Vacuum pressure system, parameter identification method and parameter identification modeling method

Abstract

The invention provides a vacuum pressure system, a parameter identification method and a parameter identification modeling method, which are applied to the technical field of semiconductor manufacturing, a mathematical model for describing the change of the pressure in a chamber along with time is constructed by applying the law of conservation of mass and an ideal gas state equation, the change of the pressure in the chamber can be accurately predicted, and the accuracy of the parameter identification is improved. And key system parameters can be determined in real time through a parameter identification process, so that the precision and the response speed of pressure control are remarkably improved, meanwhile, the adaptability and the stability of the system are enhanced, the thin film deposition process can be optimized, the quality and the uniformity of products are improved, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of semiconductor manufacturing, and in particular to a vacuum pressure system, a parameter identification method and a modeling method for parameter identification. Background Art

[0002] In the semiconductor manufacturing process, pressure control inside the reaction chamber is crucial. However, when using pressure-controlled butterfly valves for pressure control in traditional chemical vapor deposition (CVD) equipment, it is often difficult to directly obtain key system parameters such as chamber volume and inlet flow rate. In addition, under different processes, the volume of the chamber occupied by the wafers placed in the chamber is different, and the gas flow rate at the inlet end is different, making it more difficult to accurately control the chamber pressure.

[0003] At present, most of the pressure control methods of CVD equipment adopt fixed PID control and parameter adaptive pressure control methods. However, these methods do not utilize the actual parameters of the controlled object, resulting in problems such as insufficient control accuracy, slow response speed, and poor adaptability. It not only affects the quality and uniformity of the film, but also increases energy consumption and equipment wear, reduces production efficiency, and brings potential safety risks.

[0004] Based on this, a new vacuum pressure system, parameter identification method and parameter identification modeling method are needed. Summary of the invention

[0005] In view of this, the embodiments of the present specification provide a vacuum pressure system, a parameter identification method and a modeling method for parameter identification. When the reaction chamber volume and the air inlet flow rate cannot be obtained, a relationship model between the pressure and time in the chamber can be established by applying the law of conservation of mass and the ideal gas state equation. This can not only accurately predict the pressure changes in the chamber, but also improve the limitations of the existing schemes on chamber pressure control by identifying the parameters in the relationship model, especially when the chamber volume and air inlet flow rate change under different process conditions, thereby improving the accuracy and efficiency of pressure control and effectively improving the uniformity and quality of the thin film deposition process.

[0006] The embodiments of this specification provide the following technical solutions: The embodiment of this specification provides a modeling method for identifying parameters of a vacuum pressure system, which models the pressure change in a chamber. The modeling method for identifying parameters of a vacuum pressure system includes: According to the law of conservation of mass, the amount balance equation of the gas substance in the chamber at any time is established, and the expression is: ,in, Indicates the total amount of gas entering the inlet end, Indicates the total amount of gas discharged from the outlet; based on the constant inlet flow rate and the relationship between the outlet volume, chamber pressure and butterfly valve conductance, a relationship model of the amount of gas in the chamber changing with time is established: ; Using the ideal gas state equation: , we get the relationship model between the pressure and time in the chamber, the expression is: ; in, Indicates any time in the chamber pressure; is a constant in the general solution of the differential equation; is the base of natural logarithms; , R is the molar gas constant, T is the temperature, and V is the volume of the chamber gas; Indicates the current conductance of the butterfly valve; Indicates time; Indicates the mass flow rate at the inlet end.

[0007] The embodiment of this specification also provides a parameter identification method of a vacuum pressure system, comprising: Using any of the above-mentioned modeling methods for identifying parameters of a vacuum pressure system, a relationship model between pressure and time in the chamber is established; Collecting data on changes in pressure in the chamber over time over a period of time, the data including: pressure values ​​at each moment and corresponding timestamps; The collected data is fitted by an optimization algorithm to identify the parameters in the relationship model.

[0008] The embodiment of this specification also provides a vacuum pressure system, including: an air intake device, a chamber, a butterfly valve, a vacuum pump, a pressure sensor, and a control system; The air intake device is connected to the first end of the chamber and is used to continuously intake air into the chamber; The vacuum pump is connected to the second end of the chamber through the butterfly valve and is used to continuously evacuate the chamber; The pressure sensor is connected to the third end of the chamber and is used to detect the real-time pressure in the chamber and transmit the data to the control system; The control system adopts any of the above-mentioned parameter identification methods for the vacuum pressure system to control the valve plate opening of the butterfly valve.

[0009] Compared with the prior art, the at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: This application constructs a mathematical model that describes the change of pressure in the chamber over time by applying the law of conservation of mass and the ideal gas state equation. It can not only accurately predict the pressure change in the chamber, but also determine the key system parameters in real time through the parameter identification process, which significantly improves the accuracy and response speed of pressure control, and at the same time enhances the adaptability and stability of the system, which helps to optimize the thin film deposition process, improve the quality and uniformity of the product, and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 It is a schematic diagram of the structure of the vacuum pressure system of the CVD equipment in this application; Figure 2 is a flow chart of a parameter identification method of a vacuum pressure system in the present application; Figure 3 is a flow chart for fitting pressure data in this application. DETAILED DESCRIPTION

[0012] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0013] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0014] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0015] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0016] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.

[0017] In the semiconductor manufacturing process, precise control of the pressure in the reaction chamber of the CVD equipment is crucial to depositing high-quality and uniform thin films.

[0018] However, the current mainstream pressure control methods, including fixed PID control and parameter adaptive control, cannot directly obtain key system parameters, especially chamber volume and inlet gas flow rate. The uncertainty of these parameters, coupled with the changes in wafer volume and gas flow rate in different processes, increases the complexity of pressure control using pressure-controlled butterfly valves, thereby affecting the film deposition process, resulting in reduced film quality and uniformity, and ultimately affecting production efficiency and product performance.

[0019] In view of this, the inventors discovered through research and improvement exploration that when the existing pressure control method uses a pressure-controlled butterfly valve to control the pressure in the reaction chamber of the CVD equipment, the pressure-controlled butterfly valve cannot accurately control the pressure in the reaction chamber, resulting in a decrease in film quality and uniformity.

[0020] Based on this, the embodiment of this specification proposes a modeling method for identifying the parameters of a vacuum pressure system. The overall idea is: determine the amount balance equation of the gas substance through the law of conservation of mass, and then consider the relationship between the intake flow rate and the outlet volume, as well as the influence of the chamber pressure and the conductance of the butterfly valve, to establish a model of the relationship between the pressure and time in the chamber, which can accurately predict the pressure changes in the chamber and significantly improve the accuracy and response speed of pressure control.

[0021] The technical solutions provided by various embodiments of the present application are described below in conjunction with the accompanying drawings.

[0022] The embodiment of this specification provides a modeling method for identifying parameters of a vacuum pressure system, which models the pressure change in a chamber. The modeling method for identifying parameters of a vacuum pressure system includes: According to the law of conservation of mass, the amount balance equation of the gas substance in the chamber at any time is established, and the expression is: ,in, Indicates the total amount of gas entering the inlet end, Indicates the total amount of gas discharged from the gas outlet; According to the relationship between the constant inlet flow rate and the outlet volume, the chamber pressure and the butterfly valve conductance, a relationship model of the amount of gas in the chamber changing with time is established: ; Using the ideal gas state equation: , we get the relationship model between the pressure and time in the chamber, the expression is: ; in, represents the pressure in the chamber at any time t; C is the constant in the general solution of the differential equation; e is the base of the natural logarithm; , R is the molar gas constant, T is the temperature, V is the volume of the chamber gas; c represents the current conductance of the butterfly valve; t represents the time; Q represents the intake mass flow rate at the intake end.

[0023] Specifically, the intake air mass flow rate at the intake end is represented by Q, with the unit of Pa m³ / s; the pressure in the chamber at any time t is The unit is Pa; the chamber volume is V, the unit is ; The current flow conductance of the butterfly valve is represented by c, unit Because the chamber has only one end for air intake and one end for air exhaust, the amount of gas in the chamber at any time is for: (1) in is the total amount of gas entering the inlet end, is the total amount of gas discharged from the outlet. Since the inlet flow is constant, the outlet volume and chamber pressure are related to the butterfly valve conductance, so formula (1) is transformed into: (2) According to the ideal gas state equation: (3) In formula (3), p is pressure (Pa), V is gas volume ( ), T is the temperature (K), n is the amount of gas ( ), R is the molar gas constant (also called the universal gas constant) (J / ( .K)) Can get (4) Substituting equation (4) into equation (2), we can obtain: , (5) Solving the differential equation (5), we can finally obtain the pressure expression in the cavity at any time t: (6) where C is a constant in the general solution of the differential equation.

[0024] This formula shows that the pressure in the cavity at any time t is only related to the butterfly valve conductance c, the air intake volume Q, and the cavity volume V.

[0025] In some embodiments, the ideal gas state equation is used: , the relationship model between the pressure in the chamber and time is obtained, including: After substituting the ideal gas state equation into the gas substance balance equation, the solution is obtained by numerical method, analytical method or approximate method.

[0026] Based on the same inventive concept, the present application also provides a parameter identification method for a vacuum pressure system, comprising: Using any of the above-mentioned modeling methods for identifying parameters of a vacuum pressure system, a relationship model between pressure and time in the chamber is established; Collecting data on changes in pressure in the chamber over time over a period of time, the data including: pressure values ​​at each moment and corresponding timestamps; The collected data is fitted by an optimization algorithm to identify the parameters in the relationship model.

[0027] Specifically, Figure 2 As shown, the pressure change in the chamber is modeled, and a relationship model between the pressure in the chamber and time is established; The control system collects cavity pressure change data within a certain period of time and records the cavity pressure and the corresponding timestamp. For example, a pressure sensor is used to monitor the pressure in the cavity in real time, and the pressure value at each moment and its corresponding timestamp are recorded.

[0028] Then, an optimization algorithm, such as gradient descent, least squares method, genetic algorithm, etc., is used to fit the collected pressure data, so that the parameters in the model can be accurately identified from the experimental data.

[0029] In some embodiments, the butterfly valve is placed in a fully closed position before collecting data on the pressure change in the chamber over time over a period of time.

[0030] Specifically, the butterfly valve is placed in the fully closed position through the control system so that the butterfly valve flow conductance c remains unchanged. At this time, the pressure in the cavity will continue to rise under the action of air intake at the air inlet end and vacuum pump exhaust. At this time, the cavity pressure and the corresponding timestamp are recorded by the control system.

[0031] In some embodiments, Figure 3 As shown, the collected data is fitted by an optimization algorithm to identify the cavity volume and inlet flow parameters in the model, including: the optimization algorithm includes a gradient descent method; Establishing a data set based on the collected data, wherein the data set includes a timestamp and a corresponding pressure value at each moment; Initialize parameters according to the relational model and the data set; Construct loss function; Calculate the gradient of the loss function with respect to each parameter; Use the gradient descent method to iteratively update the parameters in the gradient direction, repeatedly calculate the gradient and update the parameters until the value of the loss function is less than a preset threshold, and output the value of the parameter in the relationship model.

[0032] Specifically, in formula (6), k and c are in a multiplication relationship, which makes it difficult to separate their effects when optimizing parameters. Moreover, in the gradient descent method, the gradient of the parameters needs to be calculated. If there is a multiplication relationship between the parameters, the calculation of the gradient will be complicated. Therefore, we define a new parameter , simplifying formula (6) to: (7) This reduces the complexity of calculation.

[0033] The exponential function shown in formula (7) is used to fit the collected pressure data. The parameters to be calculated are: , , , the steps are as follows: (1) Prepare the dataset As in the previous steps, the pressure data collected at different timestamps are expressed as Timestamp: t ; pressure: ; (2) Initialization parameters According to the formula (7) to be fitted and the data set, initialize the parameters: ; ; ; (3) Calculate the loss function ; in , , , ; (4) Calculate the gradient The gradient of parameter C is ; The gradient of parameter k1 is: ; The gradient of parameter k2 is: ; in , , , ; (5) Update parameters Update the three parameters according to the values ​​of the previous three parameters and their corresponding gradients; (6) Update and Iteration Repeat steps (3)-(5) until the value of the loss function sum_e in step (3) is less than a preset threshold, and output the value of the parameter in the relationship model.

[0034] In some embodiments, the value of the loss function sum_e is less than 0.001, and the iteration ends. At this time, the parameters C, k1, and k2 are the final calculated values.

[0035] In some embodiments, when the parameters are iteratively updated according to the gradient direction using the gradient descent method, the learning rate is set to 0.01.

[0036] Specifically, ; ; ; In some embodiments, the parameter identification method of the vacuum pressure system is used to identify the cavity volume and cavity inlet flow parameters in the vacuum pressure system of a CVD device.

[0037] Specifically, according to the parameters C, k1, k2 obtained by the gradient descent method above, we can get ; .

[0038] In some embodiments, the identified cavity volume and cavity inlet end flow parameters are used to control the valve plate opening of the butterfly valve to achieve precise control of the pressure in the cavity.

[0039] Specifically, based on the identified cavity volume and cavity inlet flow parameters, a control strategy is formulated to control the valve plate opening of the butterfly valve, thereby achieving precise control of the pressure in the cavity to adapt to different process conditions and system changes, which helps to optimize the thin film deposition process, improve product quality and uniformity, and improve production efficiency.

[0040] Based on the same inventive concept, the present application also provides a vacuum pressure system, such as Figure 1 As shown, it includes: an air intake device, a chamber, a butterfly valve, a vacuum pump, a pressure sensor, and a control system; The air intake device is connected to the first end of the chamber and is used to continuously intake air into the chamber; The vacuum pump is connected to the second end of the chamber through the butterfly valve and is used to continuously evacuate the chamber; The pressure sensor is connected to the third end of the chamber and is used to detect the real-time pressure in the chamber and transmit the data to the control system; The control system adopts any of the above-mentioned parameter identification methods for the vacuum pressure system to control the valve plate opening of the butterfly valve.

[0041] In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0042] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A modeling method for parameter identification of a vacuum pressure system, characterized in that: The pressure change in the chamber is modeled, and the modeling method for identifying the parameters of the vacuum pressure system includes: According to the law of conservation of mass, the amount balance equation of the gas substance in the chamber at any time is established, and the expression is: ,in, Indicates the total amount of gas entering the inlet end, Indicates the total amount of gas discharged from the gas outlet; According to the relationship between the constant inlet flow rate and the outlet volume, the chamber pressure and the butterfly valve conductance, a relationship model of the amount of gas in the chamber changing with time is established: ; Using the ideal gas state equation: , we get the relationship model between the pressure and time in the chamber, the expression is: ; in, Indicates any time in the chamber pressure; is a constant in the general solution of the differential equation; is the base of natural logarithms; , is the molar gas constant, is the temperature, is the volume of the chamber gas; Indicates the current conductance of the butterfly valve; Indicates time; Indicates the intake air mass flow rate at the intake end.

2. The modeling method for parameter identification of a vacuum pressure system according to claim 1, characterized in that: The ideal gas state equation is used: , the relationship model between the pressure in the chamber and time is obtained, including: After substituting the ideal gas state equation into the gas substance balance equation, the solution is obtained by numerical method or analytical method.

3. A parameter identification method for a vacuum pressure system, characterized in that: include: Using the modeling method for identifying parameters of a vacuum pressure system as described in any one of claims 1 to 2, a relationship model between pressure and time in the chamber is established; Collecting data on changes in pressure in the chamber over time over a period of time, the data including: pressure values ​​at each moment and corresponding timestamps; The collected data is fitted by an optimization algorithm to identify the parameters in the relationship model.

4. The parameter identification method of the vacuum pressure system according to claim 3, characterized in that: Before collecting the data of the pressure change in the chamber over time for a period of time, the butterfly valve is placed in the fully closed position.

5. The parameter identification method of the vacuum pressure system according to claim 3, characterized in that: The step of fitting the collected data by an optimization algorithm to identify the cavity volume and inlet flow parameters in the model includes: the optimization algorithm includes a gradient descent method; Establishing a data set based on the collected data, wherein the data set includes a timestamp and a corresponding pressure value at each moment; Initialize parameters according to the relational model and the data set; Construct loss function; Calculate the gradient of the loss function with respect to each parameter; Use the gradient descent method to iteratively update the parameters in the gradient direction, repeatedly calculate the gradient and update the parameters until the value of the loss function is less than a preset threshold, and output the value of the parameter in the relationship model.

6. The parameter identification method of the vacuum pressure system according to claim 5, characterized in that: When using the gradient descent method to iteratively update the parameters in the direction of the gradient, the learning rate is set to 0.

01.

7. The parameter identification method of the vacuum pressure system according to claim 3, characterized in that: The parameter identification method of the vacuum pressure system is used to identify the cavity volume and cavity inlet end flow parameters in the vacuum pressure system of the CVD equipment.

8. The parameter identification method of the vacuum pressure system according to claim 7, characterized in that: The identified cavity volume and cavity inlet end flow parameters are used to control the valve plate opening of the butterfly valve to achieve precise control of the pressure in the cavity.

9. A vacuum pressure system, characterized in that: include: Air intake device, chamber, butterfly valve, vacuum pump, pressure sensor, control system; The air intake device is connected to the first end of the chamber and is used to continuously intake air into the chamber; The vacuum pump is connected to the second end of the chamber through the butterfly valve and is used to continuously evacuate the chamber; The pressure sensor is connected to the third end of the chamber and is used to detect the real-time pressure in the chamber and transmit the data to the control system; The control system uses the parameter identification method of the vacuum pressure system according to any one of claims 3 to 8 to control the valve plate opening of the butterfly valve.

Images