A vacuum pressure system, a parameter identification method, and a modeling method for parameter identification

Abstract

The present application provides a vacuum pressure system, a parameter identification method and a modeling method for parameter identification, which are applied to the field of semiconductor manufacturing technology. By applying the law of conservation of mass and the ideal gas state equation, a mathematical model describing the change of pressure in the chamber over time is constructed. 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, significantly improving the accuracy and response speed of pressure control, while enhancing the adaptability and stability of the system, helping to optimize the thin film deposition process, improve the quality and uniformity of products, and increase production efficiency.

Description

Technical Field

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

[0002] In the process of semiconductor manufacturing, the pressure control inside the reaction chamber is crucial. However, when the traditional chemical vapor deposition (CVD) equipment uses a pressure control butterfly valve for pressure control, it is often difficult to directly obtain key system parameters such as the chamber volume and the inlet gas flow rate. Coupled with the fact that under different processes, the wafers placed in the chamber occupy different chamber volumes and the gas flow rates at the inlet end are different, it becomes more difficult to precisely control the chamber pressure.

[0003] Currently, most of the pressure control methods for CVD equipment adopt methods such as fixed PID control and parameter adaptive pressure control. 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. This not only affects the quality and uniformity of the thin 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, a parameter identification method, and a modeling method for parameter identification 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. Without being able to obtain the reaction chamber volume and the inlet flow rate, by applying the law of conservation of mass and the ideal gas state equation, a relationship model between the pressure and time in the chamber can be established. This can not only accurately predict the pressure change in the chamber, but also improve the limitations of the existing scheme for chamber pressure control by identifying the parameters in the relationship model. Especially under different process conditions where the chamber volume and the inlet gas flow rate change, the accuracy and efficiency of pressure control are improved, effectively enhancing the uniformity and quality of the thin film deposition process.

[0006] The embodiments of the present specification provide the following technical solutions:

[0007] The embodiments of the present specification provide a modeling method for parameter identification of a vacuum pressure system, which models the pressure change in the chamber. The modeling method for parameter identification of the vacuum pressure system includes:

[0008] According to the law of conservation of mass, establish the gas amount balance equation at any time in the chamber, and the expression is:

[0009] , where represents the total amount of gas entering from the inlet end, represents the total amount of gas discharged from the gas outlet; based on the constant intake gas flow rate and the relationship between the outlet gas volume and the chamber pressure and the butterfly valve conductance, a relationship model of the amount of gas substance in the chamber changing with time is established: ;

[0010] Using the ideal gas state equation: , a relationship model between the pressure in the chamber and time is obtained, and the expression is: ;

[0011] Among them, represents the pressure at any time in the chamber; is the constant in the general solution of the differential equation; is the base of the natural logarithm; , R is the molar gas constant, T is the temperature, and V is the volume of the gas in the chamber; represents the current conductance of the butterfly valve; represents time; represents the mass flow rate at the intake end.

[0012] This embodiment of the specification also provides a method for identifying parameters of a vacuum pressure system, including:

[0013] Using the modeling method for identifying parameters of the vacuum pressure system described in any one of the above to establish a relationship model between the pressure in the chamber and time;

[0014] Collect data on the change of pressure in the chamber with time for a period of time, and the data includes: the pressure value and the corresponding timestamp at each moment;

[0015] By using an optimization algorithm to fit the collected data, identify the parameters in the relationship model.

[0016] This embodiment of the specification also provides a vacuum pressure system, including: an intake device, a chamber, a butterfly valve, a vacuum pump, a pressure sensor, and a control system;

[0017] The intake device is connected to the first end of the chamber and is used to continuously introduce gas into the chamber;

[0018] The vacuum pump is connected to the second end of the chamber through the butterfly valve and is used to continuously evacuate the chamber;

[0019] 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;

[0020] The control system controls the opening degree of the valve plate of the butterfly valve by using the method for identifying parameters of the vacuum pressure system described in any one of the above.

[0021] Compared with the prior art, the beneficial effects that can be achieved by at least one of the above technical solutions adopted in the embodiments of this specification at least include:

[0022] By applying the law of conservation of mass and the ideal gas state equation, this application constructs a mathematical model that describes the change of pressure in the chamber over time. 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, significantly improving the accuracy and response speed of pressure control. At the same time, it enhances the adaptability and stability of the system, helps to optimize the thin film deposition process, improve the quality and uniformity of products, and increase production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a schematic structural diagram of the vacuum pressure system of the CVD device in this application;

[0025] Figure 2 is a flowchart of the parameter identification method for the vacuum pressure system in this application;

[0026] Figure 3 is a flowchart of fitting pressure data in this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The embodiments of this application will be described in detail below with reference to the drawings.

[0028] The following specific examples illustrate the implementation manners of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. This application can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0029] It should be noted that the following description relates to various aspects of embodiments within the scope of the appended claims. It will 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 for illustrative purposes only. Based on this application, those skilled in the art should understand that one 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 aspects set forth herein can be used to implement a device and / or practice a method. Additionally, this device can be implemented and this method can be practiced using other structures and / or functionality in addition to one or more of the aspects set forth herein.

[0030] It should also be noted that the diagrams provided in the following embodiments only illustrate the basic concept of this application schematically. Only the components related to this application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in its actual implementation can be arbitrarily changed, and the layout type of its components may also be more complex.

[0031] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that these examples can be practiced without these specific details.

[0032] In the semiconductor manufacturing process, precisely controlling the pressure inside the reaction chamber of a CVD device is crucial for depositing high-quality and uniform thin films.

[0033] However, current mainstream pressure control methods, including fixed PID control and parameter adaptive control, cannot directly obtain key system parameters, especially the chamber volume and inlet gas flow rate. The uncertainty of these parameters, combined with the changes in the volume occupied by the wafers and gas flow rates in different processes, increases the complexity of pressure control using a pressure control butterfly valve, thereby affecting the thin film deposition process, resulting in a decrease in thin film quality and uniformity, and ultimately affecting production efficiency and product performance.

[0034] In view of this, the inventors have found through research and improvement exploration that: when the existing pressure control method uses a pressure control butterfly valve to control the pressure inside the reaction chamber of a CVD device, the pressure control butterfly valve cannot precisely control the pressure inside the reaction chamber, thereby resulting in a decrease in thin film quality and uniformity.

[0035] Based on this, the embodiments of this specification propose a modeling method for parameter identification of a vacuum pressure system. The overall idea is as follows: Determine the gas amount balance equation at any time in the chamber through the law of conservation of mass, and then consider the relationship between the inlet flow rate and the outlet flow rate, as well as the influence of the chamber pressure and the butterfly valve conductance, to establish a relationship model between the pressure and time in the chamber, which can accurately predict the pressure change in the chamber and significantly improve the accuracy and response speed of pressure control.

[0036] The following will describe the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.

[0037] The embodiments of this specification provide a modeling method for parameter identification of a vacuum pressure system to model the pressure change in the chamber. The modeling method for parameter identification of the vacuum pressure system includes:

[0038] According to the law of conservation of mass, establish the gas amount balance equation at any time in the chamber, and the expression is:

[0039] , where represents the total amount of gas entering from the inlet end, represents the total amount of gas discharged from the outlet end;

[0040] According to the constant inlet flow rate and the relationship between the outlet flow rate and the chamber pressure and the butterfly valve conductance, establish a relationship model of the gas amount in the chamber changing with time: ;

[0041] Utilize the ideal gas state equation: , and obtain the relationship model between the pressure and time in the chamber, and the expression is: ;

[0042] where represents the pressure at any time t in the chamber; 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 gas in the chamber; c represents the current conductance of the butterfly valve; t represents time; Q represents the inlet mass flow rate at the inlet end.

[0043] Specifically, the inlet mass flow rate at the inlet end is represented by Q, with the unit Pa m³ / s; the pressure at any time t in the chamber is represented by , with the unit Pa; the volume of the chamber is represented by V, with the unit ; the current conductance of the butterfly valve is represented by c, with the unit . Since there is only one inlet and one outlet in the chamber, the amount of gas in the chamber at any time is:

[0044] (1)

[0045] wherein is the total amount of gas entering from the intake end, is the total amount of gas discharged from the outlet end. Since the intake flow rate is constant, the outlet flow rate and the chamber pressure are related to the butterfly valve conductance, so Equation (1) is transformed into:

[0046] (2)

[0047] According to the ideal gas state equation:

[0048] (3)

[0049] In Equation (3): p is the pressure (Pa), V is the gas volume ( ), T is the temperature (K), n is the amount of substance of the gas ( ), and R is the molar gas constant (also called the universal gas constant) (J / ( .K))

[0050] It can be obtained that

[0051] (4)

[0052] Substituting Equation (4) into (2), it can be obtained that:

[0053] , (5)

[0054] Solving the differential equation formula (5), the pressure expression in the chamber at any time t can be finally obtained as:

[0055] (6)

[0056] where C is the constant in the general solution of the differential equation.

[0057] This formula shows that the pressure in the chamber at any time t is only related to the butterfly valve conductance c, the intake gas volume Q, and the chamber volume V.

[0058] In some embodiments, the ideal gas state equation: is used to obtain the relationship model between the pressure in the chamber and time, including:

[0059] After substituting the ideal gas state equation into the gas amount balance equation, it is solved by numerical methods, analytical methods or approximate methods.

[0060] Based on the same inventive concept, the present application also provides a parameter identification method for a vacuum pressure system, including:

[0061] 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;

[0062] 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;

[0063] The collected data is fitted by an optimization algorithm to identify the parameters in the relationship model.

[0064] 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;

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] In some embodiments, such as 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;

[0070] Establishing a data set based on the collected data, wherein the data set includes a timestamp and a corresponding pressure value at each moment;

[0071] Initialize parameters according to the relational model and the data set;

[0072] Construct loss function;

[0073] Calculate the gradient of the loss function with respect to each parameter;

[0074] Iteratively update the parameters in the direction of the gradient using the gradient descent method, repeatedly calculate the gradient and update the parameters until the value of the loss function is less than the preset threshold, and output the values of the parameters in the relational model.

[0075] Specifically, in formula (6), k and c are in a multiplicative relationship, which makes it difficult to separate their influences when optimizing the parameters. Moreover, in the gradient descent method, it is necessary to calculate the gradient of the parameters. If there is a product relationship between the parameters, the calculation of the gradient will be very complicated. Therefore, define new parameters to simplify formula (6) to:

[0076] (7)

[0077] Thereby reducing the computational complexity.

[0078] Use the exponential function shown in formula (7) to fit the collected pressure data. The parameters to be calculated are , , , and the steps are as follows:

[0079] (1) Prepare the dataset

[0080] As in the previous steps, the pressure data at different timestamps collected is expressed as

[0081] Timestamp: t ;

[0082] Pressure: ;

[0083] (2) Initialize the parameters

[0084] According to the formula (7) to be fitted and the dataset, initialize the parameters:

[0085] ; ; ;

[0086] (3) Calculate the loss function

[0087] ;

[0088] Where , , , ;

[0089] (4) Calculate the gradient

[0090] The gradient of parameter C is

[0091] ;

[0092] The gradient of parameter k1 is:

[0093] ;

[0094] The gradient of parameter k2 is:

[0095] ;

[0096] where , , , ;

[0097] (5) Update the parameters

[0098] Update the three parameters according to the values of the previous three parameters and their corresponding gradients;

[0099] (6) Update the iteration

[0100] Repeat steps (3)-(5) until the value of the loss function sum_e in step (3) is less than the preset threshold, and output the values of the parameters in the relationship model.

[0101] In some embodiments, when the value of the loss function sum_e is less than 0.001, the iteration ends, and the parameters C, k1, and k2 at this time are the finally calculated values.

[0102] In some embodiments, when using the gradient descent method to iteratively update the parameters in the gradient direction, the learning rate is set to 0.01.

[0103] Specifically, ;

[0104] ;

[0105] ;

[0106] In some embodiments, the parameter identification method of the vacuum pressure system is used to identify the cavity volume and the cavity inlet flow rate parameters in the CVD equipment vacuum pressure system.

[0107] Specifically, according to the parameters C, k1, and k2 obtained by the gradient descent method above, then

[0108] ;

[0109] .

[0110] In some embodiments, the identified cavity volume and cavity inlet flow rate parameters are used to control the valve plate opening of the butterfly valve to achieve precise control of the cavity pressure.

[0111] Specifically, according to the identified cavity volume and the flow parameter at the air inlet end of the cavity, a control strategy is formulated to control the opening degree of the valve plate of the butterfly valve, thereby achieving precise control of the pressure inside the cavity, adapting to different process conditions and system changes, helping to optimize the thin film deposition process, improving product quality and uniformity, and enhancing production efficiency.

[0112] Based on the same inventive concept, the present application also provides a vacuum pressure system, as Figure 1 shown, including: an air inlet device, a chamber, a butterfly valve, a vacuum pump, a pressure sensor, and a control system;

[0113] The air inlet device is connected to the first end of the chamber and is used for continuously introducing air into the chamber;

[0114] The vacuum pump is connected to the second end of the chamber through the butterfly valve and is used for continuously evacuating the cavity;

[0115] The pressure sensor is connected to the third end of the chamber and is used for detecting the real-time pressure inside the chamber and transmitting the data to the control system;

[0116] The control system controls the opening degree of the valve plate of the butterfly valve by using the parameter identification method of the vacuum pressure system described in any one of the above.

[0117] In this specification, the same or similar parts among 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 foregoing embodiments.

[0118] The above is only the specific implementation manner 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 those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for parameter identification of a vacuum pressure system, characterized in that, Including: Establish a relationship model between the pressure and time in the chamber by using a modeling method for vacuum pressure system parameter identification; Collect data on the change of pressure in the chamber over a period of time, where the data includes: the pressure value and the corresponding timestamp at each moment; Fit the collected data through an optimization algorithm to identify the chamber volume and the chamber inlet flow rate parameters in the relationship model; Use the identified chamber volume and chamber inlet flow rate parameters to control the valve plate opening of the butterfly valve to achieve precise control of the pressure in the chamber; Wherein: the modeling method for vacuum pressure system parameter identification includes: Model the pressure change in the chamber, and the modeling method for vacuum pressure system parameter identification includes: According to the law of conservation of mass, establish the gas amount balance equation at any moment in the chamber, and the expression is: , where represents the total amount of gas entering from the intake end, represents the total amount of gas discharged from the outlet end; According to the constant intake air flow and the relationship between the outlet air volume and the chamber pressure and the butterfly valve conductance, a relationship model of the amount of gas substance in the chamber changing with time is established: ; Using the ideal gas state equation: , a relationship model between the pressure and time in the chamber is obtained, and the expression is: ; Among them, represents the pressure at any moment in the chamber; is a constant in the general solution of the differential equation; is the base of the natural logarithm; is the base of the natural logarithm; , is the molar gas constant, is the temperature, is the volume of the gas in the chamber; represents the current conductance of the butterfly valve; represents time; represents the inlet mass flow rate at the inlet end.

2. The parameter identification method of the vacuum pressure system according to claim 1, characterized in that, Using the ideal gas state equation: , a relationship model between the pressure and time in the chamber is obtained, including: Substitute the ideal gas state equation into the gas amount balance equation and solve it by numerical method or analytical method.

3. The parameter identification method of the vacuum pressure system according to any one of claims 1 or 2, characterized in that, Before collecting data on the change of pressure in the chamber over a period of time, place the butterfly valve in the fully closed position.

4. The parameter identification method of the vacuum pressure system according to any one of claims 1 or 2, characterized in that The step of fitting the collected data through an optimization algorithm to identify the chamber volume and the chamber inlet flow rate parameters in the model includes: the optimization algorithm includes the gradient descent method; According to the collected data, establish a data set, where the data set includes the timestamp and the corresponding pressure value at each moment; Initialize the parameters according to the relationship model and the data set; Construct a 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, repeat calculating the gradient and updating the parameters until the value of the loss function is less than a preset threshold, and output the values of the parameters in the relationship model.

5. The parameter identification method of the vacuum pressure system according to claim 4, characterized in that, When using the gradient descent method to iteratively update the parameters in the gradient direction, set the learning rate to 0.

01.

6. The parameter identification method of the vacuum pressure system according to any one of claims 1 or 2, characterized in that The parameter identification method of the vacuum pressure system is used to identify the chamber volume and the chamber inlet flow rate parameters in the CVD equipment vacuum pressure system.

7. A vacuum pressure system, characterized in that, Including: An intake device, a chamber, a butterfly valve, a vacuum pump, a pressure sensor, and a control system; The intake device is connected to the first end of the chamber and is used to continuously introduce gas 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 controls the valve plate opening of the butterfly valve by using the parameter identification method of the vacuum pressure system as described in any one of claims 1-6.

Images