Step temperature fuzzy control method and control device of photoetching machine

Abstract

The application discloses a step temperature fuzzy control method and device of a photoetching machine, relates to the technical field of temperature control, and comprises the following steps: setting an initial step temperature fuzzy control strategy in a temperature execution unit of the photoetching machine and executing the step temperature fuzzy control strategy through a step fuzzy controller; collecting interference signals in real time and extracting interference characteristic vectors; detecting the current step temperature fuzzy control strategy and performing step-interference compatibility evaluation on the interference characteristic vectors; if a step-interference compatibility index is smaller than a preset compatibility index threshold value, adjusting temperature fuzzy control parameters of the current step temperature fuzzy control strategy to obtain an updated current step temperature fuzzy control strategy. The application solves the technical problem of insufficient temperature control precision and stability of the photoetching machine when the photoetching machine faces complex and variable dynamic interference with different characteristics, realizes dynamic self-adjustment of the step fuzzy control strategy, and achieves the technical effect of improving the temperature control precision and stability of the photoetching machine.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, specifically to a step temperature fuzzy control method and control device for lithography machines. Background Technology

[0002] Photolithography machines are core equipment in semiconductor manufacturing, and their performance directly determines the process precision and production efficiency of integrated circuits. During the photolithography process, temperature stability is a key factor affecting lithography accuracy and device consistency. Factors such as the distribution of heat sources within the photolithography machine, environmental fluctuations, and changes in process load introduce complex temperature disturbances. Improper control can lead to wafer distortion, alignment errors, or decreased imaging quality, thus affecting product yield. Traditional temperature control methods have limited performance in dealing with nonlinear and time-varying disturbances, especially under the requirements of multi-region, high-precision temperature control, making it difficult to achieve a fast and stable dynamic response. Fuzzy control has been introduced into the temperature control system of photolithography machines to simulate human experience and handle uncertainties and complexities. However, it lacks adaptability to disturbances with varying durations, amplitudes, frequencies, and spatial distributions, thus failing to ensure the temperature control accuracy and adaptive capability of the photolithography machine in complex disturbance environments.

[0003] Therefore, in the current related technologies, there is a technical problem that the temperature control accuracy and stability of lithography machines are insufficient when facing complex and varied dynamic interferences with different characteristics. Summary of the Invention

[0004] This application provides a stepped temperature fuzzy control method and control device for lithography machines, which solves the technical problem of insufficient temperature control accuracy and stability in lithography machines when facing complex and varied dynamic interference. It realizes a dynamic self-adjusting stepped fuzzy control strategy, thereby improving the technical effect of temperature control accuracy and stability of lithography machines.

[0005] This application provides a step temperature fuzzy control method for a lithography machine. The method includes: setting an initial step temperature fuzzy control strategy in the temperature execution unit of the lithography machine, the initial step temperature fuzzy control strategy being executed by a step fuzzy controller; acquiring interference signals in real time, extracting interference feature vectors from the interference signals, the interference feature vectors including interference duration, interference amplitude, interference frequency, and interference spatial distribution; detecting the currently executed step temperature fuzzy control strategy of the temperature execution unit, performing a step-interference compatibility evaluation on the interference feature vectors based on the currently executed step temperature fuzzy control strategy, and obtaining a step-interference compatibility index; if the step-interference compatibility index is less than a preset compatibility index threshold, sending the interference feature vectors to the step fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed step temperature fuzzy control strategy, and obtaining an updated currently executed step temperature fuzzy control strategy.

[0006] In a possible implementation, the step temperature fuzzy control method for the lithography machine further performs the following processing: obtaining the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy; calling the interference cancellation adaptive analysis model to perform interference cancellation adaptive analysis on the interference feature vector to obtain the adaptive temperature control step size range; and performing a compatibility evaluation based on whether the step temperature fuzzy control step size deviates from the control step size of the adaptive temperature control step size range to obtain a step-interference compatibility index.

[0007] In a possible implementation, the step temperature fuzzy control method of the lithography machine further performs the following processing: if the step-interference compatibility index is less than a preset compatibility index threshold, the step fuzzy controller is controlled to return to the previous step temperature fuzzy control strategy that is currently executing the step temperature fuzzy control strategy; based on the previous step temperature fuzzy control strategy, the interference feature vector is re-evaluated for step-interference compatibility; if the recalculated step-interference compatibility index is greater than or equal to the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control using the previous step temperature fuzzy control strategy.

[0008] In a possible implementation, the step temperature fuzzy control method for the lithography machine further performs the following processing: taking the preset compatibility index threshold as the adjustment target, taking the interference feature vector and the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy as input variables, taking the step temperature step size correction parameter as the response variable to perform parameter optimization, and outputting the optimal solution of the step temperature step size correction parameter; updating the currently executed step temperature fuzzy control strategy according to the optimal solution of the step temperature step size correction parameter.

[0009] In a possible implementation, the step temperature fuzzy control method of the lithography machine further performs the following processing: obtaining the step size constraint range of the currently executed step temperature fuzzy control strategy, constructing a step size correction parameter particle space under the step size constraint range; performing step size correction parameter particle optimization and compatibility evaluation in the step size correction parameter particle space until a step temperature step size correction parameter optimal solution greater than the preset compatibility index threshold is obtained.

[0010] In a possible implementation, the step temperature fuzzy control method for the lithography machine further performs the following processing: collecting training data samples, which include interference signal samples corresponding to historical temperature control curves, temperature control execution step sizes, and interference signal elimination degree labels before and after the temperature control execution step sizes; extracting interference feature vectors from the interference signal samples in the training data samples and outputting interference feature vector samples; training the training data samples using a lightweight neural network with the interference signal elimination degree labels as supervision to obtain an interference elimination prediction model, wherein the output of the interference elimination prediction model includes an adaptive feedback network, which performs adaptive feedback with the goal of minimizing the interference signal elimination degree to obtain a trained adaptive analysis model for interference elimination.

[0011] In a possible implementation, the step temperature fuzzy control method of the lithography machine further performs the following processing: if the step-interference compatibility index is greater than the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control with the currently executed step temperature fuzzy control strategy.

[0012] In a possible implementation, the step temperature fuzzy control method of the lithography machine further performs the following processing: the initial step temperature fuzzy control strategy includes N step temperature fuzzy control step sizes corresponding to N steps, and the step sizes of the N step temperature fuzzy control step sizes are arranged in descending order, where N is a positive integer greater than or equal to 2.

[0013] This application also provides a stepped temperature fuzzy control device for a lithography machine, the device comprising: an initial strategy setting module, used to set an initial stepped temperature fuzzy control strategy in the temperature execution unit of the lithography machine, the initial stepped temperature fuzzy control strategy being executed by a stepped fuzzy controller; an interference feature vector extraction module, used to collect interference signals in real time and extract interference feature vectors from the interference signals, the interference feature vectors including interference duration, interference amplitude, interference frequency, and interference spatial distribution; a compatibility evaluation module, used to detect the currently executed stepped temperature fuzzy control strategy of the temperature execution unit, perform a stepped-interference compatibility evaluation on the interference feature vectors based on the currently executed stepped temperature fuzzy control strategy, and obtain a stepped-interference compatibility index; and a fuzzy control parameter adjustment module, used to send the interference feature vectors to the stepped fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed stepped temperature fuzzy control strategy if the stepped-interference compatibility index is less than a preset compatibility index threshold, thereby obtaining an updated currently executed stepped temperature fuzzy control strategy.

[0014] This application proposes a stepped temperature fuzzy control method and control device for lithography machines. An initial stepped temperature fuzzy control strategy is set in the temperature execution unit of the lithography machine and executed by a stepped fuzzy controller. Interference signals are acquired in real time, and interference feature vectors are extracted. The currently executed stepped temperature fuzzy control strategy is detected, and a stepped-interference compatibility evaluation is performed on the interference feature vectors. If the stepped-interference compatibility index is less than a preset compatibility index threshold, the temperature fuzzy control parameters of the currently executed stepped temperature fuzzy control strategy are adjusted to obtain an updated currently executed stepped temperature fuzzy control strategy. This solves the technical problem of insufficient temperature control accuracy and stability in lithography machines when facing complex, variable, and diverse dynamic interference, achieving a dynamically self-adjusting stepped fuzzy control strategy and improving the temperature control accuracy and stability of the lithography machine. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the apparatus according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0016] Figure 1 A schematic flowchart of the step temperature fuzzy control method for a lithography machine provided in this application embodiment.

[0017] Figure 2 A schematic diagram of the stepped temperature fuzzy control device for a lithography machine provided in this application embodiment.

[0018] Figure labeling: Initial strategy setting module 10, interference feature vector extraction module 20, compatibility evaluation module 30, fuzzy control parameter adjustment module 40. Detailed Implementation

[0019] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0020] This application provides a step-temperature fuzzy control method for lithography machines, such as... Figure 1 As shown, the method includes:

[0021] Step S100: Set an initial stepped temperature fuzzy control strategy in the temperature execution unit of the lithography machine. The initial stepped temperature fuzzy control strategy is executed by the stepped fuzzy controller.

[0022] Step S100 further includes that the initial stepped temperature fuzzy control strategy includes N stepped temperature fuzzy control step sizes corresponding to N steps, and the step sizes of the N stepped temperature fuzzy control step sizes are arranged in descending order, where N is a positive integer greater than or equal to 2.

[0023] Preferably, an initial stepped temperature fuzzy control strategy is set in the temperature execution unit of the lithography machine. The temperature execution unit is the actual heating or cooling device in the lithography machine, such as a thermoelectric cooler or heater, used to maintain the temperature of the lens and wafer stage at the set target value. The initial stepped temperature fuzzy control strategy includes N steps, each corresponding to a stepped temperature fuzzy control step size, and the N stepped temperature fuzzy control step sizes are arranged in descending order. Specifically, the first step size is a large step size, activated when the actual temperature deviates significantly from the target temperature, and the controller outputs a large control quantity to ensure a fast response. The second step size is a medium step size, activated when the temperature deviation enters a medium range, and the controller outputs a moderate control quantity to ensure adjustment speed while suppressing overshoot and achieving a smooth transition. The Nth step size is the smallest step size, activated when the temperature deviation is very small, and the controller performs extremely fine adjustments to eliminate steady-state errors and achieve high-precision temperature stability. Here, N is a positive integer greater than or equal to 2.

[0024] Preferably, fuzzy control refers to a controller decision based on fuzzy logic within each step size. The temperature deviation and its rate of change are processed using fuzzy linguistic variables such as "positive large," "positive small," "zero," "negative small," and "negative large." The controller internally stores fuzzy rules; for example, if the temperature deviation is negative small and the rate of change is positive small, the output control quantity is positive small. Precise control commands are calculated through fuzzy inference and defuzzification processes and output to the temperature execution unit. Specifically, the initial step-by-step temperature fuzzy control strategy is executed by a step-by-step fuzzy controller. Specifically, the step-by-step fuzzy controller continuously monitors the deviation and rate of change between the actual temperature and the target temperature of the temperature execution unit. Based on the magnitude of the current temperature deviation, it automatically determines and switches to the corresponding control step. Then, within the currently active step, it uses the corresponding fuzzy rules to calculate the precise control quantity and finally sends the control quantity to the temperature execution unit to drive it to perform intelligent control actions. By switching different control actions under different operating conditions, stability and accuracy are ensured.

[0025] Step S200: Real-time acquisition of interference signals, extraction of interference feature vectors of the interference signals, the interference feature vectors including interference duration, interference amplitude, interference frequency and interference spatial distribution.

[0026] Preferably, in the temperature control system of a lithography machine, interference signal refers to any interfering factor that causes the temperature of the lens or wafer stage to deviate from the set target value. Interference signal is acquired in real time using a high-precision temperature sensor, and its characteristics are extracted and quantified into an interference feature vector to accurately describe the characteristics of the interference. The interference feature vector includes interference duration, interference amplitude, interference frequency, and interference spatial distribution. Specifically, interference duration refers to the length of time from the onset of interference until its effect essentially disappears, determined by analyzing the time period during which the temperature sensor reading deviates from the normal fluctuation range, used to distinguish between instantaneous disturbances and long-term drift. Interference amplitude refers to the maximum impact of the interference on the temperature, expressed as a temperature value or a percentage deviation from the set target, calculated by the temperature sensor during the interference duration. The maximum difference between the reading and the target setpoint is determined to measure the intensity of the interference. The interference frequency refers to the number of times the interference repeats within a unit of time, which is determined by frequency domain analysis of the temperature error signal over a period of time to suppress periodic interference. The spatial distribution of interference refers to the consistency of the impact of interference on multiple different temperature measurement points of the lithography machine. The spatial non-uniformity of the interference is quantified by comparing the differences in reading changes of multiple temperature sensors at key locations of the lithography machine when interference occurs. It may be divided into globally uniform interference or locally non-uniform interference. In globally uniform interference, the temperature in all areas rises or falls together. In locally non-uniform interference, temperature gradients may be generated inside the component, causing non-uniform thermal deformation such as twisting and bending, which seriously affects the lithography imaging quality. Asymmetric compensation control of the execution units in different areas is required.

[0027] Step S300: Detect the current execution of the stepped temperature fuzzy control strategy of the temperature execution unit, perform a stepped-interference compatibility evaluation on the interference feature vector based on the current execution of the stepped temperature fuzzy control strategy, and obtain the stepped-interference compatibility index.

[0028] Step S300 further includes step S310, obtaining the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy; step S320, calling the interference cancellation adaptive analysis model to perform interference cancellation adaptive analysis on the interference feature vector, and obtaining the adaptive temperature control step size range; step S330, performing a compatibility evaluation based on whether the step temperature fuzzy control step size deviates from the control step size of the adaptive temperature control step size range, and obtaining the step-interference compatibility index.

[0029] Preferably, the controller queries the internal status register or strategy identifier to detect and obtain the current execution step temperature fuzzy control strategy of the temperature execution unit, and then obtains the step temperature fuzzy control step size of the current execution step temperature fuzzy control strategy. A larger step size indicates that for the same temperature deviation, the controller outputs a larger control quantity to quickly eliminate the deviation; a smaller step size indicates that the controller output is more refined and is mainly used for fine-tuning to suppress overshoot and achieve a stable steady state.

[0030] Preferably, an adaptive interference cancellation analysis model is invoked to perform adaptive interference cancellation analysis on the interference feature vector. This model is a lightweight neural network model that describes the mapping relationship between interference features and ideal control parameters. It is used to infer the most suitable controller step size range for eliminating this type of interference based on the current interference feature vector. Specifically, the current interference feature vector is input into the neural network model for adaptive interference cancellation analysis. The model analyzes based on its internal mapping relationship. For impact interference with large amplitude and short duration, it determines that a larger step size is needed for a fast response; for oscillating interference with small amplitude and high frequency, it determines that a smaller step size is needed for fine oscillation suppression; for spatially unevenly distributed interference, it outputs a step size range that balances response speed and stability. This yields the adaptive temperature control step size range, representing the step size range within which the controller can most effectively and smoothly eliminate the interference based on the current interference characteristics.

[0031] Preferably, the step size of the stepped temperature fuzzy control is compared with the step size range of the adaptive temperature control to assess whether the current step size falls within the ideal range. If it does not fall within the range, the minimum distance between the current step size and the ideal control step size range is calculated as the deviation, and a compatibility assessment is performed to obtain a step-disturbance compatibility index, which is used to represent the degree of matching between the current control strategy and the current disturbance. For example, if the current stepped temperature fuzzy control step size is within the adaptive temperature control step size range, the step-disturbance compatibility index is 1, indicating a perfect match. If the current stepped temperature fuzzy control step size is not within the adaptive temperature control step size range, the step-disturbance compatibility index decreases monotonically as the deviation between the current step size and the ideal range boundary increases. The larger the deviation, the lower the index value, indicating greater incompatibility.

[0032] Furthermore, step S320 also includes step S321, collecting training data samples, the training data samples including interference signal samples corresponding to historical temperature control curves, temperature control execution step size, and interference signal elimination degree labels before and after the temperature control execution step size; step S322, extracting interference feature vectors from the interference signal samples of the training data samples, and outputting interference feature vector samples; step S323, using a lightweight neural network to train the training data samples with the interference signal elimination degree labels as supervision to obtain an interference elimination prediction model, the output of the interference elimination prediction model including an adaptive feedback network, the adaptive feedback network performing adaptive feedback with the goal of minimizing the interference signal elimination degree, to obtain a trained interference elimination adaptive analysis model.

[0033] Preferably, training data samples are collected from the historical database of the lithography machine's temperature sensor, which shows the interference signal samples corresponding to the historical temperature control curves, the temperature control execution step size, and the interference signal elimination degree labels before and after the temperature control execution step size. The interference signal samples refer to the original temperature deviation data during the period when the interference occurred, i.e., the sequence of the difference between the actual temperature and the target temperature over time. The temperature control execution step size refers to the actual control step size value used by the controller during the interference, used to record the control action under specific interference. The interference signal elimination degree label is used to evaluate the degree to which the interference is eliminated before and after the temperature control execution step size. It is calculated by comparing the characteristics of the interference signal before and after the application of the control step size. For example, the elimination degree = (steady-state error before interference application - steady-state error after interference suppression) / peak amplitude of the interference. The larger the value, the better the control effect.

[0034] Preferably, interference feature vectors are extracted from the interference signal samples of the training data samples through signal processing, and these vectors are converted into interference feature vector samples containing duration, amplitude, frequency, and spatial distribution to clearly describe the standardized features of the interference. Then, using the interference feature vectors and the temperature control execution step size as training inputs, and the interference signal elimination degree label as supervision, a lightweight neural network is used to train the training data samples. This allows the network to learn the mapping relationship from interference features and control step size to the degree of interference elimination, thus predicting the effectiveness of the control and outputting an interference elimination prediction model. The output of the interference elimination prediction model includes an adaptive feedback network, which performs adaptive feedback with the goal of minimizing the degree of interference signal elimination. Specifically, the lightweight neural network receives the interference feature vectors and the current temperature control execution step size, outputs the predicted elimination degree value, and inputs it into the adaptive feedback network to adjust the temperature control execution step size to maximize the final interference elimination effect. Then, iterative optimization is performed, with the adaptive feedback network repeatedly fine-tuning the step size value and evaluating the control effect of the new temperature control execution step size until the step size value or step size range that produces the highest predicted elimination degree is determined.

[0035] Step S400: If the step-interference compatibility index is less than the preset compatibility index threshold, the interference feature vector is sent to the step fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed step temperature fuzzy control strategy, so as to obtain the updated currently executed step temperature fuzzy control strategy.

[0036] Preferably, a preset compatibility index threshold is configured based on historical data statistical analysis and combined with temperature control stability requirements. This threshold is compared with the step-interference compatibility index. If the step-interference compatibility index is less than the preset compatibility index threshold, it indicates that the currently used step temperature fuzzy control strategy cannot effectively cope with newly emerging interference. Continued use may lead to increased temperature fluctuations and excessively long stabilization times. Consequently, the interference feature vector is sent to the step fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed step temperature fuzzy control strategy. This involves modifying the internal parameters constituting the step temperature fuzzy control strategy, which may include adjusting the step temperature... The fuzzy control step size, the blooming factor in the fuzzification stage, the membership function of the fuzzy rule base, and the weight parameters in the defuzzification stage are all considered. Specifically, adjusting the step size rapidly changes the dynamic response characteristics of the entire controller; adjusting the quantization ratio of input and output variables such as temperature error and error change rate (e.g., increasing the error scaling factor to make the controller more sensitive to deviations in the face of large disturbances); and adjusting the shape, width, and center point of the membership function corresponding to fuzzy linguistic values ​​such as "positive large" or "positive small" in the fuzzy set (e.g., shifting the membership function of the "positive large" output to the left so that even a small error can trigger a larger control output). In other words, particle swarm optimization determines better updated parameters and replaces the corresponding parameters in the currently executed stepped temperature fuzzy control strategy, obtaining an updated currently executed stepped temperature fuzzy control strategy, thereby restoring and maintaining optimal control performance.

[0037] Furthermore, step S400 also includes step S410, if the step-interference compatibility index is less than the preset compatibility index threshold, controlling the step fuzzy controller to return to the previous step temperature fuzzy control strategy that is currently executing the step temperature fuzzy control strategy; step S420, re-evaluating the step-interference compatibility of the interference feature vector based on the previous step temperature fuzzy control strategy, if the recalculated step-interference compatibility index is greater than or equal to the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control using the previous step temperature fuzzy control strategy.

[0038] Preferably, if the step-interference compatibility index is less than the preset compatibility index threshold, it is determined that the currently used, more refined control strategy cannot effectively cope with the newly emerging interference and there is a risk of loss of control. In this case, the step-interference fuzzy controller is controlled to return to the previous step-temperature fuzzy control strategy, i.e., a degradation operation is first performed, such as switching from the current third-step temperature fuzzy control step size back to the second-step temperature fuzzy control step size, to ensure reliability when facing new or strong interference. Then, the step-interference compatibility is re-evaluated based on the previous step-temperature fuzzy control strategy, i.e., the control step size of the previous step-temperature fuzzy control strategy is compared with the ideal step size range calculated by the interference elimination model, and the step-interference compatibility index is recalculated. If the recalculated step-interference compatibility index is greater than or equal to the preset compatibility index threshold, it indicates that the previous step-control strategy can eliminate the current interference. Then, the temperature execution unit performs temperature fuzzy control using the previous step-temperature fuzzy control strategy, thereby ensuring rapid recovery of stability with extremely low computational cost and extremely high reliability.

[0039] Furthermore, step S420 also includes step S421: if the recalculated step-interference compatibility index is less than the preset compatibility index threshold, the preset compatibility index threshold is used as the adjustment target, the interference feature vector and the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy are used as input variables, and the step temperature step size correction parameter is used as the response variable to perform parameter optimization and output the optimal solution of the step temperature step size correction parameter; step S422: the currently executed step temperature fuzzy control strategy is updated according to the optimal solution of the step temperature step size correction parameter.

[0040] Preferably, if the recalculated step-interference compatibility index is less than the preset compatibility index threshold, meaning the compatibility index of the previous step temperature fuzzy control strategy still fails to meet the standard, it indicates that the current preset step temperature fuzzy control strategy is unable to effectively handle the current interference. Therefore, the preset compatibility index threshold is used as the adjustment target, meaning the compatibility index of the target solution must at least reach the preset compatibility index threshold. Specifically, the interference feature vector and the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy are used as input variables. The interference feature vector defines the constraints, and the current step temperature fuzzy control step size is used as the initial optimization point for search and correction. Then, the step temperature step size correction parameter is used as the response variable, and particle swarm optimization is employed for parameter optimization. The step temperature step size correction parameter refers to a correction coefficient that fluctuates around 1.0 to ensure high efficiency. The new step temperature fuzzy control step size is the sum of the step temperature step size correction parameter and the initial step temperature fuzzy control step size. Then, a candidate step temperature step size correction parameter is generated, and the corresponding candidate step size is calculated. The expected control effect of the candidate step size is determined through simulation calculation, and then the corresponding compatibility index is calculated. This compatibility index is then used as the fitness score of the candidate step temperature step size correction parameter. New candidate step temperature step size correction parameters are continuously generated based on the fitness score. This process is iterated until a optimal solution for the step temperature step size correction parameter that makes the expected compatibility index exceed a preset threshold is determined. Finally, the currently executed step temperature fuzzy control strategy is updated according to the optimal solution for the step temperature step size correction parameter, resulting in the updated currently executed step temperature fuzzy control strategy. This ensures the control accuracy and stability of the lithography machine when facing unprecedented complex interference.

[0041] Furthermore, step S421 also includes obtaining the step size constraint range of the currently executed step temperature fuzzy control strategy, constructing a step size correction parameter particle space under the step size constraint range, performing step size correction parameter particle optimization and compatibility evaluation in the step size correction parameter particle space, until a step temperature step size correction parameter optimal solution greater than the preset compatibility index threshold is obtained.

[0042] Preferably, the step size constraint range of the currently executed stepped temperature fuzzy control strategy is obtained, that is, the allowable value range of the stepped temperature fuzzy control step size for safety and stability, in order to meet the output capability of the temperature execution unit. Then, under the step size constraint range, the value range of the step size correction parameter is derived in reverse based on the current stepped temperature fuzzy control step size. Then, multiple step size correction coefficients are randomly generated to construct a step size correction parameter particle space. Then, based on particle swarm optimization, the step size correction parameter particles are optimized in the step size correction parameter particle space. Specifically, the new step size corresponding to each step size correction parameter particle is calculated, and then the interference cancellation adaptive analysis model is used for analysis to predict the interference cancellation effect corresponding to the new step size and perform compatibility analysis. The expected stepped-interference compatibility index is calculated, and it is checked whether the compatibility index corresponding to any step size correction parameter particle is greater than the preset compatibility index threshold. If not, the particle swarm optimization algorithm updates the velocity and position of all particles based on the current position and the historical best position of each step size correction parameter particle until a step temperature step size correction parameter optimal solution greater than the preset compatibility index threshold is obtained and output, thereby realizing the dynamic self-adjustment of the stepped fuzzy control strategy and improving the temperature control accuracy and stability of the lithography machine.

[0043] In the above text, refer to Figure 1 A stepped temperature fuzzy control method for a lithography machine according to an embodiment of the present invention is described in detail. Next, reference will be made to... Figure 2 A stepped temperature blur control device for a lithography machine according to an embodiment of the present invention is described.

[0044] The stepped temperature fuzzy control device for a lithography machine according to an embodiment of the present invention is used to solve the technical problem of insufficient temperature control accuracy and stability in lithography machines when facing complex and varied dynamic interferences, as existing in the prior art. It achieves a dynamic self-adjusting stepped fuzzy control strategy, thereby improving the technical effect of enhancing the temperature control accuracy and stability of the lithography machine. Figure 2 As shown, the stepped temperature fuzzy control device of the lithography machine includes: an initial strategy setting module 10, an interference feature vector extraction module 20, a compatibility evaluation module 30, and a fuzzy control parameter adjustment module 40.

[0045] The initial strategy setting module 10 is used to set an initial stepped temperature fuzzy control strategy in the temperature execution unit of the lithography machine. The initial stepped temperature fuzzy control strategy is executed by a stepped fuzzy controller. The interference feature vector extraction module 20 is used to collect interference signals in real time and extract interference feature vectors from the interference signals. The interference feature vectors include interference duration, interference amplitude, interference frequency, and interference spatial distribution. The compatibility evaluation module 30 is used to detect the current executed stepped temperature fuzzy control strategy of the temperature execution unit, perform a stepped-interference compatibility evaluation on the interference feature vectors based on the current executed stepped temperature fuzzy control strategy, and obtain a stepped-interference compatibility index. The fuzzy control parameter adjustment module 40 is used to send the interference feature vectors to the stepped fuzzy controller to adjust the temperature fuzzy control parameters of the current executed stepped temperature fuzzy control strategy if the stepped-interference compatibility index is less than a preset compatibility index threshold, so as to obtain an updated current executed stepped temperature fuzzy control strategy.

[0046] The specific configuration of the compatibility evaluation module 30 will be described in detail below. The compatibility evaluation module 30 further includes: obtaining the step size of the currently executing step temperature fuzzy control strategy; calling the interference cancellation adaptive analysis model to perform interference cancellation adaptive analysis on the interference feature vector to obtain the adaptive temperature control step size range; and performing a compatibility evaluation based on whether the step size of the step temperature fuzzy control deviates from the control step size of the adaptive temperature control step size range to obtain a step-interference compatibility index.

[0047] The specific configuration of the fuzzy control parameter adjustment module 40 will be described in detail below. The fuzzy control parameter adjustment module 40 further includes: if the step-interference compatibility index is less than a preset compatibility index threshold, controlling the step fuzzy controller to return to the previous step temperature fuzzy control strategy; re-evaluating the step-interference compatibility of the interference feature vector based on the previous step temperature fuzzy control strategy; if the recalculated step-interference compatibility index is greater than or equal to the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control using the previous step temperature fuzzy control strategy.

[0048] The specific configuration of the fuzzy control parameter adjustment module 40 will be described in detail below. The fuzzy control parameter adjustment module 40 further includes: using the preset compatibility index threshold as the adjustment target, the interference feature vector and the step size of the currently executed step temperature fuzzy control strategy as input variables, and the step size correction parameter as the response variable to perform parameter optimization, outputting a better solution for the step size correction parameter; and updating the currently executed step temperature fuzzy control strategy according to the better solution for the step size correction parameter.

[0049] The specific configuration of the fuzzy control parameter adjustment module 40 will be described in detail below. The fuzzy control parameter adjustment module 40 further includes: obtaining the step size constraint range of the currently executed stepped temperature fuzzy control strategy; constructing a step size correction parameter particle space within the step size constraint range; performing step size correction parameter particle optimization and compatibility evaluation in the step size correction parameter particle space until a step size correction parameter optimal solution greater than the preset compatibility index threshold is obtained.

[0050] The specific configuration of the compatibility assessment module 30 will be described in detail below. The compatibility assessment module 30 further includes: collecting training data samples, which include interference signal samples corresponding to historical temperature control curves, temperature control execution step sizes, and interference signal elimination degree labels before and after the temperature control execution step sizes; extracting interference feature vectors from the interference signal samples of the training data samples and outputting interference feature vector samples; training the training data samples using a lightweight neural network with the interference signal elimination degree labels as supervision to obtain an interference elimination prediction model. The output of the interference elimination prediction model includes an adaptive feedback network, which performs adaptive feedback with the goal of minimizing the interference signal elimination degree, resulting in a trained adaptive analysis model for interference elimination.

[0051] The specific configuration of the fuzzy control parameter adjustment module 40 will be described in detail below. The fuzzy control parameter adjustment module 40 further includes: if the step-interference compatibility index is greater than the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control using the currently executed step temperature fuzzy control strategy.

[0052] The specific configuration of the initial strategy setting module 10 will be described in detail below. The initial strategy setting module 10 further includes: the initial stepped temperature fuzzy control strategy includes N stepped temperature fuzzy control step sizes corresponding to N steps, and the step sizes of the N stepped temperature fuzzy control step sizes are arranged in descending order, where N is a positive integer greater than or equal to 2.

[0053] The step temperature fuzzy control device for a lithography machine provided in this embodiment of the invention can execute the step temperature fuzzy control method for a lithography machine provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0054] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A step-temperature fuzzy control method for a lithography machine, characterized in that, The method includes: An initial step temperature fuzzy control strategy is set in the temperature execution unit of the lithography machine, and the initial step temperature fuzzy control strategy is executed by the step fuzzy controller. The interference signal is acquired in real time, and the interference feature vector of the interference signal is extracted. The interference feature vector includes the interference duration, interference amplitude, interference frequency and interference spatial distribution. The current execution of the step temperature fuzzy control strategy of the temperature execution unit is detected, and the step-interference compatibility evaluation of the interference feature vector is performed based on the current execution of the step temperature fuzzy control strategy to obtain the step-interference compatibility index. If the step-interference compatibility index is less than the preset compatibility index threshold, the interference feature vector is sent to the step fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed step temperature fuzzy control strategy, so as to obtain the updated currently executed step temperature fuzzy control strategy.

2. The step temperature fuzzy control method for a lithography machine as described in claim 1, characterized in that, Based on the current fuzzy temperature control strategy, a step-interference compatibility assessment is performed on the interference feature vector to obtain a step-interference compatibility index. The method includes: Obtain the step size of the currently executing step temperature fuzzy control strategy; The interference cancellation adaptive analysis model is invoked to perform interference cancellation adaptive analysis on the interference feature vector to obtain the adaptive temperature control step size range. A compatibility assessment is performed based on whether the step size of the stepped temperature fuzzy control deviates from the control step size of the adaptive temperature control step size range, and a step-interference compatibility index is obtained.

3. The step temperature fuzzy control method for a lithography machine as described in claim 1, characterized in that, Before sending the interference feature vector to the stepped fuzzy controller to adjust the temperature fuzzy control parameters of the currently executing stepped temperature fuzzy control strategy, the method further includes: If the step-interference compatibility index is less than the preset compatibility index threshold, the step fuzzy controller is controlled to return to the previous step temperature fuzzy control strategy before the current step temperature fuzzy control strategy is executed. Based on the previous step temperature fuzzy control strategy, the interference feature vector is re-evaluated for step-interference compatibility. If the recalculated step-interference compatibility index is greater than or equal to the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control based on the previous step temperature fuzzy control strategy.

4. The step temperature fuzzy control method for a lithography machine as described in claim 3, characterized in that, If the recalculated step-interference compatibility index is less than the preset compatibility index threshold, the interference feature vector is sent to the step fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed step temperature fuzzy control strategy. The method includes: Using the preset compatibility index threshold as the adjustment target, the interference feature vector and the step temperature fuzzy control step size of the currently executed step temperature fuzzy control strategy as input variables, and the step temperature step size correction parameter as the response variable, parameter optimization is performed, and the optimal solution of the step temperature step size correction parameter is output. The current step temperature fuzzy control strategy is updated based on the optimal solution of the step temperature step correction parameters.

5. The step temperature fuzzy control method for a lithography machine as described in claim 4, characterized in that, The optimal solution for outputting stepped temperature step size correction parameters can be achieved through methods including: Obtain the step size constraint range of the currently executed step temperature fuzzy control strategy, and construct the step size correction parameter particle space under the step size constraint range; In the step size correction parameter particle space, step size correction parameter particle optimization and compatibility evaluation are performed until a step temperature step size correction parameter optimal solution with a value greater than the preset compatibility index threshold is obtained.

6. The step temperature fuzzy control method for a lithography machine as described in claim 2, characterized in that, The method for training the interference cancellation adaptive analysis model includes: Calling the interference cancellation adaptive analysis model to perform interference cancellation adaptive analysis on the interference feature vector. Collect training data samples, which include interference signal samples corresponding to historical temperature control curves, temperature control execution step size, and labels on the degree of interference signal elimination before and after the temperature control execution step size; Interference feature vectors are extracted from the interference signal samples of the training data samples, and interference feature vector samples are output. A lightweight neural network is used to train the training data samples with the interference signal elimination degree label as supervision to obtain an interference elimination prediction model. The output of the interference elimination prediction model includes an adaptive feedback network. The adaptive feedback network performs adaptive feedback with the goal of minimizing the interference signal elimination degree to obtain a trained interference elimination adaptive analysis model.

7. The step temperature fuzzy control method for a lithography machine as described in claim 1, characterized in that, After obtaining the step-interference compatibility index, if the step-interference compatibility index is greater than the preset compatibility index threshold, the temperature execution unit performs temperature fuzzy control using the currently executed step temperature fuzzy control strategy.

8. The step temperature fuzzy control method for a lithography machine as described in claim 1, characterized in that, An initial stepped temperature fuzzy control strategy is set in the temperature execution unit of the lithography machine, including: The initial step temperature fuzzy control strategy includes N step temperature fuzzy control step sizes corresponding to N steps, and the step sizes of the N step temperature fuzzy control step sizes are arranged in descending order, where N is a positive integer greater than or equal to 2.

9. A stepped temperature fuzzy control device for a lithography machine, characterized in that, The apparatus is used to implement the stepped temperature fuzzy control method for the lithography machine according to any one of claims 1 to 8, the apparatus comprising: An initial strategy setting module is used to set an initial stepped temperature fuzzy control strategy in the temperature execution unit of the lithography machine. The initial stepped temperature fuzzy control strategy is executed by a stepped fuzzy controller. The interference feature vector extraction module is used to collect interference signals in real time and extract interference feature vectors of the interference signals. The interference feature vectors include interference duration, interference amplitude, interference frequency, and interference spatial distribution. The compatibility evaluation module is used to detect the current execution of the step temperature fuzzy control strategy of the temperature execution unit, perform step-interference compatibility evaluation on the interference feature vector based on the current execution of the step temperature fuzzy control strategy, and obtain the step-interference compatibility index. The fuzzy control parameter adjustment module is used to send the interference feature vector to the stepped fuzzy controller to adjust the temperature fuzzy control parameters of the currently executed stepped temperature fuzzy control strategy when the stepped-interference compatibility index is less than the preset compatibility index threshold, so as to obtain the updated currently executed stepped temperature fuzzy control strategy.

Images