Spatial domain regression network for lithography alignment measurement and its use method
By using a space regression network in lithography alignment measurement, the problem that existing lithography alignment measurement algorithms cannot effectively deal with error and nonlinear problems are solved, and high-precision and high-efficiency lithography alignment is achieved.
Patent Information
- Application Number
- CN202411973760.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-04
AI Technical Summary
The existing lithographic alignment measurement algorithm cannot automatically fit and eliminate error models, cannot effectively demodulate complex alignment signals, and cannot effectively deal with nonlinear quantities, resulting in large measurement errors and limits in accuracy.
A space regression network is adopted, including multiple 3x3 convolutional layers, BN layers, ReLU activation function, maximum pooling layer and residual block structure, and finally connected to a fully connected layer to process lithography alignment signals.
This method can automatically fit error models of multiple error sources, reduce measurement errors, process complex alignment signals, effectively deal with nonlinear problems, and improve the accuracy and efficiency of lithographic alignment.
Smart Images
Figure CN119761424A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of semiconductor processing, and in particular relates to a spatial domain regression network for photolithography alignment measurement and a use method thereof. Background Art
[0002] Photolithography alignment is a key step in the photolithography process, and its purpose is to ensure that the pattern on the mask is accurately aligned with the pattern on the silicon wafer to ensure accurate overlay between the patterns after exposure. In the process of realizing the present invention, the inventors found that the existing photolithography alignment measurement algorithm has at least the following problems: it is unable to automatically fit and eliminate the error model of various error sources, resulting in large measurement errors; it is unable to effectively demodulate complex alignment signals, resulting in additional measurement errors brought by the algorithm; it is unable to effectively deal with nonlinear quantities in the measurement system, resulting in a limit to the accuracy of the algorithm strategy. Summary of the invention
[0003] The present invention aims to solve the above technical problems at least to a certain extent. To this end, the present invention aims to provide a spatial domain regression network for lithography alignment measurement and a method for using the network.
[0004] The technical solution adopted by the present invention is:
[0005] A spatial domain regression network for lithography alignment measurement includes multiple 3x3 convolutional layers, each convolutional layer is connected with a BN layer and a ReLU activation function, a maximum pooling layer is used after every two convolution operations; a residual block structure is set between every two convolution operations; and a fully connected layer is set after the last convolutional layer.
[0006] Preferably, there are twelve convolutional layers, and the number of filters in each convolutional layer is 32, 32, 32, 32, 64, 64, 64, 64, 128, 128, 128, 128, respectively.
[0007] Preferably, there are two fully connected layers, and the two fully connected layers respectively contain 1024 units and 1 unit.
[0008] A method for using a spatial domain regression network, comprising:
[0009] S1, overlap the silicon wafer and the mask, and let the translation stage start to perform step scanning. At each scanning position, the camera is used to collect and image the formed moiré fringes to form a data set;
[0010] S2, taking the image as the input image and the position value of the displacement stage as the true value, inputting the spatial domain regression network for training, and completing the training by minimizing the loss through repeated training;
[0011] S3. Use the trained spatial domain regression network to perform regression prediction on the actually collected alignment signal.
[0012] Preferably, the mask surface is etched with linear or circular alignment marks. The step scan is a one-dimensional scan or a two-dimensional scan.
[0013] The present invention uses a spatial domain regression network to process data to achieve sub-nanometer lithography alignment. The beneficial effects of the present invention are:
[0014] The spatial domain regression network can automatically fit the error models of various error sources and eliminate them, thereby reducing measurement errors; it can process various complex alignment signals and / or graphics, and can effectively deal with nonlinear problems in the strategy system; the present invention uses global signals for alignment, has good robustness, and has no stringent requirements on beam quality and measurement environment; it has fast alignment speed and high alignment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 It is a schematic diagram of the network structure of the spatial domain regression network used for lithography alignment measurement in the present invention.
[0016] Figure 2 It is a structural schematic diagram of the residual block structure of the present invention. DETAILED DESCRIPTION
[0017] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0018] It should be understood that it should also be noted that in the embodiment, the functions / actions that appear may be different from the order in which the drawings appear. For example, depending on the functions / actions involved, they can actually be executed substantially concurrently, or two figures shown in succession can sometimes be executed in the reverse order.
[0019] like Figure 1 and Figure 2 As shown, a spatial domain regression network for lithography alignment measurement of the present embodiment includes twelve 3x3 convolutional layers, each convolutional layer is followed by a BN (Batch Normalization) layer and a ReLU activation function, and the number of filters in each convolutional layer is 32, 32, 32, 32, 64, 64, 64, 64, 128, 128, 128, 128, respectively.
[0020] In the sample-based discretization process, a 2x2 maximum pooling layer (MaxPool) is used after every two convolution operations; since the depth of feature representation is crucial to the regression accuracy, a residual block structure (Residual Block) is set between every two convolution operations; two fully connected layers (Fully Connect) are set after the last convolution layer, and the two fully connected layers contain 1024 units and 1 unit respectively.
[0021] The input of the spatial domain regression network is a 512x512 single-channel grayscale moiré fringe image, which reflects the relative displacement Δx and is used for network training or prediction.
[0022] The method for using the above-mentioned spatial domain regression network includes the following steps:
[0023] S1. Overlap the silicon wafer and the mask, etch linear or circular alignment marks on the mask surface, and let the translation stage start one-dimensional or two-dimensional step scanning. Use the camera to collect and image the formed moiré fringes at each scanning position to form a data set.
[0024] S2, taking the image as the input image and the position value of the displacement stage as the true value, inputting the above-mentioned spatial domain regression network for training, and completing the training by minimizing the loss (the standard is L1 or L2 loss) through repeated training;
[0025] S3. Use the trained spatial regression network to perform regression prediction on the alignment signal actually collected to realize the alignment measurement function.
[0026] The method of using this embodiment uses a spatial domain regression network to improve the accuracy of the signal analysis algorithm of the lithography alignment system.
[0027] The present invention is not limited to the above-mentioned optional implementation modes. Anyone can derive other various forms of products under the inspiration of the present invention. However, no matter what changes are made in the shape or structure, all technical solutions that fall within the scope defined by the claims of the present invention fall within the protection scope of the present invention.
Claims
1. A spatial domain regression network for lithography alignment measurement, characterized in that: It includes multiple 3x3 convolutional layers, each of which is followed by a BN layer and a ReLU activation function. A maximum pooling layer is used after every two convolution operations. A residual block structure is set between every two convolution operations. A fully connected layer is set after the last convolution layer.
2. The spatial domain regression network according to claim 1, characterized in that: There are twelve convolutional layers, and the number of filters in each convolutional layer is 32, 32, 32, 32, 64, 64, 64, 64, 128, 128, 128, 128, respectively.
3. The spatial domain regression network according to claim 1, characterized in that: There are two fully connected layers, and the two fully connected layers respectively contain 1024 units and 1 unit.
4. A method for using the spatial domain regression network according to any one of claims 1 to 3, characterized in that: include: S1, overlap the silicon wafer and the mask, and let the translation stage start to perform step scanning. At each scanning position, the camera is used to collect and image the formed moiré fringes to form a data set; S2, taking the image as the input image and the position value of the displacement stage as the true value, inputting the spatial domain regression network for training, and completing the training by minimizing the loss through repeated training; S3. Use the trained spatial domain regression network to perform regression prediction on the actually collected alignment signal.
5. The method of use according to claim 4, characterized in that: A linear or circular alignment mark is etched on the mask surface.
6. The method of use according to claim 4, characterized in that: The step scan is a one-dimensional scan or a two-dimensional scan.