Material management method and material management system

Abstract

A material management method and a material management system method are disclosed. The material management method includes storing a carrier containing a material in a storage device, recording environmental data of the storage device to a database while the material is in the storage device, generating a forecast of the material in the carrier based on the environmental data, receiving a request for the material from a semiconductor manufacturing tool, and providing the carrier to the semiconductor manufacturing tool based on the forecast.

Description

Technical Field

[0001] This disclosure relates to a material management method and a material management system, and specifically to a material management method and a material management system for use in the semiconductor field. Background Technology

[0002] The semiconductor integrated circuit (IC) industry has experienced exponential growth. Technological advancements in IC materials and design have led to the production of several generations of ICs, each with smaller and more complex circuitry than the previous generation. In the evolution of ICs, functional density (i.e., the number of interconnected devices per chip area) has generally increased, while geometry (i.e., the smallest component (or pipeline) that can be produced using manufacturing processes) has decreased. This scaling down process typically provides benefits by increasing production efficiency and reducing associated costs. This scaling down also increases the complexity of handling and manufacturing ICs.

[0003] Materials management involves tracking, analyzing, and fulfilling the various chemicals and other production materials used in numerous semiconductor manufacturing operations. Materials are typically scrapped after their expiration date to avoid yield degradation or potential damage to sensitive processing tools. Summary of the Invention

[0004] According to embodiments disclosed herein, a material management method includes: storing a carrier containing material in a storage device; recording environmental data of the storage device to a database while the material is in the storage device; generating a forecast of the material in the carrier based on the environmental data; receiving a request for the material from a semiconductor manufacturing tool; and providing the carrier to the semiconductor manufacturing tool based on the forecast.

[0005] According to embodiments of this disclosure, a material management method includes: mounting a material-containing carrier onto a manufacturing tool for processing semiconductor wafers; writing environmental data of the manufacturing tool into a database during carrier mounting; generating a forecast of the material in the carrier based on the environmental data; and removing the carrier from the manufacturing tool before the material in the carrier is depleted based on the forecast.

[0006] According to embodiments disclosed herein, a material management system includes a carrier, a storage device, at least one environmental sensor, at least one safety sensor, a database, and a microcontroller unit. The carrier is configured to contain material and includes at least one tag. The storage device is configured to store the carrier and includes at least one reader configured to read the tag. The at least one environmental sensor is configured to generate environmental data corresponding to the at least one storage device. The at least one safety sensor is configured to generate safety data corresponding to the at least one carrier or storage device. The database is configured to store the environmental data and the safety data. The microcontroller unit is configured to predict at least one quality parameter or safety parameter of the material based on the environmental data and the safety data. Attached Figure Description

[0007] The following detailed description, taken in conjunction with the accompanying drawings, will best convey the various aspects of this disclosure. It should be noted that, in accordance with industry standard practice, the features are not drawn to scale. In fact, the dimensions of the features may be arbitrarily increased or decreased for clarity of explanation.

[0008] Figures 1A to 1D This is a view of a material management system according to an embodiment of the present disclosure.

[0009] Figures 2A to 2B This is a view of the processes for managing materials according to various aspects of this disclosure.

[0010] Figures 3A to 3C A view illustrating the methods for forecasting material quality / safety according to various aspects of this disclosure.

[0011] Explanation of icon numbers

[0012] 100: Integrated Circuit Manufacturing System / Materials Management System;

[0013] 120: Material supplier;

[0014] 121, 1430: Carrier;

[0015] 122, 3354C: Materials;

[0016] 125: Information;

[0017] 130: Warehouse;

[0018] 132: Storage device;

[0019] 134: RFID reader;

[0020] 135: Warehouse information;

[0021] 137: Environmental and / or quality information;

[0022] 140: IC manufacturer / producer / factory;

[0023] 142: Temporary storage area / stacker;

[0024] 144: Chip manufacturing tools;

[0025] 146: Semiconductor wafer;

[0026] 148: Material installation port;

[0027] 150: Data Center;

[0028] 152: Database;

[0029] 160: IC device;

[0030] 400, 410, 420, 430, 500, 510, 520, 530, 3410, 3420, 3430: Operation;

[0031] 401, 501, 3400: Process;

[0032] 1000: IC manufacturing process;

[0033] 1320: Storage room;

[0034] 1321: Outer Gate;

[0035] 1322: Shelf;

[0036] 1323: Inner door;

[0037] 1324: Drainage outlet;

[0038] 1325: Interlock;

[0039] 1326: Leak detector;

[0040] 1400: Processing chamber;

[0041] 1410: Access interface;

[0042] 1420: Carrier platform;

[0043] 1425: Temporary information;

[0044] 1445: Tool Information;

[0045] 1450: Access point;

[0046] 1485: Tool loading information;

[0047] 3224: System;

[0048] 3302: Analysis Model;

[0049] 3304: Training module;

[0050] 3306: Training dataset;

[0051] 3308: Historical security data;

[0052] 3310: Historical environmental conditions data;

[0053] 3312: Resource processing;

[0054] 3314: Memory resources;

[0055] 3316: Communication resources;

[0056] 3318: Historical process results data;

[0057] 3324: Control system;

[0058] 3352: Material condition matrix / Reflector condition matrix;

[0059] 3354: Data vector / data field;

[0060] 3356a: First neural layer;

[0061] 3356b: Second neural layer;

[0062] 3356c: Third neural layer;

[0063] 3356d: Neural layer;

[0064] 3356e: Final neural layer;

[0065] 3358: Node;

[0066] 3368, 3370: Data values;

[0067] 3372: Error value. Detailed Implementation

[0068] The following disclosure provides numerous different embodiments or examples for implementing various features of the provided subject matter. Specific examples of components and arrangements are described below to simplify this disclosure. These are, of course, merely examples and are not intended to be limiting. For example, in the following description, the formation of a first feature on or on a second feature may include embodiments where the first and second features are formed in direct contact, and may also include embodiments where an additional feature may be formed between the first and second features so that the first and second features do not need to be in direct contact. Furthermore, reference numerals and / or letters may be repeated in various instances of this disclosure. This repetition is for the purpose of simplicity and clarity and does not, in itself, define the relationship between the various embodiments and / or configurations discussed.

[0069] Additionally, for ease of description, spatially relative terms such as “below,” “under,” “lower,” “above,” “upper,” and the like may be used herein to describe the relationship between one element or feature and another, as shown in the figures. Besides the orientations depicted in the figures, spatially relative terms are intended to cover different orientations of the device during use or operation. The device may be oriented in other ways (rotated 90 degrees or in other orientations), and the spatially relative descriptive terms used herein shall be interpreted accordingly.

[0070] For ease of description, terms such as “about,” “approximately,” “substantially,” and the like are used herein. Those skilled in the art will be able to understand and derive the meaning of such terms. For example, “about” may indicate a variation in dimensions of 20%, 10%, 5%, or the like, but other values ​​may be used where appropriate. Large features (e.g., the longest dimension of a semiconductor fin) may have variations of less than 5%, while very small features (e.g., the thickness of an interface layer) may have variations of up to 50%, and both types of variations may be indicated by the term “about.” “Substantially” is generally more stringent than “about,” making variations of 10%, 5%, or less than 5% appropriate, but not limited to these. A “substantially planar” feature may have variations within 10% or less of a straight line. A material having a “substantially constant concentration” may have concentration variations along one or more dimensions within 5% or less of 5%. Again, those skilled in the art will be able to understand and derive the appropriate meaning of such terms based on their understanding of the industry, current manufacturing techniques, and the like.

[0071] Semiconductor manufacturing typically involves forming electronic circuits through multiple depositions, etchings, annealings, and / or implantations of material layers, thereby creating a stacked structure containing numerous semiconductor devices and interconnects. Scale-down (shrinkage) is a technique for fitting an increasingly larger number of semiconductor devices into a single area. However, scale-down becomes increasingly difficult at advanced technology nodes. The patterning of photoresist layers forms the basis for etching features that are smaller and more tightly packed together. Therefore, from a materials management perspective, photoresist quality becomes increasingly important.

[0072] The embodiments disclosed herein include methods and systems for managing materials (e.g., photoresist) to ensure freshness, safety, and timely delivery, which improve yield and reduce tool downtime. Material management systems lack real-time responsiveness when managing raw material quality and safety. The material management systems disclosed herein are capable of responding substantially in real-time when managing raw material quality and safety. Intelligent and purposeful use of smart tags and responsive systems effectively prevents material aging and contamination. Environmental sensing and big data collection and forecasting also unlock improved quality control, material tracking, production reliability, data mining, and intelligent control, while significantly reducing operator error.

[0073] Figure 1A This is a block diagram of an integrated circuit (IC) manufacturing system 100 (or “material management system 100”) and its associated IC manufacturing process according to at least one embodiment of the present disclosure. Figure 1B A block diagram illustrating an IC manufacturing process 1000 according to various embodiments is shown in another view. Figures 2A to 2B This is a flowchart of a process for manufacturing an IC device according to various embodiments.

[0074] exist Figure 1AIn this system, IC manufacturing system 100 (hereinafter referred to as "System 100") includes entities that interact with each other in manufacturing and / or services related to manufacturing IC devices 160, such as material suppliers 120, warehouses 130, IC manufacturers / fabs ("fab") 140, and data centers 150. Entities in System 100 are connected via a communication network. In some embodiments, the communication network is a single network. In some embodiments, the communication network is a variety of different networks, such as a corporate intranet and the Internet. The communication network includes wired and / or wireless communication channels. In some embodiments, the communication network includes short-range asset tracking hardware and software, such as radio-frequency identification (RFID), Bluetooth Low Energy (BLE), Wi-Fi, ultra-wideband (UWB), or the like. In some embodiments, the communication network includes wide-range asset tracking hardware and software, such as low-power wide-area network (LPWAN), Long-Term Evolution (LTE), 5th generation (5G), Global Positioning System (GPS), or the like. Each entity interacts with one or more other entities and provides services to one or more other entities and / or receives services from one or more other entities. In some embodiments, one or more of material supplier 120, warehouse 130, IC manufacturing plant 140, and data center 150 are owned by a single, larger company. In some embodiments, one or more of material supplier 120, warehouse 130, IC manufacturing plant 140, and data center 150 coexist in a shared facility and use shared resources.

[0075] refer to Figure 1A and Figure 1B Material supplier 120 produces material 122. In some embodiments, material 122 is photoresist; however, other production materials besides or in lieu of photoresist may be produced by material supplier 120. For example, material supplier 120 may design, manufacture, and / or distribute materials for photolithography, such as photoresist, antireflective coating, outer coating, developer, remover, polymer, stripper, or the like. In some embodiments, material supplier 120 further or alternatively designs and / or manufactures materials for planarization (e.g., chemical mechanical planarization), such as slurries, cleaning agents, or the like. In some embodiments, material supplier 120 further or alternatively designs and / or manufactures materials for encapsulation, such as adhesives, encapsulants, thermal compounds, or the like.

[0076] Material supplier 120 may further encapsulate material 122 in a container, such as in a carrier 121, which is, for example, a bottle made of glass, plastic, or another suitable material. In some embodiments, carrier 121 has a volume of less than about 100 liters, less than about 80 liters, less than about 50 liters, or another suitable volume. In some embodiments, the volume of carrier 121 is greater than 100 liters. Material supplier 120 may further label the container. In some embodiments, the label is a read-only label, such as a barcode, Quick Response (QR) code, or the like. In some embodiments, the label is a read / write label, such as an RFID tag, Near-Field Communications (NFC) tag, or the like. In some embodiments, the container is labeled with more than one label, such as a read-only label and a read / write label. Figure 1B As illustrated, in some embodiments, the label contains information 125, such as an item identifier, batch identifier, lot identifier, supplier identifier, expiration date, unique identifier (ID), or the like. In some embodiments, the material supplier 120 writes the information 125 contained in the label into a database 152 of the data center 150, such as... Figure 1A shown in.

[0077] In some embodiments, carrier 121 includes at least one safety mechanism in / on carrier 121, which may include a drop protection mechanism, a leak isolation mechanism, a venting mechanism, and / or an air purification mechanism. In some embodiments, when any of the safety mechanisms is activated, information regarding the activation of the safety mechanism (e.g., event time, event measurement, or the like) is recorded in database 152. The information can be used to predict the expiration and / or safety of material 122. In some embodiments, expiration is related to the aging of material 122 attributable to time and can also be accelerated by exposure to a wide range of environmental conditions (including temperature, pressure, light, humidity, and the like).

[0078] In some embodiments, material 122 is transported from material supplier 120 to warehouse 130 in a transport vehicle. In some embodiments, travel information is recorded in database 152, including one or more of real-time location, route, travel distance, travel duration, and / or other suitable travel parameters. For example, the transport vehicle may be equipped with an RFID reader and a GPS (or other navigation system) receiver. When material 122 enters the transport vehicle (e.g., at material supplier 120), the RFID reader identifies material 122 via an RFID tag associated with material 122 and generates an entry timestamp indicating the time when material 122 entered the transport vehicle. In some embodiments, the transport vehicle includes an environmental control and / or monitoring system. The environmental control and / or monitoring system may control and / or monitor temperature, air cleanliness, light, vibration, and other suitable environmental parameters. While the transport vehicle is transporting materials from material supplier 120, the transport vehicle may record environmental parameters to upload to database 152. In some embodiments, the upload is performed in real time along the transport route. In some embodiments, the upload is performed in batches after arrival at material supplier 120 or at appropriate times thereafter. Upon arrival at warehouse 130, when material 122 leaves the transport vehicle, the RFID reader can again identify material 122 through the RFID tag associated with material 122 and generate a departure timestamp indicating the time when material 122 left the transport vehicle.

[0079] Warehouse 130 includes storage device 132. Figure 1C The diagram illustrates a storage device 132 according to various embodiments. In some embodiments, a warehouse 130 performs material intake, storage, and fulfillment. The warehouse 130 receives materials 122 from a material supplier 120 and may perform at least one intake inspection, including inspection for quality, safety, or other suitable parameters. In some embodiments, the intake inspection includes obtaining information 125 about the material 122 by scanning a tag. In some embodiments, obtaining information 125 includes decoding information 125 (e.g., information 125 encoded and stored in the tag itself) of images, text, or other data immediately received from the scanned tag. In some embodiments, obtaining information 125 includes decoding at least a unique ID of images, text, or other data immediately received from the scanned tag, querying a database 152 by sending a query containing at least a unique ID to a data center 150, and receiving information 125 from the database 152. In some embodiments, information 125 includes an item identifier, a batch identifier, a lot identifier, a supplier identifier, an expiration date, or the like, as described above.

[0080] Based on information 125 received from the label and / or database 152, warehouse 130 may accept material 122. In some embodiments, if a violation is found in any of the information 125 of material 122, then warehouse 130 may reject material 122. For example, if material 122 is mislabeled, for example, the item identifier does not match the known physical appearance of material 122, then warehouse 130 may determine that an incorrect label has been applied to material 122 and request that material 122 be returned to material supplier 120. In some embodiments, if no violation is found, then warehouse 130 may accept material 122.

[0081] The accepted material 122 is stored in the storage device 132, corresponding to Figure 2A The process 401 shown is in operation 400. After material 122 is accepted, warehouse 130 can update database 152 to record warehouse information 135 (see...). Figure 1B The warehouse information 135 may include the receiving time. The warehouse information 135 may further include the retrieval time, storage device identifier (ID), and other suitable information relating to the storage device 132. The receiving time may include the date and time when material 122 is received at warehouse 130. Material 122 is stored in storage device 132, which in some embodiments may be or include storage chamber 1320 and interlock 1325. In some embodiments, storage device 132 includes one or more shelves 1322 in storage chamber 1320. In some embodiments, shelves 1322 are enclosed in a cabinet, such as a refrigeration unit, which may maintain a temperature below 0°C, but depending on the type of material 122 stored therein, a cabinet maintaining a higher temperature may also be appropriate. In some embodiments, each shelf 1322 includes a weight sensor (not shown separately) for measuring the weight load on which an object (e.g., material 122) is placed on the shelf 1322.

[0082] Storage device 132 may include an RFID reader 134, enabling accurate records of how long material 122 has been stored in storage device 132 to be maintained. In some embodiments, RFID reader 134 communicates with database 152. In some embodiments, when RFID reader 134 detects and / or reads a tag on material 122 and determines that material 122 is entering storage device 132, RFID reader 134 associates an entry timestamp with material 122. RFID reader 134 may update database 152 to record an entry timestamp associated with a storage device ID, which uniquely identifies the storage device 132 storing material 122. In some embodiments, storage device ID includes the location of storage device 132. In some embodiments, location includes building / facility name / identifier, building / facility floor, building / facility room, and / or one or more other suitable identification values. In some embodiments, storage device ID further includes a unique storage unit identifier. In some embodiments, the unique storage unit identifier includes the model and / or type of storage device 132, the condition of storage device 132 (e.g., age, maintenance records, or the like), the function of storage device 132 (e.g., leak detection), and the like.

[0083] Storage device 132 may include environmental, quality, security, and access monitoring and / or management (e.g., control). In some embodiments, storage device 132 includes environmental and / or quality control and / or monitoring, including temperature, hydrogen potential ("potential of hydrogen; pH"), humidity, light, vibration, electrostatic discharge (ESD), cleanliness, leakage, pressure, particles, and other suitable controls and / or monitoring. In some embodiments, storage device 132 periodically records environmental and / or quality information 137 corresponding to the environmental and / or quality control and / or monitoring just described into database 152, corresponding to... Figure 2A Operation 410 of process 401 shown. In some embodiments, periodic recording of environmental and / or quality information 137 is performed independently of the presence of material 122 in storage device 132. For example, database 152 may be a relational database, and environmental and / or quality information 137 may be stored in a first table, and entry and exit timestamps (described below with reference to staging 142) may be stored in a second table that can be linked to the first table.

[0084] In some embodiments, storage device 132 further includes security monitoring and / or control, including access monitoring and / or control. For example, material 122 may be transferred to storage device 132 by an operator (e.g., a person or robot). In some embodiments, the operator may carry a key card, key fob, or other electronically readable access device. In some embodiments, to store material 122 in storage device 132, an electronic access reader (not shown separately) reads the operator's access device and unlocks storage device 132 to receive material 122 when an authorized operator has access to storage device 132. For example, outer door 1321 of interlock 1325 may be opened while inner door 1323 of interlock 1325 is closed. After closing outer door 1321 and an optional cleaning process in interlock 1325 to remove, for example, particles, the inner door 1323 may be opened to allow operator access to transfer material 122 to storage chamber 1320. In some embodiments, the electronic access reader updates database 152 with operator information stored on and / or corresponding to operator information stored thereon. In some embodiments, the operator information stored on the electronic access device includes a personnel identifier, which may include supplier / contractor company name, employee number / code, and the like.

[0085] In some embodiments, safety monitoring and / or control includes one or more safety sensors, such as weight sensors, position sensors, interlock sensors, and / or other suitable safety sensors. As previously mentioned, each shelf 1322 may include a weight sensor configured to measure the weight load of an object (e.g., material 122) on the shelf 1322. In some embodiments, the weight sensor includes at least one of a strain gauge, capacitive sensor, hydraulic sensor, pneumatic sensor, or other suitable weight sensor. In some embodiments, the weight sensor acquires periodic and / or asynchronous weight readings, and the weight readings can be recorded in a database 152 by the weight sensor or by a controller networked with the weight sensor.

[0086] A position sensor may be located on or near shelf 1322 to sense the presence or absence of material 122 at, for example, a designated area of ​​shelf 1322. In some embodiments, the position sensor includes at least a camera, a proximity sensor (e.g., an infrared sensor), or other suitable position sensor capable of detecting the presence or absence of material 122. In some embodiments, the position sensor acquires periodic and / or asynchronous position / proximity readings, and the position / proximity readings may be recorded in database 152 by the position sensor or by a controller networked with the position sensor.

[0087] An interlock sensor may be located on or near the outer door 1321 and / or the inner door 1323 to sense the state of the interlock 1325. In some embodiments, the interlock sensor includes at least one sensor capable of detecting the state of the outer door 1321 and / or the inner door 1323. For example, the state may include whether the outer door 1321 or the inner door 1323 is open or closed, or whether the interlock 1325 is sealed, whether the seal of the outer door 1321 has been broken, or whether the seal of the inner door 1323 has been broken. In some embodiments, the interlock sensor includes a magnetic contact sensor that can detect the loss of contact when the outer door 1321 or the inner door 1323 is open and / or detect the presence of contact when the outer door 1321 or the inner door 1323 is closed. In some embodiments, the interlock sensor acquires periodic and / or asynchronous interlock state readings, and the interlock state readings may be recorded in a database 152 by the interlock sensor or by a controller networked with the interlock sensor.

[0088] In some embodiments, storage device 132 stores material 122 for a period of time before it is delivered to manufacturing plant 140. In some embodiments, storage device 132 periodically updates database 152 with stored data, including temperature data, humidity data, pressure data, particle data, other environmental control data, safety data, and / or other monitoring data. For example, storage device 132 may periodically write stored data to database 152 every 1 minute, every 5 minutes, or at another suitable interval.

[0089] In some embodiments, storage device 132 may also write stored data to database 152 in a non-periodic manner (e.g., after an interruption condition is detected). In some embodiments, an interruption condition may include one or more of a security condition, an environmental condition, or other suitable conditions. For example, a security condition may include detecting a leak of material 122 in storage device 132. In some embodiments, a leak of material 122 is detected by a leak detector 1326, which collects and analyzes fluid from a drain 1324 at the floor of storage device 132. If the collected fluid contains material 122 (e.g., photoresist), the leak detector 1326 may generate security data including a timestamp corresponding to the detection of the leak and a material identifier corresponding to a chemical analysis of the fluid.

[0090] In some embodiments, environmental conditions may include temperature, humidity, pressure, particles, and other environmental controls and / or monitoring that are above or below thresholds. For example, if the temperature exceeds -5°C, quality data may be generated, including a timestamp of the detection corresponding to the temperature and the measured temperature (e.g., -3°C). Upon detection of an interruption condition (e.g., a safety condition or an environmental condition), storage device 132 may write safety data or quality data to database 152.

[0091] Writing safety or quality data to database 152 is described in terms of non-periodic (or asynchronous) updates. In some embodiments, storage device 132 may delay writing safety or quality data to database 152 so as to update database 152 synchronously with periodically updated data (e.g., temperature data, humidity data, pressure data, particle data, other environmental control data, and / or other monitoring data). In cases where data with repetitive types is written (e.g., periodic temperature data and temperature data originating from interruptions), two or more data items may be uniquely identified, for example, by a flag or other suitable identifier.

[0092] Warehouse 130 further fulfills the material 122 to manufacturing plant 140. In some embodiments, warehouse 130 receives a request from data center 150 to transfer material 122 to manufacturing plant 140. In some embodiments, the request to transfer material 122 from warehouse 130 to manufacturing plant 140 is generated by manufacturing plant 140. In some embodiments, the request is generated by data center 150. In some embodiments, manufacturing plant 140 is an IC manufacturing entity that includes one or more manufacturing facilities for manufacturing various different IC products. In some embodiments, manufacturing plant 140 is a semiconductor foundry. For example, there may be manufacturing facilities for front-end-of-line (FEOL) manufacturing of multiple IC products, while a second manufacturing facility may provide back-end-of-line (BEOL) manufacturing for interconnection and packaging of IC products, and a third manufacturing facility may provide other services to the foundry entity.

[0093] Manufacturing plant 140 includes wafer fabrication tooling 144 (hereinafter referred to as "manufacturing tooling 144") configured to perform various manufacturing operations on semiconductor wafer 146 to manufacture IC device 160. In various embodiments, manufacturing tooling 144 includes one or more of the following: wafer stepper, ion implanter, photoresist coater, process chamber (e.g., CVD chamber or LPCVD boiler), chemical-mechanical planarization (CMP) system, plasma etching system, wafer cleaning system, or other manufacturing equipment capable of performing one or more suitable manufacturing processes as discussed herein. In some embodiments, material 122 may be mounted in manufacturing tooling 144 for performing semiconductor manufacturing processes (e.g., photoresist coating of wafer 146).

[0094] Figure 1DThis is a perspective view of a manufacturing tool 144 according to various embodiments. An access port 1450 of the manufacturing tool 144 is configured to transfer a semiconductor wafer (e.g., wafer 146) into / out of a processing chamber 1400. The access port 1450 includes at least one access interface 1410, such as a door, and at least one corresponding carrier platform 1420 aligned with the corresponding access interface 1410. A carrier 1430 (which may be similar to carrier 121) holding at least one wafer (e.g., wafer 146) can be positioned on the carrier platform 1420, and the wafer can be removed from the carrier 1430 through the access interface 1410, for example, by a robotic arm. After entering the access port 1450, the wafer can be transferred to the processing chamber 1400 for at least one semiconductor manufacturing process, such as implantation, photoresist coating, annealing, deposition, etching, planarization, cleaning, or other suitable processes.

[0095] The manufacturing tool 144 further includes a material mounting port 148, which may include a door and a housing. Material 122 can be mounted in the manufacturing tool 144 by opening the door, and a carrier 121 containing material 122 is positioned in the housing, for example, by an operator. In some embodiments, the carrier 121 is further in fluid communication with the processing chamber 1400 after being mounted in the housing. For example, a sleeve or other fluid delivery conduit may be attached to the carrier 121 containing material 122 to provide fluid communication between the carrier 121 and an applicator (e.g., a nozzle) in the processing chamber 1400. In some embodiments, material 122 is photoresist, and the applicator includes a nozzle for dripping or spraying photoresist onto the wafer 146.

[0096] Before material 122 is mounted in manufacturing tool 144, the temperature of material 122 may be raised to room temperature or another suitable temperature for semiconductor manufacturing processes. In some embodiments, manufacturing plant 140 includes a temporary storage area 142 (or “stacker 142”), which may resemble storage device 132 and is used to adapt material 122 (e.g., raise its temperature) in preparation for mounting material 122 into manufacturing tool 144. When material 122 is photoresist, for example, temporary storage area 142 may have an ambient temperature above 0°C, such as room temperature or another suitable ambient temperature, to adapt the photoresist, which may be at a temperature below about 0°C after being removed from storage device 132 and transported to temporary storage area 142. Adaptation may be performed for a duration of time related to the volume of material 122, initial temperature (e.g., <0°C), and target temperature (e.g., about 20°C to about 25°C).

[0097] In some embodiments, the temporary storage area 142 may include an RFID reader, enabling accurate recording of how long material 122 is stored in the temporary storage area 142. In some embodiments, the RFID reader communicates with a database 152. In some embodiments, when the RFID reader detects and / or reads a tag on material 122 and determines that material 122 is entering the temporary storage area 142, the RFID reader associates an entry timestamp with material 122. The RFID reader may update the database 152 to record an entry timestamp associated with a temporary storage area ID that uniquely identifies the temporary storage area where material 122 is stored, the entry timestamp may be temporary storage information 1425 (see Temporary Storage Information 1425). Figure 1B Part of ).

[0098] The temporary storage area 142 may include environmental, quality, security, and access monitoring and / or management (e.g., control). In some embodiments, the temporary storage area 142 includes environmental and / or quality control and / or monitoring, including temperature, humidity, light, vibration, electrostatic discharge (ESD), and other suitable controls and / or monitoring. In some embodiments, the temporary storage area 142 periodically stores temporary information 1425 (see [link to documentation]). Figure 1B A portion of the environmental and / or quality information is recorded in database 152, which may correspond to the environmental and / or quality control and / or monitoring just described. In some embodiments, the periodic recording of environmental and / or quality information is performed independently of the presence of material 122 in temporary storage area 142. For example, database 152 may be a relational database, and environmental and / or quality information 137 may be stored in a first table, with entry and exit timestamps (described below) stored in a second table that is linked to the first table.

[0099] In some embodiments, the temporary storage area 142 further includes security monitoring and / or control, including access monitoring and / or control. For example, material 122 may be delivered to the temporary storage area 142 by an operator (e.g., a person or a robot). In some embodiments, the operator may carry a key card, key fob, or other electronically readable access device. In some embodiments, to store material 122 in the temporary storage area 142, an electronic access reader (not shown separately) reads the operator's access device and unlocks the temporary storage area 142 to receive material 122 when an authorized operator accesses it. In some embodiments, the electronic access reader updates the database 152 with operator information stored on the electronically readable access device and / or corresponding to operator information stored thereon. In some embodiments, the operator information stored on the electronically readable access device includes a personnel identifier, which may include a supplier / contractor company name, employee number / code, and the like.

[0100] The temporary storage area 142 further performs the delivery of material 122 to the manufacturing tool 144. In some embodiments, the temporary storage area 142 receives a request to transfer material 122 to the manufacturing tool 144, for example, for installation into the manufacturing tool 144, corresponding to Figure 2A Operation 430 of process 401 shown. In some embodiments, the request originates from data center 150 for transferring material 122 to manufacturing tool 144. In some embodiments, the request to transfer material 122 from storage area 142 to manufacturing tool 144 is generated by manufacturing tool 144 or its operator. In some embodiments, the request is generated by data center 150, for example, based on production plans, forecasts of material 122 being used by manufacturing tool 144, and / or other suitable parameters.

[0101] Based on reference Figures 3A to 3C In a more detailed description, the carrier 121 containing material 122 may be provided to the manufacturing tool 144. Similar to the transfer of material 122 to the temporary storage area 142, in some embodiments, upon receiving a request to transfer material 122 to the manufacturing tool 144, an operator with an electronically readable access device retrieves material 122 from the temporary storage area 142 and transfers it to the manufacturing tool 144. In some embodiments, the access performed by the operator is verified and recorded by the temporary storage area 142. In some embodiments, the retrieval time corresponding to (e.g., as detected by an RFID reader) the time when material 122 leaves the temporary storage area 142 is recorded as part of temporary storage information 1425 in a database 152. In some embodiments, after leaving the temporary storage area 142, the contents of material 122 are verified to ensure that material 122 matches the request, for example, having the same item identifier, batch identifier, and lot identifier specified in the request.

[0102] To ensure that the manufacturing tool 144 receives the correct material 122, the batch identifier of the material 122 can be retrieved and compared with the request. In some embodiments, the correctness of the material 122 is verified before it leaves the temporary storage area 142 and / or before it is installed into the manufacturing tool 144. For photoresist, the adaptation time can be further verified to ensure that the material 122 has spent sufficient time in the temporary storage area 142 to reach the adaptation temperature, such as room temperature, as described above. This avoids potential damage to the manufacturing tool 144 or negative impacts on yield that could occur due to using the material 122 at excessively low temperatures (e.g., before adaptation is achieved).

[0103] The material 122 retrieved from the temporary storage area 142 is installed in the manufacturing tool 144, corresponding to Figure 2BThe process 501 shown is in operation 500. In some embodiments, the manufacturing tool 144 includes, for example, an RFID reader at or near the material loading port 148. The RFID reader can read a tag on the carrier 121 containing material 122 and can record a loading timestamp corresponding to the time when material 122 is installed in the material loading port 148. The loading timestamp may be tool loading information 1485 (see...). Figure 1B As part of the process, the tool loading information 1485 may be recorded periodically or aperiodically / asynchronously in the database 152. For example, within seconds of an RFID reader identifying material 122, a loading timestamp may be recorded to the database 152 via the manufacturing tool 144. In some embodiments, an operator may create data items indicating that material 122 is installed in a material mounting port 148. In some embodiments, the door of the material mounting port 148 may include an access sensor, such as a magnetic contact sensor, and any opening and / or closing of the door may be recorded in the database 152. In some embodiments, the housing of the material mounting port 148 may include a proximity sensor, such as an infrared sensor, and / or a weight sensor. In some embodiments, tracking the installation of material 122 into the material mounting port 148 may include reading a tag via an RFID reader, detecting the opening of the door via an access sensor, detecting the proximity of material 122 via a proximity sensor, detecting the closing of the door via an access sensor, and / or receiving data items by the operator. In some embodiments, data associated with tracking the installation may be recorded in the database 152.

[0104] In manufacturing tool 144, tool information 1445 corresponding to material 122 (see...) Figure 1B ) can be recorded in database 152, corresponding to Figure 2B The process 501 shown is operation 510. In some embodiments, tool information 1445 includes usage time, which may include time values ​​in hours, minutes, and seconds representing the time that material 122 is present in the manufacturing tool 144. In some embodiments, usage time represents the time that material 122 is used in the manufacturing tool 144, such as the time that material 122 is consumed by the manufacturing tool 144, but does not include the time that material 122 is not consumed by the manufacturing tool 144, such as when the manufacturing tool 144 is idle or when there is no transfer of material 122 from carrier 121 to processing chamber 1400 (e.g., the outflow of material 122 from carrier 121 is substantially zero). In some embodiments, tool information 1445 further includes environmental data of the manufacturing tool 144, such as temperature, pressure, humidity, light, process parameters, or other suitable environmental data. Environmental data may be recorded periodically and / or non-periodically on a continuous basis to database 152, corresponding to Figure 2B Operation 520 of process 501 shown.

[0105] One consideration for the use of material 122 in manufacturing tooling 144 corresponds to the expiration status of material 122. By tracking environmental, quality, and safety data of material 122 from material supplier 120 to warehouse 130 and from warehouse 130 to manufacturing plant 140, a highly accurate prediction of the expiration status of material 122 can be achieved (which can correspond to...). Figure 2A Operation 430 and / or Figure 2B Operation 520) enables real-time monitoring of the expiration status of material 122 even when it is in manufacturing tool 144. In some embodiments, when material 122 expires, the supply of material 122 (e.g., outflow from carrier 121 to processing chamber 1400) can be cut off, even if expiration occurs while material 122 is in manufacturing tool 144. The carrier 121 containing material 122 can be removed from manufacturing tool 144 without being emptied (e.g., some of material 122 is still in carrier 121), which can correspond to Figure 2B Operation 530 allows for the request of new materials that have not yet expired from, for example, a staging area 142. In some embodiments, the retrieval of materials 122 from the staging area 142 can be intelligently managed by using a database 152 in conjunction with, for example, first-in-first-out (FIFO) allocation in batches, which can reduce the risk of expiration.

[0106] In some embodiments, FIFO allocation is based on forecasts of the expiration status of a number of different carriers containing material 122, such that a carrier 121, based on the forecast of containing the closest-to-expire material 122, is retrieved and transferred to the manufacturing tool 144 before other carriers with longer expiration dates are retrieved. In some embodiments, FIFO allocation takes into account production schedules. For example, if two carriers containing the same material 122 and with similar forecast expiration dates are both adapted (ready) and present in the temporary storage area 142, and the first of the two carriers has a lower remaining material 122 than the second of the two carriers, then if the production schedule indicates that a relatively low volume of forecasted material 122 will be consumed, the first carrier with the lower volume of material 122 may be retrieved before / in place of the second carrier, even if the forecasted expiration date of the first carrier is slightly later than that of the second carrier.

[0107] System 100 is illustrated as having material supplier 120, warehouse 130, IC manufacturing plant 140, or data center 150 as separate components or entities. However, it should be understood that one or more of material supplier 120, warehouse 130, IC manufacturing plant 140, or data center 150 are part of the same component or entity.

[0108] Figures 3A to 3CThis is a view illustrating forecasts corresponding to various parameters of material 122 according to various embodiments. Several forecasts may be made by a microcontroller unit (MCU) using information stored in database 152. In some embodiments, the forecasts include quality parameters (e.g., expiration) and / or safety parameters (e.g., leakage) of material 122, consumption of material 122, the order in which material 122 is transferred from warehouse 130 and / or temporary storage area 142, procurement of material 122 from material supplier 120, control / management of inventory of material 122, and / or other suitable forecasts.

[0109] Figure 3A This is a block diagram of a system 3224 according to one embodiment, which may be used for performing... Figure 2A Operation 420 or Figure 2B The control system 3224 of the operation 520 utilizes machine learning to predict the parameters corresponding to material 122.

[0110] In one embodiment, the control system 3224 includes an analysis model 3302 and a training module 3304. The training module 3304 trains the analysis model 3302 using a machine learning process. In some embodiments, the machine learning process trains the analysis model 3302 to select a carrier 121 containing material 122 based on quality and / or safety parameters. Although the training module 3304 is depicted as separate from the analysis model 3302, in practice, the training module 3304 may be part of the analysis model 3302.

[0111] The control system 3224 includes or stores training set data 3306. Training set data 3306 includes historical safety data 3308, historical environmental condition data 3310, and historical process result data 3318. Historical safety data 3308 contains data related to the safety of material 122. Historical environmental condition data 3310 contains data related to the environment in which material 122 is present. Historical process result data 3318 contains data related to the wafer quality following the manufacturing process in which material 122 is present. As will be described in more detail below, training module 3304 uses historical safety data 3308, historical environmental condition data 3310, and historical process result data 3318 to train analysis model 3302 using a machine learning process.

[0112] In one embodiment, historical safety data 3308 includes data related to safety parameters, such as location, orientation, chemical control strips, access permissions, formula management systems, drop events, leak events, discharge / purification events, or other suitable safety data. For example, thousands or millions of readings of the aforementioned safety parameters may be generated over hours or days. After each generation, the safety of material 122 can be calculated. Historical safety data 3308 contains safety parameters for each carrier 121 of material 122. Therefore, historical safety data 3308 may contain safety data for a large number of carriers of material 122. In some embodiments, safety data is generated on a run-by-run or batch-by-batch basis.

[0113] In one embodiment, historical environmental condition data 3310 includes various environmental conditions or parameters during the transport and / or storage of material 122. Therefore, for each carrier 121 of material 122 having data in historical safety data 3308, historical environmental condition data 3310 may include environmental conditions or parameters present during the transport and / or storage of material 122. For example, historical environmental condition data 3310 may include data related to temperature, pH, humidity, light, acclimatization time, vibration, ESD, cleanliness, production schedule, and / or other suitable environmental condition parameters.

[0114] In one embodiment, historical process result data 3318 includes various wafer quality parameters, directly or indirectly derived from the use of material 122 in a semiconductor manufacturing process. For example, material 122 may be used in photoresist coating processes, planarization processes, cleaning processes, deposition processes, or other suitable manufacturing processes. In some embodiments, historical process result data 3318 may include measurements of etching profiles after a photoresist coating process. Other measurements may include layer thickness, layer uniformity, roughness, cleanliness, or other suitable measurements. In some embodiments, measurements include results of electrical testing, wafer acceptance testing, optical testing, or other suitable tests, which may include pass / fail measurements, reliability measurements, data retention measurements, or the like. In some embodiments, historical process result data 3318 is associated with multiple previously processed semiconductor wafers. In some embodiments, historical process result data 3318 is associated with an individual semiconductor wafer, an individual operation of a semiconductor wafer, and / or an individual batch of semiconductor wafers.

[0115] In one embodiment, training set data 3306 links historical safety data 3308 and / or historical environmental condition data 3310 with historical process result data 3318. In other words, safety parameters in historical safety data 3308 and / or environmental parameters in environmental condition data 3310 (e.g., through labeling) are linked to measurements in historical process result data 3318. As will be explained in more detail below, the labeled training set data can be used in the machine learning process to train analytical model 3302 to generate the various forecasts mentioned above.

[0116] In one embodiment, the control system 3324 includes processing resources 3312, memory resources 3314, and communication resources 3316. Processing resources 3312 may include one or more controllers or processors. Processing resources 3312 are configured to execute software instructions, process data, make thin-film etching control decisions, perform signal processing, read data from memory, write data to memory, and perform other processing operations. Processing resources 3312 may include physical processing resources 3312 and / or virtual processing resources 3312. Processing resources 3312 may include cloud-based processing resources, including processors and servers accessed via one or more cloud computing platforms.

[0117] In one embodiment, memory resource 3314 may include one or more computer-readable storage devices. Memory resource 3314 is configured to store software instructions associated with the functionality of the control system and its components (including, but not limited to, analysis model 3302). Memory resource 3314 may store data associated with the functionality of the control system 3224 and its components. The data may include training set data 3306, current process condition data, and any other data associated with the operation of the control system 3224 or any of its components. Memory resource 3314 may include physical memory resources and / or virtual memory resources. Memory resource 3314 may include cloud-based memory resources accessed via one or more cloud computing platforms. In some embodiments, memory resource 3314 includes database 152.

[0118] In one embodiment, communication resource 3316 may include wired and wireless communication resources that facilitate communication via one or more networks, such as a wired network, a wireless network, the Internet, or a corporate intranet. Communication resource 3316 enables components of control system 3224 to communicate with each other.

[0119] Figure 3B To illustrate according to one embodiment Figure 3AA block diagram of the operational and training aspects of the analysis model 3302 is provided. As previously described, the training set data 3306 contains data related to multiple previously processed semiconductor wafers. Each previously processed semiconductor wafer is processed under specific environmental conditions, producing specific processing results. The material 122 supplier, expiration date, temperature, light, adaptation, humidity, usage time, delivery time, and / or other suitable parameters of each previously processed semiconductor wafer are formatted into a corresponding material condition matrix 3352. The material condition matrix 3352 contains multiple data vectors 3354. Each data vector 3354 corresponds to a specific parameter.

[0120] Figure 3B An example is shown where a single material condition matrix 3352 will be passed to the analysis model 3302 during the training process. Figure 3B In this example, the material condition matrix 3352 contains nine data vectors 3354, each corresponding to an environmental or safety parameter of material 122. For condition types not naturally represented by numbers, such as material 3354C, numbers may be assigned to each possible material.

[0121] The analysis model 3302 comprises multiple neural layers 3356a to 3356e. Each neural layer contains multiple nodes 3358. Each node 3358 can also be called a neuron. Each node 3358 from the first neural layer 3356a receives the data value of each data field from the reflector condition matrix 3352. Therefore, in Figure 3B In this example, each node 3358 from the first neural layer 3356a receives 36 data values ​​because the reflector condition matrix 3352 has 36 data scalars (9*4=36). Each neuron 3358 contains... Figure 3B The corresponding internal mathematical function is labeled F(x). By applying the internal mathematical function F(x) to the data values ​​from the data field 3354 of the reflector condition matrix 3352, each node 3358 of the first neural layer 3356a produces a scalar value. Further details about the internal mathematical function F(x) are provided below.

[0122] Each node 3358 of the second neural layer 3356b receives a scalar value generated by each node 3358 of the first neural layer 3356a. Therefore, in Figure 3B In this example, each node of the second neural layer 3356b receives four scalar values ​​because there are four nodes 3358 in the first neural layer 3356a. Each node 3358 of the second neural layer 3356b produces a scalar value by applying the corresponding internal mathematical function F(x) to the scalar values ​​from the first neural layer 3356a.

[0123] Each node 3358 of the third neural layer 3356c receives a scalar value generated by each node 3358 of the second neural layer 3356b. Therefore, in Figure 3B In the example, each node of the third neural layer 3356c receives five scalar values ​​because there are five nodes 3358 in the second neural layer 3356b. Each node 3358 of the third neural layer 3356c produces a scalar value by applying the corresponding internal mathematical function F(x) to the scalar values ​​of the nodes 3358 from the second neural layer 3356b.

[0124] Each node 3358 of neural layer 3356d receives a scalar value generated by each node 3358 of the previous neural layer (not shown). Each node 3358 of neural layer 3356d generates a scalar value by applying the corresponding internal mathematical function F(x) to the scalar value of the node 3358 from the second neural layer 3356b.

[0125] The final neural layer contains only a single node 3358. The final neural layer receives scalar values ​​generated by each node 3358 of the previous neural layer 3356d. By applying the mathematical function F(x) to the scalar values ​​received from the nodes 3358 of the neural layer 3356d, the nodes 3358 of the final neural layer 3356e produce data values ​​3368.

[0126] exist Figure 3B In one example, data value 3368 corresponds to the predicted expiration of the carrier 121 of material 122, generated from data corresponding to values ​​contained in the material condition matrix 3352. In other embodiments, the final neural layer 3356e may generate multiple data values, each corresponding to a specific material property (e.g., the quality, safety, or other properties of material 122). In some embodiments, the final neural layer 3356e may generate data values ​​corresponding to the various forecasts described above. The final neural layer 3356e will contain a corresponding node 3358 for each output data value to be generated. In the case of a predicted expiration, in one instance, the engineer may provide a constraint specifying that the predicted expiration 3368 is within a selected range (e.g., greater than 1 hour). The analysis model 3302 will adjust the internal function F(x) to ensure that the data value 3368 corresponding to the predicted expiration will be within the specified range.

[0127] During the machine learning process, the analysis model compares the predicted due dates in data value 3368 with the actual due dates of material 122 as indicated by data value 3370. As previously explained, the training set data 3306 contains historical process result data indicating the characteristics of the semiconductor wafer produced by the manufacturing process for each set of historical environmental condition data. Therefore, data field 3370 contains the actual due dates of material 122 produced by the manufacturing process reflected in material condition matrix 3352. Analysis model 3302 compares the predicted due dates from data value 3368 with the actual due dates from data value 3370. Analysis model 3302 generates an error value 3372 indicating the error or difference between the predicted due dates from data value 3368 and the actual due dates from data value 3370. Analysis model 3302 is trained using error value 3372.

[0128] The training of model 3302 can be more fully understood by discussing the internal mathematical function F(x). Although all nodes 3358 are labeled with the internal mathematical function F(x), the mathematical function F(x) for each node is unique. In one instance, each internal mathematical function has the following form:

[0129] F(x)=x1*w1+x2*w2+…xn*w1+b.

[0130] In the above formulas, each value x1 to xn corresponds to a data value received from node 3358 in the previous neural layer, or, in the case of the first neural layer 3356a, each value x1 to xn corresponds to a corresponding data value from data field 3354 of the reflector condition matrix 3352. Therefore, for a given node, n equals the number of nodes in the previous neural layer. Values ​​w1 to wn are scalar weights associated with the corresponding nodes from the previous layer. Analysis model 3302 selects the values ​​of weights w1 to wn. The constant b is a scalar bias value and can also be multiplied by the weights. The values ​​generated by node 3358 are based on weights w1 to wn. Therefore, each node 3358 has n weights w1 to wn. Although not illustrated above, each function F(x) may also contain an activation function. The sum described in the above formulas is multiplied by the activation function. Instances of activation functions may include rectified linear unit (ReLU) functions, sigmoid functions, hyperbolic tension functions, or other types of activation functions.

[0131] After the error value 3372 has been calculated, the analysis model 3302 adjusts the weights w1 to wn for various nodes 3358 in various neural layers 3356a to 3356e. After adjusting the weights w1 to wn, the analysis model 3302 again provides the reflector condition matrix 3352 to the input neural layer 3356a. Because the weights are different for various nodes 3358 in the analysis model 3302, the predicted reflectivity 3368 will differ from the previous iteration. The analysis model 3302 then generates the error value 3372 again by comparing the actual reflectivity 3370 with the predicted reflectivity 3368.

[0132] Analysis model 3302 readjusts the weights w1 associated with various nodes 3358 to weights wn. Analysis model 3302 then processes the material condition matrix 3352 again, generating the predicted expiration 3368 and associated error value 3372. The training process involves iteratively adjusting the weights w1 to wn until the error value 3372 is minimized.

[0133] Figure 3B A single material condition matrix 3352 is shown being passed to the analysis model 3302. In practice, the training process includes passing a large number of material condition matrices 3352 through the analysis model 3302, generating a predicted expiration date 3368 for each material condition matrix 3352, and generating an associated error value 3372 for each predicted expiration date. The training process may also include generating an aggregated error value indicating the average error for all predicted expiration dates of a batch of material condition matrices 3352. After processing each batch of material condition matrices 3352, the analysis model 3302 adjusts the weights w1 to wn. The training process continues until the average error across all material condition matrices 3352 is less than a selected threshold tolerance. When the average error is less than the selected threshold tolerance, the analysis model 3302 is trained to accurately predict the expiration date of material 122 based on environmental and / or safety conditions. The analysis model 3302 can then be used to predict expiration dates and select environmental and / or safety conditions that will extend the expiration dates. During the use of the trained model 3302, an environmental condition vector or matrix representing the current environmental conditions of the current material 122 and having a similar format to the material condition matrix 3352 is provided to the trained analysis model 3302. The trained analysis model 3302 can then predict the expiration of the material 122 caused by those environmental conditions.

[0134] Based on about Figure 3BA specific example of the neural network-based analysis model 3302 has been described. However, other types of neural network-based analysis models, or analysis models of other types besides neural networks, may be used without departing from the scope of this disclosure. Furthermore, without departing from the scope of this disclosure, the neural network may have different numbers of neural layers with different numbers of nodes. Additionally, the neural network-based analysis model 3302 may generate any of the previously described forecasts, such as the quality parameters (e.g., expiration) and / or safety parameters (e.g., leakage) of material 122, the consumption of material 122, the order in which material 122 is transferred from warehouse 130 and / or temporary storage area 142, the procurement of material 122 from material supplier 120, the control / management of the inventory of material 122, and / or other suitable forecasts.

[0135] Based on the above, and with reference to Figure 3C The process 3400 for managing material 122 based on the neural network-based analysis model 3302 may include (e.g., on a run-by or batch-by-batch basis) forecasting of quality and / or safety parameters of the carrier 121 containing material 122, corresponding to operation 3410. The process 3400 may further include accepting or rejecting the carrier 121 based on the forecast generated in operation 3410, corresponding to operation 3420. In operation 3430, the carrier 121 may be analyzed, for example, to determine whether the material 122 contained therein has expired. Based on the analysis performed in operation 3430, the neural network-based analysis model 3302 may be updated to improve the forecasting of future carrier quality / safety parameters in operation 3410.

[0136] The embodiments offer advantages. Methods and systems for managing materials 122, such as photoresist, ensure freshness, safety, and timely fulfillment. They improve yield and reduce tool downtime. The material management system can respond largely in real time when managing raw material quality and safety. Intelligent and purposeful use of smart tags and response systems effectively prevents material aging and contamination. Environmental sensing and big data collection and forecasting also improve quality control, material tracking, production reliability, data mining, and intelligent control, while reducing operator error.

[0137] According to at least one embodiment, a method includes: storing a carrier containing material in a storage device; recording environmental data of the storage device to a database while the material is in the storage device; generating a forecast of the material in the carrier based on the environmental data; receiving a request for the material from a semiconductor manufacturing tool; and providing the carrier to the semiconductor manufacturing tool based on the forecast.

[0138] According to at least one embodiment, the material management method further includes: recording the safety data of the carrier into a database.

[0139] According to at least one embodiment, the material management method records security data during at least one of the following periods: (1) transporting a carrier from a material supplier to a storage device; (2) storing the carrier in the storage device; or (3) transporting the carrier from the storage device to a semiconductor manufacturing tool.

[0140] According to at least one embodiment, transporting the carrier from the storage device to the semiconductor manufacturing tool includes: transporting the carrier from the storage device to a staging area, and transporting the carrier from the staging area to the semiconductor manufacturing tool.

[0141] According to at least one embodiment, the safety data includes activation information of at least one of the carrier's anti-drop mechanism, leak isolation, venting mechanism, or air purification mechanism.

[0142] According to at least one embodiment, the material is photoresist. The initial temperature of the storage device is less than about 0°C.

[0143] According to at least one embodiment, the material management method further includes recording the adaptation time of the material in a temporary storage area having a second temperature of about 20°C to about 25°C.

[0144] According to at least one embodiment, a method includes: mounting a carrier containing material onto a manufacturing tool for processing a semiconductor wafer; writing environmental data of the manufacturing tool into a database during the mounting of the carrier; generating a forecast of the material in the carrier based on the environmental data; and removing the carrier from the manufacturing tool before the material in the carrier is depleted based on the forecast.

[0145] According to at least one embodiment, generating a forecast includes predicting the expiration date of materials based on environmental data.

[0146] According to at least one embodiment, the material management method further includes removing the carrier from the temporary storage area based on a forecast before the second carrier.

[0147] According to at least one embodiment, the first predicted expiration of the carrier is earlier than the second predicted expiration of the second carrier, and the carrier is removed before the second carrier.

[0148] According to at least one embodiment, mounting the carrier includes mounting a carrier containing photoresist into a photoresist coating machine.

[0149] According to at least one embodiment, the material includes photoresist, antireflective coating, overlay layer, developer, remover, polymer, stripper, paste, cleaner, adhesive, encapsulant, or thermal compound. According to at least one embodiment, a system includes a carrier, a storage device, at least one environmental sensor, at least one safety sensor, a database, and a microcontroller unit. The carrier is configured to contain the material and includes at least one tag. The storage device is configured to store the carrier and includes at least one reader configured to read the tag. The at least one environmental sensor is configured to generate environmental data corresponding to at least the storage device. The at least one safety sensor is configured to generate safety data corresponding to at least the carrier or the storage device. The database is configured to store the environmental data and the safety data. The microcontroller unit is configured to predict at least one quality parameter or safety parameter of the material based on the environmental data and the safety data.

[0150] According to at least one embodiment, the storage device includes a freezer.

[0151] According to at least one embodiment, the storage device includes an interlock. The security sensor includes an interlock sensor configured to generate information corresponding to the interlock.

[0152] According to at least one embodiment, the microcontroller unit is configured to generate a neural network-based analysis module. The prediction is based on said neural network-based analysis module.

[0153] According to at least one embodiment, the microcontroller unit is further configured to accept or reject a carrier based on the at least one quality parameter or safety parameter.

[0154] According to at least one embodiment, the at least one environmental sensor includes at least one of a temperature sensor, a hydrogen potential (pH) sensor, a humidity sensor, a light sensor, a vibration sensor, an electrostatic discharge (ESD) sensor, a cleanliness sensor, a leakage sensor, a pressure sensor, or a particle sensor.

[0155] According to at least one embodiment, the storage device includes a drain configured to receive material when the carrier has a leak, and a leak detector configured to detect the leak in fluid communication with the drain.

[0156] The foregoing outlines features of several embodiments to enable those skilled in the art to better understand various aspects of this disclosure. Those skilled in the art will understand that this disclosure can be readily used as a basis for designing or modifying other processes and structures for performing the same purposes and / or achieving the same advantages of the embodiments described herein. Those skilled in the art will also recognize that such equivalent constructions do not depart from the spirit and scope of this disclosure, and that various changes, substitutions, and modifications can be made herein without departing from the spirit and scope of this disclosure.

Claims

1. A material management method, comprising: A carrier containing photoresist is stored in a storage device, the first temperature of which is less than 0°C; First environmental data and first security data related to the photoresist are recorded by transporting the carrier from the material supplier to the storage device; When the photoresist is in the storage device, the second environmental data of the storage device is recorded to the database; The photoresist in the storage device records the second security data of the carrier into the database; Record the adaptation time of the photoresist in a temporary storage area with a second temperature of 20°C to 25°C; Based on the first environmental data, the second environmental data, the first security data, and the second security data, a forecast of the expiration of the photoresist in the carrier is generated; Receive a request for the photoresist from semiconductor manufacturing tools; as well as The carrier is provided to the semiconductor manufacturing tool based on the predicted expiration date of the photoresist.

2. The material management method according to claim 1, further comprising: Third security data is recorded during the transport of the carrier from the storage device to the semiconductor manufacturing tool.

3. The material management method of claim 2, wherein the transport of the carrier from the storage device to the semiconductor manufacturing tool includes transporting the carrier from the storage device to the temporary storage area and transporting the carrier from the temporary storage area to the semiconductor manufacturing tool.

4. The material management method according to claim 1, wherein the second safety data includes activation information of at least one of the carrier's anti-drop mechanism, leakage isolation mechanism, exhaust mechanism, or air purification mechanism.

5. The material management method according to claim 1, further comprising: An analysis module, trained with historical environmental and security data, indicates the expiration date of the photoresist to predict its expiration after transportation and storage. The forecast mentioned above is generated based on a neural network.

6. The material management method according to claim 1, wherein the first environmental data includes at least one of temperature data, hydrogen potential data, humidity data, light data, vibration data, electrostatic discharge data, cleanliness data, leakage data, pressure data, or particle data.

7. A material management method, comprising: An analysis module, trained with historical environmental and security data, provides information on the expiration date of the photoresist to predict its expiration after transportation and storage. The carrier containing the first photoresist is mounted onto a manufacturing tool used to process semiconductor wafers; During the installation of the carrier, the environmental data of the manufacturing tool is written into the database; The microcontroller unit generates a prediction of the first photoresist in the carrier based on the environmental data, the historical environmental condition data, and the historical security data; as well as The carrier is removed from the manufacturing tool before the first photoresist in the carrier is exhausted based on the predicted expiration date.

8. The material management method according to claim 7, wherein the environmental data includes at least one of temperature data, hydrogen potential data, humidity data, light data, vibration data, electrostatic discharge data, cleanliness data, leakage data, pressure data, or particle data.

9. The material management method according to claim 7, further comprising retrieving the carrier from the temporary storage area based on the forecast before the second carrier.

10. The material management method of claim 9, wherein the carrier is removed before the second carrier based on a first predicted expiration date of the carrier being earlier than a second predicted expiration date of the second carrier.

11. The material management method according to claim 7, wherein mounting the carrier comprises mounting the carrier containing photoresist into a photoresist coating machine.

12. The material management method of claim 7, further comprising recording the adaptation time of the photoresist in the temporary storage area, wherein the forecast is based on the adaptation time.

13. A materials management system, comprising: A carrier configured to contain material and including at least one label; A storage device configured to store the carrier, and including at least one reader configured to read the tag; At least one environmental sensor is configured to generate environmental data corresponding to at least the storage device; At least one security sensor is configured to generate security data corresponding to at least the carrier or the storage device; The database is configured to store the environmental data and the security data; as well as The microcontroller unit is configured to predict at least one quality parameter or safety parameter of the material based on the environmental data and the safety data.

14. The material management system of claim 13, wherein the storage device includes a freezer.

15. The material management system of claim 14, wherein the storage device includes an interlock, and the security sensor includes an interlock sensor configured to generate information corresponding to the interlock.

16. The material management system of claim 13, wherein the microcontroller unit is configured to generate a neural network-based analysis module, and the prediction is based on the neural network-based analysis module.

17. The material management system of claim 13, wherein the microcontroller unit is further configured to accept or reject the carrier based on the at least one quality parameter or safety parameter.

18. The material management system of claim 13, wherein the at least one environmental sensor comprises at least one of a temperature sensor, a hydrogen potential sensor, a humidity sensor, a light sensor, a vibration sensor, an electrostatic discharge sensor, a cleanliness sensor, a leakage sensor, a pressure sensor, or a particle sensor.

19. The material management system of claim 13, wherein the storage device includes a drain configured to receive the material when the carrier has a leak, and a leak detector configured to detect the leak in fluid communication with the drain.

20. The material management system of claim 13, wherein the material comprises photoresist, antireflective coating, overlay, developer, remover, polymer, stripper, paste, cleaner, adhesive, encapsulant, or thermal compound.

Images