Automatic semiconductor production monitoring method and device based on AI, terminal and medium

Abstract

The invention provides a semiconductor production monitoring method and system based on AI and full automation, a terminal and a medium, and aims at integrating the running process of a full-automatic production system (Full Auto4), and processing logics of all steps from beginning to end of Pod Run (product running), EQ Test (daily machine testing) and PM-EQ Test (machine period machine testing) are processed through Full Autoamp; according to intelligent processing of the AI production monitoring system, functional logics of related systems (such as MES, EAP, APC, RTD, crown block system-AMHS and the like) are sequentially connected in series, and content instructions currently made by each machine table are displayed; monitoring personnel in each area of a production line can visually and quickly see the system operation condition and the actual generation condition of the area in charge of the monitoring personnel through the system interface, and the system can automatically display the instruction information and the completion condition currently issued to each machine on the interface and prompt the information about to be made in the next step.

Description

Technical Field

[0001] The present application relates to the field of semiconductor wafer processing technology, and in particular to AI-based and fully automatic semiconductor production monitoring methods, devices, terminals and media. Background Art

[0002] The 12-inch semiconductor factory is an unmanned fully automated factory. Currently, the industry's full auto systems are still at the auto3 Prod Run stage (daily testing, post-PM testing, and auto continue run are not implemented). That is, the current mainstream semiconductor 12-inch system manufacturers do not provide a monitoring system that automatically monitors the entire operation process of the automated production system. The existing known solutions are:

[0003] (1) If there is no alarm during the delivery process but the machine is unable to deliver goods (for example, when the goods are not delivered to the machine by the overhead crane for a long time), production personnel must check the corresponding reporting tool to discover the abnormality and notify IT personnel to query and handle it.

[0004] (2) If an EQ alarm occurs during the delivery process and the other party sends an error message to the new alarm management system AMS (Alarm Manager System), an email or SMS message will be sent to the corresponding production-related personnel group to remind them to check and handle the situation. The corresponding production-related personnel generally check the system check SOP based on past experience and then go to the corresponding different production system interfaces to find the setting problem. If the production-related personnel cannot confirm the problem generator (owner), they need to find IT personnel to analyze the log and query the system function settings to troubleshoot and handle the problem.

[0005] However, the above prior art still has the following defects:

[0006] First, if an EQ alarm occurs during the delivery process and the other party sends an error message (Error Message) to the new alarm management system AMS (Alarm Manager System), an email or SMS message will be sent to the corresponding set group of production-related personnel to remind them to check and handle the problem. Generally, the set group message notification is sent to production-related personnel and IT personnel, but the problem generator (owner) cannot be sure whether the problem needs to be checked by himself; there is no system or personnel to track the handling results for whether the problem generator (owner) follows up and handles it in time.

[0007] Secondly, there is no comprehensive automatic monitoring system to provide production-related personnel with monitoring of the specific operating conditions of the entire fully automatic (full auto4) production system. Once the action determined by the system is inconsistent with the actual situation, the on-site personnel cannot be informed immediately. For example, if there is a problem with abnormal handling, the current system mechanism will not remind the owner to handle it in time, which will cause the machine to be idle all the time. The production-related personnel will not discover this problem until they check the corresponding production report. In this way, it is impossible to notify the relevant personnel in time to check and handle it in time, which greatly affects the efficiency of handling automation failures and affects the improvement of machine production capacity. Summary of the invention

[0008] In view of the shortcomings of the prior art described above, the purpose of the present application is to provide an AI-based and fully automatic semiconductor production monitoring method, device, terminal and medium to solve the technical problem that the owner is unable to follow up on the fault in a timely manner.

[0009] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides an AI-based and fully automatic semiconductor production monitoring method, including: obtaining the original production data of each system in the semiconductor fully automatic production process and storing it in the production monitoring system database, calculating and summarizing the original production data to determine the abnormal situation of the current fully automatic running state of each machine group, and generating the running process steps for each production scene; generating corresponding visual monitoring screens according to the sorted running process steps for each production scene; generating corresponding production monitoring systems according to different functional areas, so that the operation procedures of each functional area remain independent.

[0010] In some embodiments of the first aspect of the present application, the original production data of each system in the semiconductor fully automatic production process is obtained and stored in the production monitoring system database, and the original production data is calculated and summarized to determine the abnormal situation of the current fully automatic running state of each machine group, and the running process steps for each production scene are generated, which include the following: obtaining real-time running and handling information of each system in the semiconductor fully automatic production process, and summarizing the original production data related to semiconductor production into the production monitoring system database; based on the original production data related to semiconductor production, according to the running process sequence of each scene of the fully automatic production line as the basis for logical judgment, each original production data is summarized and calculated to display the current fully automatic running state of each machine group, and to display the current machine running status and the preparation information for running; the running process of each production scene of the fully automatic process is generated, which is product running, daily machine testing and machine periodic testing, which is used as the basic logical basis of the fully automatic production monitoring system.

[0011] In some embodiments of the first aspect of the present application, the method includes intelligently calculating and summarizing various original production data through an electronic timer; wherein, if the current machine cargo running information or overhead crane transportation information is abnormal, the electronic timer compares the actual processing time of each cargo running step with the standard deviation of the preset processing time, extracts the abnormal data, and notifies the corresponding problem generator through the alarm system for quick processing.

[0012] In some embodiments of the first aspect of the present application, the corresponding visual monitoring screen is generated according to the steps of the delivery process of each production scenario obtained by sorting out, which includes: based on the Web Socket method, the user terminal accesses the production monitoring system database according to the preset access frequency, calls the middleware to read the production monitoring system database and returns it to the graphical interface module for automatic data refresh and display; when an alarm is displayed in the current step, the current status is changed in color, and the corresponding problem generator is automatically notified; the preset information that requires the attention of the monitoring personnel is captured and displayed.

[0013] In some embodiments of the first aspect of the present application, the method includes monitoring and displaying the advance stocking stage, the automatic stocking stage and the automatic delivery stage respectively.

[0014] In some embodiments of the first aspect of the present application, the monitoring display in the advance stocking stage includes: when the production monitoring system logically judges that the goods currently running on the machine have been completed within a preset time, whether the monitoring automation system will prepare other goods with the highest priority in advance to the carrier used to store goods near the machine in preparation for running goods; and, displaying whether the status of the wafer loading system of the monitoring machine is in normal use.

[0015] In some embodiments of the first aspect of the present application, the monitoring display in the automatic delivery stage includes any one or more combinations of the following scenarios:

[0016] Scenario 1: When the wafer loading system of the current machine is idle and there are goods to be transported, but the automation system has not dispatched them, the production monitoring system sends a self-check command to the real-time dispatch system;

[0017] Scenario 2: The automation system dispatches goods to the current machine, but if the wafer loading system of the machine still shows that it is idle for a certain period of time, a self-check command is sent to the overhead crane system to check whether the goods handling command has not been executed;

[0018] Scenario 3: When the goods have been transported to the wafer loading system of the machine but the wafer group status still shows the waiting state after exceeding the preset time, the production monitoring system sends a self-check command to the machine automation system to check the communication connection status;

[0019] Scenario 4: If the machine is constantly running out of stock and the time it takes exceeds the preset range, the production monitoring system will send a self-check command to the machine.

[0020] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an AI-based and fully automatic semiconductor production monitoring device, including: a data aggregation module, used to obtain the original production data of each system in the semiconductor fully automatic production process and store it in the production monitoring system database, calculate and summarize the original production data to determine the abnormal situation of the current fully automatic running state of each machine group, and generate the running process steps for each production scene; a visualization module, used to generate corresponding visual monitoring screens according to the sorted running process steps of each production scene; a production monitoring module, used to generate corresponding production monitoring systems according to different functional areas, so that the operation procedures of each functional area remain independent.

[0021] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the AI-based and fully automatic semiconductor production monitoring method is implemented.

[0022] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides an electronic terminal, including: a processor and a memory; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory, so that the terminal executes the AI-based and fully automatic semiconductor production monitoring method.

[0023] As described above, the AI-based and fully automatic semiconductor production monitoring method, device, terminal and medium of the present application have the following beneficial effects: the present application provides a set of intelligent automatic monitoring system through the calculation control of the system intelligent program, and provides production-related personnel with the operating status of each link of the monitoring system (auto4); when an abnormality or alarm occurs at each link node, the system will intelligently and quickly locate the problem, automatically notify the corresponding person in charge to respond and handle it in time, and production-related personnel can also promptly remind the corresponding person in charge to handle it when they see the abnormal prompt, so as to achieve highly intelligent and fully automatic automatic monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 Shown is a flow chart of an AI-based and fully automatic semiconductor production monitoring method in one embodiment of the present application.

[0025] Figure 2 Shown is a schematic diagram of the process of generating goods for each production holiday in one embodiment of the present application.

[0026] Figure 3AShown is a schematic diagram of the full auto 4 continuous running process of Prod Run in one embodiment of the present application.

[0027] Figure 3B Shown is a schematic diagram of the full auto 4 continuous running process of the daily machine test (EQ Test) in one embodiment of the present application.

[0028] Figure 3C Shown is a schematic diagram of the full auto 4 continuous running process of PM-EQ Test (machine periodic test) in one embodiment of the present application.

[0029] Figure 4 Shown is a schematic diagram of the generation process of a visual monitoring screen in one embodiment of the present application.

[0030] Figure 5 Shown is a flow chart of an AI-based and fully automatic semiconductor production monitoring method in one embodiment of the present application.

[0031] Figure 6 Shown is a structural schematic diagram of an AI-based and fully automatic semiconductor production monitoring device in one embodiment of the present application.

[0032] Figure 7 Shown is a schematic diagram of the structure of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0033] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0034] It should be noted that in the following description, with reference to the accompanying drawings, several embodiments of the present application are described in the accompanying drawings. It should be understood that other embodiments may also be used, and mechanical composition, structure, electrical and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is limited only by the claims of the published patents. The terms used here are only for describing specific embodiments and are not intended to limit the present application. Spatially related terms, such as "upper", "lower", "left", "right", "below", "below", "lower", "above", "upper", etc., may be used in the text to facilitate the description of the relationship between an element or feature shown in the figure and another element or feature.

[0035] In this application, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", "fix", "hold" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0036] Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless there is an indication to the contrary in the context. It should be further understood that the terms "comprise", "include" indicate the presence of the described features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Exceptions to this definition will only occur when the combination of elements, functions or operations is inherently mutually exclusive in some way.

[0037] In order to solve the problems in the above-mentioned background technology, the present invention provides an AI-based and fully automatic semiconductor production monitoring method, system, terminal and medium, which aims to integrate the running process of the fully automatic production system (Full Auto4), and connect the processing logic of each step of Prod Run (product running), EQ Test (daily machine testing) and PM-EQ Test (machine periodic machine testing) from the beginning to the end through the intelligent processing of the Full Auto&AI production monitoring system. The functional logic of each system involved (such as MES, EAP, APC, RTD, overhead crane system-AMHS, etc.) is connected in series in an orderly manner, and the content instructions currently being performed by each machine are displayed, so that the monitoring personnel in each area of ​​the production line can intuitively and quickly see the system operation status and actual generation status of the area they are responsible for through this system interface. The system will automatically display the current instruction information and completion status of each machine on the interface, and prompt the information to be done next.

[0038] At the same time, through visual information, production-related personnel can monitor whether the current instruction decision given by the system is consistent with the actual situation and whether there are any alarms. If there are alarms, it is convenient for production personnel to quickly contact the corresponding responsible personnel for resolution. The system will also automatically notify the clear problem generator (owner) for timely processing, improve system operation efficiency and production efficiency, reduce abnormal processing time, reduce machine idle time, and further improve machine production capacity.

[0039] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the technical solution in the embodiments of the present invention is further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the invention.

[0040] Before further describing the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are applicable to the following interpretations:

[0041] <1> Inch: Inch, a unit of length in the British and American systems.

[0042] <2> MES system: a production information management system for the execution layer of the workshop of manufacturing enterprises. MES system can provide enterprises with management modules including manufacturing data management, planning and scheduling management, production scheduling management, inventory management, quality management, human resources management, work center / equipment management, tool and fixture management, procurement management, cost management, project kanban management, production process control, bottom-level data integration analysis, raw-level data integration decomposition, etc., so as to create a solid, reliable, comprehensive and feasible manufacturing collaborative management platform.

[0043] <3> EAP (Equipment Automation Programming): Equipment Automation Programming System, also known as Machine Automation System, is a system used to control semiconductor manufacturing equipment for automated production. The EAP system is integrated with the MES system to verify product information and automatically do accounting. At the same time, it collects process data and equipment parameter data during product generation, helping to improve the production efficiency of semiconductor factories, avoid manual operation errors, and improve product yield.

[0044] <4> APC system: Advanced control system is a system that is superior to the classic PID control effect on the basis of distributed control system DCS. It usually adopts predictive control, inference control, statistical process control, fuzzy control, neural network control, nonlinear control, robust control and soft measurement technologies, with process control scheme analysis and mathematical model calculation as the core, to achieve process optimization control and process edge operation, improve automation level and enhance economic benefits.

[0045] <5> RTD system: Real-time dispatch system, used to help semiconductor factories optimize dispatch, improve production efficiency and increase equipment utilization.

[0046] <6> AMHS (Automatic Material Handling System): Automatic material handling system, also known as overhead crane system.

[0047] <7> Load Port: Wafer handler and wafer loader, installed in front of the Equipment Front End Module (EFEM), used as a window for wafers to enter and exit the Equipment Front End Module.

[0048] <8> FOUP (Front Opening Unified Pod): A front-opening wafer transfer box is a container used to protect, transport and store wafers in the semiconductor process. A FOUP with a wafer length of 12 inches (300mm) can accommodate 25 300mm wafers. Its main component is a front-opening container that can accommodate 25 wafers and a front-opening door frame dedicated to the opening and closing of the container.

[0049] <9> Stocker: Wafer storage cabinet used for semiconductor production processes within clean rooms and for storing wafer boxes between processes.

[0050] <10> Dummy wafer: used to fill all wafers in batch process equipment to ensure a stable and identical state.

[0051] <11> Full auto4: It is defined as seamless switching and continuous running of three scenarios: Prod Run (product run), EQ Test (daily machine test), and PM-EQ Test (machine periodic test).

[0052] <12> IMP: A semiconductor process, its full name is P-ESDIMP. The P-ESDIMP process is to add a P-ESDIMP after the active area is heavily doped, its purpose is to dope a medium concentration of boron (P type) into the interface between the NMOS drain end and the PW just below the N+ diffusion area by ion implantation, thereby reducing the breakdown voltage between the NMOS drain end and the PW.

[0053] The embodiments of the present invention provide an AI-based and fully automatic semiconductor production monitoring method, an AI-based and fully automatic semiconductor production monitoring method system, and a storage medium storing an executable program for implementing the AI-based and fully automatic semiconductor production monitoring method. As far as the implementation of the AI-based and fully automatic semiconductor production monitoring method is concerned, the embodiments of the present invention will illustrate an exemplary implementation scenario of AI-based and fully automatic semiconductor production monitoring.

[0054] like Figure 1 As shown, a flow chart of a semiconductor production monitoring method based on AI and fully automatic in an embodiment of the present invention is shown. The semiconductor production monitoring method based on AI and fully automatic in this embodiment mainly includes the following steps:

[0055] Step S1: Obtain the original production data of each system in the semiconductor fully automatic production process and store it in the production monitoring system database, calculate and summarize the original production data to determine the abnormal situation of the current fully automatic running state of each machine group, and generate the running process steps for each production scenario.

[0056] In the embodiment of the present invention, the above step S1 specifically includes: Figure 2 The sub-steps shown in are as follows:

[0057] Step S11: Acquire the real-time cargo transportation information of each system in the semiconductor fully automatic production process, and aggregate the original production data related to semiconductor production into the production monitoring system database.

[0058] In some examples, the raw production data related to semiconductor production includes but is not limited to the current stocking data of machines in each semiconductor production area, running data, EAP system product number identification process time data (EAP PPIDProcess Time), machine condition data, machine wafer loading system status data, front-opening wafer transfer box position data, wafer storage cabinet storage data, aerial suspension crane transportation position data, conventional machine testing data, machine maintenance data, machine warm-up data, online product data, next destination data of goods, Dummy wafer inventory data, Dummy wafer usage data, etc. The raw production data (raw data) of the above data are all summarized in the full-auto monitor database (Full-Auto Monitor database).

[0059] Step S12: Based on the original production data related to the semiconductor production, the order of the delivery process of each scene of the fully automatic production line is used as the basis for logical judgment, and the various original production data are summarized and calculated to display the current fully automatic delivery status of each machine group, as well as the current machine delivery status and the preparation information for delivery.

[0060] Specifically, based on the various raw production data mentioned above, according to the order of the running process of each scene of the full automatic production line, for example, the current running order is product running or daily machine testing or post-PM machine testing, the various raw production data are intelligently calculated and summarized through an electronic timer (such as a watchdog timer, which can be set to execute once every minute, etc.), and the current full-automatic running status of each machine group is displayed to show the current status of the goods being run by the machine, as well as the next step of preparing other goods in advance and placing them in the carrier (OHB) for storing goods near the current machine, waiting for the continuous running information.

[0061] Furthermore, if the current machine cargo transport information or overhead crane handling information is abnormal, the electronic timer compares the standard deviation between the actual processing time of each cargo transport step and the preset processing time, extracts the abnormal data, and notifies the corresponding problem generator through the alarm system for quick processing.

[0062] For example, if the current machine cargo transport information or overhead crane transport information is abnormal, Watch Dog will also perform logical judgment, specifically comparing the actual processing time (actual process time) of each cargo transport step with the standard deviation of the set processing time, capturing abnormal data, and automatically calling the corresponding problem generator (Owner) through the alarm system for rapid processing.

[0063] Furthermore, the method also includes setting a telephone reply function, which includes: setting a reply response time after the user receives the alarm information. If there is no response within a first preset time, continue to notify the problem generator for processing. If there is still no response within a second preset time, notify the upper-level administrator of the problem generator according to the preset warning level order.

[0064] Specifically, since a telephone reply function has been added, a reply time is set after the user receives the alarm information. If there is no reply within the set time value, the problem generator (Owner) will continue to be called for processing; if there is still no response after a certain period of time, the telephone notification level will be increased, and a call will be automatically made to the upper-level supervisor to promote timely response and processing of the problem.

[0065] Preferably, a manual intervention processing mode is also set, which is used to manually initiate a notification when no response is received after the warning level is exceeded. In other words, the production-related personnel, as the monitoring personnel, need to intervene and notify the user by phone when the user has not responded after the warning level exceeds the warning level.

[0066] Step S13: Generate the product running, daily machine testing and machine periodic machine testing processes for each production scenario of the fully automatic process, which are used as the basic logic basis of the fully automatic production monitoring system.

[0067] Specifically, the fully automatic process in the embodiment of the present invention refers to full auto 4, where the definition of auto 4 refers to the seamless switching of three scenarios: Prod Run, EQ Test, and PM-EQ Test. In this embodiment, in order to achieve the effect of automatic monitoring and abnormal alarm according to actual scenarios, the running process steps of each scenario of full auto 4 are organized from the perspective of the system. The process steps are Prod Run, daily test, and PM post-test in sequence, and the process steps are used as the basic logical basis for developing the Full Auto & AI production monitoring system.

[0068] For example, Figure 3A , 3B 3C demonstrated a specific example of a full auto 4-step continuous run process of Prod Run, daily machine test (EQ Test), and PM-EQ Test (machine periodic test):

[0069] As can be seen from the figure, the monitoring screen of each stage of the production monitoring process is divided into the first-layer data model analysis (Layer I) and the second-layer data model analysis (Layer II). The first-layer data model analysis (Layer I) shows the specific production steps in each stage, and the second-layer data model analysis (Layer II) corresponds to the specific execution module of each production step in the first-layer data model analysis (Layer I). Take the Prod Run stage as an example: its production monitoring screen is divided into the first layer data model analysis (Layer I) and the second layer data model analysis (Layer II). The first layer data model analysis (Layer I) includes the following production steps: Pre-Send (preparation in advance), RTD (real-time delivery), Transfer, OHB (storage cargo carrier), Trigger what next (trigger the next step), RTD (real-time delivery), job prepare (preparation work), recipe check (recipe check), transfer, start load (start loading), eap job in (automatic start of delivery), EQ Run (running), run finish (end of delivery), eqpjob out (automatic end of delivery), Trigger what next (trigger the next step), transfer, OHB (storage cargo carrier). In the second-layer data model analysis (Layer II), each production step in the first-layer data model analysis (Layer I) is further broken down in detail. For example, Tranfer in the first-layer data model analysis (Layer I) is specifically broken down into two steps in the second-layer data model analysis (Layer II): actual handling time, standard time spec; exceeding spec Alarm (an alarm is issued when the standard time spec is exceeded).

[0070] It should be understood that there are many steps in the semiconductor process. Figures 3A to 3C The above examples are only used as examples to show the monitoring content and screens, are provided for illustrative purposes, and should not be understood as limiting.

[0071] Step S2: Generate corresponding visual monitoring screens according to the sorted out steps of the delivery process of each production scenario.

[0072] Optionally, a C-sharp language tool is used to produce corresponding visual monitoring screens of the operation status of the Full Auto & AI production monitoring system in each production area for monitoring and viewing by production-related personnel. It should be understood that the C-sharp language, also known as the C# language, is an object-oriented, high-level programming language that runs on the .NET Framework.

[0073] In this embodiment, the steps of the running process of each production scenario are sorted out to generate corresponding visual monitoring screens, which specifically include Figure 4 Steps S21 to S23 shown in FIG.

[0074] Step S21: Based on the Web Socket method, the client accesses the production monitoring system database according to the preset access frequency, calls the middleware to read the production monitoring system database and returns it to the graphical interface module for automatic data refresh and display.

[0075] It should be understood that Web Socket is a very important feature in the HTML5 specification, which allows users to achieve two-way communication in the browser, realize timely data push, and can be applied through web pages. The functional design of the C-sharp language tool uses the Web Socket method. The client can set a preset access frequency (for example, every few seconds) to actively access the Full Auto&AI production monitoring system database, and use the call web service middleware to read the data in the Full Auto&AI production monitoring system database (for example, daily test machine full automatic status data EQ Full Auto Status Data) and return it to the graphical interface module GUI for automatic data refresh and display, specifically displaying the full automatic status data of Prod Run (product running), daily test machine (EQ Test), PM-EQ Test (machine cycle test) in the three stages of advance stocking stage (Pre-send), automatic stocking stage (EQRunning), and automatic delivery stage (Post-send).

[0076] Step S22: When an alarm is displayed in the current step, the color of the current state is changed and the corresponding problem generator is automatically notified.

[0077] Specifically, when an alarm is displayed in the current step, the color of the current status will be changed, preferably the color will be highlighted to enhance visual prominence (for example, displayed in red), and the system will automatically notify the generator of the corresponding alarm by phone to handle it.

[0078] Furthermore, a detail display button is provided in the display interface. The display interface responds to the user's selection operation (such as touch, keyboard or mouse operation, etc.) to enter the next level of detail display information for viewing the alarm details, and further urges and notifies the problem generator (Owner) to deal with it in time.

[0079] Step S23: capturing and displaying the preset information that requires the monitoring personnel's attention.

[0080] In some examples, the information that requires the monitoring personnel's attention includes wafer LOT information and / or EQ information, such as Q-time LOT information, Chamber Idle information, etc. These are information that the monitoring personnel need to pay attention to in a timely manner and need to be displayed on the monitoring screen for the monitoring personnel to observe in real time.

[0081] The Full Auto & AI production monitoring system displays the progress information of the fully automatic process and performs anomaly detection according to the actual running process. For example, if the current running process is the Prod Run process, the display interface GUI will display the full auto status according to the actual running process as follows, and the Full Auto & AI production monitoring system will monitor the operation status of each link as follows:

[0082] First, the display monitoring of the advance stocking stage (Pre-send). The Full Auto & AI production monitoring system will monitor whether the automation system will prepare other goods with the highest priority in advance to the carrier (OHB) used to store goods near the machine for running goods when the goods currently running on the machine are finished within a preset time; and display whether the wafer loading system (LOAD PORT) status of the monitoring machine is in normal use. Furthermore, if it is monitored that the automation system has not prepared other goods with the highest priority in advance to the carrier (OHB) used to store goods near the machine for running goods, the Full Auto & AI production monitoring system will notify (for example, automatically by dialing a phone call) the MES on-duty personnel to check and handle it.

[0083] Secondly, the display monitoring of the automatic running stage (EQ Running) is described using the following four scenarios as examples:

[0084] Scenario 1: When the wafer loading system (LOAD PORT) of the current machine is idle and there are goods to be transported but the automation system has not dispatched them, the Full Auto&AI production monitoring system notifies the administrator of the real-time dispatch system (RTD) to check the status of the real-time dispatch system (RTD).

[0085] Scenario 2: The automation system dispatches goods to the current machine, but if the wafer loading system (LOAD PORT) of the machine still shows that it is idle for a certain period of time, the crane manager is notified to check whether the crane system has executed the cargo handling command.

[0086] For example, the automation system dispatches goods to the current machine, but the wafer loading system (LOAD PORT) of the machine is still displayed as idle for more than a certain period of time. At this time, the crane operator on duty will be automatically called to check whether the crane system has not executed the cargo handling instruction.

[0087] Scenario 3: When the goods have been transported to the wafer loading system (LOAD PORT) of the machine, if the wafer group status (LOT status) still shows the waiting status (for example, wait job in status) for more than the preset time, the Full Auto&AI production monitoring system notifies the machine automation system (EAP) to check whether the communication between the machine automation system (EAP) and EQ (machine) is abnormal.

[0088] Scenario 4: If the machine is constantly running out of goods and the running time exceeds the preset range, the FullAuto&AI production monitoring system will send a notification to the equipment so that the equipment manager can check whether there is any abnormality in the machine.

[0089] Exemplarily, if the goods have been in a running state in the machine, and the running time of the goods has exceeded or fallen below 20% of the standard running time (Recipe Standard Process Time), the Full Auto & AI production monitoring system will notify the administrator (Owner) of the machine equipment to check whether the machine has any abnormal conditions. It should be understood that the value of the standard running time in the embodiment of the present invention can be set by the machine equipment and process engineers according to actual conditions, and there is no limitation on this. At the same time, the 20% limit is only a reference example and is not intended to be limiting.

[0090] Finally, the display monitoring of the automatic delivery stage (Post-send). After receiving the notification that the goods have been delivered to the machine, the automation system notifies the overhead crane system to move the goods to the carrier used to store goods near the machine at the next station. The FullAuto&AI production monitoring system monitors whether the wafer loading system (LOAD PORT) of the machine still has this batch of goods within the scheduled time; if there is still this batch of goods, an alarm will be automatically issued and a notification will be sent to the overhead crane system.

[0091] For example, after receiving the notification that the goods have been moved from the machine, the automation system will notify the overhead crane system to move the goods to the OHB near the machine at the next station. The Full Auto&AI production monitoring system will monitor the machine LOADPORT for more than a certain period of time. If it is still shown that the batch of goods has not been moved away, it will automatically alarm the production personnel and automatically call the overhead crane on-duty personnel to check and handle it in time.

[0092] Step S3: Generate corresponding production monitoring systems according to different functional areas, so that the operation procedures of each functional area remain independent.

[0093] Specifically, since the running of goods, daily machine testing characteristics, machine maintenance information, and machine warm-up information in each functional area are different, the corresponding intelligent computing logic that needs to be converted is also different. Therefore, the design of the embodiment of the present invention is divided according to the area, specifically the wafer start area (Wafer Start), measurement area, furnace tube area, IMP area, LITHO area, Milti-chamber area, WET area, CMP area, WAT area, etc. In this way, the operating procedures of each area are kept independent, and each area does not affect each other. At the same time, the judgment rules of the corresponding area can be calculated according to the actual situation of the production line and the switching of the corresponding area.

[0094] To facilitate understanding by those skilled in the art, Figure 5 The whole process of an AI-based and fully automatic semiconductor production monitoring method in the implementation of the present invention is further explained.

[0095] exist Figure 5 In the example shown, the first is data collection, which aims to collect the original production data (CIM Raw Data) of 10 systems (including MES system, APC system, EAP system, RMS system, FDC system, AMHS system, PMS system, RTD system, Watch Dog system, EQ Monitor system), store it in the production monitoring system database (full auto monitor database), and generate the corresponding visual monitoring screen through the full auto monitor engine (full auto monitor Engine), such as using the C-sharp language tool. In the generated visual monitoring screen, there are first-layer data model analysis and second-layer data model analysis. In the second-layer data model analysis, the abnormal points that should be monitored in each step are sorted and analyzed to provide an analysis basis for the system to distinguish true alarms from false alarms, and the alarm ratio that occurs is marked and classified; for false alarms that do not affect the fully automatic delivery of goods, self-correction is performed to achieve automatic monitoring of real alarms, and the real problem generator (Owner) is automatically notified by phone for processing.

[0096] It is worth noting that the technical solution provided by the embodiment of the present invention has at least the following advantages:

[0097] First of all, the Full Auto&AI production monitoring system can quickly detect and locate problems, and automatically notify the corresponding owner by phone as soon as the problem occurs for timely processing.

[0098] Secondly, the Full Auto&AI production monitoring system provides a visual interface, so that monitoring personnel in each area of ​​the production line can intuitively and quickly see the system operation status and actual production status of the area they are responsible for through this system interface. Production personnel can monitor whether the current instruction decision given by the system is consistent with the actual situation and whether there is an alarm; if there is an alarm, it is convenient for production personnel to quickly contact the corresponding responsible personnel to resolve it, improve system operation efficiency and production efficiency, reduce exception processing time and machine idle time (Idle Time), and thus increase machine production capacity.

[0099] The above is a detailed explanation of the implementation process and implementation principle of an AI-based and fully automatic semiconductor production monitoring method provided by an embodiment of the present invention. The following is a further description of the AI-based and fully automatic semiconductor production monitoring device, terminal and medium provided by the present invention.

[0100] like Figure 6 , a schematic diagram of the structure of a semiconductor production monitoring device based on AI and fully automatic in an embodiment of the present invention is shown. The semiconductor production monitoring device 600 in an embodiment of the present invention includes: a data aggregation module 601, a visualization module 602, and a production monitoring module 603.

[0101] The data aggregation module 601 is used to obtain the original production data of each system in the semiconductor fully automatic production process and store it in the production monitoring system database, calculate and aggregate the original production data to determine the abnormal situation of the current fully automatic running status of each machine group, and generate the running process steps for each production scenario.

[0102] The visualization module 602 is used to generate corresponding visualization monitoring screens according to the sorted out steps of the delivery process of each production scenario.

[0103] The production monitoring module 603 is used to generate corresponding production monitoring systems according to different functional areas, so that the operation procedures of each functional area remain independent.

[0104] It should be noted that the AI-based and fully automatic semiconductor production monitoring device provided in the above embodiment only uses the division of the above program modules as an example when performing AI-based and fully automatic semiconductor production monitoring. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the AI-based and fully automatic semiconductor production monitoring device provided in the above embodiment and the AI-based and fully automatic semiconductor production monitoring method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0105] The AI-based and fully automatic semiconductor production monitoring method provided in the embodiment of the present invention can be implemented on the terminal side or the server side. As for the hardware structure of the electronic terminal, please refer to Figure 7 , is an optional hardware structure diagram of an electronic terminal 700 provided in an embodiment of the present invention. The terminal 700 may be a mobile phone, a computer device, a tablet device, a personal digital processing device, a factory background processing device, etc. The electronic terminal 700 includes: at least one processor 701, a memory 702, at least one network interface 704 and a user interface 706. The various components in the device are coupled together through a bus system 705. It can be understood that the bus system 705 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 705 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, in Figure 7 In the specification, various buses are labeled as bus systems.

[0106] The user interface 706 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0107] It is understood that the memory 702 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of exemplary but not limiting explanation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0108] The memory 702 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 700. Examples of these data include: any executable program for operating on the electronic terminal 700, such as an operating system 7021 and an application 7022; the operating system 7021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 7022 may include various applications, such as a media player (MediaPlayer), a browser (Browser), etc., for implementing various application services. The AI-based and fully automatic semiconductor production monitoring method provided by the embodiment of the present invention may be included in the application 7022.

[0109] The method disclosed in the above embodiment of the present invention can be applied to the processor 701, or implemented by the processor 701. The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 701 or the instruction in the form of software. The above processor 701 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 701 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 701 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0110] In an exemplary embodiment, the electronic terminal 700 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0111] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0112] In the embodiments provided in the present application, the computer readable and writable storage medium may include a read-only memory, a random access memory, an EEPROM, a CD-ROM or other optical disk storage device, a disk storage device or other magnetic storage device, a flash memory, a USB flash drive, a mobile hard disk, or any other medium that can be used to store a desired program code in the form of an instruction or data structure and can be accessed by a computer. In addition, any connection can be appropriately referred to as a computer-readable medium. For example, if the instruction is sent from a website, a server or other remote source using a coaxial cable, an optical fiber cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, optical fiber cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. However, it should be understood that computer readable and writable storage media and data storage media do not include connections, carriers, signals, or other temporary media, but are intended to be non-temporary, tangible storage media. Disk and disc, as used in this application, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.

[0113] In summary, the present application provides a semiconductor production monitoring method, device, terminal and medium based on AI and full automation. The present application provides a set of intelligent automatic monitoring system through the operation control of the system intelligent program, which provides the production-related personnel with the operating status of each link of the monitoring system (auto4); when an abnormality or alarm occurs at each link node, the system will intelligently and quickly locate the problem, automatically notify the corresponding person in charge to respond and handle it in time, and the production-related personnel can also promptly remind the corresponding person in charge to handle it when they see the abnormal prompt, so as to achieve highly intelligent and fully automated automatic monitoring. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0114] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A semiconductor production monitoring method based on AI and fully automatic, characterized in that: include: The original production data of each system in the semiconductor fully automatic production process is obtained and stored in the production monitoring system database, and the original production data is calculated and summarized to determine the abnormal situation of the current fully automatic running state of each machine group, and the running process steps of each production scenario are generated; Generate corresponding visual monitoring screens based on the steps of the delivery process of each production scenario; Generate corresponding production monitoring systems according to different functional areas to keep the operating procedures of each functional area independent.

2. The AI-based and fully automatic semiconductor production monitoring method according to claim 1, characterized in that: The original production data of each system in the semiconductor fully automatic production process is obtained and stored in the production monitoring system database, and the original production data is calculated and summarized to determine the abnormal situation of the current fully automatic running state of each machine group, and the running process steps of each production scene are generated, which include the following: Obtain real-time cargo handling information of each system in the semiconductor fully automatic production process, and aggregate the original production data related to semiconductor production into the production monitoring system database; Based on the original production data related to the semiconductor production, the order of the running process of each scene of the fully automatic production line is used as the basis for logical judgment, and the various original production data are summarized and calculated to display the current fully automatic running status of each machine group, as well as the current running status of the machine and the preparation information for the running of the goods; The production scenarios of the fully automatic process are generated, which are the product running, daily machine testing and machine cycle testing processes, which serve as the basic logical basis of the fully automatic production monitoring system.

3. The AI-based and fully automatic semiconductor production monitoring method according to claim 2, characterized in that: The method includes intelligently calculating and summarizing various original production data through an electronic timer; wherein, if the current machine cargo running information or overhead crane handling information is abnormal, the electronic timer compares the standard deviation between the actual processing time of each cargo running step and the preset processing time, extracts the abnormal data, and notifies the corresponding problem generator through an alarm system for rapid processing.

4. The AI-based and fully automatic semiconductor production monitoring method according to claim 1, characterized in that: The corresponding visual monitoring screen is generated according to the steps of the running goods process of each production scenario obtained by sorting out, which includes: Based on the Web Socket method, the client accesses the production monitoring system database according to the preset access frequency, calls the middleware to read the production monitoring system database and returns it to the graphical interface module for automatic data refresh and display; When an alarm is displayed in the current step, the current status will change color and the corresponding problem generator will be automatically notified; Capture the preset information that requires the monitoring personnel's attention and display it.

5. The AI-based and fully automatic semiconductor production monitoring method according to claim 4, characterized in that: The method includes monitoring and displaying the advance stocking stage, the automatic stocking stage and the automatic delivery stage respectively.

6. The AI-based and fully automatic semiconductor production monitoring method according to claim 5, characterized in that: The monitoring display in the advance stocking stage includes: when the production monitoring system logically judges that the goods currently running on the machine have been completed within a preset time, whether the monitoring automation system will prepare other goods with the highest priority in advance to the carrier used to store goods near the machine in preparation for running goods; and whether the status of the wafer loading system of the monitoring machine is displayed in normal use.

7. The AI-based and fully automatic semiconductor production monitoring method according to claim 5, characterized in that: The monitoring display during the automatic delivery phase includes any one or more combinations of the following scenarios: Scenario 1: When the wafer loading system of the current machine is idle and there are goods to be transported, but the automation system has not dispatched them, the production monitoring system sends a self-check command to the real-time dispatch system; Scenario 2: The automation system dispatches goods to the current machine, but if the wafer loading system of the machine still shows that it is idle for a certain period of time, a self-check command is sent to the overhead crane system to check whether the goods handling command has not been executed; Scenario 3: When the goods have been transported to the wafer loading system of the machine but the wafer group status still shows the waiting state after exceeding the preset time, the production monitoring system sends a self-check command to the machine automation system to check the communication connection status; Scenario 4: If the machine is constantly running out of stock and the time it takes exceeds the preset range, the production monitoring system will send a self-check command to the machine.

8. An AI-based and fully automatic semiconductor production monitoring device, characterized in that: include: The data aggregation module is used to obtain the original production data of each system in the semiconductor fully automatic production process and store it in the production monitoring system database, calculate and aggregate the original production data to determine the abnormal situation of the current fully automatic running state of each machine group, and generate the running process steps for each production scenario; The visualization module is used to generate corresponding visualization monitoring screens according to the steps of the delivery process of each production scenario; The production monitoring module is used to generate corresponding production monitoring systems according to different functional areas, so that the operation procedures of each functional area remain independent.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the AI-based and fully automatic semiconductor production monitoring method described in any one of claims 1 to 7 is implemented.

10. An electronic terminal, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the terminal executes the AI-based and fully automatic semiconductor production monitoring method as described in any one of claims 1 to 7.

Images