AI-Optimized Maskless Digital Lithography Method for Micro-LEDs

Abstract

This application discloses an AI-optimized Micro-LED maskless digital lithography method, apparatus, and storage medium, relating to the field of lithography. The method includes acquiring target lithography performance parameters and a bidirectional neural network. The bidirectional neural network includes a forward network and a backward network. The forward network is trained to predict corresponding lithography performance parameters based on lithography process parameters, and the backward network is trained to predict corresponding lithography process parameters based on lithography performance parameters. Candidate lithography process parameters corresponding to the target lithography performance parameters are obtained through the backward network. Reference lithography performance parameters corresponding to the candidate lithography process parameters are obtained through the forward network. When the reference lithography performance parameters are the same as the target lithography performance parameters, the candidate lithography process parameters are used as the target lithography process parameters for the Micro-LED maskless digital lithography system. This allows for the rapid determination of lithography process parameters that meet the lithography performance requirements, thereby improving the efficiency of Micro-LED maskless digital lithography.

Description

Technical Field

[0001] This application relates to the field of photolithography, and in particular to an AI-optimized maskless digital photolithography method, apparatus, and storage medium for Micro-LEDs. Background Technology

[0002] Maskless lithography eliminates the need for traditional physical masks, directly projecting design patterns onto photoresist. This significantly reduces fabrication costs, shortens development cycles, and enhances the flexibility of the lithography process. Micro-LED (micro-light-emitting diode) image sources demonstrate significant advantages in maskless lithography. First, the micrometer-level pixel pitch of Micro-LEDs enables extremely high pixel density, and single or multiple pixels can be illuminated via driving circuits. For example, Micro-LEDs can achieve a resolution of >6000 PPI. This high-density pixel arrangement allows for finer patterns, i.e., smaller linewidths and spacing, which is crucial for micro- and nano-manufacturing. Furthermore, compared to DLP (Digital Light Processing) technology, the mainstream image source in maskless lithography, Micro-LEDs offer a significant self-emissive advantage, eliminating the need for external light sources and allowing for further compact lithography systems.

[0003] Current maskless lithography technology for Micro-LEDs is still in its early stages, and it cannot yet match traditional lithography technologies in terms of lithographic performance parameters such as linewidth, line spacing, resolution, overlay error, and LWR / LER (line edge roughness). Specifically, lithography process parameters such as photoresist type and thickness, coating speed, soft baking temperature, exposure time, and development time affect lithography performance parameters. However, current maskless lithography technology cannot determine the mapping relationship between lithography process parameters and lithography performance parameters, making it difficult to quickly determine lithography process parameters that meet performance requirements. This necessitates operators to conduct tedious trial and error within the Micro-LED maskless lithography system, resulting in low lithography efficiency and hindering performance optimization. Summary of the Invention

[0004] The purpose of this application is to provide an AI-optimized Micro-LED maskless digital lithography method, apparatus, and storage medium that can quickly determine lithography process parameters that meet the lithography performance requirements, thereby improving the efficiency of Micro-LED maskless digital lithography and solving the problem of low lithography efficiency in existing Micro-LED maskless lithography technologies.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] In a first aspect, this application provides an AI-optimized maskless digital lithography method for Micro-LEDs, comprising:

[0007] The target lithography performance parameters and a bidirectional neural network are obtained. The bidirectional neural network includes a forward network and a backward network. The forward network is trained to predict the corresponding lithography performance parameters based on the lithography process parameters, and the backward network is trained to predict the corresponding lithography process parameters based on the lithography performance parameters.

[0008] The target lithography performance parameters are used as input to the reverse network, and candidate lithography process parameters corresponding to the target lithography performance parameters are obtained through the reverse network.

[0009] The candidate lithography process parameters are used as input to the forward network, and reference lithography performance parameters corresponding to the candidate lithography process parameters are obtained through the forward network.

[0010] When the reference lithography performance parameters are the same as the target lithography performance parameters, the candidate lithography process parameters are used as the target lithography process parameters for the Micro-LED maskless digital lithography system.

[0011] In a second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the AI-optimized Micro-LED maskless digital lithography method described in any one of the above.

[0012] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the AI-optimized Micro-LED maskless digital lithography method described above.

[0013] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the AI-optimized Micro-LED maskless digital lithography method described above.

[0014] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0015] This application provides an AI-optimized Micro-LED maskless digital lithography method, apparatus, and storage medium. It employs a bidirectional neural network to learn the mapping relationship between lithography performance parameters and lithography process parameters. The forward network of the bidirectional neural network predicts the lithography performance parameters corresponding to the input lithography process parameters, while the backward network predicts the corresponding lithography process parameters. Because inputting the user-desired target lithography performance parameters into the backward network yields corresponding candidate lithography process parameters, and these candidate parameters can be verified by the forward network, if the reference lithography performance parameters corresponding to the candidate lithography process parameters obtained from the forward network are the same as the target lithography performance parameters, then when the Micro-LED maskless digital lithography system uses these candidate lithography process parameters, it can generate a lithography pattern with the target lithography performance parameters on the photoresist. Therefore, this invention can quickly determine lithography process parameters that meet the lithography performance requirements, thereby improving the efficiency of Micro-LED maskless digital lithography and solving the problem of low lithography efficiency in existing Micro-LED maskless lithography technologies. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 An application environment diagram of an AI-optimized Micro-LED maskless digital lithography method provided in an embodiment of this application;

[0018] Figure 2 A schematic flowchart of an AI-optimized Micro-LED maskless digital lithography method provided in an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of the structure of a bidirectional neural network used in one embodiment of this application;

[0020] Figure 4 This is a schematic diagram of the structure of the Micro-LED maskless digital lithography system used in one embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the membrane structure used in one embodiment of this application;

[0022] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] The AI-optimized Micro-LED maskless digital lithography method provided in this application can be applied to, for example... Figure 1 In the application environment shown, the terminal communicates with the server via a network. A data storage system stores the data the server needs to process. This data storage system can be set up independently, integrated into the server, or located in the cloud or on another server. The terminal can send target lithography performance parameters to the server. Upon receiving the target lithography performance parameters, the server: uses the target lithography performance parameters as input to a reverse network to obtain candidate lithography process parameters corresponding to the target lithography performance parameters; uses the candidate lithography process parameters as input to a forward network to obtain reference lithography performance parameters corresponding to the candidate lithography process parameters; when the reference lithography performance parameters are the same as the target lithography performance parameters, the candidate lithography process parameters are used as the target lithography process parameters for the Micro-LED maskless digital lithography system. The server can then feed back the obtained target lithography process parameters to the terminal. Furthermore, in some embodiments, the AI-optimized Micro-LED maskless digital lithography method can also be implemented independently by the server or the terminal.

[0026] The terminal can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, etc. The server can be a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0027] In one specific implementation, such as Figure 2 As shown, an AI-optimized maskless digital lithography method for Micro-LEDs is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 The following steps, 210 to 240, are used as an example of the server in the example.

[0028] Step 210: Obtain the target lithography performance parameters and a bidirectional neural network. The bidirectional neural network includes a forward network and a backward network. The forward network is trained to predict the corresponding lithography performance parameters based on the lithography process parameters, and the backward network is trained to predict the corresponding lithography process parameters based on the lithography performance parameters.

[0029] Step 220: Use the target lithography performance parameters as input to the reverse network to obtain the candidate lithography process parameters corresponding to the target lithography performance parameters.

[0030] Step 230: The candidate lithography process parameters are used as input to the forward network to obtain the reference lithography performance parameters corresponding to the candidate lithography process parameters.

[0031] Step 240: When the reference lithography performance parameters are the same as the target lithography performance parameters, the candidate lithography process parameters are used as the target lithography process parameters for the Micro-LED maskless digital lithography system.

[0032] In the above specific embodiments, the target lithography performance parameters are the lithography performance parameters that the user believes meet the requirements of high-precision imaging; that is, the user expects the lithography pattern on the photoresist to have the target lithography performance parameters. The target lithography process parameters are the lithography process parameters when the Micro-LED maskless digital lithography system generates a lithography pattern on the photoresist that meets the requirements of high-precision imaging.

[0033] It should be noted that, depending on the actual scenario, users can choose different parameters as lithography performance parameters and lithography process parameters.

[0034] In the above specific implementation, the bidirectional neural network consists of two parts: a forward network and a reverse network, aiming to establish a high-dimensional nonlinear mapping relationship between maskless lithography process parameters and imaging performance (characterized by lithography performance parameters).

[0035] After training, the forward network can be directly used for prediction: inputting any set of lithography process parameters, it outputs the corresponding minimum linewidth and tilt angle, thus assisting in process window evaluation and process debugging. The inverse network is used for lithography process parameter optimization: inputting the user-defined target lithography performance parameters, it first generates a preliminary prediction of lithography process parameters, the prediction result being the candidate lithography process parameters. Then, the prediction result is verified by the forward network, which outputs reference lithography performance parameters. If the reference lithography performance parameters are the same as the target lithography performance parameters, it indicates that the mapping relationship between the candidate lithography process parameters and the target lithography performance parameters is accurate. Therefore, the candidate lithography process parameters can be directly used as the target lithography process parameters for the Micro-LED maskless digital lithography system, meaning the Micro-LED maskless digital lithography system uses the candidate lithography process parameters for maskless digital lithography.

[0036] In summary, in the above specific embodiments, a bidirectional neural network is used to learn the mapping relationship between lithography performance parameters and lithography process parameters. The forward network in the bidirectional neural network is used to predict the lithography performance parameters corresponding to the input lithography process parameters, and the backward network in the bidirectional neural network is used to predict the lithography process parameters corresponding to the input lithography performance parameters. This is because inputting the user's desired target lithography performance parameters into the backward network yields corresponding candidate lithography process parameters, which can be verified by the forward network. If the reference lithography performance parameters corresponding to the candidate lithography process parameters obtained by the forward network are the same as the target lithography performance parameters, then when the Micro-LED maskless digital lithography system uses these candidate lithography process parameters, a lithography pattern with the target lithography performance parameters can be generated on the photoresist. Therefore, through steps 210 to 240, lithography process parameters that meet the lithography performance requirements can be quickly determined, thereby improving the efficiency of Micro-LED maskless digital lithography and solving the problem of low lithography efficiency in existing Micro-LED maskless lithography technologies.

[0037] In another specific implementation, the AI-optimized Micro-LED maskless digital lithography method further includes step 250.

[0038] Step 250: When the reference lithography performance parameters are different from the target lithography performance parameters, the candidate lithography process parameters are optimized by an optimization algorithm so that the reference lithography performance parameters tend to the target lithography performance parameters. The optimized candidate lithography process parameters are then used as the target lithography process parameters for the Micro-LED maskless digital lithography system.

[0039] In some cases, the candidate lithography process parameters and the target lithography performance parameters are the same, which meets the implementation requirements of the previous specific implementation method. Conversely, in other cases, the candidate lithography process parameters and the target lithography performance parameters differ. In such cases, it is necessary to optimize the candidate lithography process parameters so that the reference lithography performance parameters predicted by the forward network based on the candidate lithography process parameters tend to converge with the target lithography performance parameters. When the Micro-LED maskless digital lithography system uses the optimized candidate lithography process parameters for lithography, the lithography performance parameters of the lithography pattern generated on the photoresist can then tend to converge with the target lithography performance parameters.

[0040] For example, in one embodiment, the optimization algorithm is a particle swarm optimization algorithm or a gradient descent algorithm.

[0041] For example, in one embodiment, the photolithography process parameters include the light intensity and exposure time of the light source, the photoresist thickness and the soft baking temperature, and the photolithography performance parameters include the line width, line spacing, resolution, overlay error, and LWR / LER of the photolithography pattern. The target photolithography performance parameters are the line width and line spacing of the photolithography pattern. Correspondingly, other photolithography performance parameters can also be selected as the target photolithography performance parameters according to actual needs.

[0042] Accordingly, in this embodiment, reference is made to Figure 3 The forward network employs a fully connected feedforward neural network (MLP) structure. The input layer contains four nodes, corresponding to the light intensity and exposure time of the light source, the photoresist thickness, and the soft baking temperature, respectively. The input data is standardized or normalized to ensure dimensional consistency. The first hidden layer has 64 neurons, performing initial feature abstraction of the input data through a fully connected layer and ReLU activation function. The second hidden layer contains 32 neurons, further learning higher-order combinations of lithography process parameters. The third hidden layer has 16 neurons, extracting a more compact deep representation. The output layer has two nodes, directly outputting continuous numerical values ​​for linewidth and line spacing, with no activation or using a linear activation function. The inverse network structure is similar to the forward network, except that the input layer receives the linewidth and line spacing, while the output layer generates predictions of the light intensity and exposure time of the light source, the photoresist thickness, and the soft baking temperature.

[0043] During model training, a large number of data samples obtained through experimental measurements are used to construct input-output pairs. For the forward network, each row of sample data includes the light intensity and exposure time of the light source, the photoresist thickness and softening temperature as inputs, and the linewidth and line spacing as outputs. During training, the input parameters are first fed into the forward network for forward propagation to obtain the prediction results. After comparing with the actual measured values, the mean squared error (MSE) is used to calculate the loss. Then, the network weights are iteratively updated using the backpropagation algorithm until the loss function converges. After multiple rounds of training, the forward network can accurately identify the complex nonlinear mapping between lithography process parameters and lithography performance. Similarly, for the backward network, each row of sample data includes the light intensity and exposure time of the light source, the photoresist thickness and softening temperature as outputs, and the linewidth and line spacing as inputs for training.

[0044] The above describes the data processing portion of the AI-optimized Micro-LED maskless digital lithography method, which can quickly determine the target lithography process parameters of the Micro-LED maskless digital lithography system. The Micro-LED maskless digital lithography system used in the method is described below.

[0045] Reference Figure 4 In some embodiments, the Micro-LED maskless digital lithography system includes a Micro-LED light source 101, a microlens array 102, a focusing lens 103, a projection lens group 104, and a sample 106 coated with photoresist arranged sequentially. The device structure of the Micro-LED light source 101 includes a Fabry-Perot resonator structure. The microlens array 102 faces the light-emitting surface of the Micro-LED light source 101. The focusing lens 103 faces the microlens array 102. The light input side of the projection lens group 104 faces the focusing lens 103. The sample 106 is disposed on the light output side of the projection lens group 104.

[0046] The Fabry-Perot resonator structure includes two reflective layers, sandwiching the traditional Micro-LED light source device structure in the middle; the upper reflective layer is deposited on the light-emitting surface of the Micro-LED light source, and the lower reflective layer is located on the side of the Micro-LED light source 101 away from the light-emitting surface.

[0047] The Micro-LED light source 101 can be a silicon-based driven (deep) ultraviolet Micro-LED display screen with an emission wavelength of 200~450nm and a single pixel size of less than 100 micrometers. It can emit light from a single pixel or output specific patterns. The displayed pattern is controlled by a computer or other equipment. The Micro-LED light source 101 is located at the beginning of the optical path. The emitting surface of the Micro-LED light source 101 is composed of a Micro-LED pixel array.

[0048] Figure 5 The image shows a structural example of a Micro-LED light source 101. Figure 5 The upper reflective layer (multi-layer Bragg reflective film, i.e.) is clearly marked. Figure 5 The multilayer film structure in the middle) and the lower reflective layer ( Figure 5 The lower reflective layer in the example is an Ag reflective layer, but in practice it can be a metal with high reflectivity (200-450nm) or a multilayer Bragg reflective film. The structure between the upper and lower reflective layers constitutes the Micro-LED light source 101.

[0049] The Fabry-Perot resonator structure is achieved by using an upper reflective layer (partially transmitting and partially reflecting) and a lower reflective layer (highly reflective) to form an optical resonant cavity, where light undergoes multiple reflections. When the round-trip optical path difference of light of a specific wavelength (λ) within the cavity is an integer multiple of the wavelength (satisfying 2nd = mλ, where n is the refractive index of the thin film, d is the thickness of the optical resonant cavity, and m is an integer), constructive interference occurs, resulting in a highly coherent beam. This highly coherent beam reduces diffraction effects, decreases spatial modes, and improves the resolution of photolithographic patterns.

[0050] The microlens array 102 can be a resin / glass microlens array, located after the ultraviolet Micro-LED display and before the focusing lens 103. The ultraviolet Micro-LED display and the resin / glass microlens array are physically bonded (separated by a film structure). The pixel emitting surface of the ultraviolet Micro-LED display faces the microlens surface of the resin / glass microlens array, ensuring efficient beam transmission. The size of each microlens in the resin / glass microlens array is similar to that of a single Micro-LED pixel in the ultraviolet Micro-LED display. Each Micro-LED pixel occupies its own microlens, and the array spacing is consistent, forming a pixel-level one-to-one correspondence, ensuring independent beam shaping for each pixel. The resin / glass microlens array further reduces the beam divergence angle output from the ultraviolet Micro-LED display, decreases spatial modes, and improves the resolution and edge sharpness of the lithographic pattern, overcoming the low lithographic resolution problem caused by the multiple spatial modes resulting from the incoherent light source characteristics of Micro-LEDs.

[0051] The focusing lens 103 is located after the microlens array 102 and before the projection lens group 104, forming a key node in the core beam transmission path. Its relationship with the microlens array 102 is a tight optical series coupling; the focusing lens 103 receives the optimized beam from the microlens array 102. Therefore, the optical parameters of the focusing lens 103 are designed to adapt to the collimation characteristics and spot distribution of the output beam from the microlens array 102, ensuring that the beam is transmitted to the subsequent imaging module with minimal energy loss and aberrations.

[0052] The focusing lens 103 functions in two ways. First, it optimizes beam collimation by correcting the residual divergence angle of the output beam from the microlens array 102, significantly reducing energy loss during optical transmission and providing highly stable light input for subsequent imaging modules. Second, the focusing lens 103, together with the microscope objectives in the projection lens group 104, forms an infinity correction system, allowing the beam to enter the microscope objectives in a parallel light pattern. This eliminates field curvature and astigmatism defects in traditional finite conjugate distance systems, ensuring uniform aberration correction throughout the entire field of view, thereby directly improving the linewidth consistency and edge sharpness of the lithographic pattern.

[0053] The projection lens group 104 consists of a series of convex and concave lenses, which work together with the focusing lens 103 to gather light rays, perform infinity correction, form collimated light, focus and scale the photolithography pattern to the photolithography area, and finally form the photolithography pattern on the photoresist of the sample 106.

[0054] In one embodiment, in order to further improve the imaging quality of the photolithography pattern, the light output end of the projection lens group 104 emits light onto the photoresist of the sample 106 through the liquid 105.

[0055] The liquid 105 is a liquid with a high refractive index, such as water or oil. Filling the space between the output end of the projection lens group 104 and the photoresist with the liquid 105, which has a high refractive index, can effectively improve the numerical aperture NA of the projection lens group 104, thereby achieving higher exposure accuracy and imaging resolution.

[0056] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an AI-optimized Micro-LED maskless digital lithography method.

[0057] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0058] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0059] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0060] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0062] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0063] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0064] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0065] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An AI optimization-based Micro-LED maskless digital lithography method, characterized in that, The method comprises the following steps: obtaining a target lithography performance parameter and a bidirectional neural network, the bidirectional neural network comprising a forward network and a reverse network, the forward network being trained to be able to predict a corresponding lithography performance parameter according to a lithography process parameter, and the reverse network being trained to be able to predict a corresponding lithography process parameter according to a lithography performance parameter; inputting the target lithography performance parameter into the reverse network to obtain a candidate lithography process parameter corresponding to the target lithography performance parameter through the reverse network; inputting the candidate lithography process parameter into the forward network to obtain a reference lithography performance parameter corresponding to the candidate lithography process parameter through the forward network; when the reference lithography performance parameter is the same as the target lithography performance parameter, taking the candidate lithography process parameter as a target lithography process parameter of a Micro-LED maskless digital lithography system.

2. The AI optimization-based Micro-LED maskless digital lithography method of claim 1, wherein, The method further comprises the following steps: when the reference lithography performance parameter is different from the target lithography performance parameter, optimizing the candidate lithography process parameter through an optimization algorithm to make the reference lithography performance parameter tend to the target lithography performance parameter, and taking the optimized candidate lithography process parameter as the target lithography process parameter of the Micro-LED maskless digital lithography system.

3. The AI optimization-based Micro-LED maskless digital lithography method of claim 2, wherein, The optimization algorithm is a particle swarm optimization algorithm or a gradient descent algorithm.

4. The AI optimization-based Micro-LED maskless digital lithography method of claim 1, wherein, The lithography process parameters comprise light intensity and exposure time of a light source, photoresist thickness, and soft baking temperature. And / or, the lithography performance parameters comprise line width, line spacing, resolution, overlay error, LWR / LER of a lithography pattern.

5. The AI optimization-based Micro-LED maskless digital lithography method of claim 1, wherein, The Micro-LED maskless digital lithography system comprises a Micro-LED light-emitting source, a microlens array, a focusing lens, a projection objective group, and a sample coated with photoresist, which are sequentially arranged. The Micro-LED light-emitting source has a Fabry-Perot resonator structure. The microlens array is opposite to a light-emitting surface of the Micro-LED light-emitting source. The focusing lens is opposite to the microlens array. The light input side of the projection objective group is opposite to the focusing lens. The sample is arranged on the light output side of the projection objective group.

6. The AI optimization-based Micro-LED maskless digital lithography method of claim 5, wherein, The light output end of the projection objective group emits light to the photoresist of the sample through a liquid.

7. The AI optimization-based Micro-LED maskless digital lithography method of claim 5, wherein, The Fabry-Perot resonator structure comprises upper and lower reflection layers. The upper reflection layer is deposited on the light-emitting surface of the Micro-LED light-emitting source, and the lower reflection layer is located on the side of the Micro-LED light-emitting source away from the light-emitting surface.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the AI optimization-based Micro-LED maskless digital lithography method in any one of claims 1-7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the AI optimization-based Micro-LED maskless digital lithography method in any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the AI optimization-based Micro-LED maskless digital lithography method in any one of claims 1-7.

Images