Temperature compensation method, temperature compensation device, and process chamber

Abstract

The application provides a temperature compensation method and a process chamber applied to the process chamber. The temperature compensation method comprises the following steps: for each temperature measuring instrument, determining a first temperature compensation value corresponding to the temperature measuring instrument according to a film thickness value of a film layer at a position corresponding to the temperature measuring instrument and a temperature sensitivity value of the process chamber; inputting a difference between the film thickness value corresponding to each temperature measuring instrument and an average value of a plurality of film thickness values, a difference between a uniform value of the film layer and a preset uniform value of the film layer, and the first temperature compensation value corresponding to each temperature measuring instrument into a pre-trained temperature compensation model to obtain a second temperature compensation value corresponding to each temperature measuring instrument; and obtaining a target temperature compensation value corresponding to the temperature measuring instrument according to the first temperature compensation value and the second temperature compensation value corresponding to the temperature measuring instrument. The temperature compensation method provided by the application can find the temperature compensation value meeting the requirement only by one-step debugging, saves the consumption of test wafers, simplifies the operation of the machine, and can realize the automatic determination of the temperature compensation value by the machine.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of process chambers, in particular, to a temperature compensation method applied to a process chamber, a temperature compensation device and a process chamber. BACKGROUND

[0002] In the process of IC manufacturing, a thin oxide film is needed to be formed between the silicon substrate and other deposition layers according to special requirements. For example, in the process of manufacturing flash memory, an oxide-nitride-oxide (ONO) layer is needed to be formed between the control gate and the word line for isolation, so that the electrons can flow normally and the stability of the device can be improved. The oxide layer in the ONO layer is obtained by rapid thermal oxidation (RTO) process, that is, a silicon dioxide (SiO2) layer with controllable thickness and thickness uniformity is formed on the surface of silicon (Si) by rapid temperature rising and falling. The rapid thermal oxidation process is completed in a rapid thermal processing (RTP) machine.

[0003] The rapid thermal processing machine generally includes a cavity, a plurality of heating lamps arranged in the cavity, a carrier disc and a plurality of infrared temperature measuring instruments. The heating lamps are used to heat the wafer carried on the carrier disc, and the infrared temperature measuring instruments are used to monitor the temperature of the wafer in real time. In order to ensure that the thickness uniformity of the oxide film generated by the rapid thermal oxidation process is within the required range, tempMatch operation is needed to be performed on the seven infrared temperature measuring instruments in the cavity after each opening operation, that is, single-point temperature calibration is performed on the seven infrared temperature measuring instruments by a standard light source, so as to realize the re-calibration of the rapid thermal oxidation process. The specific meaning of re-calibration is that by adding appropriate offset values to the seven infrared temperature measuring instruments, the thickness uniformity of the oxide film generated by the rapid thermal oxidation process is adjusted to a suitable value.

[0004] In the related art, the appropriate offset values are usually manually adjusted by a process engineer in the re-calibration step. The process engineer needs to perform multiple rapid thermal oxidation processes to confirm whether the adjustment direction is correct, so a certain number of wafers are consumed to find the appropriate combination of offset values. In addition, the adjustment amount of the offset value each time is based on the experience and feeling of the process engineer, which is not conducive to popularization at the customer end.

[0005] Therefore, how to provide a temperature compensation method applied to a process chamber, which can accurately and efficiently determine the offset value of the temperature measuring instrument, has become a technical problem to be solved in the field. SUMMARY

[0006] The present application aims to provide a temperature compensation method applied to a process chamber, a temperature compensation device and a process chamber capable of implementing the method, which can accurately and efficiently determine the compensation value of a temperature measuring instrument.

[0007] To achieve the above-mentioned purpose, as one aspect of the present application, a temperature compensation method applied to a process chamber is provided, the process chamber comprising a carrying base for carrying a substrate, a heater and a plurality of temperature measuring instruments arranged along the radial direction of the carrying base, the temperature compensation method comprising:

[0008] The compensation method comprises:

[0009] For each temperature measuring instrument, a first temperature compensation value corresponding to the temperature measuring instrument is determined according to the film thickness value of the film layer at the position corresponding to the temperature measuring instrument and the temperature sensitivity value of the process chamber; wherein the film layer is formed on the substrate by controlling the heater under an initial set temperature by the plurality of temperature measuring instruments; the temperature sensitivity value refers to the thickness change amount of the film layer under unit temperature change;

[0010] The difference between the film thickness value corresponding to each temperature measuring instrument and the average value of the plurality of film thickness values, the difference between the uniformity value of the film layer and the preset film layer uniformity value and the first temperature compensation value corresponding to each temperature measuring instrument are input into a pre-trained temperature compensation model to obtain a second temperature compensation value corresponding to each temperature measuring instrument;

[0011] For each temperature measuring instrument, a target temperature compensation value corresponding to the temperature measuring instrument is obtained according to the first temperature compensation value and the second temperature compensation value corresponding to the temperature measuring instrument.

[0012] Optionally, a fully connected neural network algorithm is used to construct the temperature compensation model, and the temperature compensation model comprises an input layer, an output layer and at least one hidden layer;

[0013] The difference between the film thickness value corresponding to each temperature measuring instrument and the average value of the plurality of film thickness values, the difference between the uniformity value of the film layer and the preset film layer uniformity value and the first temperature compensation value corresponding to each temperature measuring instrument are input into a pre-trained temperature compensation model to obtain a second temperature compensation value corresponding to each temperature measuring instrument, comprising:

[0014] The difference between the film thickness value corresponding to each temperature measuring instrument and the average value of the plurality of film thickness values, the difference between the uniformity value of the film layer and the preset film layer uniformity value and the first temperature compensation value corresponding to each temperature measuring instrument are input into the input layer;

[0015] The second temperature compensation value corresponding to each temperature measuring instrument is obtained from the output layer.

[0016] Optionally, the expression of the input layer is a1=(x-offset1)×gain1+x min , wherein x is the difference between the film thickness value and the average value, the difference between the uniform value of the film layer and the preset film layer uniform value, and the first temperature compensation value, offset1, gain1, and x min are training parameters, and a1 is the output result of the input layer.

[0017] Optionally, the expression of the hidden layer is n=b1+LW1×a1, , wherein LW1 is the first layer weight parameter, b1 is the training parameter, and a2 is the output result of the input layer.

[0018] Optionally, the expression of the output layer is a3=b2+LW2×a2, y=(a3-y min )÷gain2+offset2, wherein LW2 is the second layer weight parameter, b2, gain2, offset2, and y min are training parameters, and y is the second temperature compensation value.

[0019] Optionally, the determination of the first temperature compensation value corresponding to the pyrometer according to the film thickness value of the film layer at the position corresponding to the pyrometer and the temperature sensitivity value of the process chamber comprises:

[0020] For each pyrometer, the difference between the film thickness value of the film layer at the position corresponding to the pyrometer and the average value of a plurality of film thickness values is divided by the temperature sensitivity value to obtain the first temperature compensation value corresponding to the pyrometer.

[0021] Optionally, the determination of the target temperature compensation value corresponding to the pyrometer according to the first temperature compensation value and the second temperature compensation value corresponding to the pyrometer comprises:

[0022] The first temperature compensation value and the second temperature compensation value are weighted and summed to obtain the corresponding target temperature compensation value.

[0023] Optionally, the weight factor of the first temperature compensation value is greater than the weight factor of the second temperature compensation value, and the weight factor of the first temperature compensation value and the weight factor of the second temperature compensation value are both greater than 0 and less than or equal to 1.

[0024] As a second aspect of the present application, a temperature compensation device is provided, which comprises a processor and a memory, the memory stores a computer program, and the processor executes the computer program to execute the temperature compensation method described above.

[0025] As a third aspect of the present application, a process chamber is provided, comprising a cavity, a controller, a carrier disk, a plurality of heating lamps and a plurality of temperature detectors, the carrier disk is arranged in the cavity, the plurality of heating lamps are used for heating a wafer carried on the carrier disk, and the plurality of temperature detectors are used for detecting the temperature of the wafer at each position; the controller comprises a processor and a memory, the memory stores a computer program, and the processor executes the computer program to execute the temperature compensation method described above.

[0026] In the temperature compensation method, the temperature compensation device and the process chamber provided by the present application, the controller first determines a first temperature compensation value corresponding to each temperature detector according to the difference value corresponding to each temperature detector, then determines a second temperature compensation value corresponding to each temperature detector based on the neural network algorithm according to the data calculated above, and finally determines a target temperature compensation value for compensating the temperature detector according to the first temperature compensation value and the second temperature compensation value.

[0027] The temperature compensation method provided by the present application only needs one film deposition process and debugging to find a temperature compensation value meeting the requirements, saves the consumption of test wafers, and simplifies the required machine operation after completing the tempMatch operation each time. Moreover, the controller replaces the operation of selectively amplifying or reducing the temperature compensation value according to the understanding of the process engineer by the neural network algorithm, can automatically determine the temperature compensation value by the machine, and thus improves the machine debugging efficiency, improves the machine capacity and user experience. BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used together with the following specific embodiments to explain the present application, but do not constitute a limitation on the present application. In the drawings:

[0029] Figure 1 is a structural schematic diagram of a process chamber provided by an embodiment of the present application;

[0030] Figure 2 is a flowchart of a temperature compensation method applied to a process chamber provided by an embodiment of the present application;

[0031] Figure 3 is a structural schematic diagram of a neural network in the temperature compensation method applied to a process chamber provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] The specific embodiments of the present application are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0033] In the related art, the difference Δd between the film thickness value at the corresponding position of the pyrometer and the average value of the plurality of film thickness values is usually determined by a process engineer through a pyrometer i The required temperature compensation value is calculated, and the calculated temperature compensation value is selectively amplified or reduced according to the understanding of the process engineer, that is, the calculated result is fine-tuned according to the "feeling", so as to achieve the effect of flattening the film thickness. This process requires the process engineer to perform multiple rapid thermal oxidation processes to confirm whether the direction of the feeling-based debugging is correct, and the adjustment amount is seriously dependent on the experience and feeling of the process engineer, which is not conducive to promotion at the customer end.

[0034] To solve the above technical problems, as one aspect of the present application, a temperature compensation method applied to a process chamber is provided, the process chamber comprising a supporting base for supporting a substrate, a heater, and a plurality of pyrometers arranged in sequence along the radial direction of the supporting base, such as Figure 2 As shown, the temperature compensation method comprises:

[0035] Step S1, for each pyrometer, determining a first temperature compensation value offset corresponding to the pyrometer according to the film thickness value of the film layer at the corresponding position of the pyrometer and the temperature sensitivity value δ of the process chamber i (i = 1, 2, … n, where n is the number of pyrometers); wherein the film layer is a film layer formed on the substrate by controlling the heater at the initial set temperature by the plurality of pyrometers; the temperature sensitivity value δ refers to the thickness change amount of the film layer per unit temperature change;

[0036] Step S2, determining the difference Δd between the film thickness value corresponding to each pyrometer and the average value of the plurality of film thickness values i , the difference Δr between the uniformity value of the film layer and the preset film layer uniformity value, and the first temperature compensation value offset corresponding to each pyrometer i Inputting a pre-trained temperature compensation model to obtain a second temperature compensation value Δt corresponding to each pyrometer i ;

[0037] Step S3, for each pyrometer, obtaining a target temperature compensation value ΔT corresponding to the pyrometer according to the first temperature compensation value and the second temperature compensation value corresponding to the pyrometer i .

[0038] In the temperature compensation method applied to the process chamber provided by the present application, the difference Δd i corresponding to each pyrometer is first determined to preliminarily determine the first temperature compensation value offset corresponding to each pyrometer i (corresponding to the step of calculating the temperature compensation value in the related art), and then the second temperature compensation value Δt i(This corresponds to the step in related technologies where process engineers scale up or down the temperature compensation value according to their own understanding), and finally, based on the first temperature compensation value offset... i With the second temperature compensation value Δt i Determine the final target temperature compensation value ΔT used for the thermometer. i .

[0039] The temperature compensation method for process chambers provided by this invention can find the target temperature compensation value ΔT that meets the requirements with only one step of film deposition process and debugging. i This reduces the consumption of test wafers and simplifies the machine operations required after each tempMatch operation. Furthermore, the temperature compensation method provided by this invention utilizes a neural network algorithm to replace the process engineer's selective amplification or reduction of temperature compensation values ​​based on their own understanding. This enables automated determination of temperature compensation values ​​on the machine, thereby improving machine debugging efficiency, increasing machine capacity, and enhancing user experience.

[0040] As an optional embodiment of the present invention, the preset film uniformity value (i.e., the target value for film thickness uniformity) can be set to 0.3%.

[0041] As an optional embodiment of the present invention, a temperature compensation model is constructed using a fully connected neural network algorithm. The temperature compensation model includes an input layer, an output layer, and at least one hidden layer.

[0042] The difference Δd between the film thickness value corresponding to each thermometer and the average of multiple film thickness values ​​is calculated. i The difference Δr between the uniform value of the film layer and the preset uniform value of the film layer, and the first temperature compensation value offset for each thermometer. i Input the pre-trained temperature compensation model to obtain the second temperature compensation value Δt for each thermometer. i ,include:

[0043] The difference Δd between the film thickness value corresponding to each thermometer and the average of multiple film thickness values ​​is calculated. i The difference Δr between the uniform value of the film layer and the preset uniform value of the film layer, and the first temperature compensation value offset for each thermometer. i Input layer;

[0044] The second temperature compensation value Δt for each thermometer is obtained from the output layer. i .

[0045] Considering that the use scene of the neural network algorithm in the application is not complex (so-called complex refers to factors affecting the same input but the system gives different outputs, such as in automatic driving, the same destination is input, but there are often unexpected situations on the road, such as pedestrians suddenly crossing, cars suddenly not obeying traffic rules, resulting in different paths to the destination each time, and in the image recognition task, the same face is identified, and the recognition result is different because the light causes different light and dark areas, and different accessories on the face (such as different glasses and different hairstyles), and in the current scene, the same offset value is input, and the film thickness value obtained after the chamber runs the RTO process is necessarily the same or fluctuates within a very small range, and the conditions of each RTO process are the same, so it can be considered that the use scene is not complex), therefore, a fully connected neural network algorithm with a relatively simple structure is selected, and neural network algorithms with more complex structures such as deep convolutional neural network and ResNet are not considered.

[0046] As an optional embodiment of the application, as shown in Figure 3 , the neural network algorithm comprises an input layer, a hidden layer and an output layer.

[0047] As an optional embodiment of the application, the expression of the input layer is a1=(x-offset1) x gain1+x min , wherein x is the difference value Ad between the film thickness value and the average value i , the difference value Ar between the uniform value of the film layer and the preset uniform value of the film layer, and the first temperature compensation value offset i , offset1, gain1 and x min are training parameters (the values of the training parameters are automatically updated by the algorithm during the model training process, and the training parameters are fixed as constants after the training is completed), and a1 is the output result of the input layer.

[0048] The input value x of the input layer is:

[0049] [Ad1, Ad2, …, Ad n , Ar, offset1, offset2, …, offset n ]. That is, the input value of the input layer includes a plurality of difference values Ad1, Ad2, …, Ad n corresponding to a plurality of thermometers, the difference value Ar between the average value and the target film thickness average value, and a plurality of first temperature compensation values offset1, offset2, …, offset n .

[0050] As an optional embodiment of the application, as shown in Figure 1As shown, the process chamber includes 7 temperature measuring instruments (300). Therefore, the input value x of the input layer is:

[0051] [Δd1,Δd2,Δd3,Δd4,Δd5,Δd6,Δd7,Δr,offset1,offset2,offset3,offset4,offset5,offset6,offset7].

[0052] As an optional embodiment of the present invention, the hidden layer uses the Sigmoid activation function, and the expression of the hidden layer is: n = b1 + LW1 × a1, Wherein, LW1 is the first layer weight parameter (i.e., the weight parameter of this layer, which is automatically updated by the algorithm during training and fixed as a constant after training), b1 is the training parameter, and a2 is the output result of the input layer.

[0053] As an optional embodiment of the present invention, the output layer adopts a linear regression output function, and the expression of the output layer is: a3=b2+LW2×a2, y=(a3-y min )÷gain2+offset2, where LW2 is the second-level weight parameter, b2, gain2, offset2, and y min All parameters are training parameters, and y is the second temperature compensation value Δt. i .

[0054] As an optional embodiment of the present invention, such as Figure 1 As shown, the process chamber includes 7 temperature measuring instruments (300). Therefore, the output value y of the output layer is:

[0055] [Δt1,Δt2,Δt3,Δt4,Δt5,Δt6,Δt7].

[0056] As an optional embodiment of the present invention, the temperature compensation method applied to the process chamber further includes:

[0057] The parameters of the neural network algorithm are initialized using the Xavier initialization algorithm, and the neural network algorithm is trained using the Levenberg-Marquardt algorithm.

[0058] As an optional embodiment of the present invention, the training process of the neural network algorithm uses a dataset obtained from actual machine data collection. Specifically, the training dataset can be all the film thickness data and temperature compensation value variation data previously used by the machine during debugging starting from zero compensation (0 offset).

[0059] As an optional embodiment of the present application, the first temperature compensation value offset corresponding to the temperature measuring instrument is determined according to the film thickness value of the film layer at the position corresponding to the temperature measuring instrument and the temperature sensitivity value δ of the process chamber in step S1 i Specifically includes:

[0060] For each temperature measuring instrument, the difference Δd between the film thickness value of the film layer at the position corresponding to the temperature measuring instrument and the average value of the plurality of film thickness values i is divided by the temperature sensitivity value δ to obtain the first temperature compensation value offset corresponding to the temperature measuring instrument i .

[0061] That is, the first temperature compensation value offset i = Δd i ÷ δ, wherein the temperature sensitivity value δ is a constant that can be determined in advance.

[0062] As an optional embodiment of the present application, the target temperature compensation value ΔT corresponding to the temperature measuring instrument is obtained according to the first temperature compensation value and the second temperature compensation value corresponding to the temperature measuring instrument in step S3 i Specifically includes:

[0063] Each first temperature compensation value offset i is weighted and summed with the corresponding second temperature compensation value Δt i to obtain the corresponding target temperature compensation value ΔT i .

[0064] That is, the target temperature compensation value ΔT i = offset i × a + Δt i × b, wherein a and b are weight factors that can be determined in advance through experiments, the numerical value of the weight factor ranges from 0 to 1, and according to the experimental results, the numerical value of the weight factor a is generally greater than the numerical value of the weight factor b.

[0065] As an optional embodiment of the present application, the weight factor of the first temperature compensation value can be set to 0.9, and the weight factor of the second temperature compensation value can be set to 0.2.

[0066] As an optional embodiment of the present application, the temperature compensation method applied to the process chamber further includes:

[0067] The target temperature compensation value ΔT i is filled into the host computer software, and the film layer deposition process is performed again to verify the compensation effect.

[0068] As a second aspect of the present application, a temperature compensation device is provided, the temperature compensation device comprising a processor and a memory, the memory storing a computer program, and the processor executing the computer program to perform the temperature compensation method provided by the embodiments of the present application.

[0069] In the temperature compensation device provided by the present application, the processor first determines the first temperature compensation value offset i corresponding to each temperature measuring instrument according to the difference Δd i (corresponding to the step of calculating the temperature compensation value in the related art), and then determines the second temperature compensation value Δt i (corresponding to the step of amplifying or reducing the temperature compensation value according to the understanding of the process engineer in the related art), and finally determines the target temperature compensation value ΔT i corresponding to each temperature measuring instrument according to the first temperature compensation value offset i and the second temperature compensation value Δt i .

[0070] The temperature compensation device provided by the present application only needs one step of film deposition process and debugging to find the target temperature compensation value ΔT i that meets the requirements, saving the consumption of test wafers and simplifying the required machine operation after completing the tempMatch operation each time. Moreover, the controller replaces the operation of selectively amplifying or reducing the temperature compensation value according to the understanding of the process engineer by the neural network algorithm, which can realize automatic determination of the temperature compensation value by the machine, thereby improving the user experience.

[0071] As a third aspect of the present application, a process chamber is provided, as shown in Figure 1 the process chamber comprising a cavity, a controller, a carrier disk 200, a plurality of heating lamps 100, and a plurality of temperature measuring instruments 300, the carrier disk 200 being arranged in the cavity, the plurality of heating lamps being used to heat the wafer 10 carried on the carrier disk 200, and the plurality of temperature measuring instruments 300 being used to detect the temperature at each position of the wafer 10; the controller comprising a processor and a memory, the memory storing a computer program, and the processor executing the computer program to perform the temperature compensation method provided by the embodiments of the present application.

[0072] In the process chamber of the temperature measuring instrument provided by the present application, the controller first determines the first temperature compensation value offset iThe initial temperature compensation value offset for each temperature sensor is determined (corresponding to the step of calculating the temperature compensation value in related technologies). Then, based on the previously calculated data, a second temperature compensation value Δt is determined for each temperature sensor using a neural network algorithm (corresponding to the step in related technologies where process engineers scale up or down the temperature compensation value according to their understanding). Finally, the first temperature compensation value offset is used to determine the second temperature compensation value Δt for each temperature sensor. i With the second temperature compensation value Δt i Determine the final target temperature compensation value ΔT used for the thermometer. i .

[0073] The process chamber provided by this invention only requires a single film deposition process and debugging step to find the target temperature compensation value ΔT that meets the requirements. i This reduces the consumption of test wafers and simplifies the equipment operations required after each tempMatch operation. Furthermore, the controller uses a neural network algorithm to replace the process engineer's selective scaling of temperature compensation values ​​based on their own understanding, enabling automated determination of temperature compensation values ​​and thus improving the user experience.

[0074] As an optional embodiment of the present invention, the process chamber is a rapid thermal processing (RTP) device.

[0075] As an optional embodiment of the present invention, the thermometer 300 is an infrared thermometer.

[0076] As an optional embodiment of the present invention, such as Figure 1 As shown, the process chamber includes 7 temperature measuring instruments (300).

[0077] In other embodiments of the present invention, the process chamber may also include other numbers of temperature measuring instruments 300. For example, the process chamber may include 3 temperature measuring instruments 300, and the controller needs to calculate 3 target temperature compensation values ​​(offset values) accordingly; or, the process chamber may include 9 temperature measuring instruments 300, then the controller needs to calculate 9 target temperature compensation values ​​accordingly.

[0078] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A temperature compensation method applied to a process chamber, characterized in that, The process chamber includes a substrate support, a heater, and a plurality of temperature sensors arranged radially along the substrate support. The temperature compensation method includes: For each of the aforementioned temperature measuring instruments, a first temperature compensation value corresponding to the temperature measuring instrument is determined based on the film thickness value of the film layer at the corresponding position of the temperature measuring instrument and the temperature sensitivity value of the process chamber; wherein, the film layer is a film layer formed on the substrate by controlling the heater with multiple temperature measuring instruments at an initial set temperature; the temperature sensitivity value refers to the change in film thickness under unit temperature change. The difference between the film thickness value corresponding to each of the thermometers and the average value of multiple film thickness values, the difference between the uniform value of the film layer and the preset uniform value of the film layer, and the first temperature compensation value corresponding to each of the thermometers are input into the pre-trained temperature compensation model to obtain the second temperature compensation value corresponding to each of the thermometers. For each of the aforementioned temperature measuring instruments, the target temperature compensation value corresponding to the temperature measuring instrument is obtained based on the first temperature compensation value and the second temperature compensation value corresponding to the temperature measuring instrument.

2. The temperature compensation method for process chambers according to claim 1, characterized in that, The temperature compensation model is constructed using a fully connected neural network algorithm, and the temperature compensation model includes an input layer, an output layer, and at least one hidden layer. The step of inputting the difference between the film thickness value corresponding to each of the thermometers and the average of multiple film thickness values, the difference between the uniformity value of the film layer and a preset uniformity value of the film layer, and the first temperature compensation value corresponding to each of the thermometers into a pre-trained temperature compensation model to obtain the second temperature compensation value corresponding to each of the thermometers includes: The difference between the film thickness value corresponding to each of the thermometers and the average value of multiple film thickness values, the difference between the uniformity value of the film layer and the preset uniformity value of the film layer, and the first temperature compensation value corresponding to each of the thermometers are input into the input layer. The output layer yields the second temperature compensation value for each of the thermometers.

3. The temperature compensation method for process chambers according to claim 2, characterized in that, The expression for the input layer is: a1 = (x - offset1) × gain1 + x min Where x is the difference between the film thickness value and the average value, the difference between the uniformity value of the film layer and the preset uniformity value of the film layer, and the first temperature compensation value, offset1, gain1, and x min All of these are training parameters, and a1 is the output result of the input layer.

4. The temperature compensation method for process chambers according to claim 2, characterized in that, The expression for the hidden layer is: n = b1 + LW1 × a1, Where LW1 is the weight parameter of the first layer, b1 is the training parameter, and a2 is the output result of the input layer.

5. The temperature compensation method for process chambers according to claim 2, characterized in that, The expression for the output layer is: a3 = b2 + LW2 × a2, y = (a3 - y) min )÷gain2+offset2, where LW2 is the second-level weight parameter, b2, gain2, offset2, and y min All of these are training parameters, and y is the second temperature compensation value.

6. The temperature compensation method for a process chamber according to any one of claims 1 to 5, characterized in that, The step of determining the first temperature compensation value corresponding to the temperature measuring instrument based on the film thickness value of the film layer at the corresponding position of the temperature measuring instrument and the temperature sensitivity value of the process chamber includes: For each of the aforementioned temperature measuring instruments, the difference between the film thickness value at the corresponding position of the temperature measuring instrument and the average value of multiple film thickness values ​​is divided by the temperature sensitivity value to obtain the first temperature compensation value corresponding to the temperature measuring instrument.

7. The temperature compensation method for a process chamber according to any one of claims 1 to 5, characterized in that, The step of obtaining the target temperature compensation value corresponding to the thermometer based on the first temperature compensation value and the second temperature compensation value corresponding to the thermometer includes: The first temperature compensation value and the second temperature compensation value are weighted and summed to obtain the corresponding target temperature compensation value.

8. The temperature compensation method for a process chamber according to claim 7, characterized in that, The weighting factor of the first temperature compensation value is greater than the weighting factor of the second temperature compensation value, and both the weighting factor of the first temperature compensation value and the weighting factor of the second temperature compensation value are greater than 0 and less than or equal to 1.

9. A temperature compensation device, characterized in that, The temperature compensation device includes a processor and a memory, the memory storing a computer program, and when the processor executes the computer program, it performs the temperature compensation method according to any one of claims 1-8.

10. A process chamber, characterized in that, The device includes a cavity, a controller, a carrier plate, multiple heating lamps, and multiple temperature measuring instruments. The carrier plate is disposed in the cavity, the multiple heating lamps are used to heat the wafer carried on the carrier plate, and the multiple temperature measuring instruments are used to detect the temperature at various points on the wafer. The controller includes a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, it executes the temperature compensation method according to any one of claims 1-8.

Images