Power quality signal disturbance classification method based on T-S fuzzy model
A fuzzy model, power quality technology, applied in character and pattern recognition, complex mathematical operations, instruments, etc., can solve the problems affecting the generalization ability and classification ability of the classifier, and achieve the effect of strong classification accuracy and robustness
Pending Publication Date: 2022-04-15
MAANSHAN POWER SUPPLY COMPANY STATE GRID ANHUI ELECTRIC POWER
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This type of method is simple and feasible, but the selection of training sample data and quantity will greatly affect the generalization ability and classification ability of the classifier
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0050] Such as figure 1 As shown, a power quality signal disturbance classification method based on the T-S fuzzy model includes the following steps:
[0051] Step 1: Construct the T-S fuzzy model, train the model to determine the model parameters, and form a fuzzy classifier;
[0052] Step 2: Using the fuzzy classifier formed in step 1 to identify and classify the disturbance signal;
[0053] The process of determining model parameters in step 1 is as follows:
[0054] S1: Determine the type and quantity p of the signal disturbance feature, as the input variable of the fuzzy model, determine the initial clustering number c=p;
[0055] The process of determining the type and quantity of disturbance features is as follows:
[0056] Let the signal be h(x), and perform S transformation on the signal to obtain the S matrix:
[0057]
[0058...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a power quality signal disturbance classification method based on a T-S fuzzy model, and the method comprises the following steps: 1, constructing a T-S fuzzy model, training the model, determining model parameters, and forming a fuzzy classifier; 2, a fuzzy classifier is adopted to identify and classify disturbance signals; the model parameter determination process comprises the following steps: S1, determining the type and number p of signal disturbance characteristics as an input variable of a fuzzy model, and determining an initial clustering number; s2, calculating a discourse domain interval corresponding to the disturbance characteristics according to the multiple disturbance type sample data; s3, performing fuzzy division on the discourse domain interval in the step S2, and determining a discourse domain space corresponding to the disturbance type; s4, inputting a to-be-classified disturbance signal characteristic value to obtain a conclusion parameter aip; according to the method, the nonlinear disturbance characteristics of a plurality of transient power quality disturbance signals are considered, the complex nonlinear fitting of the system is realized, and the method has very high classification accuracy and robustness.
Description
technical field [0001] The invention relates to signal transient disturbance classification, in particular to a method for classification of power quality signal disturbance based on a T-S fuzzy model. Background technique [0002] With the wide application of power electronic equipment, the components of different nonlinear, impact and fluctuating loads have increased greatly, making the power quality problems of power systems more and more serious. The transient disturbance of power quality is short in duration, and has complexity, diversity and overlapping characteristics. In order to find the cause of transient disturbance in power quality degradation in time, it is necessary to accurately identify and classify the disturbance data. [0003] In recent years, scholars at home and abroad have proposed many methods for transient disturbance classification. Traditional power quality transient disturbance classifiers are all machine learning methods based on training. They le...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/62G06F17/16
Inventor 马伟陈建方汤俊珺戎瑜王健郑迪文
Owner MAANSHAN POWER SUPPLY COMPANY STATE GRID ANHUI ELECTRIC POWER