VI sensor and method for monitoring plasma state

Abstract

There is a need for technological development that can more accurately confirm the plasma state or plasma process state, thereby resolving the problem of reduced productivity. [Solution] The present invention relates to a VI sensor and method for monitoring the plasma state, and includes an acquisition unit that collects RF voltage, current, and power of incident and reflected waves generated during the plasma process as sensing data, and a processor that applies the sensing data and the plasma equipment settings confirmed at the time of the generation of the sensing data to an artificial intelligence algorithm to learn the artificial intelligence algorithm, and uses the learned artificial intelligence algorithm to derive predictive data that can monitor the plasma state and plasma process state, and is applicable to other embodiments as well.

Description

Technical Field

[0001] The present invention relates to a VI sensor for monitoring a plasma state and a method thereof.

Background Art

[0002] Generally, during the manufacturing process of semiconductor devices, plasma equipment that utilizes plasma generated through high-frequency power to perform etching, deposition, etc. of semiconductor substrates is widely used. Various sensors are attached to such plasma equipment, and based on the sensing data obtained from the sensors, the operation and operating conditions of the plasma equipment or accessories are confirmed.

[0003] Currently, by analyzing the sensing data obtained from the sensors attached to the plasma equipment, functions such as determining the start and end points of the plasma process, determining whether there is any functional abnormality such as the presence or absence of plasma generation, determining the end point of wafer etching, and determining whether the process by-products generated inside the plasma equipment have been removed are performed. However, the accuracy of this is very low, so the process may stop in the middle of the plasma process, or it may be determined as an abnormal operation even though it is operating normally, or it may be determined as a normal operation even though it is operating abnormally, frequently occurring and causing a problem of reduced productivity.

[0004] Therefore, there is a need for technological development to more accurately confirm the plasma state or plasma process state and solve the problem of reduced productivity.

Summary of the Invention

Problems to be Solved by the Invention

[0005] To address these conventional problems, an embodiment of the present invention provides a VI sensor and method for monitoring the plasma state, which learns an artificial intelligence algorithm mounted on a VI sensor using sensing data acquired from the VI sensor attached to plasma equipment, and derives data related to the plasma state based on the learned results to monitor the plasma state. [Means for solving the problem]

[0006] The VI sensor for monitoring the plasma state according to an embodiment of the present invention is characterized by including an acquisition unit that collects RF voltage, current, and power of incident and reflected waves generated during the plasma process as sensing data, and a processor that applies the sensing data and the plasma equipment setting values ​​confirmed at the time the sensing data is generated to an artificial intelligence algorithm to learn the artificial intelligence algorithm, and uses the learned artificial intelligence algorithm to derive predictive data that can monitor the plasma state and plasma process state.

[0007] Furthermore, the processor is characterized by performing verification against the predicted data.

[0008] Furthermore, the processor is characterized by confirming whether to discontinue the plasma process or whether to retrain the artificial intelligence algorithm based on the verification results for the verification.

[0009] Furthermore, the system further includes a communication unit, the communication unit being characterized by transmitting the predicted data, which has been verified by the processor, to an electronic device.

[0010] Furthermore, the method for performing plasma state monitoring according to an embodiment of the present invention is characterized by including the steps of: a VI sensor collecting RF voltage, current, and power of incident and reflected waves generated during the plasma process as sensing data; the VI sensor applying the sensing data and the plasma equipment setting values ​​confirmed at the time of generation of the sensing data to an artificial intelligence algorithm to learn the artificial intelligence algorithm; and the VI sensor using the learned artificial intelligence algorithm to derive predictive data that allows monitoring of the plasma state and plasma process state.

[0011] Furthermore, the VI sensor is characterized by further including a step of performing verification against the predicted data.

[0012] Furthermore, the VI sensor is characterized by further including a step of confirming whether to discontinue the plasma process or whether to retrain the artificial intelligence algorithm based on the verified verification results.

[0013] Furthermore, the VI sensor is characterized by further including the step of transmitting a message requesting the termination of the plasma process to the electronic device if it is necessary to terminate the plasma process.

[0014] Furthermore, the method is characterized by further including a step of performing retraining of the artificial intelligence algorithm if the VI sensor requires retraining of the artificial intelligence algorithm.

[0015] Furthermore, the VI sensor is characterized by further including the step of transmitting the verified prediction data to an electronic device. [Effects of the Invention]

[0016] As described above, the VI sensor and method for monitoring the plasma state according to the present invention have the effect of monitoring the plasma state by learning an artificial intelligence algorithm mounted on the VI sensor using sensing data acquired from the VI sensor attached to the plasma equipment, and deriving data related to the plasma state based on the learned results. [Brief explanation of the drawing]

[0017] [Figure 1] This figure schematically shows a plasma equipment in which a VI sensor according to an embodiment of the present invention is arranged. [Figure 2] This figure shows a system including a VI sensor for monitoring the plasma state according to an embodiment of the present invention. [Figure 3] This is a flowchart illustrating a method for monitoring the plasma state using a VI sensor according to an embodiment of the present invention. [Modes for carrying out the invention]

[0018] The following is information on the national research and development projects that supported this invention. [Project-Specific Number] 1711203519 [Issue Number] CRC20014-000 [Department Name] Department of Science, Technology and ICT [Project Management (Specialized) Organization Name] National Science and Technology Research Association [Research Project Name] National Science and Technology Research Association Research Operating Expense Support (Major Project Expenses) - Future-Leading Integrated Research Project [Research Project Title] Development and Demonstration of Intelligent Technology for Semiconductor Plasma Process Equipment [Project Implementation Organization] Korea Fusion Energy Research Institute [Research period] November 1, 2020 to October 31, 2026 Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The detailed description disclosed below together with the accompanying drawings is intended to explain exemplary embodiments of the present invention and is not intended to show the only embodiments in which the present invention can be implemented. In the drawings, parts not related to the description may be omitted for the purpose of clearly explaining the present invention, and the same reference numerals can be used for the same or similar components throughout the specification.

[0019] FIG. 1 is a schematic diagram showing a plasma equipment in which a VI sensor according to an embodiment of the present invention is arranged. Referring to FIG. 1, the plasma equipment may include a process chamber 10 that forms a processing space S in which plasma is formed and sealed for performing substrate processing, a substrate support portion 11 provided in the processing space S on which a substrate W is placed, and a gas injection port 12 that injects gas for performing a process into the processing space S.

[0020] The process chamber 10 may be configured in various ways in a configuration that forms a sealed processing space S in which plasma is formed for performing substrate processing. The substrate support portion 11 may be configured in various ways in a configuration provided in the processing space S on which the substrate W is placed. For example, the substrate support portion 11 may include a susceptor portion (not shown) on which the substrate W is placed and a support rod portion (not shown) that extends from the bottom surface of the susceptor portion and supports the susceptor portion.

[0021] The gas injection port 12 is configured to inject gas for performing a process into the processing space S and may be configured in various ways depending on the gas injection structure. For example, the gas injection port 12 may include a shower head (not shown) that injects the gas supplied through a gas supply pipe (not shown) provided on the upper side downward.

[0022] The plasma equipment is characterized by performing substrate processing by applying one or more RF power supplies 30 to at least one of the process chamber 10, substrate support section 11, and gas injection port 12. For this purpose, one or more RF power supplies 30 are applied to at least one of the process chamber 10, substrate support section 11, and gas injection port 12, and a matching network 20 may be provided between the RF power supplies 30 and the power supply application line 110. Depending on the process conditions, one or more RF power supplies such as high frequency and low frequency can be applied to the RF power supplies 30.

[0023] The VI sensor 200 is a VI probe sensor, provided adjacent to at least one of the first power supply line 110 for applying the RF power supply 30 and the grounding line 120 for grounding, and can measure the RF voltage, current, and power of the incident and reflected waves generated by the plasma generated in the processing space S as sensing data. The VI sensor 200 can learn an artificial intelligence algorithm using the measured sensing data and derive predictive data that can monitor the plasma state and plasma process state using the artificial intelligence algorithm. A more specific operation of the VI sensor 200 for this purpose will be explained using Figure 2 below. In addition, although the embodiment of the present invention is described using an example in which one VI sensor 200 is provided in the plasma equipment, it is not necessarily limited to this, and the number of VI sensors can be changed depending on the number of antennas and electrodes provided in the plasma equipment.

[0024] Figure 2 shows a system including a VI sensor for monitoring the plasma state according to an embodiment of the present invention. Referring to Figure 2, the VI sensor 200 according to the present invention may include a communication unit 210, an acquisition unit 220, a processor 230, and a memory 240.

[0025] The communication unit 210 transmits result data derived by the processor 230 to the electronic device 300 in order to monitor the plasma state and plasma process state through communication with the electronic device 300. For this purpose, the communication unit 210 can communicate with the electronic device 300 using Wi-Fi (wireless fidelity), Bluetooth, BLE (Bluetooth low energy), etc.

[0026] The data collection unit 220 collects sensing data, including RF voltage, current, and power of incident and reflected waves generated during the plasma process, and transmits it to the processor 230. The processor 230 applies the collected sensing data and the set values ​​used when acquiring the sensing data to the artificial intelligence algorithm to perform learning of the artificial intelligence algorithm. In this case, the set values ​​may include the plasma state at the time of sensing data acquisition (e.g., electron density and electron temperature) and the plasma process state (e.g., processes such as etching processes).

[0027] The processor 230 can adjust the number of training iterations, the size of the sensing data load, the number of layers, etc., to improve training accuracy. It can also provide a function to repeatedly input settings within a certain range and find the settings that derive the best result values. In this case, the settings within a certain range may refer to values ​​set through the GridSearchCV technique, which finds the training conditions that can most accurately predict the result values ​​for training.

[0028] The processor 230 inputs test data into the artificial intelligence algorithm, checks the prediction accuracy and the time spent on prediction, and uses only the learning results that match the accuracy and response time set by the user of the VI sensor 200. At this time, the processor 230 can set one or more learning execution results that match the accuracy and response time set by the user. Through this, the predicted values ​​are continuously logged as learning is repeated, and the artificial intelligence algorithm with the highest accuracy can be selected. The processor 230 stores the completed artificial intelligence algorithm in the memory 240.

[0029] The processor 230 applies the sensing data collected by the VI sensor 200 to the artificial intelligence algorithm after it has finished learning, in order to generate prediction data for the plasma state and plasma process state. At this time, the sensing data applied to the artificial intelligence algorithm may be sensing data collected after the artificial intelligence algorithm has finished learning. In addition, the prediction data may include the sensing data applied to the artificial intelligence algorithm, the prediction time, the artificial intelligence algorithm used for prediction, the prediction results (plasma state, plasma process state), actual measured values, etc.

[0030] The processor 230 performs validation of the predicted data by comparing the actual measurement results obtained during the inspection process performed after the completion of the actual plasma process with the predicted data predicted by the processor 230. At this time, the processor 230 can compare the predicted data with the actual measurement results periodically or in real time.

[0031] The processor 230 can confirm that if the error between the predicted data and the actual measurement result exceeds a critical number of cycles beyond the acceptable error range included in the pre-set verification information, it is necessary to stop the process and can transmit a message to the electronic device 300 informing it that the plasma process needs to be stopped.

[0032] The processor 230 can determine that the artificial intelligence algorithm needs to be retrained if the error between the predicted data and the actual measurement result exceeds the acceptable error range included in the pre-set verification information by a critical number of times. At this time, the criteria for deciding whether to stop the plasma process and the criteria for deciding whether the artificial intelligence algorithm needs to be retrained may differ. If the processor 230 determines that the artificial intelligence algorithm needs to be retrained, it will perform the retraining of the artificial intelligence algorithm.

[0033] Furthermore, if the artificial intelligence algorithm does not require retraining or if retraining is complete, the processor 230 transmits prediction data for the plasma state and plasma process state, generated by applying sensing data to the artificial intelligence algorithm trained by the VI sensor 200, to the electronic device 300. Through this, the electronic device 300 can monitor the plasma state and plasma process state predicted by the VI sensor 200.

[0034] Memory 240 stores the operating program for operating the VI sensor 200. More specifically, memory 240 can store artificial intelligence algorithms learned by the processor 230.

[0035] The electronic device 300 is a device that can control the plasma equipment (not shown) through communication with the plasma equipment, and may be an electronic device such as a computer, laptop computer, or tablet PC. The electronic device 300 displays the predicted data received from the VI sensor 200 so that the user can check the plasma state and the plasma process state. The electronic device 300 also controls the operation of the plasma equipment based on the predicted data received from the VI sensor 200.

[0036] More specifically, the electronic device 300 can plan parameter values ​​to be controlled during process progression with plasma equipment based on the predicted data received from the VI sensor 200. When the plasma state value confirmed based on the predicted data differs from a previously set range by more than a threshold, the electronic device 300 can receive input from the user regarding the changed items, amount of change, process parameters, number of process steps, process execution time, etc.

[0037] When the plasma process state, confirmed based on the predicted data, differs from a pre-set range of process states by more than a threshold, the electronic device 300 can receive input from the user regarding the process impact associated with the change in the plasma state.

[0038] The electronic device 300 can generate control combinations based on control factors that can be adjusted using parameter control combination conditions, which have information on items that can be adjusted in at least one of the following processes: a process in which the confirmed predicted plasma state value is outside the range of previously set plasma state values ​​by more than a threshold, and a process in which the confirmed process state is outside the range of previously set process states by more than a threshold.

[0039] The process control combination can perform learning by applying the sensing data acquired during the executed process, along with the predicted plasma state values ​​and plasma process states corresponding to the sensing data, to a reinforcement learning algorithm, which is an artificial intelligence algorithm.

[0040] The electronic device 300 uses a reinforcement learning algorithm to perform a process impact evaluation on the predicted control combination once the prediction for the process control combination is complete. The process impact evaluation determines whether the control combination falls within the range defined by the previously set parameter control constraints. If it does, it can store the parameter control recommendation combination and parameter adjustment amount control information to be used as data for more stable control of the plasma equipment.

[0041] The electronic device 300 can perform parameter value control for plasma equipment based on a set process control combination. Figure 3 is a flowchart illustrating a method for monitoring the plasma state using a VI sensor according to an embodiment of the present invention.

[0042] Referring to Figure 3, in step 301, the processor 230 performs step 303 when it receives a start signal to monitor the plasma state and plasma process state of the plasma equipment, and waits for a start signal to be received if it does not. At this time, the start signal may be an activation signal of the VI sensor 200 received from the electronic device 300 through the communication unit 210.

[0043] In step 303, the acquisition unit 220 collects sensing data. At this time, the sensing data may include RF voltage, current, and power of the incident and reflected waves generated during the plasma process.

[0044] In step 305, the processor 230 applies the collected sensing data and the setpoints used when acquiring the sensing data to the artificial intelligence algorithm to perform learning of the artificial intelligence algorithm. At this time, the setpoints may include the plasma state (e.g., electron density and electron temperature) and the plasma process state (e.g., processes such as the etching process) when acquiring the sensing data.

[0045] The processor 230 can adjust the number of training iterations, the size of the sensing data load, the number of layers, etc., to improve training accuracy. It can also provide a function to repeatedly input settings within a certain range and find the settings that derive the best result values. In this case, the settings within a certain range may refer to values ​​set through the GridSearchCV technique, which finds the training conditions that can most accurately predict the result values ​​for training.

[0046] The processor 230 inputs test data into the artificial intelligence algorithm, checks the prediction accuracy and the time spent on prediction, and uses only the learning results that match the accuracy and response time set by the user of the VI sensor 200. At this time, the processor 230 can set one or more learning execution results that match the accuracy and response time set by the user. Through this, the predicted values ​​are continuously logged as learning is repeated, and the artificial intelligence algorithm with the highest accuracy can be selected. The processor 230 stores the completed artificial intelligence algorithm in the memory 240.

[0047] In step 307, the processor 230 applies the sensing data collected by the VI sensor 200 to the trained artificial intelligence algorithm to generate predictive data for the plasma state and plasma process state. At this time, the sensing data applied to the artificial intelligence algorithm may be sensing data collected after the training of the artificial intelligence algorithm is completed. In addition, the predictive data may include the sensing data applied to the artificial intelligence algorithm, the prediction time, the artificial intelligence algorithm used for prediction, the prediction results (plasma state, plasma process state), actual measured values, etc.

[0048] In step 309, the processor 230 performs validation of the predicted data by comparing the actual measurement results obtained during the inspection process performed after the actual plasma process is completed with the predicted data predicted by the processor 230. At this time, the processor 230 can compare the predicted data with the actual measurement results periodically or in real time.

[0049] In step 311, the processor 230 executes step 315 if the verification results indicate that the plasma process needs to be stopped, and executes step 315 if the plasma process does not need to be stopped. More specifically, the processor 230 can confirm that the process needs to be stopped if the error between the predicted data and the actual measurement result exceeds the range of tolerance included in the pre-set verification information by a critical number of times.

[0050] In step 313, the processor 230 can generate and transmit a message to the electronic device 300 indicating that the plasma process needs to be stopped. Conversely, at step 315, the processor 230 checks whether the artificial intelligence algorithm needs to be retrained. More specifically, the processor 230 can determine that the artificial intelligence algorithm needs to be retrained if the error between the predicted data and the actual measurement result exceeds the range of acceptable error included in the pre-set verification information by a critical number of steps. At this point, the criteria for deciding whether to abort the plasma process and the criteria for deciding whether the artificial intelligence algorithm needs to be retrained may differ.

[0051] If, after checking step 315, it is determined that the artificial intelligence algorithm needs to be retrained, the processor 230 proceeds to step 317; otherwise, it proceeds to step 319. In step 317, the processor 230 performs the retraining of the artificial intelligence algorithm.

[0052] Conversely, if the artificial intelligence algorithm does not need to be retrained or if retraining is complete, in step 319, the processor 230 transmits to the electronic device 300 predictive data for the plasma state and plasma process state generated by applying the sensing data to the artificial intelligence algorithm that has been trained by the VI sensor 200. Through this, the electronic device 300 can monitor the plasma state and plasma process state predicted by the VI sensor 200.

[0053] The embodiments of the present invention disclosed herein and in the drawings are provided merely to illustrate the technical content of the invention and to aid in understanding the invention, and are not intended to limit the scope of the invention. Accordingly, the scope of the invention should be interpreted as including all modifications or alterations derived from the technical idea of ​​the invention, in addition to the embodiments disclosed herein.

Claims

1. A data collection unit that collects RF voltage, current, and power of incident and reflected waves generated during the plasma process as sensing data; and A processor that applies the sensing data and the plasma equipment settings confirmed at the time the sensing data was generated to an artificial intelligence algorithm to learn the artificial intelligence algorithm, and uses the learned artificial intelligence algorithm to derive predictive data that can monitor the plasma state and plasma process state; A VI sensor for performing plasma state monitoring, characterized by including [a specific component].

2. The aforementioned processor, A VI sensor for monitoring the plasma state according to claim 1, characterized by performing verification against the aforementioned predicted data.

3. The aforementioned processor, A VI sensor for performing plasma state monitoring according to claim 2, characterized in that it confirms whether to discontinue the plasma process or whether to retrain the artificial intelligence algorithm based on the verification results for the aforementioned verification.

4. Communications Department; It further includes, The aforementioned communications unit is A VI sensor for monitoring the plasma state according to claim 3, characterized in that the processor transmits the predicted data for which the verification has been completed to an electronic device.

5. The VI sensor collects RF voltage, current, and power of the incident and reflected waves generated during the plasma process as sensing data; The VI sensor applies the sensing data and the plasma equipment setting values ​​confirmed at the time the sensing data was generated to the artificial intelligence algorithm to learn the artificial intelligence algorithm; and The VI sensor derives predictive data that allows it to monitor the plasma state and plasma process state using the artificial intelligence algorithm that has completed the learning process; A method for performing plasma state monitoring, characterized by including [a certain element].

6. The VI sensor performs verification of the predicted data; A method for performing plasma state monitoring according to claim 5, further comprising the following:

7. The VI sensor then determines, based on the verified results, whether to discontinue the plasma process or to retrain the artificial intelligence algorithm; A method for performing plasma state monitoring according to claim 6, further comprising the following:

8. If the VI sensor determines that it is necessary to stop the plasma process, it transmits a message to the electronic device requesting the termination of the plasma process; A method for performing plasma state monitoring according to claim 7, further comprising the following:

9. If the VI sensor requires the artificial intelligence algorithm to be retrained, the VI sensor performs the retraining of the artificial intelligence algorithm; A method for performing plasma state monitoring according to claim 7, further comprising the following:

10. The VI sensor transmits the verified prediction data to the electronic device; A method for performing plasma state monitoring according to claim 7, further comprising the following:

Images