Generative adversarial network-based non-intrusive household electrical equipment identification method
A kind of electric equipment, non-invasive technology, applied in character and pattern recognition, biological neural network model, neural learning method and other directions, can solve the problem of low accuracy, achieve the effect of easy operation, high recognition accuracy and simple method
Pending Publication Date: 2022-03-15
STATE GRID LIAONING ELECTRIC POWER CO LTD SHENYANG POWER +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the present invention provides a non-intrusive household electrical equipment identification method based on a generative confrontation network to solve the problem of low accuracy in the previous household electrical identification methods
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
[0029] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of approaches consistent with aspects of the invention as recited in the appended claims.
[0030] In order to solve the problem of low accuracy in the previous household power identification methods, this implementation provides a non-intrusive identification method for household electrical equipment based on generative adversarial networks. Class sample data is generated to expand the minority class sample data to achieve the balance of training sample data, and then train the classification neur...
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 non-intrusive household electrical equipment identification method based on a generative adversarial network, and the method employs the generative adversarial network for solving a problem of unbalanced training sample data for the first time, and carries out the secondary inspection of training data generated by the generative adversarial network through sensitivity measurement. Data with relatively high sensitivity is deleted, the authenticity of the generated data is further improved, balanced training sample data is finally obtained, and training of a classification neural network model is carried out, so that accurate identification of the classification neural network model on household power equipment is realized; the recognition method has the advantages of being simple, easy to operate, high in recognition accuracy and the like.
Description
technical field [0001] The disclosure of the present invention relates to the technical field of household electrical equipment identification, and in particular to a non-invasive identification method of household electrical equipment based on a generative confrontation network. Background technique [0002] The identification of household electrical equipment is to identify what type of electrical appliances the electrical user owns through the total electricity consumption data of the electrical user's household. Therefore, electrical equipment identification is also regarded as a classification problem, and the proposed model is driven by data . [0003] The input data of the network model is based on time series. For time series data, the conventional one-dimensional convolution operation can only extract useful features from the neighborhood sequence, which is not suitable for feature extraction of long time series data. . And for the deep learning model, generally t...
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): G06Q50/06G06K9/62G06N3/04G06N3/08
CPCG06Q50/06G06N3/04G06N3/08G06F18/214G06F18/24
Inventor 王浩淼李铁石白明王明睿赵博远吴冲赵昊东杨勇韩放
Owner STATE GRID LIAONING ELECTRIC POWER CO LTD SHENYANG POWER