Xiuqiao Xiang

T-S fuzzy model identification based on a novel fuzzy c-regression model clustering algorithm

This paper proposes a novel approach for identification of Takagi-Sugeno (T-S) fuzzy model, which is based on a new fuzzy c-regression model (FCRM) clustering algorithm. The clustering prototype in fuzzy space partition is hyper-plane, so FCRM clustering technique is more suitable to be applied in premise parameters identification of T-S fuzzy model. A new FCRM clustering algorithm (NFCRMA) is presented, which is deduced from the fuzzy clustering objective function of FCRM with Lagrange multiplier rule, possessing integrative and concise structure. The proposed approach consists mainly of two steps: premise parameter identification and consequent parameter identification. The NFCRMA is utilized to partition the input-output data and identify the premise parameters, which can discover the real structure of the training data; on the other hand, orthogonal least square is exploited to identify the consequent parameters. Finally, some examples are given to verify the validity of the proposed modeling approach, and the results show the new approach is very efficient and of high accuracy.

A new T-S fuzzy-modeling approach to identify a boiler-turbine system

In order to build accurate model for complicated nonlinear system in engineering, like boiler-turbine system, a novel fuzzy-modeling approach is proposed, which is based on a new fuzzy c-regression model (NFCRM) clustering algorithm and is able to determine the right number of rules automatically. In this method, NFCRM is applied to build the fuzzy structure and then identify the premise parameters; a new criterion is proposed to auto determine the number of rules in fuzzy modeling; after the fuzzy rules have been decided, orthogonal least square is exploited to identify the consequent parameters. Simulation examples are given to demonstrate the validity of the proposed modeling approach, and the results show the new approach is very efficient with high accuracy. Finally, the new approach is applied in fuzzy modeling of a typical boiler-turbine system successfully.

Mechanic signal analysis based on the Haar-type orthogonal matrix

Between Haar and Walsh, there exist other Haar-type orthogonal matrixes (HTOMs), which are rarely utilized in practice. In this paper, we introduce HTOMs, which have fast algorithm, to the mechanic signal analysis. Concretely speaking, the mechanic signals are transformed by various HTOMs, which can be generated easily by varying any one of two parameters in the same program, then the performance of the transform results is compared by viewing FDC as the evaluation criterion, and the most optimal HTOM is achieved, which provides guidance and reference for the HTOMs applied in the signal analysis.

Improved algorithm about NSFOT

For the purpose of further saving computing time, an improved algorithm about NSFOT is provided in this paper. That is, by introducing the simple operations such as preprocessing or after-processing, Haar and Walsh transforms are performed conveniently on the multiprocessor. As a result, one large size problem is divided into several small size sub-problems, load on every processor not only decreases greatly but also gets so uniform that much time is saved. Both the theoretical analysis and experimental results demonstrate the effectiveness of the proposed approach.

A new method for automatically identifying the shaft orbit moving direction of hydroelectric generating set

Purpose – Shaft orbit is an important characteristic for vibration monitoring and diagnosing system of hydroelectric generating set. Because of the low accuracy and poor reliability of traditional methods in identifying the shaft orbit moving direction (MD), the purpose of this paper is to present a novel automatic identification method based on trigonometric function and polygon vector (TFPV).Design/methodology/approach – First, some points on shaft orbit were selected with inter‐period acquisition method and joined together orderly to form a complex plane polygon. Second, by using the coordinate transformation and rotation theory, TFPV were applied comprehensively to judge the concavity or convexity of the polygon vertices. Finally, the shaft orbit MD is identified.Findings – The simulation and experiment demonstrate that the method proposed can effectively identify the common shaft orbit MD.Originality/value – In order to identity the shaft orbit MD effectively, a novel automatic identification method ...

Vibration Fault Diagnosis of Hydraulic Generator Units Based on Pattern Recognition and Grey Incidence Analysis

The aim of this investigation is to describe a way of grey incidence analysis to achieve vibration fault pattern recognition for hydraulic generator units. In order to recognise the fault, the collected fault data are analyzed and then standard fault pattern sets of typical vibration faults for hydraulic generator units are founded. Fault pattern recognition is performed by calculating the degree of grey incidence between the pending pattern characteristics and the standard fault pattern sets, according to the criterion for maximum degree of incidence. Results are presented which demonstrate the effectiveness of the proposed method and it can be used as an online diagnosis tool for hydraulic generator units.

Optimum selection of haar type orthogonal matrix in the fault diagnosis

Haar type orthogonal matrices (HTOMs) include Haar, Walsh and other orthogonal matrices intervenient former two. These matrices not only have fast algorithm but also can be obtained conveniently by varying any one of two parameters in the same program. However, they are rarely utilized in practice. For this reason, HTOMs are applied in the fault diagnosis in this paper. Namely, different mechanic state signals are transformed by various HTOMs, respectively. Meanwhile, Fisher classification rule is viewed as the evaluation criterion, and the transform results are compared. As a result, the most optimal HTOM in the fault diagnosis is obtained.

Recognition of Shaft Orbit Based on Walsh Spectrum and Support Vector Machine

In order to recognize shaft orbits exactly and quickly, a novel recognition method based on Walsh spectrum and support vector machine is proposed in this paper. Firstly, distance vector between the point on the shaft orbit and its center is calculated and obtained. Secondly, the distance vector is transformed by Walsh orthogonal matrix, and obtained Walsh spectrum has property of invariance to rotation, scaling and translation. Thirdly, Walsh spectrum, as feature of shaft orbit, is trained by support vector machine, and classifying functions are obtained. Finally, the remaining samples are tested by the classifying functions, and experimental results are encouraging which demonstrates the effectiveness and robustness of the proposed approach.