Semiconductor process data correction method based on correlation entropy and deep neural network
A deep neural network and process data technology, applied in the field of semiconductor process data correction based on correlation entropy and deep neural network, can solve problems such as inappropriate correction results and failure to consider relationships, etc., to improve process performance and maintenance efficiency, reduce Disturbance of random and severe errors, effect of good correction results
Active Publication Date: 2020-10-30
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this method only considers the statistical knowledge of a single variable, and does not consider the relationship between other variables in the whole process, which may cause inappropriate correction results
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
[0063] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.
[0064] Taking the estimation of the deposition process results of a domestic factory as an example, the virtual measurement of the wafer height value through the multi-stage chemical process is carried out.
[0065] During production, the chemical vapor deposition process is similar to the process of applying solid thin film coatings on surfaces often used in the semiconductor industry. This process is complex because it involves many chemical reactions, and the reactors in a multi-reactor system are independently controlled to allow the film to be deposited in the process chamber under various conditions. Chemical vapor deposition equipment is equipped with a considerable number of sensors. Th...
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 semiconductor process data correction method based on correlation entropy and a deep neural network. The method comprises the following steps of: (1) collecting an output signal of a process variable sensor corresponding to a variable to be corrected; (2) inputting each variable into the established deep neural network model, extracting correlation information of the variables layer by layer, collecting features of the last layer of the model, outputting the features to a mapping function, comparing the features with the input variables, and establishing a regressionmodel; (3) storing the parameter weight of the current model, calculating a final objective function value, and under the condition that the final objective function value does not meet a stop condition, updating the parameter weight and repeating the step (2); (4) changing the number of network layers and the number of feature iteration layers, and repeating the steps (2) and (3) until reaching the maximum number of layers; and (5) selecting to obtain the network layer number and the feature iteration layer number with the best correction result, and storing the parameter values of each layer, and calculating to-be-corrected data to obtain a correction value. According to the semiconductor process data correction method based on the correlation entropy and the deep neural network of the invention, a data correction result with a lower error is obtained.
Description
technical field [0001] The invention belongs to the field of process monitoring in industrial systems, and in particular relates to a semiconductor process data correction method based on correlation entropy and deep neural network. Background technique [0002] In recent years, data-driven approaches such as process monitoring, soft sensing, etc. have been established as powerful process control tools in the semiconductor industry. Therefore, the reliability and accuracy of measured process data is critical to the efficient, profitable and safe operation of plants in the chemical industry. [0003] However, due to factors such as process variability and limitations of measurement techniques, the data measured online are usually disturbed by random errors and significant errors. By improving the raw data set, process performance and maintenance efficiency can be significantly improved. Therefore, data rectification, which can mitigate the effects of errors in raw data, has...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G01D18/00G06N3/04G06N3/08
CPCG01D18/00G06N3/08G06N3/048G06N3/045
Inventor 谢磊吴小菲徐浩杰苏宏业
Owner ZHEJIANG UNIV