Control method and system for chip manufacturing process, and computer-readable storage medium

Abstract

Provided are a control method and system for a chip manufacturing process, and a computer-readable storage medium. The method comprises: acquiring product data of an input chip and a control parameter of a manufacturing tool (S1); determining product data of an output chip on the basis of the product data of the input chip, the control parameter of the manufacturing tool, and a preconfigured virtual measurement model (S2); determining first feedback information on the basis of the product data of the output chip and feeding the first feedback information forward to a previous production process, so that production parameter adjustment is performed on the basis of the first feedback information in the previous production process, and / or determining second feedback information on the basis of the product data of the output chip and feeding the second feedback information backward to a subsequent production process, so that a production parameter is determined on the basis of the second feedback information in the subsequent production process (S3).

Description

Chip manufacturing process control methods, control systems, and computer-readable storage media

[0001] Cross-references to related applications

[0002] This disclosure claims priority to Chinese patent application No. 202411790936.9, filed on December 5, 2024, entitled "Control Method, Control System and Computer-Readable Storage Medium for Chip Manufacturing Process", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of chip manufacturing technology, and in particular to a chip manufacturing process control method, a computer-readable storage medium, and a chip manufacturing process control system. Background Technology

[0004] To ensure chip manufacturing quality, the process capability of the equipment is typically monitored through wafer control. In related technologies, wafer control testing is performed on the equipment before formal chip production. The test results are used to evaluate the equipment's process capability, determining whether the equipment's process meets standards, and then using a compliant equipment for chip production. However, this technical solution relies solely on offline wafer control test results to control the chip manufacturing process, which is prone to data deviations and can lead to inaccuracies in automated process control.

[0005] Public content

[0006] This disclosure aims to at least partially address one of the technical problems in the related art. To this end, the first objective of this disclosure is to propose a chip manufacturing process control method that uses a virtual metrology system to determine the product data of the output chip in the production process, enabling real-time data feedback during production and significantly improving the control accuracy of the chip manufacturing process.

[0007] The second objective of this disclosure is to provide a computer-readable storage medium.

[0008] The third objective of this disclosure is to provide a control system for chip manufacturing processes.

[0009] To achieve the above objectives, a first aspect of this disclosure provides a chip manufacturing process control method applied to a current production process. The chip manufacturing process control method includes: acquiring product data of an input chip and control parameters of a process tool, wherein the process tool is used for chip production; determining product data of an output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model; determining first feedback information based on the product data of the output chip and feeding the first feedback information forward to an earlier production process so that the earlier production process can adjust production parameters based on the first feedback information; and / or determining second feedback information based on the product data of the output chip and feeding the second feedback information backward to a later production process so that the later production process can determine production parameters based on the second feedback information.

[0010] According to the chip manufacturing process control method of this disclosure, in the current production process, firstly, product data of the input chip and control parameters of the process tool are acquired, wherein the process tool is used for chip production; based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model, product data of the output chip is determined; then, first feedback information is determined based on the product data of the output chip, and the first feedback information is fed forward to the preceding production process so that the preceding production process can adjust the production parameters based on the first feedback information; and / or second feedback information is determined based on the product data of the output chip, and the second feedback information is fed back to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information. Therefore, this method uses a virtual measurement system to determine the product data of the output chip in the production process, which can realize real-time data feedback during the production process and greatly improve the control accuracy of the chip manufacturing process.

[0011] In addition, the chip manufacturing process control method according to the above embodiments of this disclosure may also have the following additional technical features:

[0012] According to one embodiment of this disclosure, the chip manufacturing process control method further includes: adjusting the control parameters of the process tool for the current production process based on the data deviation between the product data of the output chip and the target product threshold.

[0013] According to one embodiment of this disclosure, after adjusting the control parameters of the process tool based on the data deviation between the product data of the output chip and the target product threshold, the chip process control method further includes: determining the product data of the output chip based on the product data of the input chip, the adjusted control parameters of the process tool, and a preset virtual measurement model; and determining first feedback information based on the product data of the output chip, including: determining the first feedback information based on the product data of the output chip when the adjusted control parameters of the process tool reach the preset parameter threshold and the product data of the output chip does not reach the target product threshold.

[0014] According to one embodiment of this disclosure, the chip manufacturing process control method further includes: acquiring offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data, wherein the monitoring sensor is used to acquire offline chip monitoring data and online chip monitoring data; and training a preset virtual measurement model based on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0015] According to one embodiment of this disclosure, before training a preset virtual measurement model, the chip manufacturing process control method further includes: determining the aging state of the detection tools corresponding to offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data; and performing data calibration on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data based on the aging state of the corresponding detection tools.

[0016] According to one embodiment of this disclosure, before training the virtual measurement model, the chip process control method further includes: filtering the calibrated offline chip monitoring data and the calibrated online chip monitoring data; and filtering the calibrated process tool operation data and the calibrated monitoring sensor operation data.

[0017] According to one embodiment of this disclosure, the chip manufacturing process control method further includes: receiving second feedback information fed back from a previous manufacturing process, and determining control parameters of the process tool for the current manufacturing process based on the second feedback information sent by the previous manufacturing process and the target product threshold of the current manufacturing process.

[0018] According to one embodiment of this disclosure, the chip manufacturing process control method further includes: receiving first feedback information fed forward in a subsequent production process, and adjusting the target product threshold of the current production process based on the first feedback information fed back in the subsequent production process.

[0019] To achieve the above objectives, a second aspect of this disclosure provides a computer-readable storage medium storing a chip manufacturing process control program thereon, which, when executed by a processor, implements the chip manufacturing process control method described above.

[0020] According to the computer-readable storage medium of the present disclosure, when the chip manufacturing process control program is executed by the processor, the above-described chip manufacturing process control method is implemented. Based on the above-described chip manufacturing process control method, a virtual measurement system is used to determine the product data of the output chip of the production process, which can realize real-time data feedback in the production process and greatly improve the control accuracy of the chip manufacturing process.

[0021] To achieve the above objectives, a third aspect of this disclosure provides a chip manufacturing process control system applied to a current production process. The chip manufacturing process control system includes: an acquisition module for acquiring product data of an input chip and control parameters of a process tool, wherein the process tool is used for chip production; a determination module for determining product data of an output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model; a control module for determining first feedback information based on the product data of the output chip and feeding the first feedback information forward to an earlier production process so that the earlier production process can adjust production parameters based on the first feedback information; and / or determining second feedback information based on the product data of the output chip and feeding the second feedback information backward to a later production process so that the later production process can determine production parameters based on the second feedback information.

[0022] According to an embodiment of the chip manufacturing process control system of this disclosure, an acquisition module acquires product data of the input chip and control parameters of the process tool, wherein the process tool is used for chip production. A determination module determines product data of the output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model. The control module determines first feedback information based on the product data of the output chip and feeds the first feedback information forward to the preceding production process so that the preceding production process can adjust the production parameters based on the first feedback information; and / or determines second feedback information based on the product data of the output chip and feeds the second feedback information backward to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information. Therefore, this system uses a virtual measurement system to determine the product data of the output chip in the production process, enabling real-time data feedback during the production process and greatly improving the control accuracy of the chip manufacturing process.

[0023] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0025] Figure 1 is a flowchart of a chip manufacturing process control method according to an embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of a chip manufacturing process according to an embodiment of the present disclosure;

[0027] Figure 3 is a schematic diagram of a chip manufacturing process according to a specific embodiment of the present disclosure;

[0028] Figure 4 is a flowchart of a chip manufacturing process control method according to a specific embodiment of the present disclosure;

[0029] Figure 5 is a connection diagram of the control system for chip manufacturing process according to an embodiment of the present disclosure. Detailed Implementation

[0030] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0031] The following description, with reference to the accompanying drawings, outlines a chip manufacturing process control method, a computer-readable storage medium, and a chip manufacturing process control system according to embodiments of this disclosure.

[0032] Figure 1 is a flowchart of a chip manufacturing process control method according to an embodiment of the present disclosure.

[0033] As shown in Figure 1, the chip manufacturing process control method of this disclosure embodiment is applied to the current production process, and the chip manufacturing process control method may include:

[0034] S1, acquire product data of the input chip and control parameters of the process tool, wherein the process tool is used for chip production;

[0035] S2, based on the product data of the input chip, the control parameters of the process tool and the preset virtual measurement model, determines the product data of the output chip;

[0036] S3, determine first feedback information based on the product data of the output chip, and feed the first feedback information forward to the previous production process so that the previous production process can adjust the production parameters based on the first feedback information; and / or determine second feedback information based on the product data of the output chip, and feed the second feedback information backward to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information.

[0037] Specifically, the chip's product data may include the input product's size information, material information, etc., without any specific limitations. Each production process has at least one process tool, and the input chip is processed accordingly by controlling the process tool to produce the output chip.

[0038] A pre-set virtual measurement model corresponds to the production process it outputs. Utilizing collected parameters, such as equipment sensor parameters, the model is created through AI (Artificial Intelligence) to predict measurement values, eliminating the need for actual on-site measurements. This pre-set virtual measurement model enables real-time product quality prediction based on the input chip's product data and the process control parameters, obtaining the output product data for the corresponding production process. For example, if the current production process is chemical mechanical polishing, and the output product data is chip thickness, the pre-set virtual measurement model can determine the output chip thickness—the product data—based on the input chip thickness and the process tool control parameters.

[0039] First and / or second feedback information is generated based on the product data of the output chip from the preset virtual measurement module. Specifically, this can be achieved by performing operations such as data packaging, communication protocol conversion, and conversion into target identification information on the product data of the output chip. This feedback information allows the preceding and / or subsequent production processes to understand the production status of the current process and make timely production adjustments. It is understood that the chip manufacturing process includes multiple production steps. The preceding production step can be the step before the current production step, or it can be the nth step before the current production step. Similarly, the subsequent production step can be the step after the current production step, or it can be the nth step after the current production step; there are no specific limitations.

[0040] For example, as shown in Figure 2, in the chip manufacturing process, the chip undergoes manufacturing processes A, B, and C sequentially. Assuming the current process is process B, then process A is the preceding process, and process C is the following process. The preset virtual metrology system in process B calculates the output chip product data based on the input chip product data and the control parameters of the process tools. This output chip product data is then used to generate first and second feedback information. The first feedback information is sent to process A, and the second feedback information is sent to process C. If process A is used for deposition, process B for chemical mechanical polishing (CMP), and process C for etching, after CMP, process B determines the post-polish product thickness based on the virtual metrology model B and feeds it forward to process A. This allows process A to correct the deposited film thickness. The post-polish product thickness is also fed back to process C as input product data for adjusting the etching depth and thickness. This process, involving less deposition, less polishing, and less etching, not only makes the process more precise but also reduces material costs, process time, and increases output time. Among them, APC (Auto Process Control) can be used for data storage, processing, and data exchange, and can also optimize and control the production process based on product data output from a preset measurement model and received target data. RMS (Recipe Management System) is used to manage and control recipes in factory equipment, ensuring recipe consistency and accuracy during the production process, thereby improving production quality and yield.

[0041] Therefore, this embodiment can determine the product data of the output chip in real time through the preset virtual measurement module of the production process, and provide feedback signals to the preceding and / or subsequent production processes to make overall parameter adjustments, so as to make the chip process control more accurate and improve the production speed and production precision.

[0042] In one embodiment of this disclosure, the chip manufacturing process control method further includes: adjusting the control parameters of the process tool for the current production process based on the data deviation between the product data of the output chip and the target product threshold.

[0043] Specifically, the target product threshold corresponds to the product data and can be set as parameters according to actual conditions. These parameters are the data that the chip produced in the current production process needs to meet. Continuing with production process B, specifically chemical mechanical polishing, as an example, suppose the preset virtual measurement model B determines the polished thickness of the output product to be 98mm based on the input chip's product data and the control parameters of the process tool, while the target product threshold is 95mm. Then, the control parameters of the process tool are adjusted to increase the polishing intensity, ensuring the final output product thickness reaches 95mm to meet production requirements. Furthermore, the adjustment of the process tool's control parameters can be based on a preset control strategy for step-by-step adjustment, or the preset control strategy can determine the final adjustment parameters based on the deviation between the output product data and the target product threshold; there are no specific limitations.

[0044] In one embodiment of this disclosure, after adjusting the control parameters of the process tool based on the data deviation between the product data of the output chip and the target product threshold, the chip process control method further includes: determining the product data of the output chip based on the product data of the input chip, the adjusted control parameters of the process tool, and a preset virtual measurement model; and determining first feedback information based on the product data of the output chip, including: determining the first feedback information based on the product data of the output chip when the adjusted control parameters of the process tool reach the preset parameter threshold and the product data of the output chip does not reach the target product threshold.

[0045] Specifically, after adjusting the control parameters of the process tool, a preset virtual measurement model determines the adjusted output chip product data based on the input chip's product data and the adjusted process tool's control parameters. If the determined output product data still deviates from the target product threshold after adjusting the process tool's control parameters, the process tool's control parameters are further adjusted based on the data deviation until the output chip's product data determined by the preset virtual measurement model meets the target product threshold. Furthermore, to ensure the normal operation of the process tool, it has corresponding preset parameter thresholds. If, even when the adjusted process tool's control parameters reach the preset parameter thresholds, the output chip's product data still does not meet the target product threshold, it is determined that the current production process cannot meet production requirements based on the control parameter adjustments. In this case, first feedback information is determined based on the output chip's product data to assist the current production process in achieving its production target through adjustments made in the previous production process.

[0046] Continuing with the example of production process A being used for deposition and production process B being used for chemical mechanical polishing, the current production process is production process B, and the target product threshold for production process B is 95mm. If the thickness of the output product is 96mm when the control parameters of the adjusted process tool reach the preset parameter threshold, then a first feedback signal is sent to production process A. Production process A can then adjust the target thickness based on the first feedback signal to reduce the thickness to be polished by production process B.

[0047] In one embodiment of this disclosure, the chip manufacturing process control method further includes: acquiring offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data, wherein the monitoring sensor is used to acquire offline chip monitoring data and online chip monitoring data; and training a preset virtual measurement model based on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0048] Specifically, as shown in Figure 3, offline chip monitoring data is the monitoring data obtained during offline testing of the control chip before production begins, while online chip monitoring data is the monitoring data obtained during the production process by inspecting the processed chip. The operating data of the process tool can be obtained through sensors installed within the process tool, such as operating torque. Monitoring sensors are used to monitor the control chip and the processed chip to obtain offline and online chip monitoring data. A preset virtual measurement model is trained using the offline chip monitoring data, online chip monitoring data, process tool operating data, and monitoring sensor operating data, so that the trained preset virtual measurement model can be used to measure the product data of the output chip. Among these, FDC (Failure Detection Collection) identifies potential faults by periodically checking the key components and performance of the system, and SPC (Statistical Process Control) is a process control tool that uses mathematical statistics methods. The above data can be directly obtained based on FDC and SPC.

[0049] In one embodiment of this disclosure, before training a preset virtual measurement model, the chip manufacturing process control method further includes: determining the aging state of the detection tools corresponding to offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data; and performing data calibration on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data based on the aging state of the corresponding detection tools.

[0050] Specifically, the aging state can be determined based on the usage time of the testing tool. Different aging states correspond to different calibration adjustment coefficients or calibration parameters for data calibration. Offline and online chip monitoring data can be calibrated based on the aging state of the monitoring sensors. Process tool operation data can be calibrated based on the aging state of the sensors within the process tool. Monitoring sensor operation data can be calibrated based on the aging state of the sensors within the monitoring sensors. Then, the calibrated data is used to train a preset virtual measurement model.

[0051] In one embodiment of this disclosure, before training the virtual measurement model, the chip process control method further includes: filtering the calibrated offline chip monitoring data and the calibrated online chip monitoring data; and filtering the calibrated process tool operation data and the calibrated monitoring sensor operation data.

[0052] Specifically, filtering conditions can be set according to actual conditions to filter calibrated offline chip monitoring data, calibrated online chip monitoring data, calibrated process tool operation data, and calibrated monitoring sensor operation data, which are then used for model training of a preset virtual measurement model. For example, the current working status of the production process can be determined, and a preset reasonable parameter range can be determined based on the working status, filtering out data outside the preset reasonable parameter range; alternatively, mutual calibration filtering between data can also be performed, with no specific restrictions.

[0053] In one embodiment of this disclosure, the chip manufacturing process control method further includes: receiving second feedback information fed back from the previous manufacturing process, and determining control parameters of the process tool for the current manufacturing process based on the second feedback information fed back from the previous manufacturing process and the target product threshold of the current manufacturing process.

[0054] Specifically, taking the current production process as production process B and the preceding production process as production process A as an example, production process A is used for deposition, and production process B is used for chemical mechanical polishing. When production process B receives the second feedback information, it determines the product thickness of the input chip based on the second feedback information, and determines the target product thickness. Based on the data deviation between the product thickness of the input chip and the target product thickness, it determines the polishing thickness, thereby determining the control parameters of the process tool of production process B, so that the process tool of production process B can complete the polishing of the corresponding thickness and meet the production requirements.

[0055] In one embodiment of this disclosure, the chip manufacturing process control method further includes: receiving first feedback information fed forward in a subsequent production process, and adjusting the target product threshold of the current production process based on the first feedback information fed forward in the subsequent production process.

[0056] Specifically, taking the current production process as production process A and the subsequent production process as production process B as an example, production process A is used for deposition, and production process B is used for chemical mechanical polishing. When production process A receives the first feedback information, if it determines based on the first feedback information that production process B cannot produce an output chip that meets the target product requirements by adjusting the control parameters, then it adjusts its own target product threshold according to the first feedback information. For example, if production process B can only polish the chip to 96mm based on the adjustment of the control parameters, while the target product threshold of production process B is 95mm, then production process A lowers its target product threshold by 1mm based on the first feedback information to ensure that the polishing process meets the production requirements.

[0057] As a specific embodiment of this disclosure, as shown in FIG4, the chip manufacturing process control method may include the following steps:

[0058] S101, Receive the first feedback information fed forward in the subsequent production process;

[0059] S102, Adjust the target product threshold based on the first feedback information.

[0060] S103 receives the second feedback information fed back from the previous production process.

[0061] S104, determine the control parameters of the process tool based on the second feedback information and the target product threshold.

[0062] S105 acquires product data of the input chip and control parameters of the process tool.

[0063] S106 determines the chip data of the output chip based on the product data of the input chip, the control parameters of the process tool, and the preset virtual measurement model.

[0064] S107, determine the first feedback information based on the product data of the output chip, and feed the first feedback information forward to the previous production process. This allows the previous production process to adjust production parameters based on the first feedback information.

[0065] S108: Determine the second feedback information based on the product data of the output chip, and feed the second feedback information back to the subsequent production process. This allows the subsequent production process to adjust the production parameters based on the second feedback information.

[0066] S109, adjust the control parameters of the process tool for the current production process based on the data deviation between the product data of the output chip and the target product threshold. Execute step S105.

[0067] S110 acquires offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0068] S111, determine the aging status of the testing tools corresponding to offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0069] S112 performs data calibration on offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data based on the aging status of the corresponding testing tools.

[0070] S113 filters the calibrated offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0071] S114, Train the preset virtual measurement model based on offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data. Execute step S105.

[0072] Therefore, this chip manufacturing process control method employs an advanced virtual measurement system to provide real-time predictive data for precise adjustment by the automated process control system. Based on process integration requirements, it provides rapid and effective data to relevant upstream and downstream process stations, enabling the automated process control system to make precise adjustments and promptly correct process parameters for the next chip. Simultaneously, it uses statistical process control and fault detection data for retraining the artificial intelligence computing system, providing more accurate parameter data and information. This solves the technical problems in related automated process control methods, such as excessive predictive data errors leading to inaccurate automated process control, and some methods relying solely on SPC data without real-time data, resulting in deviations due to insufficient sampling measurement data.

[0073] In summary, according to the chip manufacturing process control method of this disclosure, in the current production process, firstly, product data of the input chip and control parameters of the process tool are acquired, wherein the process tool is used for chip production; based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model, product data of the output chip is determined; then, first feedback information is determined based on the product data of the output chip, and the first feedback information is fed forward to the preceding production process so that the preceding production process can adjust the production parameters based on the first feedback information; and / or second feedback information is determined based on the product data of the output chip, and the second feedback information is fed back to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information. Therefore, this method uses a virtual measurement system to determine the product data of the output chip in the production process, which can realize real-time data feedback during the production process and greatly improve the control accuracy of the chip manufacturing process.

[0074] Corresponding to the above embodiments, this disclosure also proposes a computer-readable storage medium.

[0075] The computer-readable storage medium of this disclosure stores a chip manufacturing process control program thereon, which, when executed by a processor, implements the chip manufacturing process control method described above.

[0076] According to the computer-readable storage medium of the present disclosure, when the chip manufacturing process control program is executed by the processor, the above-described chip manufacturing process control method is implemented. Based on the above-described chip manufacturing process control method, a virtual measurement system is used to determine the product data of the output chip of the production process, which can realize real-time data feedback in the production process and greatly improve the control accuracy of the chip manufacturing process.

[0077] Corresponding to the above embodiments, this disclosure also proposes a control system for chip manufacturing processes.

[0078] As shown in Figure 5, the chip manufacturing process control system of this embodiment is applied to the current production process. The chip manufacturing process control system may include: an acquisition module 10, a determination module 20, and a control module 30.

[0079] The acquisition module 10 is used to acquire product data of the input chip and control parameters of the process tool, wherein the process tool is used for chip production. The determination module 20 is used to determine product data of the output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model. The control module 30 is used to determine first feedback information based on the product data of the output chip and feed the first feedback information forward to the preceding production process so that the preceding production process can adjust the production parameters based on the first feedback information; and / or determine second feedback information based on the product data of the output chip and feed the second feedback information backward to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information.

[0080] According to one embodiment of this disclosure, the control module 30 is further configured to: adjust the control parameters of the process tool for the current production process based on the data deviation between the product data of the output chip and the target product threshold.

[0081] According to one embodiment of this disclosure, after adjusting the control parameters of the process tool based on the data deviation between the product data of the output chip and the target product threshold, the control module 30 is further configured to: determine the product data of the output chip based on the product data of the input chip, the adjusted control parameters of the process tool, and a preset virtual measurement model; and determine first feedback information based on the product data of the output chip, including: determining the first feedback information based on the product data of the output chip when the adjusted control parameters of the process tool reach the preset parameter threshold and the product data of the output chip does not reach the target product threshold.

[0082] According to one embodiment of this disclosure, the acquisition module 10 is further configured to: acquire offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data, wherein the monitoring sensor is used to acquire offline chip monitoring data and online chip monitoring data; the chip manufacturing process control device further includes a training module, which is configured to train a preset virtual measurement model based on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data.

[0083] According to one embodiment of this disclosure, the chip manufacturing process control device further includes a data processing module, which is used to determine the aging state of the detection tools corresponding to the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data before training the preset virtual measurement model; and to perform data calibration on the offline chip monitoring data, online chip monitoring data, process tool operation data, and monitoring sensor operation data based on the aging state of the corresponding detection tools.

[0084] According to one embodiment of this disclosure, before training the virtual measurement model, the data processing module is further configured to: filter the calibrated offline chip monitoring data and the calibrated online chip monitoring data; and filter the calibrated process tool operation data and the calibrated monitoring sensor operation data.

[0085] According to one embodiment of this disclosure, the control module 30 is further configured to: receive second feedback information fed back from the previous production process, and determine the control parameters of the process tool for the current production process based on the second feedback information fed back from the previous production process and the target product threshold of the current production process.

[0086] According to one embodiment of this disclosure, the control module 30 is further configured to: receive first feedback information fed forward in a subsequent production process, and adjust the target product threshold of the current production process based on the first feedback information fed back in the subsequent production process.

[0087] It should be noted that for details not disclosed in the chip manufacturing process control system of the embodiments of this disclosure, please refer to the details disclosed in the chip manufacturing process control method of the above embodiments of this disclosure, which will not be repeated here.

[0088] According to an embodiment of the chip manufacturing process control system of this disclosure, an acquisition module acquires product data of the input chip and control parameters of the process tool, wherein the process tool is used for chip production. A determination module determines product data of the output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model. The control module determines first feedback information based on the product data of the output chip and feeds the first feedback information forward to the preceding production process so that the preceding production process can adjust the production parameters based on the first feedback information; and / or determines second feedback information based on the product data of the output chip and feeds the second feedback information backward to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information. Therefore, this system uses a virtual measurement system to determine the product data of the output chip in the production process, enabling real-time data feedback during the production process and greatly improving the control accuracy of the chip manufacturing process.

[0089] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0090] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0091] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0092] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0093] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0094] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A chip manufacturing process control method, applied to the current production process, the method comprising: The product data of the input chip and the control parameters of the process tool are acquired, wherein the process tool is used for chip production; The product data of the output chip is determined based on the product data of the input chip, the control parameters of the process tool, and the preset virtual measurement model. First feedback information is determined based on the product data of the output chip, and this first feedback information is fed forward to the preceding production process so that the preceding production process can adjust production parameters based on the first feedback information; and / or The second feedback information is determined based on the product data of the output chip, and the second feedback information is fed back to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information.

2. The chip manufacturing process control method of claim 1, wherein, The method further includes: The control parameters of the process tool for the current production process are adjusted based on the data deviation between the product data of the output chip and the target product threshold.

3. The chip manufacturing process control method of claim 2, wherein, After adjusting the control parameters of the process tool based on the data deviation between the product data of the output chip and the target product threshold, the method further includes: The product data of the output chip is determined based on the product data of the input chip, the control parameters of the adjusted process tool, and the preset virtual measurement model. The step of determining the first feedback information based on the product data of the output chip includes: If the control parameters of the adjusted process tool reach the preset parameter threshold and the product data of the output chip does not reach the target product threshold, the first feedback information is determined based on the product data of the output chip.

4. The chip manufacturing process control method according to any one of claims 1 to 3, wherein The method further includes: The system acquires offline chip monitoring data, online chip monitoring data, and the operating data of the process tool and the operating data of the monitoring sensor, wherein the monitoring sensor is used to acquire the offline chip monitoring data and the online chip monitoring data. The preset virtual measurement model is trained based on the offline chip monitoring data, the online chip monitoring data, the process tool operation data, and the monitoring sensor operation data.

5. The chip manufacturing process control method of claim 4, wherein, Before training the preset virtual measurement model, the method further includes: Determine the aging status of the detection tools corresponding to the offline chip monitoring data, the online chip monitoring data, the process tool operation data, and the monitoring sensor operation data; Data calibration is performed on the offline chip monitoring data, the online chip monitoring data, the process tool operation data, and the monitoring sensor operation data based on the aging status of the corresponding testing tools.

6. The chip manufacturing process control method of claim 5, wherein, Before training the virtual measurement model, the method further includes: The calibrated offline chip monitoring data and the calibrated online chip monitoring data are filtered. The operating data of the calibrated process tool and the operating data of the calibrated monitoring sensor are filtered.

7. The chip manufacturing process control method according to any one of claims 1 to 6, wherein The method further includes: The system receives second feedback information from the preceding production process and determines the control parameters of the process tool for the current production process based on the second feedback information from the preceding production process and the target product threshold of the current production process.

8. The chip manufacturing process control method according to any one of claims 1 to 7, wherein The method further includes: Receive first feedback information fed forward in subsequent production processes, and adjust the target product threshold of the current production process based on the first feedback information fed back in subsequent production processes.

9. A computer-readable storage medium storing a chip manufacturing process control program thereon, wherein the chip manufacturing process control program, when executed by a processor, implements the chip manufacturing process control method according to any one of claims 1-8.

10. A control system for a chip manufacturing process, applied to the current production process, the system comprising: An acquisition module is used to acquire product data of the input chip and control parameters of the process tool, wherein the process tool is used for chip production; The determination module is used to determine the product data of the output chip based on the product data of the input chip, the control parameters of the process tool, and a preset virtual measurement model. The control module is configured to determine first feedback information based on the product data of the output chip, and feed the first feedback information forward to the preceding production process so that the preceding production process can adjust production parameters based on the first feedback information; and / or The second feedback information is determined based on the product data of the output chip, and the second feedback information is fed back to the subsequent production process so that the subsequent production process can determine the production parameters based on the second feedback information.

Images