Electric energy meter fault classification method and device based on MATLAB neural network
A neural network and fault classification technology, applied in the field of electric energy meters, can solve problems such as low detection efficiency and large task load
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0050] see figure 1 as well as figure 2 , this embodiment provides a MATLAB neural network-based electric energy meter fault classification method, which is applied to software fault classification of smart electric energy meters, also to hardware fault classification, and also to fault classification combining software and hardware. The classification method classifies electric energy meter faults based on the MATLAB neural network, and includes the following steps, namely steps S1-S5. Among them, the neural network has a three-layer structure, and the three-layer structure is an input layer, a hidden layer, and an output layer. In other embodiments, the neural network may have more hidden layer structures, which can be selected according to actual needs.
[0051] Step S1: Extract common fault types of electric energy meters and their corresponding software and hardware features, and establish a fault type matrix and corresponding feature data matrix. In this embodiment, th...
Embodiment 2
[0061] This embodiment provides a kind of electric energy meter fault classification method based on MATLAB neural network, and this method is similar to the method of embodiment 1, difference is that this embodiment provides the calculation formula of hidden layer neuron number, and calculation formula is:
[0062]
[0063] In the formula, M is the number of neurons in the hidden layer, N is the number of neurons in the input layer, L is the number of neurons in the output layer; α is a constant, and its value ranges from 1 to 10.
[0064] For example, if the number of neurons in the input layer is 8, the number of neurons in the output layer is 6, and α is 2, then the number of neurons in the hidden layer M=4+2=6. However, this formula may calculate a fractional part, therefore, in some embodiments, after optimizing this formula, the following optimization formula is obtained:
[0065]
[0066] In the formula, INT() is an upward rounding function, so that no matter W...
Embodiment 3
[0072] This embodiment provides a fault classification method for electric energy meters based on MATLAB neural network, which is similar to the method in Embodiment 2, except that the calculation formula for the number of neurons in the hidden layer is different. In this embodiment, the calculation formula is:
[0073] M=log 2 N
[0074] Obviously, in this embodiment, the number of neurons in the hidden layer is only determined by the number of neurons in the input layer, and no information about the number of neurons in the output layer is required. For some embodiments, neurons in the hidden layer are only associated with neurons in the input layer In terms of , the calculation formula is more reasonable, and it is also in line with the actual construction environment of the neural network.
[0075] Of course, the formula can be optimized here, and the optimized formula is: M=INT(log 2 N).
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


