Ning Lv

A fault diagnosis model through G-K fuzzy clustering

A new method for fast building the knowledge based fault diagnosis model by means of fuzzy clustering is proposed. The scheme is contrived by Gustafson-Kessel (GK) algorithm, which is of many good properties. In this paper, it is first investigated how to integrate the properties of fault diagnosis systems into the GK clustering algorithm in the product space of input and output variables. Then the way to convert the fuzzy clusters to the fault diagnosis model is suggested. Hence, an efficient algorithm to acquire the knowledge-based fault diagnosis model from observations is worked out. As a result, the obtained fault diagnosis model can identify fault patterns of different shape and orientation in one data set. Moreover, by introducing the concept of the fuzzy degree of faultiness (DoF), the proposed approach seems to be much more flexible and with more powerful ability to deal with data contaminated by noise compared with the traditional fault diagnosis method. Finally, an experiment of the fault diagnosis of a satellite power supply subsystem demonstrates the effectiveness of the proposed fault diagnosis model.

A novel feature selection approach by hybrid genetic algorithm

Feature selection plays an important role in pattern classification. In this paper, a hybrid genetic algorithm (HGA) is adopted to find a subset of the most relevant features. The approach utilizes an improved estimation of the conditional mutual information as an independent measure for feature ranking in the local search operations. It takes account of not only the relevance of the candidate feature to the output classes but also the redundancy between the candidate feature and the already-selected features. Thus, the ability of the HGA to search for the optimal subset of features has been greatly enhanced. Experimental results on a range of benchmark datasets demonstrate that the proposed method can usually find the excellent subset of features on which high classification accuracy is achieved.

The Fault Diagnosis Algorithm of PLS-LSSVM Process Based on Base Vector Space

The method of least squares support vector machine has been improved based on base vector space theory, which solved the problem of weak handling ability of nonlinear, sparsity and variable multiple correlation in the fault diagnosis process for LSSVM. This article proposed a double sections fault diagnosis algorithm combined PLS with LSSVMBVS, it first builds regression analysis model, then puts the detected fault data in the trained LSSVMBVS classifier, diagnosing troubles. It verified the algorithm has better prediction accuracy and generalization performance by the TE platform.

Fault Diagnosis Model of Beer Fermentation Process Based on Multiway Kernel Principal Component Analysis

Aiming at the limitation of the application of principal component analysis model for fault diagnosis in nonlinear time-varying process, kernel transformation theory is introduced into the data feature extraction of nonlinear space, on the basis of the periodic characteristics of the batch process, putting forward a kind of improved multi-way kernel principal component analysis fault diagnosis model, which effectively solves the nonlinear problem of process data and ensures integrity of data and information extraction. By comparing with other methods in experiment, the results show that the proposed method has good real-timing and accuracy to slow time-varying of batch process.

Based on PID Optimization Of Synchronous Motor Control

In view of the automatic handling stackers master-slave synchronous motor transmission system, and put forward a genetic algorithm to optimize the PID controller. The current and speed double closed loop control are used in systems, and PID is adopted in speed loop control. The PID parameters are optimized offline with the genetic algorithm, so as to achieve the high accuracy of the synchronous transmission control of master-slave motor.

A Study on De-Icing Technology for Electric Transmission Line

The article aims to analyze kinds of de-icing methods in detail with the present condition that the transmission lines often suffered serious damage with the deep ice over them. It also points out the development trend of de-icing technology in the next years and provides some advices for the de-icing research work of transmission line in our country.

Delay-dependent robust stability for a class of uncertain time-delay systems

This paper studies the robust stability problem for a class of uncertain linear systems with time-varying delay. A vector inequality and the stability theory of Lyapunov are employed to derive a sufficient condition for the stability of uncertain time-delay systems. The obtained criterion can include information on the size of delay, and therefore, belongs to delay-dependent criterion. An illustrative example is given to show that the obtained criterion is better than the existing one in the literature