Control Method of Semiconductor Process Equipment and Semiconductor Process Equipment

Abstract

The present application provides a control method for a semiconductor process device and a semiconductor process device. The control method includes the steps of: a gas supply valve sending valve opening information to a processing module; a detection module acquiring and sending optical information generated by plasma in a semiconductor chamber to the processing module; the processing module obtaining a first starting time when gas flows through the gas supply valve according to the valve opening information, and obtaining a second starting time when plasma is generated in the semiconductor chamber according to the optical information, and obtaining a delay time for the Nth process process according to the first starting time and the second starting time, where N is a positive integer greater than or equal to 1; a control module obtaining a compensation time pre-enabled by an execution module in the (N + 1)th process process according to the delay time of the Nth process process, and controlling the execution module to operate according to the compensation time in the (N + 1)th process process. The compensation time in the present application has high precision, is more conducive to improving the stability and controllability of semiconductor processes, and improves the yield of products.

Description

Technical Field

[0001] The present application relates to the field of semiconductor technology, and particularly to a control method for a semiconductor process equipment and a semiconductor process equipment. Background Art

[0002] Semiconductor process equipment is the key processing equipment for front-end process machines such as thin film deposition, etching, ion implantation, and cleaning. Plasma etching and deposition processes carried out in semiconductor process equipment have become an important technology in the field of semiconductor processing. And with the increasing requirements for etching and deposition processes, cyclic etching and cyclic deposition have become a major trend. For example, in a relatively complex Through Silicon Via (TSV) etching machine, etching and deposition gases will be repeatedly switched within 1 s. In such a rapid cyclic process, there will be a phenomenon that the turn-on time of the radio frequency power supply (RF) is not synchronized with the actual time when the gas reaches the semiconductor process chamber, resulting in a decrease in the stability and controllability of the deposition process or etching process, which will affect the yield of the entire product. Summary of the Invention

[0003] The purpose of the present application is to provide a control method for a semiconductor process equipment and a semiconductor process equipment, which are beneficial to improving the stability and controllability of semiconductor processes and enhancing the yield of products.

[0004] In a first aspect, to achieve the above object, the present application provides a control method for the semiconductor process equipment, including the following steps:

[0005] Provide a detection module, a gas supply valve, a processing module respectively connected to the gas supply valve and the detection module, a control module sequentially connected to the processing module, and an execution module. The detection module is arranged in a semiconductor chamber, and the gas supply valve is arranged on a gas supply pipeline communicating with the semiconductor chamber;

[0006] The gas supply valve controls the opening and closing of the gas supply pipeline and sends valve opening information to the processing module;

[0007] The detection module acquires and sends the optical information generated by the plasma in the semiconductor chamber to the processing module;

[0008] The processing module obtains a first start time when the gas flows through the gas supply valve according to the valve opening information, and obtains a second start time when the plasma is generated in the semiconductor chamber according to the optical information, and obtains a delay time of the Nth round of process according to the first start time and the second start time, where N is a positive integer greater than or equal to 1;

[0009] The control module obtains the compensation time pre-enabled for the execution module in the (N + 1)-th process according to the delay time of the N-th process, and controls the execution module to operate according to the compensation time in the (N + 1)-th process.

[0010] Preferably, the step in which the control module obtains the compensation time pre-enabled for the execution module in the (N + 1)-th process according to the delay time of the N-th process includes: the control module corrects the delay time of the N-th process through a compensation time correction formula to obtain the compensation time pre-enabled for the execution module in the (N + 1)-th process.

[0011] Preferably, the control method of the semiconductor process equipment further includes the steps of: the control module constructs a compensation time correction model for the compensation time and the delay time of several processes through a machine learning model; and calculates and fits the compensation time and the delay time of several processes through the compensation time correction model to generate the compensation time correction formula.

[0012] Preferably, the compensation time correction formula satisfies the following relationship: the compensation time of the (N + 1)-th process is equal to the sum of a delay time parameter and a time correction parameter; the delay time parameter is directly proportional to the delay time of the N-th process, and the delay time parameter is directly proportional to a delay time weight coefficient; both the delay time weight coefficient and the time correction parameter are obtained by fitting through the compensation time correction model.

[0013] Preferably, the compensation time correction formula is:

[0014]

[0015] wherein, T is the compensation time of the (N + 1)-th process, ΔT is the delay time of the N-th process, α is the delay time weight coefficient, and β is the time correction parameter.

[0016] Preferably, the control method of the semiconductor process equipment further includes the steps of: the control module inputs the obtained compensation time and delay time in each process into the machine learning model in real time, and calculates and fits all the compensation time and delay time in the machine learning model through the compensation time correction model to correct the delay time weight coefficient and the time correction parameter in the compensation time correction formula, and makes the delay time weight coefficient greater than 0 and less than 3, and the time correction parameter greater than -1 s and less than 1 s.

[0017] Preferably, the step of the control module constructing a compensation time correction model for the compensation time and the delay time of several rounds of process manufacturing through a machine learning model further includes: the control module also inputs the process parameters of several rounds of process manufacturing into the machine learning model to construct the compensation time correction model; the process parameters include gas type, gas flow rate, pressure in the gas pipeline, pressure in the semiconductor cavity, ambient temperature where the gas pipeline is located, and service life of the gas valve.

[0018] Preferably, the control method of the semiconductor process equipment further includes the step of: when the compensation time is greater than a preset time threshold, the control module controls to issue an alarm.

[0019] In a second aspect, the present application provides a semiconductor process equipment, including a gas valve, a detection module, a processing module, a control module and an execution module; the gas valve is arranged on a gas pipeline communicating with a semiconductor cavity, and the gas valve is used to control the opening and closing of the gas pipeline and send valve opening information to the processing module; the detection module is arranged in the semiconductor cavity, and the detection module is used to acquire and send optical information generated by plasma in the semiconductor cavity to the processing module; the processing module is connected to the gas valve and the detection module, and the processing module is used to obtain a first start time when the gas flows through the gas valve according to the valve opening information, and obtain a second start time when plasma is generated in the semiconductor cavity according to the optical information, and obtain a delay time of the Nth round of process manufacturing according to the first start time and the second start time, where N is a positive integer greater than or equal to 1; the control module is connected to the processing module and the execution module, and the control module is used to obtain a compensation time pre-enabled by the execution module in the (N + 1)th round of process manufacturing according to the delay time of the Nth round of process manufacturing, and control the execution module to operate according to the compensation time in the (N + 1)th round of process manufacturing.

[0020] Preferably, the detection module includes a photodetector and a clamping member, and the clamping member includes a light blocking portion, a fixed seat and a mounting portion; a receiving cavity is formed on a working surface of the light blocking portion facing the observation window, and a projection area of the light blocking portion on the observation window is greater than or equal to the area of the observation window; the fixed seat is arranged in the receiving cavity, and the photodetector is fixed to the fixed seat; the mounting portion includes an outer edge groove adapted to an outer edge boss of the observation window, the outer edge groove is annularly arranged on an edge of the light blocking portion, and the detection module is detachably arranged on the observation window through clamping of the outer edge groove and the outer edge boss.

[0021] The control method of the semiconductor process equipment and the semiconductor process equipment of the present application can / at least have the following advantages:

[0022] (1) The present application realizes precise monitoring of the total delay time of gas transmission and plasma generation in the gas pipeline from the gas passing through the gas transmission valve to the generation of plasma in the semiconductor cavity by real-time monitoring of the first start time when the gas transmission valve is opened, i.e., the gas flows through the gas transmission valve, and the second start time when the execution module is enabled to generate plasma in the semiconductor cavity, avoiding the inaccurate compensation time caused by the omission of the delay time for plasma generation from the gas entering the semiconductor cavity to the generation of plasma in the semiconductor cavity.

[0023] (2) The present application adopts dual-signal synchronous detection, namely the valve opening signal and the optical signal, to realize real-time monitoring of gas transmission and plasma generation. The obtained delay time is more accurate, avoiding errors caused by indirect parameters, and is more conducive to improving the stability and controllability of semiconductor processes.

[0024] (3) The present application uses the detection module to detect the optical information generated by the plasma in the semiconductor cavity, which is more accurate than detecting the gas concentration in the semiconductor cavity in the related art.

[0025] (4) The present application obtains the compensation time pre-enabled for the execution module in the (N + 1)-th round of process based on the delay time of the N-th round of process, so that the start time of the execution module in the (N + 1)-th round of process can be adaptively adjusted according to the delay time of the N-th round of process. Compared with setting a fixed delay time parameter to adjust the start time of the execution module such as the radio frequency power supply depending on experience in some related arts, the compensation time for the start of the execution module in the (N + 1)-th round of process obtained by the present application through the delay time of the N-th round of process is more accurate and precise, and realizes real-time compensation for the start time of the execution module.

[0026] (5) The compensation time enabled for the execution module in each round of cycle in the present application is obtained based on the delay time of the previous round, realizing adaptive adjustment, that is, the compensation time of the present application can be dynamically adapted in real time according to changes in the external environment, the usage of the gas pipeline, the gas type, etc. The compensation time has high precision and is more conducive to improving the stability and controllability of the deposition process or etching process, and improving the yield of products.

[0027] In summary, through the single or collaborative regulation of the above multiple factors, the present application obtains the precise delay time of gas transmission and plasma generation by real-time detecting the time difference between the optical information of the plasma and the valve opening information, and realizes the synchronous optimization of the process by adaptively adjusting the start of the execution module through the dynamic compensation time.

[0028] Other advantages of the present application will be described in the following specific embodiments. Brief Description of the Drawings

[0029] Figure 1 A flowchart showing a control method for a semiconductor processing apparatus according to some embodiments of the present application.

[0030] Figure 2 A structural schematic diagram of a semiconductor processing apparatus according to some embodiments of the present application.

[0031] Figure 3 A structural block diagram of a semiconductor processing apparatus according to some embodiments of the present application.

[0032] Figure 4 A structural block diagram of a semiconductor processing apparatus according to other embodiments of the present application.

[0033] Figure 5 A structural schematic diagram of a detection module in a semiconductor processing apparatus according to some embodiments of the present application. Detailed implementation manners

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application. Unless otherwise defined, the technical terms or scientific terms used herein shall have the ordinary meanings as understood by those of ordinary skill in the art in the field to which the present application belongs. The words such as "including" used herein mean that the elements or items appearing before the word cover the elements or items listed after the word and their equivalents, without excluding other elements or items.

[0035] TSV etching machines generally use the Bosch process. The Bosch process is to inject specific gases (such as CF4, CHF3, Ar, etc.) into a closed chamber and apply a radio frequency power supply to generate plasma. Plasma is a mixture of charged particles (ions, electrons, etc.) formed by the ionization of gas molecules under the action of an electric field and has high reactivity. In the related art, due to the delay in the time from when the solenoid valve is opened to when the gas actually enters the chamber, the delay time is usually 50 ms to 500 ms, which may cause the following problems: (1) The etching or deposition is uneven due to the asynchronous time between the opening of the radio frequency power supply and the arrival of the gas at the semiconductor chamber; (2) The process repeatability is poor, affecting the control of the aspect ratio and sidewall morphology.

[0036] To overcome the problems existing in the related art, the embodiments of the present application provide a control method for a semiconductor processing apparatus and a semiconductor processing apparatus, which are beneficial to improving the stability and controllability of the semiconductor process and enhancing the yield of products.

[0037] In some embodiments, referring to Figure 1 , a control method for the semiconductor process equipment includes the following steps:

[0038] S0. Provide a detection module, a gas supply valve, a processing module respectively connected to the gas supply valve and the detection module, a control module and an execution module sequentially connected to the processing module. The detection module is disposed in the semiconductor cavity, and the gas supply valve is disposed in the gas pipeline connecting the semiconductor cavity;

[0039] S1. The gas supply valve controls the opening and closing of the gas pipeline and sends valve opening information to the processing module; the detection module acquires and sends the optical information generated by the plasma in the semiconductor cavity to the processing module;

[0040] S2. The processing module obtains a first start time when the gas flows through the gas supply valve according to the valve opening information, and obtains a second start time when the plasma is generated in the semiconductor cavity according to the optical information, and obtains a delay time of the Nth round of process according to the first start time and the second start time, where N is a positive integer greater than or equal to 1;

[0041] S3. The control module obtains a compensation time pre-enabled by the execution module in the (N + 1)th round of process according to the delay time of the Nth round of process, and controls the execution module to operate according to the compensation time in the (N + 1)th round of process.

[0042] In this embodiment, the gas transmission valve controls the opening and closing of the gas transmission pipeline and sends valve opening information to the processing module; the detection module acquires and sends the optical information generated by the plasma in the semiconductor cavity to the processing module; S2. The processing module obtains the first starting time when the gas flows through the gas transmission valve according to the valve opening information, and obtains the second starting time when the plasma is generated in the semiconductor cavity according to the optical information, and obtains the delay time of the Nth round of process according to the first starting time and the second starting time. That is, the present application can not only accurately monitor the delay time of the gas transmitted from the gas transmission valve to the semiconductor cavity, that is, the time when the gas is transmitted in the gas transmission pipeline, but also compared with the related art that only monitors the delay time of the gas transmitted in the gas transmission pipeline from the gas transmission valve to the semiconductor cavity, the present application also accurately monitors the delay time of the plasma generation from the time when the gas enters the semiconductor cavity to the time when the plasma is generated in the semiconductor cavity. That is, the delay time includes all the delay times existing in each procedure of the execution module receiving the enabling instruction, actually enabling, and generating plasma in the semiconductor cavity. The present application can realize the accurate monitoring of the total delay time of the gas transmission and plasma generation in the gas transmission pipeline from the time when the gas transmission valve is opened, that is, the first starting time when the gas flows through the gas transmission valve, to the time when the plasma is generated in the semiconductor cavity by the execution module, and avoid the situation of inaccurate compensation time caused by missing the delay time of the plasma generation from the time when the gas enters the semiconductor cavity to the time when the plasma is generated in the semiconductor cavity. At the same time, the present application adopts dual-signal synchronous detection, that is, the valve opening signal and the optical signal, to realize the real-time monitoring of the gas transmission and plasma generation, and the obtained delay time is more accurate, avoiding the error caused by indirect parameters, which is more conducive to improving the stability and controllability of the semiconductor process. Moreover, the present application uses the detection module to detect the optical information generated by the plasma in the semiconductor cavity, which is more accurate than detecting the gas concentration in the semiconductor cavity in the related art.

[0043] In addition, the control module obtains the compensation time pre-enabled for the execution module in the (N + 1)-th process according to the delay time of the N-th process, and controls the execution module to operate according to the compensation time in the (N + 1)-th process, so that the enabling time of the execution module in the (N + 1)-th process can be adaptively adjusted according to the delay time of the N-th process, that is, the execution module, such as a radio frequency power supply, outputs power after advancing or delaying the compensation time. Compared with setting a fixed delay time parameter to adjust the enabling time of the execution module depending on experience in some related technologies, the compensation time for the execution module to be enabled in the (N + 1)-th process obtained by the control module according to the delay time of the N-th process is more accurate and precise. Thus, real-time compensation for the enabling time of the execution module is achieved. At the same time, the compensation time enabled for the execution module in each process is obtained according to the delay time of the previous process, realizing adaptive adjustment. That is, the compensation time of the present application can be dynamically adapted in real time according to changes in the external environment such as temperature, the usage of the gas pipeline, the type and rate of the gas, etc. The compensation time is highly accurate, which is more conducive to improving the stability and controllability of the deposition process or the etching process, and improving the yield of the product.

[0044] In this embodiment, the N-th process and the (N + 1)-th process are the same processing process, where the process includes but is not limited to an etching process or a deposition process, etc. That is, the application scope of the present application is wide and it can be applied to various semiconductor processes. For example, in some embodiments, in the Bosch process, the control module obtains the compensation time pre-enabled for the execution module in the (N + 1)-th etching process according to the delay time of the N-th etching process, and obtains the compensation time pre-enabled for the execution module in the (N + 1)-th deposition process according to the delay time of the N-th deposition process. The compensation time obtained according to the delay time in the etching process cannot be applied to the deposition process to control the pre-enabling of the execution module. They are two different process lines and do not interfere with each other.

[0045] In this embodiment, the execution module is a radio frequency power supply. The radio frequency power supply generates a high-frequency electromagnetic field to ionize the gas under low pressure or normal pressure to form a plasma. Specifically, the control module controls the radio frequency power supply to be enabled after advancing or delaying the compensation time in the (N + 1)-th process according to the compensation time obtained in the N-th process. The synchronization range of the radio frequency power supply can reach ±500 ms, and the resolution is 1 μs.

[0046] In some embodiments, the step of the control module obtaining the compensation time pre-enabled for the execution module in the (N + 1)-th process by using the delay time of the N-th process includes: the control module corrects the delay time of the N-th process by using a compensation time correction formula to obtain the compensation time pre-enabled for the execution module in the (N + 1)-th process. By correcting the delay time, it helps to improve the accuracy of the compensation time, avoid errors caused by indirect parameters, realize real-time dynamic adjustment of the enabling time of the execution module in the next process, and improve the stability of the process.

[0047] In some embodiments, the control method of the semiconductor processing equipment further includes the steps of: the control module constructs a compensation time correction model for the compensation time and the delay time of several processes by using a machine learning model; and calculates and fits the compensation time and the delay time of several processes by using the compensation time correction model to generate the compensation time correction formula. By constructing the compensation time correction model by using the machine learning model, it enables dynamic prediction of the trend of time delay increase or decrease, and dynamic adaptation to changes in the gas path state (such as pipeline aging, gas type switching) and external environment changes, helps to improve the accuracy of the compensation time, realizes real-time dynamic adaptive adjustment of the enabling time of the execution module, realizes process synchronization optimization, and improves the stability of the process.

[0048] In this embodiment, the machine learning model analyzes a large amount of data to find patterns and correlations therein, so as to be able to effectively predict new and unseen data. In some embodiments, the machine learning model includes but is not limited to an LSTM time series network, etc.

[0049] In some embodiments, the step of the control module constructing a compensation time correction model for the compensation time and the delay time of several processes by using a machine learning model further includes: the control module inputs the process parameters of several processes into the machine learning model to construct the compensation time correction model; the process parameters include gas type, gas flow rate, pressure in the gas pipeline, pressure in the semiconductor cavity, external environment temperature where the gas pipeline is located, and service life of the gas valve. The process parameters help to construct a more accurate compensation time correction model, enable the compensation time to dynamically adapt to changes in the gas path state (such as pipeline aging, gas type switching) and external environment changes, help to improve the accuracy of the compensation time, realize real-time dynamic adjustment of the enabling time of the execution module in the next process, and improve the stability of the process.

[0050] In some embodiments, the compensation time correction formula satisfies the following relationship: the compensation time T for the (N + 1)-th round of process is equal to the sum of the delay time parameter A and the time correction parameter β; the delay time parameter A is directly proportional to the delay time ΔT for the N-th round of process, and the delay time parameter A is directly proportional to the delay time weight coefficient α; both the delay time weight coefficient α and the time correction parameter β are obtained by fitting through the compensation time correction model. This enables dynamic adaptation to changes in the gas path state (such as pipeline aging, gas type switching) and external environment changes, helps improve the accuracy of the compensation time, realizes real-time dynamic adjustment of the enabling time of the execution module in the next round of process, and enhances the stability of the process.

[0051] In some specific embodiments, the compensation time correction formula is:

[0052] 。

[0053] In some specific embodiments, the delay time parameter satisfies the following formula:

[0054] 。

[0055] In some embodiments, the compensation time correction formula is:

[0056]

[0057] Wherein, T is the compensation time for the (N + 1)-th round of process, ΔT is the delay time for the N-th round of process, that is, ΔT is equal to the difference between the second start time and the first start time; α is the delay time weight coefficient, and β is the time correction parameter.

[0058] In some embodiments, the control method of the semiconductor process equipment further includes the steps of: the control module inputs the obtained compensation time and the delay time in each round of process in real time into the machine learning model, and calculates and fits all the compensation time and the delay time in the machine learning model through the compensation time correction model to correct the delay time weight coefficient and the time correction parameter in the compensation time correction formula, and makes the delay time weight coefficient greater than 0 and less than 3, and the time correction parameter greater than -1 s and less than 1 s. In this embodiment, when the number of cycles of the process being carried out is small, the data that the machine learning model can analyze is less. For example, when only one round of process is carried out, there may be a situation where the compensation time of the second round of process is equal to the delay time of the first round of process. As the number of cycles of the process being carried out increases, the machine learning model updates and supplements the data of the compensation time correction model in real time, thereby dynamically generating a new compensation time correction formula, that is, the delay time weight coefficient and the time correction parameter in the compensation time correction formula can be corrected in real time, which is beneficial to improving the accuracy of the compensation time and effectively avoiding the influence of the aging of the gas pipeline, the external environmental temperature where the gas pipeline is located, the liquefaction of the gas in the gas pipeline, etc. on the delay time weight coefficient and the time correction parameter.

[0059] In this embodiment, during the entire process, the delay time weight coefficient α may be the same or different in several rounds of process; the time correction parameter β may be the same or different in several rounds of process. The delay time weight coefficient α and the time correction parameter β will be fitted and updated through the compensation time correction model, which helps to improve the accuracy of the compensation time and avoid the errors caused by indirect parameters. For example, some components in the semiconductor process equipment will dissipate heat, resulting in an increase in the external environmental temperature where the gas pipeline is located, thereby causing the delay time weight coefficient α and the time correction parameter β to become smaller, even if the obtained compensation time becomes smaller. Another example is that as the service life of the gas pipeline increases, the gas pipeline will gradually age, thereby causing the delay time weight coefficient α and the time correction parameter β to become larger, even if the obtained compensation time becomes larger.

[0060] In some specific embodiments, the delay time weight coefficient α is 0.01, 0.1, 0.5, 1, 1.2, 1.5, 1.8, 2, 2.3, 2.7, or 2.9, etc.

[0061] In some specific embodiments, the time correction parameter β is -0.9 s, -0.5 s, -0.2 s, -0.1 s, -0.05 s, 0 s, 0.07 s, 0.1 s, 0.3 s, 0.6 s, 0.75 s, or 0.95 s, etc.

[0062] In some embodiments, the control method of the semiconductor process equipment further includes the step of: when the compensation time is greater than a preset time threshold, the control module controls to issue an alarm to remind the staff to check whether the equipment is damaged or not. This helps to avoid process instability and affect product yield caused by inaccurate compensation time due to equipment damage; for example, inaccurate data detected due to damage of the gas supply valve or the detection module, or deviation of the output power or activation time of the current cycle caused by damage of the execution module, increased delay time caused by blockage of the gas pipeline, or inaccurate compensation time caused by vulnerabilities in the software of the processing module or the control module.

[0063] The preset time threshold in this embodiment is specifically set according to the machine type, gas type, process, etc. in actual applications. For example, in some specific embodiments, in certain etching processes, the compensation time is generally 0 to 3 s, and the preset time threshold is 5 s. When the control module determines that the obtained compensation time is greater than 5 s, it controls to issue an alarm to remind the staff to check whether the equipment is damaged or not.

[0064] In some embodiments, when the delay time weighting coefficient α is less than or equal to 0 and greater than or equal to 3, and / or the time correction parameter β is less than or equal to -1 s and greater than or equal to 1 s, the obtained compensation time will be relatively large. At this time, the control module will control to issue an alarm.

[0065] In some specific embodiments, the control method of the semiconductor process equipment further includes the following steps:

[0066] The gas supply valve is opened and the valve opening information is sent to the processing module. The processing module obtains the first start time T1 of the gas flowing through the gas supply valve according to the valve opening information.

[0067] The gas enters the semiconductor cavity and generates plasma. The detection module acquires and sends the optical information generated by the plasma in the semiconductor cavity to the processing module. The processing module obtains the second start time T2 of the plasma generation in the semiconductor cavity according to the optical information.

[0068] The processing module obtains the delay time ΔT of the Nth process and sends it to the control module according to the first start time T1 and the second start time T2, where ΔT = T2 - T1.

[0069] The control module inputs the delay time ΔT into the machine learning model to correct the compensation time correction formula through the compensation time correction model, and obtains the compensation time T for the (N + 1)-th process. The control module controls the execution module to be enabled in the (N + 1)-th process according to the compensation time T for the (N + 1)-th process;

[0070] In the (N + 1)-th process, the execution module is enabled after delaying or advancing for a duration of T, ensuring synchronization with the generation of plasma.

[0071] In some embodiments, referring to Figures 2 to 5 , the semiconductor process equipment includes a detection module 100, a gas supply valve 200, a processing module 300, a control module 400, and an execution module 500; the gas supply valve 200 is arranged on a gas supply pipeline 610 communicating with a semiconductor cavity 600, and the gas supply valve 200 is used for controlling the opening and closing of the gas supply pipeline 610 and sending valve opening information to the processing module 300; the detection module 100 is arranged in the semiconductor cavity 600, and the detection module 100 is used for acquiring and sending optical information generated by plasma in the semiconductor cavity 600 to the processing module 300; the processing module 300 is connected to the gas supply valve 200 and the detection module 100, and the processing module 300 is used for obtaining a first start time when gas flows through the gas supply valve 200 according to the valve opening information, and obtaining a second start time when plasma is generated in the semiconductor cavity 600 according to the optical information, and obtaining a delay time for the N-th process according to the first start time and the second start time, where N is a positive integer greater than or equal to 1; the control module 400 is connected to the processing module 300 and the execution module 500, and the control module 400 is used for obtaining a compensation time for pre-enabling the execution module 500 in the (N + 1)-th process according to the delay time for the N-th process, and controlling the execution module 500 to operate according to the compensation time in the (N + 1)-th process.

[0072] In this embodiment, the gas supply valve 200 is disposed on the gas supply pipeline 610 communicating with the semiconductor cavity 600. The gas supply valve 200 is used to control the opening and closing of the gas supply pipeline 610 and send valve opening information to the processing module 300. The detection module 100 is disposed in the semiconductor cavity 600. The detection module 100 is used to acquire and send the optical information generated by the plasma in the semiconductor cavity 600 to the processing module 300. The processing module 300 is connected to the gas supply valve 200 and the detection module 100. The processing module 300 is used to obtain the first start time when the gas flows through the gas supply valve 200 according to the valve opening information, and obtain the second start time when the plasma is generated in the semiconductor cavity 600 according to the optical information, and obtain the delay time of the Nth round of process according to the first start time and the second start time. That is, the present application can not only accurately monitor the delay time of the gas transmitted from the gas supply valve 200 to the semiconductor cavity 600, that is, the time when the gas is transmitted in the gas supply pipeline 610, but also, compared with the related art that only monitors the delay time of the gas transmitted in the gas supply pipeline 610 from the gas supply valve 200 to the semiconductor cavity 600, the present application also accurately monitors the delay time of the plasma generation from the time when the gas enters the semiconductor cavity 600 to the time when the plasma is generated in the semiconductor cavity 600. That is, the delay time includes all the delay times existing in the processes of the execution module 500 receiving the enabling instruction, actually enabling, and generating the plasma in the semiconductor cavity 600. The present application can realize accurate monitoring of the total delay time of the gas transmission and plasma generation in the gas supply pipeline from the time when the gas supply valve 200 is opened, that is, the first start time when the gas flows through the gas supply valve 200, and the second start time when the execution module 500 is enabled to generate the plasma in the semiconductor cavity, avoiding the situation of inaccurate compensation time caused by missing the delay time of the plasma generation from the time when the gas enters the semiconductor cavity to the time when the plasma is generated in the semiconductor cavity 600. At the same time, the present application adopts dual-signal synchronous detection, that is, the valve opening signal and the optical signal, to realize the real-time monitoring of the gas transmission and plasma generation, and the obtained delay time is more accurate, avoiding the error caused by the indirect parameter, which is more conducive to improving the stability and controllability of the semiconductor process. Moreover, the present application uses the detection module 100 to detect the optical information generated by the plasma in the semiconductor cavity 600, which is more accurate than detecting the gas concentration in the semiconductor cavity 600 in the related art.

[0073] In addition, in this embodiment, the control module 400 is connected to the processing module 300 and the execution module 500. The control module 400 is configured to obtain the compensation time pre-enabled for the execution module 500 in the (N + 1)-th process according to the delay time of the N-th process, and control the execution module 500 to operate according to the compensation time in the (N + 1)-th process, so that the semiconductor processing equipment can obtain the compensation time for the (N + 1)-th process according to the delay time of the N-th process, thereby adaptively adjusting the enabling time of the execution module 500 in the (N + 1)-th process. Compared with some related technologies that rely on experience to set fixed delay time parameters to adjust the enabling time of the execution module 500, such as the turn-on time of the radio frequency power supply, the compensation time for the execution module 500 enabled in the (N + 1)-th process obtained in this application according to the delay time of the N-th process is more accurate and precise, and realizes real-time compensation for the enabling time of the execution module 500. At the same time, the compensation time enabled by the execution module 500 in each process is obtained according to the delay time of the previous process, realizing adaptive adjustment. That is, the compensation time in this application can be dynamically adapted in real time according to changes in the external environment, the usage of the gas pipeline 610, the gas type, etc. The compensation time has high precision, which is more conducive to improving the stability and controllability of the deposition process or etching process, and improving the product yield.

[0074] In this embodiment, a gas supply valve 200 can be provided on the corresponding gas pipeline 610 for transporting gas, or the gas supply valve 200 that already exists in the original semiconductor processing equipment can be used to control the opening and closing of the gas pipeline 610 and send valve opening information to the processing module 300, with less modification to the original equipment and low investment cost.

[0075] In some embodiments, the gas supply valve 200 is disposed close to the semiconductor cavity 600 to avoid or reduce the indirect error caused by the excessive length of the gas pipeline 610 between the gas supply valve 200 and the semiconductor cavity 600, resulting in a large influence from the external environment. In some specific embodiments, the gas supply valve 200 is a solenoid valve, and the response time of the solenoid valve is less than 10 ms, with a fast valve response speed, further avoiding the error caused by indirect parameters.

[0076] In some embodiments, refer to Figure 2 and Figure 5, the detection module 100 includes a photodetector 110, the photodetector 110 is detachably disposed outside the observation window 620 of the semiconductor cavity 600, and the detection portion 111 of the photodetector 110 is aligned with the region where plasma is generated in the semiconductor cavity 600, so that the photodetector 110 can detect the optical information generated by the plasma through the observation window 620. Based on the characteristic that atoms or molecules in the plasma generated in the semiconductor cavity 600 emit light when they are excited to an excited state by electrons and then return to another energy state, the present application can use the photodetector 110 to detect the situation of the plasma generated in the semiconductor cavity 600 in a timely and accurate manner, that is, the second start time of the plasma generated in the semiconductor cavity 600 can be accurately detected, thereby realizing the accurate monitoring of the delay time of the gas flowing through the gas supply valve 200 to generate plasma in the semiconductor cavity 600, avoiding the situation that the compensation time is inaccurate due to the omission of the delay time from when the gas enters the semiconductor cavity 600 to when plasma is generated in the semiconductor cavity 600. The delay time obtained in the present application is more accurate, avoiding errors caused by indirect parameters, and thus is more conducive to improving the stability and controllability of the semiconductor process.

[0077] In some embodiments, the photodetector includes, but is not limited to, a photodiode. The photodiode is inexpensive and easy to obtain, which is beneficial to reducing the input cost. The photodiode is a photodiode with a wavelength range of 200nm to 1000nm.

[0078] In some embodiments, referring to Figure 2 and Figure 5 , the detection module 100 further includes a clamping member 120, the clamping member 120 includes a light shielding portion 121 and a fixing base 122; a receiving cavity 1211 is formed on the acting surface of the light shielding portion 121 facing the observation window 620, the fixing base 122 is disposed in the receiving cavity 1211, and the photodetector 110 is fixed to the fixing base 122; and the projected area of the light shielding portion 121 on the observation window 620 is greater than or equal to the area of the observation window 620, so that the light shielding portion 121 can form a shielding cover for the observation window 620 to block external light sources, avoiding the influence of external light sources on the photodetector 110 to detect the optical information generated by the plasma in the semiconductor cavity 600, avoiding or reducing detection errors, making the delay time obtained in the present application more accurate, and enabling more accurate control of the activation of the execution module, and thus being more conducive to improving the stability and controllability of the semiconductor process.

[0079] In this embodiment, the projected area of the light shielding portion 121 on the observation window 620 is: when projected along the direction perpendicular to the surface of the observation window 620, the projected area of the light shielding portion 121 on the observation window 620.

[0080] In some embodiments, the light-shielding portion 121 includes, but is not limited to, a cylindrical structure, a conical structure, a frustum structure (as Figure 5 shown), a hemispherical structure, a semi-frame structure, etc. Of course, in some embodiments, the light-shielding portion 121 may also be a circular plate-like structure, a square plate-like structure, etc.

[0081] In some embodiments, referring to Figure 5 , the lead portion 112 of the photodetector 110 penetrates through the light-shielding portion 121 to be connected to the processing module 300.

[0082] In some embodiments, the clamping member further includes a mounting portion, and the detection module 100 is detachably disposed on the observation window 620 through the mounting portion. The disassembly and installation are convenient and fast, which not only realizes the installation and fixation of the detection module 100, but also does not affect the original use of the observation window 620, and is convenient for regularly disassembling and replacing the photodetector 110 in the detection module 100 to ensure the accuracy of the light information collected by the photodetector 110.

[0083] In some embodiments, the connection manner between the mounting portion and the observation window 620 includes, but is not limited to, a pasting manner, a snap-fastening manner, a threaded connection manner, etc.

[0084] In some embodiments, referring to Figure 5 , the mounting portion includes an outer-edge groove 123, the outer-edge groove 123 is disposed around the edge of the light-shielding portion 121, and the outer-edge groove 123 is adapted to the outer-edge boss of the observation window 620. The detection module is detachably disposed on the observation window through the engagement of the outer-edge groove 123 and the outer-edge boss, that is, the detection module 100 is detachably disposed on the observation window 620. In this embodiment, the installation of the detection module 100 can be realized by using the outer-edge boss on the original observation window 620, with less modification to the original equipment and low input cost, and the clamping member 120 can be detachably disposed on the observation window 620. Thus, when it is necessary to observe the situation inside the semiconductor cavity 600 through the observation window 620, the detection module 100 can be removed. The disassembly and installation are convenient and fast, which not only realizes the installation and fixation of the detection module 100, but also does not affect the original use of the observation window 620, and is convenient for regularly replacing the photodetector 110 in the detection module 100 to ensure the accuracy of the light information collected by the photodetector 110.

[0085] In some specific embodiments, the inner wall of the outer-edge groove 123 is provided with an internal-thread structure, and the internal-thread structure is adapted to the external-thread structure on the outer-edge boss of the observation window 620, so that the detection module 100 is detachably disposed on the observation window 620 through a threaded connection manner.

[0086] In some embodiments, referring toFigure 3 and Figure 4 , the processing module 300 includes an amplifier 310, a band-pass filter 320, and a noise suppression unit 330 that are sequentially connected to the detection module 100, and a processing unit 340 that is connected to the noise suppression unit 330 and the gas transmission valve 200 respectively; the amplifier 310 is configured to convert the optical signal in the optical information into an electrical signal and amplify it; the band-pass filter 320 is configured to perform filtering processing on the amplified electrical signal; the noise suppression unit 330 is configured to perform noise reduction processing on the filtered electrical signal; the processing unit is configured to obtain the first start time according to the valve opening information, and obtain the second start time according to the optical information, and obtain the delay time of the Nth round of process according to the first start time and the second start time. To reduce the influence of other signal interferences on the optical information collected by the detection module 100, it is beneficial to obtain a more accurate delay time and avoid errors caused by indirect parameters.

[0087] In some embodiments, the center frequency of the band-pass filter is 1 kHz and the bandwidth is ±100 Hz.

[0088] In some embodiments, the processing unit includes an analog-to-digital converter and a digital signal processor. The analog-to-digital converter is respectively connected to the noise suppression unit and the digital signal processor. The digital signal processor is connected to the control module, and the sampling rate of the analog-to-digital converter is greater than or equal to 1 MHz to ensure that the detection accuracy is less than or equal to 1 ms, which is beneficial to obtaining a more accurate delay time.

[0089] In some embodiments, refer to Figure 3 and Figure 4, the control module 400 includes a model construction unit 410 and an analysis unit 420; the model construction unit 410 is configured to construct a compensation time correction model for the compensation time and the delay time of several rounds of process manufacturing through a machine learning model, and calculate and fit the compensation time and the delay time of several rounds of process manufacturing through the compensation time correction model to generate a compensation time correction formula; the analysis unit 420 is respectively connected to the model construction unit 410 and the processing module 300, and the analysis unit 420 is configured to correct the delay time of the Nth round of process manufacturing through the compensation time correction formula to obtain the compensation time pre-enabled by the execution module 500 in the (N + 1)th round of process manufacturing. In some specific embodiments, the analysis unit 420 is connected to the processing unit 340 in the processing module 300. In this embodiment, the compensation time correction model is constructed through the machine learning model, so that the trend of time delay increase and decrease can be dynamically predicted, and the changes of the gas path state (such as pipeline aging, gas type switching) and the external environment can be dynamically adapted, which helps to improve the accuracy of the compensation time, realize the real-time dynamic adaptive adjustment of the enabling time of the execution module 500, achieve the process synchronization optimization, and improve the stability of the process; moreover, with the change of the delay time in each round of process manufacturing, the machine learning model can update and supplement the data of the compensation time correction model in real time, so as to dynamically correct the compensation time correction formula to ensure higher and more accurate compensation time accuracy.

[0090] In some embodiments, with reference to Figure 3 and Figure 4 , the control module 400 further includes a storage unit 430 respectively connected to the processing module 300 and the model construction unit 410; the storage unit 430 is configured to store the compensation time, the delay time, and process parameters of each round of process manufacturing; the model construction unit 410 is configured to call the compensation time, the delay time, and the process parameters of each round of process manufacturing stored in the storage unit 430 and input them into the machine learning model to construct the compensation time correction model. That is, the compensation time, the delay time, and the process parameters of each round of process manufacturing are stored in the storage unit 430 for the model construction unit 410 to call when constructing the compensation time correction model, so that the data of the compensation time correction model can be updated and supplemented in real time, thereby dynamically correcting the compensation time correction formula to ensure higher and more accurate compensation time accuracy.

[0091] In some embodiments, the control module 400 further includes an input unit connected to the storage unit 430, and the input unit is configured to input the process parameters.

[0092] In some specific embodiments, the processing module 300 sends the delay time and the compensation time of N rounds of process manufacturing to the storage unit for storage; the input unit inputs the process parameters of each round of process manufacturing and sends them to the storage unit for storage.

[0093] In some embodiments, refer to Figure 3 and Figure 4 , the control module 400 further includes a control unit 440 connected to the analysis unit 420, and the control unit 440 is configured to control the execution module to be enabled after delaying or advancing the compensation time in the (N + 1)-th round of process manufacturing according to the compensation time of the (N + 1)-th round of process manufacturing.

[0094] In some embodiments, the control module is a host computer, and the host computer software integrates a machine learning algorithm written in Python.

[0095] In some embodiments, the communication interface between the control module 400 and the execution module 500 adopts the EtherCAT protocol, and the time delay is less than 1 ms, ensuring real-time performance and avoiding errors caused by indirect parameters.

[0096] In some embodiments, the semiconductor process equipment further includes an alarm module connected to the control module, and the alarm module is configured to issue an alarm when the compensation time is greater than a preset time threshold to remind the staff to check whether the equipment is damaged, etc., which is beneficial to avoiding process instability and affecting product yield caused by inaccurate compensation time due to equipment damage.

[0097] In some embodiments, the semiconductor process equipment includes an inductively coupled plasma etching device, a capacitively coupled plasma etching device, a through-silicon via etching device, a chemical vapor deposition equipment, etc. It only needs to install the detection module 100 on the original semiconductor process equipment such as an inductively coupled plasma etching machine, a capacitively coupled plasma etching machine, a through-silicon via etching machine, a chemical vapor deposition equipment, etc., and be equipped with the processing module 300 and the control module 400. It has strong adaptability, a wide application range, is simple and convenient to transform, and has a low input cost.

[0098] For example, in some embodiments, in a TSV etcher, the Bosch process requires alternately introducing an etching gas (such as SF6) and a passivation gas (such as C4F8) during the reactive ion etching process. The silicon via etching device originally has solenoid valves respectively provided on the gas pipelines for the etching gas and the passivation gas. Only by setting the detection module outside the observation window of the silicon via etching device, and then configuring a processing module respectively connected to the solenoid valve and the detection module, and a control module connected to the processing module, can the first starting time when the etching gas flows through the solenoid valve be obtained by monitoring the opening of the solenoid valve in real time. After obtaining the second starting time when the etching gas enters the semiconductor cavity to generate plasma by monitoring the optical information of the radio frequency power supply being enabled by the detection module, the delay time of this round of etching process can be obtained by the processing module analyzing the first starting time and the second starting time. Based on this, the control module can adjust the enabling time of the radio frequency power supply in the next round of etching process according to the compensation time obtained in real time for this round of etching process; and the third starting time when the passivation gas flows through the solenoid valve can be obtained by monitoring the opening of the solenoid valve in real time. After obtaining the fourth starting time when the passivation gas enters the semiconductor cavity to generate plasma by monitoring the optical information of the radio frequency power supply being enabled by the detection module, the delay time of this round of deposition process can be obtained by the processing module analyzing the third starting time and the fourth starting time. Based on this, the control module can adjust the enabling time of the radio frequency power supply in the next round of deposition process according to the compensation time obtained in real time for this round of deposition process. This enables the synchronous optimization of the etching process or the deposition process, thereby facilitating the improvement of the product stability and the product yield.

[0099] Although the embodiments of the present application have been described in detail above, it is obvious to those skilled in the art that various modifications and changes can be made to these embodiments. However, it should be understood that such modifications and changes are all within the scope and spirit of the present application described in the claims. Moreover, the present application described herein can have other embodiments and can be implemented or realized in various ways.

Claims

1. A control method for a semiconductor process equipment, characterized in that Including the following steps: Providing a detection module, a gas supply valve, a processing module respectively connected to the gas supply valve and the detection module, a control module sequentially connected to the processing module, and an execution module. The gas supply valve is arranged on a gas pipeline communicating with a semiconductor cavity, and the detection module is arranged in the semiconductor cavity; The gas supply valve controls the opening and closing of the gas pipeline and sends valve opening information to the processing module; The detection module acquires and sends the optical information generated by the plasma in the semiconductor cavity to the processing module; The processing module obtains the first start time when the gas flows through the gas supply valve according to the valve opening information, and obtains the second start time when the plasma is generated in the semiconductor cavity according to the optical information, and obtains the delay time of the Nth round of process according to the first start time and the second start time, where N is a positive integer greater than or equal to 1; The control module obtains the compensation time pre-enabled by the execution module in the (N + 1)th round of process according to the delay time of the Nth round of process, and controls the execution module to operate according to the compensation time in the (N + 1)th round of process.

2. The control method of the semiconductor process equipment according to claim 1, wherein, The step that the control module obtains the compensation time pre-enabled by the execution module in the (N + 1)th round of process according to the delay time of the Nth round of process includes: The control module corrects the delay time of the Nth round of process through a compensation time correction formula to obtain the compensation time pre-enabled by the execution module in the (N + 1)th round of process.

3. The control method of the semiconductor process equipment according to claim 2, wherein It further includes steps: The control module constructs a compensation time correction model for the compensation time and the delay time of several rounds of processes through a machine learning model; and calculates and fits the compensation time and the delay time of several rounds of processes through the compensation time correction model to generate the compensation time correction formula.

4. The control method of the semiconductor process equipment according to claim 3, characterized in that, The compensation time correction formula satisfies the following relationship: The compensation time of the (N + 1)th round of process is equal to the sum of a delay time parameter and a time correction parameter; the delay time parameter is proportional to the delay time of the Nth round of process, and the delay time parameter is proportional to a delay time weight coefficient; both the delay time weight coefficient and the time correction parameter are obtained by fitting through the compensation time correction model.

5. The control method of the semiconductor process equipment according to claim 4, wherein, The compensation time correction formula is: Where, T is the compensation time of the (N + 1)th round of process, ΔT is the delay time of the Nth round of process, α is the delay time weight coefficient, and β is the time correction parameter.

6. The control method of the semiconductor process equipment according to claim 5, characterized in that, It further includes steps: The control module inputs the compensation time and the delay time obtained in each round of process into the machine learning model in real time, and calculates and fits all the compensation time and the delay time in the machine learning model through the compensation time correction model to correct the delay time weight coefficient and the time correction parameter in the compensation time correction formula, and makes the delay time weight coefficient greater than 0 and less than 3, and the time correction parameter greater than -1 s and less than 1 s.

7. The control method of the semiconductor process equipment according to claim 3, wherein, The steps of the control module constructing a compensation time correction model for the compensation time and the delay time of several rounds of process manufacturing through a machine learning model further include: The control module also inputs the process parameters of several rounds of process manufacturing into the machine learning model to construct the compensation time correction model; The process parameters include gas type, gas flow rate, pressure in the gas pipeline, pressure in the semiconductor cavity, external ambient temperature where the gas pipeline is located, and service life of the gas valve.

8. The control method of the semiconductor process equipment according to claim 1, characterized in that, It further includes the steps: The control module issues an alarm when the compensation time is greater than a preset time threshold.

9. A semiconductor process equipment, characterized in that, It includes a gas valve, a detection module, a processing module, a control module, and an execution module; The gas valve is arranged on the gas pipeline communicating with the semiconductor cavity, and the gas valve is used to control the opening and closing of the gas pipeline and send valve opening information to the processing module; The detection module is arranged in the semiconductor cavity, and the detection module is used to acquire and send the light information generated by the plasma in the semiconductor cavity to the processing module; The processing module is connected to the gas valve and the detection module. The processing module is used to obtain the first start time when the gas flows through the gas valve according to the valve opening information, and obtain the second start time when the plasma is generated in the semiconductor cavity according to the light information, and obtain the delay time of the Nth round of process manufacturing according to the first start time and the second start time, where N is a positive integer greater than or equal to 1; The control module is connected to the processing module and the execution module. The control module is used to obtain the compensation time pre-enabled by the execution module in the (N + 1)th round of process manufacturing according to the delay time of the Nth round of process manufacturing, and control the execution module to operate according to the compensation time in the (N + 1)th round of process manufacturing.

10. The semiconductor processing equipment according to claim 9, wherein The detection module includes a photoelectric detector and a clamping member, and the clamping member includes: A light-blocking portion, on the working surface facing the observation window, a receiving cavity is formed, and the projected area of the light-blocking portion on the observation window is greater than or equal to the area of the observation window; A fixed seat, arranged in the receiving cavity, and the photoelectric detector is fixed on the fixed seat; An installation portion, including an outer edge groove adapted to the outer edge boss of the observation window, the outer edge groove is arranged around the edge of the light-blocking portion, and the detection module is detachably arranged on the observation window through the engagement of the outer edge groove and the outer edge boss.

Images