Solar cell silicon wafer cutting parameter prediction method based on neural network

Abstract

The invention discloses a solar cell silicon wafer cutting parameter prediction method based on a neural network, which relates to the technical field of the neural network. The method comprises the following steps: collecting sample data, selecting different cutting parameters, cutting the silicon ingot with a cutting machine, and measuring the surface roughness of the silicon wafer; training theneural network according to the appropriate parameters and network structure, and continuously updating the weights of each neuron according to the error value, and achieving the optimal matching ratio until the error reaches the limited standard; performing parameter prediction through a prediction model, comparing the relationship between surface roughness and cutting parameters, and finding the optimal configuration of cutting parameters corresponding to surface roughness. The method of the invention can establish a neural network prediction model and carry out parameter prediction by relying on a small amount of sample data, and according to the prediction result, the optimal cutting parameters can be selected on the premise of considering low roughness and fast cutting.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a method for predicting cutting parameters of silicon wafers of solar cells based on neural networks. Background technique [0002] In recent years, the country has gradually begun to attach importance to the development of green industries, and solar cells are an environmentally friendly and green industry that uses solar power to generate electricity. In solar cell production, the processing cost of cutting silicon ingots into wafers (slicing) accounts for 28% of the total cost of solar cell module production. In recent decades, the use of DWS to cut silicon ingots has become the current trend for solar cells due to its high production capacity, low material consumption, precise thickness measurement and low surface roughness (Ra) of the cut silicon wafers. A conventional method in the field of silicon wafer processing. During DWS processing, the cutting time is long ...

AI Technical Summary

Problems solved by technology

[0003] Due to the large number of parameters and the wide range of options for each parameter, the method of controlling variables needs to measure a large amount of data, which is a great waste of material and time, and the relationship between each group of data is relatively complicated, so it is difficult to find the optimal cutting parameter

Images