acquire timely feedback information from students, a Bilingual Teaching Evaluation System based on BP neural network is established. Based on the investigation and analysis of the bilingual instructing process in Nanchang University, an evaluation index system is built, which(More)
The attribute reduction and value reduction of rough set were discussed in this paper. The discernibility matrix was extended to value reduction firstly and the attribute significance was redefined based on attribute dependence. An algorithm for classification rules extraction based on discernibility matrix and attribute significance is proposed, which(More)
Directing to the low precision of single fault diagnosis method, a decision-level information fusion diagnosis system model was proposed to obtain more reliability and more accurate diagnosis, in which, the method based on the BP neural network was applied to the fault diagnosis firstly, and then the D-S evidence theory was utilized to partial fusions in(More)
  • 1