Sustainability Monitoring Platform Including Sensor Support

Abstract

In an embodiment, the method includes receiving, by a processing device, first sensor data generated by a plurality of sensors of a processing chamber of a manufacturing system during execution of a manufacturing process. The method includes receiving, by the processing device, second sensor data generated by one or more external sensors that are not components of the processing chamber during execution of the manufacturing process. The method includes determining, by the processing device, environmental resource usage data indicative of an environmental resource consumption amount of a manufacturing process executed in the processing chamber based on the first sensor data and the second sensor data. The method includes providing, by the processing device, the environmental resource usage data for display on a graphical user interface (GUI).

Description

Technical Field

[0001] This specification generally relates to the environmental impact of manufacturing equipment such as semiconductor manufacturing equipment. More specifically, this specification relates to the monitoring of the environmental efficiency (eco-efficiency) of manufacturing processes and manufacturing equipment using sensors of the manufacturing equipment and external sensors that are not part of the manufacturing equipment.

Background Art

[0002] The continuous demand for electronic devices has created an ever-increasing demand for semiconductor wafers. The increase in manufacturing to produce the wafers causes significant damage to the environment in the form of resource utilization and the generation of environmentally harmful waste. Therefore, there is an increasing need for more environmentally friendly and environmentally responsible methods in wafer manufacturing methods and manufacturing methods in general. Considering that wafer processing consumes a large amount of energy, it is valuable to decouple the growth of the semiconductor industry from its environmental impact. The increasing demand for chips and the increasing complexity of the chips are increasing resource consumption that affects the environment.

Summary of the Invention

[0003] The following description is a simplified summary of the present disclosure intended to facilitate a basic understanding of some aspects of the present disclosure. This summary is not an exhaustive summary of the present disclosure. It is not intended to describe any scope of particular embodiments of the present disclosure or any scope of the claims. The sole purpose of this summary is to present some concepts of the present disclosure in a simplified form as an introduction to the more detailed description that will be presented later.

[0004] Techniques related to an environmental efficiency monitoring and investigation platform for semiconductor manufacturing are described. In some embodiments, a method includes receiving, by a processing device, first sensor data generated by a plurality of sensors of a processing chamber of a manufacturing system during execution of a manufacturing process; receiving, by the processing device, second sensor data generated by one or more external sensors that are not components of the processing chamber during execution of the manufacturing process; determining, by the processing device, environmental resource usage data indicative of an environmental resource consumption amount of the manufacturing process executed in the processing chamber based on the first sensor data and the second sensor data; and providing, by the processing device, the environmental resource usage data for display on a graphical user interface (GUI). As used herein, the environmental resource usage data may include data relating to consumption amounts of resources and / or chemicals, environmental impacts of the resources and / or chemicals used / consumed, energy consumption amounts, and / or environmental impacts of the energy consumed.

[0005] In some embodiments, the system includes a manufacturing system, the manufacturing system including one or more processing chambers for processing a substrate, the one or more processing chambers including a first plurality of sensors, a transfer chamber coupled to the one or more processing chambers, the transfer chamber including a robot for transferring a substrate between the one or more processing chambers, and a system controller for controlling the one or more processing chambers and the transfer chamber. The system further includes a second plurality of sensors that are external sensors and not components of any of the one or more processing chambers, and a hub that communicates with the second plurality of sensors. The system controller is configured to perform the following: receive first sensor data generated by the first plurality of sensors during execution of a manufacturing process in a first processing chamber of the one or more processing chambers; receive second sensor data generated by the second plurality of sensors associated with the first processing chamber; determine environmental resource usage data indicating an environmental resource consumption amount of the manufacturing process executed in the first processing chamber based on application of the first sensor data and the second sensor data to one or more models; and provide the environmental resource usage data for display on a graphical user interface (GUI).

[0006] In some embodiments, a non-transitory machine-readable storage medium includes instructions that, when executed by a processing device, cause the processing device to perform the following: receive first sensor data generated by a plurality of sensors of a processing chamber of a manufacturing system during execution of a manufacturing process; receive second sensor data generated by one or more external sensors that are not components of the processing chamber during execution of the manufacturing process; determine environmental resource usage data indicating an environmental resource consumption amount of the manufacturing process executed in the processing chamber based on the first sensor data and the second sensor data; and provide the environmental resource usage data for display on a graphical user interface (GUI).

[0007] Aspects and embodiments of the present disclosure will be more fully understood from the detailed description provided below and the accompanying drawings. In the following detailed description and the accompanying drawings, aspects and embodiments are intended to be described by way of illustration and not limitation.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9A

Figure 9B

Figure 9C

Figure 9D

Figure 9E

Figure 10

DETAILED DESCRIPTION OF THE INVENTION

[0009] The characteristic evaluation of environmental efficiency (eco-efficiency) is a complex technique used to determine how various levels of inputs (e.g., resources, utilization, etc.) associated with a particular manufacturing tool affect the environmental efficiency of that manufacturing tool during the use of the particular manufacturing tool. The characteristic evaluation of environmental efficiency can be beneficial in supporting the development of a manufacturing tool that maximizes the environmental efficiency per unit (or per unit time) and minimizes harmful environmental impacts during the development of the manufacturing tool. The characteristic evaluation of environmental efficiency can also be beneficial after the development of the tool to fine-tune the environmental efficiency characteristic value per unit of the tool in view of the specific parameters according to which the tool operates while the tool is operating.

[0010] The embodiments described herein provide a system for systematically performing an environmental efficiency characterization of a manufacturing tool through the design, development, and deployment of the tool. In some embodiments, an environmental efficiency platform can assist in engineering in the development and / or operation of processing processes and tools that meet both materials engineering and environmental efficiency specifications. In an embodiment, sensor data, physics, models, algorithms, and / or a user interface (UI) are utilized to provide the flexibility and ease of monitoring and investigating the environmental efficiency of a number of manufacturing systems and individual processing chambers of the manufacturing systems. Additionally, the environmental efficiency platform can enable the monitoring and investigation of processing recipes and manufacturing hardware configurations. In an embodiment, further, an environmental efficiency characterization is used, using a digital replica associated with the manufacturing process and / or manufacturing apparatus, to further determine the environmental resource consumption and / or environmental impact (e.g., per unit of device, die, wafer, etc.) and / or to reduce the environmental resource consumption and / or environmental impact. In an embodiment, further, a digital replica is used to provide a platform for modifying a manufacturing system and investigating the resulting environmental efficiency impact (e.g., without requiring physical tests and empirical results).

[0011] In an embodiment, the environmental efficiency platform receives sensor data in roughly two categories, and the sensor data includes first sensor data from sensors included in the processing chamber and second sensor data from external sensors that are not components of the processing chamber (e.g., not included in the processing chamber). In an embodiment, the first sensor data and the second sensor data are received in parallel (e.g., substantially simultaneously). In some embodiments, the first sensor data and the second sensor data are received at different times (e.g., serially or consecutively). The external sensor can be, for example, an IoT (Internet-of-Things) sensor that can be wirelessly connected and / or does not need to be connected to a power source. The external sensor reports the sensor data to a hub (e.g., an IoT hub), and the IoT hub can then transmit the sensor data to a system controller of a manufacturing system that includes the processing chamber for which the data is being collected. The system controller can include software (e.g., the environmental efficiency platform), and the software can input the first sensor data and the second sensor data into one or more models. The one or more models can include trained machine learning models, physics-based models (e.g., digital twins), and / or other models. The one or more models can output environmental resource usage data indicating an environmental resource consumption amount (e.g., consumption amounts of chemicals, gases, electricity, and water). As used herein, the environmental resource usage data can include data regarding the consumption amount of resources and / or chemicals, the environmental impact of the resources and / or chemicals used / consumed, the energy consumption amount, and / or the environmental impact of the energy consumed.

[0012] In some embodiments, environmental efficiency is calculated per unit. Typically, in the development process of a manufacturing tool, the environmental efficiency per unit is not considered. Additionally, it can be a cumbersome and complex process to characterize the environmental efficiency per unit in order to adjust the settings on that tool during the use of the manufacturing tool (e.g., while the tool is being used for wafer manufacturing). Further, in previous solutions, personnel and special environmental efficiency training for specialized engineers and analysts were used for the characterization of environmental efficiency. Embodiments of the present disclosure provide an improved method, system, and software for unit-based environmental efficiency characterization. The above method, system, and software can be used by individuals who have not received special environmental efficiency training.

[0013] In one embodiment, the environmental efficiency characterization can be performed by a software tool at all stages of the life of a manufacturing apparatus, including the design stage and the operation stage of the manufacturing apparatus. The environmental efficiency can include the amount of environmental resources (e.g., electrical energy, water, gas, chemicals, etc.) consumed per production by the equipment (e.g., per wafer manufactured, or per device). The environmental efficiency can also be characterized as the amount of environmental impact (e.g., CO2 emissions, heavy metal waste, etc.) generated per production by the equipment.

[0014] Any measurable quantity (e.g., substrate (wafer), die, area (cm 2) By performing per-unit analysis based on units such as time periods, devices, etc., more accurate characterization of environmental efficiency becomes possible. The "per-unit" environmental efficiency enables accurate determination of resource usage and environmental impact per unit produced and can be easily manipulated as a measure of value. For example, it can be determined that a particular manufacturing tool has an evaluation of electrical energy per wafer pass of 1.0 to 2.0 kWh (in other embodiments, the evaluation of environmental efficiency may be less than 0.5 kWh per wafer pass, may be up to 20 kWh, or even exceed 20 kWh), which indicates that each wafer processed by the manufacturing tool may use, for example, 1.0 to 2.0 kWh of electrical energy per wafer processed. In other embodiments, various other amounts of electrical energy may be used. Determining environmental efficiency on a wafer-pass basis enables easy comparison with other manufacturing tools whose annual electrical energy consumption values vary due to variations in annual wafer throughput. In one embodiment, the environmental efficiency can also be determined in device units by dividing the environmental efficiency characteristic value per wafer by the number of devices per wafer.

[0015] The characterization or calculation of environmental efficiency can be performed on a manufacturing apparatus during operation. The manufacturing apparatus can access real-time variables such as utilization and utility usage data of the equipment from a first sensor on the manufacturing apparatus and a second sensor that is an external sensor not a component of the manufacturing apparatus, and can use the real-time variables in one or more environmental efficiency models. The manufacturing apparatus can fine-tune the settings on the equipment to maximize environmental efficiency considering the current operating status of the manufacturing apparatus.

[0016] In some embodiments, modifications to a manufacturing process (e.g., a subset of processes or multiple processes) can be determined based on environmental resource usage data or environmental efficiency characteristic evaluations. For example, the environmental resource usage data can be used as an input to a machine learning model. One or more outputs from a machine learning model can be obtained that indicate a modification to the manufacturing process and, in some embodiments, the confidence level that the modification meets a threshold condition. The modification to the manufacturing process can be associated with an improvement in the environmental efficiency of the selected manufacturing process (e.g., a reduction in environmental resource consumption and / or a reduction in environmental impact).

[0017] In some embodiments, a compliance report can include a report based on generally recognized specifications and / or standards such as SEMI (Semiconductor Equipment and Materials International) S23-0813, published by SEMI for energy, power, and production maintenance of semiconductor manufacturing equipment. For example, SEMI S23-0813 provides the energy conversion factor (ECF) for key utilities (e.g., energy consumption per unit flow rate). The ECF can estimate the energy consumption of the utility and is used to evaluate energy savings in a semiconductor manufacturing facility.

[0018] In some embodiments, environmental efficiency is based on the consumption of resources such as energy consumption, chemical consumption (e.g., gases such as hydrogen, nitrogen, chemicals used for thin film etching or deposition, and / or liquids that can be vaporized, atomized, or converted to a gaseous state via a bubbler, injector, or atomizer), CDA (clean dry air)), and / or water consumption (e.g., process cooling water (PCW), de-ionized water (DIW), and ultrapure water (UPW)). However, in some embodiments, environmental efficiency is based on the lifetime data of components associated with the manufacturing equipment. For example, the environmental resource consumption and / or environmental impact associated with the environmental efficiency characteristic evaluation can be associated with the replacement or maintenance procedures of the consumable parts of the manufacturing equipment. Modifications can be associated with the maintenance procedures of the consumable parts of the manufacturing equipment. Some embodiments are considered herein with respect to gas consumption. However, it should be understood that such embodiments are also applicable to the consumption of chemicals in other states, such as chemicals in a liquid state. The embodiments described in the specification with reference to gas consumption are equally applicable to the consumption of other types of chemicals, such as liquids.

[0019] As described above, in an embodiment, an environmental efficiency platform determines the environmental resource usage of a processing chamber that executes a manufacturing process based on first sensor data from a first sensor set integrated with the processing chamber and second sensor data from a second sensor set not integrated with the processing chamber. The second sensor set provides data regarding resource consumption generally not measured for the processing chamber, such as the amount of clean dry air (CDA), electricity, and / or water used by the manufacturing system for pumps and / or decontamination systems associated with the manufacturing process being executed in the processing chamber, which is data regarding resource consumption that the processing chamber is not configured to measure. By adding an external sensor capable of measuring such parameters, it is possible to more accurately determine the amount of resources used for the process executed on the processing chamber. By improving the accuracy of the environmental efficiency platform using such data, in an embodiment, better process development and lower overall resource consumption can be achieved.

[0020] FIG. 1 is a schematic top view of an exemplary processing system 100 (also referred to herein as a manufacturing system) according to one embodiment. In some embodiments, the processing system 100 can be an electronics processing system configured to perform one or more processes on a substrate 102. In some embodiments, the processing system 100 can be an electronic device manufacturing system. The substrate 102 can be a planar article of any suitable hardness and fixed dimensions (e.g., a silicon-containing disk or wafer, a patterned wafer, or a glass plate, etc.) that is suitable for fabricating an electronic device or circuit component thereon. In some embodiments, the processing system 100 is a semiconductor processing system. Alternatively, the processing system 100 can be configured to process other types of devices such as display devices.

[0021] The processing system 100 includes a processing tool 104 (e.g., a mainframe) and a factory interface 106 coupled to the processing tool 104. The processing tool 104 includes a housing 108 having a transfer chamber 110 therein. The transfer chamber 110 includes one or more processing chambers (also referred to as process chambers) 114, 116, 118 disposed around and coupled to itself. The processing chambers 114, 116, 118 can be coupled to the transfer chamber 110 via respective ports such as slit valves.

[0022] The processing chambers 114, 116, 118 can be adapted to perform any number of processes on the substrate 102. Within each of the processing chambers 114, 116, 118, the same or different substrate processes can be performed. Examples of substrate processes can include atomic layer deposition (ALD), physical vapor deposition (PVD), or chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, removal of metals or metal oxides, etc. In one example, a PVD process is performed in one or both of the processing chambers 114, an etching process is performed in one or both of the processing chambers 116, and an annealing process is performed in one or both of the processing chambers 118. Other processes can be performed on the substrate among these. Each of the processing chambers 114, 116, 118 can include a substrate support assembly. The substrate support assembly can be configured to hold the substrate in a fixed position while the substrate process is being performed.

[0023] The transfer chamber 110 also includes a transfer chamber robot 112. The transfer chamber robot 112 can include one or more arms, and each arm can include one or more end effectors at the tip of the arm. The end effector can be configured to handle a specific object such as a wafer. In some embodiments, the transfer chamber robot 112 is a SCARA (selective compliance assembly robot arm) robot, for example, a 2-axis SCARA robot, a 3-axis SCARA robot, and a 4-axis SCARA robot, etc.

[0024] The load lock 120 can also be coupled to the housing 108 and the transfer chamber 110. The load lock 120 can be configured such that one side is connected and coupled to the transfer chamber 110, and the other side is coupled to the factory interface 106. In some embodiments, the load lock 120 can have an environmentally controlled atmosphere that is changed from a reduced pressure environment (where the substrate is transferred between the transfer chamber 110) to an inert gas environment at atmospheric pressure or near atmospheric pressure (where the substrate is transferred between the transfer chamber and the factory interface 106). In some embodiments, the load lock 120 is a stacked load lock having a pair of upper internal chambers and a pair of lower internal chambers located at various vertical levels (e.g., one above the other). In some embodiments, the pair of upper internal chambers is configured to receive the processed substrate from the transfer chamber 110 for removal from the processing tool 104, while the pair of lower internal chambers is configured to receive the substrate from the factory interface 106 for processing within the processing tool 104. In some embodiments, the load lock 120 is configured to perform a substrate process (e.g., etching or pre-cleaning) on one or more received substrates 102.

[0025] The factory interface 106 may be any suitable housing, for example, it may be an EFEM (Equipment Front End Module). The factory interface 106 may be configured to receive the substrate 102 from a substrate carrier 122 (e.g., a FOUP (Front Opening Unified Pod, front opening type unified pod)) docked to various loading ports 124 of the factory interface 106. A robot 126 (shown in dotted lines) of the factory interface may be configured to transfer the substrate 102 between the substrate carrier 122 (also referred to as a container) and the load lock 120. In other embodiments and / or similar embodiments, the factory interface 106 is configured to receive replacement parts from a replacement part storage container 123. The robot 126 of the factory interface may include one or more robot arms and may be a scalar robot or include a scalar robot. In some embodiments, the robot 126 of the factory interface has more axes and / or degrees of freedom than the robot 112 in the transfer chamber. The robot 126 of the factory interface may include an end effector at the end of each robot arm. The end effector may be configured to pick up and handle a specific object such as a wafer. Alternatively or additionally, the end effector may be configured to handle an object such as a ring of a processing kit.

[0026] Any conventional robot type may be used for the robot 126 of the factory interface. The transfer may be performed in any order or in any direction. In some embodiments, the factory interface 106 may be maintained, for example, in a slightly positive pressure non-reactive gas environment (e.g., using nitrogen as the non-reactive gas).

[0027] The processing system 100 may also include a system controller 128. The system controller 128 can be a computing device such as a personal computer, a server computer, a programmable logic controller (PLC), and a microcontroller, and / or may include the computing device. The system controller 128 may include one or more processing devices that can be a general-purpose processing device such as a microprocessor or a central processing unit. More specifically, the processing device can be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing another instruction set or a combination of instruction sets. The processing device may also be one or more special-purpose processing devices such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor. The system controller 128 may include a data storage device (e.g., one or more disk drives and / or solid state drives), main memory, static memory, a network interface, and / or other components. The system controller 128 is capable of executing instructions for performing any one or more of the methods and / or embodiments described herein. The instructions can be stored in a computer-readable storage medium, which may include main memory, static memory, secondary storage, and / or the processing device (while the instructions are being executed).In an embodiment, by executing instructions by system controller 128, the system controller is caused to execute the method of FIG. 8. System controller 128 may also be configured to permit the input and display of data and processing commands, etc., by a human operator.

[0028] In an embodiment, system controller 128 includes an environmental efficiency module 129, and environmental efficiency module 129 may be a local server and is executed on system controller 128 of processing system 100. Environmental efficiency module 129 may be responsible for processing first sensor data generated by sensors of one or more processing chambers 114, 116, 118 and second sensor data from additional sensors 140, 142, 144 external to processing chambers 114, 116, 118. The first sensor data may be generated by sensors integrated with processing chambers 114, 116, 118. Such sensors may include, for example, temperature sensors, power sensors, current sensors, pressure sensors, and concentration sensors. The first sensor data output by the integrated sensors of processing chambers 114, 116, 118 may include measurements of current, voltage, power, flow rate (e.g., of one or more gases, CDA, water, etc.), pressure, concentration (e.g., of one or more gases), velocity (e.g., of one or more moving parts, gases, etc.), acceleration (e.g., of one or more moving parts, gases, etc.), velocity (e.g., of one or more moving parts, gases, etc.), acceleration (e.g., of one or more moving parts, gases, etc.), or temperature (e.g., of a substrate being processed and various locations within the processing chamber). In one embodiment, each chamber includes from about 20 to about 100 sensors.

[0029] One or more external sensors 140, 142, 144, 152 are attached to the processing chambers 114, 116, 118, and / or to the supply lines to and / or from the processing chambers 114, 116, 118, and / or to sub-components (e.g., pumps and / or decontamination systems, etc.) operating for the benefit of the processing chambers 114, 116, 118 to obtain additional data that is generally not accessible by the integrated sensors of the processing chambers 114, 116, 118. In one embodiment, each processing chamber includes approximately 3 to 6 external sensors attached to the processing chamber, a subsystem associated with the processing chamber, and / or input / outputs between the processing chambers. The second sensor data output by the external sensors 140, 142, 144, 152 can include, for example, current, flow rate, temperature, eddy current, concentration, vibration, voltage, or power factor. Examples of external sensors 140, 142, 144, 152 that can be used include clamp sensors (also referred to as current clamps) that measure alternating current or direct current, clamp sensors that measure voltage, and clamp sensors that measure leakage current. Other examples of external sensors include vibration sensors, temperature sensors, ultrasonic sensors (e.g., ultrasonic flow sensors), accelerometers (e.g., acceleration sensors), and the like.

[0030] In the illustrated example, the decontamination system 130, the gas supply system 134, the water system 132, and / or the CDA system 136 can provide environmental resources to the processing chambers 114, 116, 118 and / or other components of the processing system 100 (e.g., transfer chambers, factory interfaces, load locks, etc.). In an embodiment, the decontamination system 130 performs decontamination on residual gases, reactants, and / or outputs associated with the processes executed in the processing chambers 114, 116, 118. The decontamination system 130 can, for example, combust the residual gases and / or reactants to ensure that they do not pose an environmental risk. Further, in an embodiment, one or more pumps 150 are attached to and / or can operate in place of one or more of the processing chambers 114, 116, 118. The external sensors 140, 142, 144, 152 are shown with respect to a single processing chamber 116 for simplicity of illustration. However, it should be understood that similar external sensors can be attached on additional processing chambers and / or on lines between such additional chambers and / or to subsystems associated with such additional processing chambers.

[0031] The external sensors 140, 142, 144, 152 can be IoT sensors in some embodiments. In some embodiments, the external sensor includes a power source such as a battery. In some embodiments, the external sensor is a wired sensor connected to a power source such as an AC power outlet. In some embodiments, the external sensor does not include a power source and instead receives sufficient power to operate based on environmental conditions. For example, a sensor that detects voltage, power, and / or current can be wirelessly powered (e.g., by obtaining energy from the current flowing through the wire that secures the sensor) by such power or current.

[0032] In one embodiment, the external sensors 140, 142, 144, 152 are sensors incorporated into the system. An embedded system is a class of computing device that is incorporated as a component of that device into other devices. The external sensors 140, 142, 144, 152 typically also include other hardware, electrical and / or mechanical components that can be connected to the embedded system. The embedded system is typically configured to process a specific task or set of tasks, and for that purpose, the embedded system can be optimized (e.g., for generating and / or transmitting measurements). Thus, the embedded system can have a minimum cost and a minimum size compared to a general-purpose computing device.

[0033] Each embedded system can include a communication module (not shown), which enables the embedded system (and thus the external sensors 140, 142, 144, 152) to connect to a LAN, hub 150, and / or a wireless carrier network (implemented using, for example, various data processing devices, communication towers, etc.). The communication module can be configured to perform functions such as security management, session management, access control management, and communication management with external devices.

[0034] In one embodiment, the communication modules of the external sensors 140, 142, 144, 152 are configured to communicate using Wi-Fi®. Alternatively, the communication modules may be configured to communicate using Bluetooth®, Zigbee®, 6LowPAN (Internet Protocol version 6 over Low power Wireless Area Networks), power line communication (PLC), Ethernet (e.g., 10 megabits per second (Mb), 100 Mb, and / or 1 gigabit per second (Gb) Ethernet), or other communication protocols. If the communication modules are configured to communicate with a wireless carrier network, the communication modules may communicate using GSM (Global Systems for Mobile Communications), CDMA (Code-Division Multiple Access), UMTS (Universal Mobile Telecommunications Systems), LTE (3GPP Long Term Evaluation), WiMAX (Worldwide Interoperability for Microwave Access), or any other second generation wireless telephone technology (2G), third generation wireless telephone technology (3G), fourth generation wireless telephone technology (4G), or other wireless telephone technology.

[0035] In one embodiment, the communication module is configured to communicate with hub 150, which can be, for example, a Wi-Fi router, or another type of router, switch, or hub. Hub 150 is configured to communicate with the communication modules of external sensors 140, 142, 144, 152 respectively, and can be configured to transmit the measurement values received from external sensors 140, 142, 144, 152 to system controller 128. In one embodiment, hub 150 has a wired connection (e.g., Ethernet connection, parallel connection, serial connection, Modbus connection, etc.) to system controller 128, and transmits the measurement values to system controller 128 via this wired connection. In one embodiment, hub 150 is connected to one or more external sensors via a wired connection.

[0036] In some embodiments, hub 150 is connected to a network device connected to a local area network (LAN). System controller 128 and the network device can each be connected to the LAN via a wireless connection and can be wirelessly connected to each other via the LAN. External sensors 140, 142, 144, 152 may not be compatible with any of the communication types supported by the network device. For example, external sensor 140 may support Zigbee, and external sensor 142 may support Bluetooth. To enable such devices to connect to the LAN, hub 150 can function as a gateway device connected to a network device (not shown) via one of the connection types supported by the network device (e.g., via Ethernet or Wi-Fi). The gateway device can further support other communication protocols such as Zigbee, PLC, and / or Bluetooth, and can perform conversions between the supported communication protocols.

[0037] The system controller 128 can be connected to a wide area network (WAN). The WAN can be a private WAN (e.g., an intranet), or a public WAN such as the Internet, or can include a combination of a private network and a public network. In an embodiment, the system controller 128 can be connected to a local area network (LAN) including a router and / or a modem (e.g., a cable modem, a DSL (direct serial link) modem, a WiMAX (registered trademark) (Worldwide Interoperability for Microwave Access) modem, an LTE (registered trademark) (long term evolution) modem, etc.) that provides connection to the WAN.

[0038] The WAN can include or be connected to one or more server computing devices (not shown). The server computing device can include a physical machine and / or a virtual machine hosted by the physical machine. The physical machine can be a rack-mounted server, a desktop computer, or other computing device. In one embodiment, the server computing device includes a virtual machine managed and provided by a cloud provider system. Each virtual machine provided by a cloud service provider can be hosted on a physical machine configured as part of a cloud. Such physical machines are often located within a data center. The cloud provider system and the cloud can be provided as an IaaS (Infrastructure as a Service) layer. An example of such a cloud is Amazon (registered trademark)'s EC2 (Elastic Compute Cloud (registered trademark)).

[0039] The server computing device can host one or more services, which can be web-based services and / or cloud services (e.g., web-based services hosted within a cloud computing platform). The above services can maintain sessions with system controllers 128 and / or system controllers of other manufacturing systems at the same location (e.g., within a manufacturing facility or a fab) and / or at various locations (e.g., via continuous or intermittent connections). Alternatively, the above services can periodically establish sessions with the system controllers. Through the session with system controller 128, the above services can receive status updates from the environmental efficiency module 129 running on system controller 128. The above services can collect data and provide a graphical user interface (GUI) accessible via any device connected to the WAN (e.g., mobile phone, tablet computer, laptop computer, desktop computer, etc.).

[0040] The environmental efficiency module 129 running on system controller 128 can process the first sensor data from the integrated sensors of one or more processing chambers 114, 116, 118 and the second sensor data from external sensors 140, 142, 144, 152 to determine environmental resource usage data reflecting environmental resource consumption such as water consumption, gas consumption, and power consumption. The processing that can be performed by environmental efficiency module 129 will be described below with reference to the remaining figures.

[0041] In some embodiments, sensor data from one or more external sensors can be used to evaluate the health of a processing chamber or a sub-component (e.g., a pump) of the processing chamber. The sensor data from one or more external sensors can be compared to one or more criteria (e.g., thresholds), and if the sensor data does not meet the criteria, it can be determined that the tool or sub-component is not operating reliably. For example, a vibration sensor can sense the vibration of a pump. If the vibration exceeds a vibration threshold, it can be determined that the pump may be starting to fail or that there may be a problem with the pump. If the first sensor data of a sub-component or tool does not meet one or more criteria, the calculation of the environmental resource consumption associated with that sub-component or tool can be determined to be unreliable. For example, if a pump has increased vibration, it may be consuming more power than normal, and a model regarding the power consumption of the pump may be inaccurate regarding the current state of the pump. Thus, sensor data from external sensors and / or internal sensors of the processing chamber can be used to perform a health assessment of the processing chamber and / or one or more sub-components of the processing chamber.

[0042] FIG. 2 is a block diagram showing a logical view of an exemplary environmental efficiency platform 200 according to one embodiment. The environmental efficiency platform 200 can be executed on a system controller 201 in an embodiment. In one embodiment, the system controller 201 corresponds to the system controller 128 of FIG. 1, and the environmental efficiency platform 200 is provided by the environmental efficiency module 129 of FIG. 1.

[0043] The environmental efficiency platform 200 can receive first sensor data 270 from a tool sensor 202, which can be an integrated sensor of the processing chambers 114, 116, 118 of FIG. 1 in an embodiment. The environmental efficiency platform 200 can further receive second sensor data 272 from a hub 206, and the hub 204 receives second sensor data from one or more external sensors 204. The external sensors 204 can correspond to the external sensors 140, 142, 144, 152 of FIG. 1 in an embodiment. In some embodiments, the hub 206 provides the second sensor data to a server 207, which can be executed on one or more computing devices (e.g., a cloud environment). The server (e.g., an IoT platform) 207 can aggregate the second sensor data into aggregated second sensor data 274 and transmit the aggregated second sensor data 274 to the environmental efficiency platform 200. Such aggregated second sensor data 274 can be provided to the environmental efficiency platform 200 instead of or in addition to the second sensor data 272.

[0044] In some embodiments, past data 208 (e.g., past sensor data) can be stored in a data store such as a database. Such past data 208 can be additionally provided to the environmental efficiency platform 200 in some embodiments.

[0045] In block 230, the environmental efficiency platform 200 collects the first sensor data 270, the second sensor data 272, the aggregated second sensor data 274, and / or the past data 208. In block 232, the environmental efficiency platform 200 can preprocess some or all of the received data. The preprocessing includes data normalization, changing the unit of the data, adding a timestamp to the data, synchronizing the data based on the timestamp, and adding a label to the data.

[0046] In block 234, the environmental efficiency platform 200 performs data processing on the received data (e.g., the first sensor data 270 and the second sensor data 272). This includes inputting the data into one or more data processing algorithms or functions, inputting the data into one or more physics-based models (e.g., digital twins, etc.), inputting the data into one or more trained machine learning models, and the like. In block 236, an output is generated by one or more models, data processing algorithms, functions, and the like. The above output may include physical conditions and / or environmental resource usage data associated with the manufacturing process executed on the processing chamber. The above output may be stored in a local data store such as the database 210.

[0047] A client computing device that executes a web client 220 or other client application including a graphical user interface (GUI) 222 or other type of user interface can be connected to the environmental efficiency platform 200. The web client 220 can send a request 212 to the environmental efficiency platform 200 and receive a response 214. The request 212 may include requests for, for example, environmental resource usage data for one or more processing chambers, for a manufacturing system including a plurality of processing chambers, and for recipes executed on the processing chamber. The above request may also include a request to present the environmental resource usage data in graphs, tables, and the like.

[0048] In some embodiments, the environmental efficiency platform 200 of the plurality of system controllers 201 connects to a remote computing device 250 (e.g., via a WAN). The remote computing device 250 can include a remote server, which collects data from the plurality of environmental efficiency platforms and stores the collected data in a data store such as a database 255. A web client 220 (or other client application) can connect to the remote server of the computing device 250 to access environmental resource usage data for a plurality of manufacturing systems, a plurality of fabs, etc. within the fab.

[0049] FIG. 3 is a block diagram showing an exemplary system structure 300 in which embodiments of the present disclosure can function. As shown in FIG. 3, the system structure 300 includes a manufacturing system 302, a data store 312, a server 320, a client device 350, and / or a machine learning system 370. The machine learning system 370 can be part of the server 320. In some embodiments, one or more components of the machine learning system 370 can be fully or partially incorporated into the client device 350. The manufacturing system 302, the data store 312, the server 320, the client device 350, and the machine learning system 370 can each be hosted by one or more computing devices, which can include a server computer, a desktop computer, a laptop computer, a tablet computer, a notebook computer, a personal digital assistant (PDA), a mobile communication device, a mobile phone, a handheld computer, an augmented reality (AR) display and / or headset, a virtual reality (VR) display and / or headset, a mixed reality (MR) display and / or headset, or a similar computing device. As used herein, the term "server" can refer to a server, but can also include edge computing devices, on-premise servers, and the cloud, etc.

[0050] The manufacturing system 302, the data store 312, the server 320, the client device 350, and the machine learning system 370 can be connected to each other via a network (e.g., to execute the methods described herein). In some embodiments, the network 340 is a private network that provides access rights to each element of the system architecture 300 to each other and provides access rights to other privately available computing devices. The network 340 can include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), cloud networks, cloud services, routers, hubs, switches, server computers, and / or any combination thereof. Alternatively or additionally, any of the above elements of the system architecture 300 can be integrated together or otherwise connected without using the network 340.

[0051] The client device 350 can be or can include any personal computer (PC), laptop, mobile phone, tablet computer, netbook computer, network-connected television (“smart TV”), network-connected media player (e.g., Blu-ray player), set-top box, over-the-top (OTT) streaming device, operator box, etc. The client device 350 can include a browser 352, an application 354, and / or other tools as described above executed by other systems of the system architecture 300. In some embodiments, the client device 350 can access the manufacturing system 302, the data store 312, the server 320, and / or the machine learning system 370, and can communicate (transmit and / or receive) an environmental efficiency indication that includes one or more environmental resource consumption amounts (e.g., environmental resource consumption), and / or environmental impacts, and / or inputs and outputs of various processing tools (e.g., component integration tool 322, digital replica tool 324, optimization tool 326, recipe builder tool 328, and resource consumption tool 330, etc.) at various stages of the processing of the system architecture 300 described herein.

[0052] As shown in FIG. 3, the manufacturing system 302 includes a manufacturing apparatus 304, a system controller 306, a processing recipe 308, and a sensor 310. The manufacturing apparatus 304 can be an ion implantation apparatus, an etching reactor (e.g., a processing chamber), a photolithography apparatus, a deposition apparatus (e.g., for performing chemical vapor deposition (CVD), physical vapor deposition (PVD), and ion-assisted deposition (IAD), etc.), or any other combination of manufacturing apparatuses.

[0053] The processing recipe 308, also referred to as a manufacturing recipe or manufacturing process instruction, includes the order of machine operations, which, when applied in the specified order, includes the execution of a process to produce a manufactured sample (e.g., a substrate or wafer having predetermined characteristics or meeting predetermined specifications). In some embodiments, the processing recipe is stored in a data store or, alternatively or additionally, stored to generate a table of data indicating steps or processes of the manufacturing process. Each step can be associated with known environmental resource usage data. Alternatively or additionally, each processing step can be associated with parameters indicating the physical conditions of the processing step (e.g., target pressure, temperature, exhaust, and energy throughput, etc.).

[0054] The system controller 306 can include software components and / or hardware components capable of executing the steps of the processing recipe 308. The system controller 306 can monitor the manufacturing process through the sensor 310. The sensor 310 can measure processing parameters to determine whether processing criteria are met. The processing criteria can be associated with a processing parameter value window. The sensor 310 can include various sensors that can be used to measure consumption (e.g., power, current, etc.) (either explicitly or as a measure of consumption). The sensor 310 can include physical sensors, integrated sensors that are components of the processing chamber, external sensors, IoT (Internet-of-Things) sensors, and / or virtual sensors (e.g., sensors based on virtual measurements that are not physical sensors but are based on models that estimate parameter values), etc.

[0055] Additionally or alternatively, the system controller 306 can monitor environmental efficiency by measuring the resource consumption of various processing steps (e.g., exhaust volume, energy consumption, process component consumption, etc.). In some embodiments, the system controller 306 determines the environmental efficiency of the associated machinery 304. The system controller 306 can also adjust the settings associated with the manufacturing apparatus 304, in view of the current manufacturing conditions, to optimize the environmental efficiency of the apparatus 304 based on the determined environmental efficiency model (e.g., including the determined modifications to the processing recipe 308).

[0056] In one embodiment, the system controller 306 can include a main memory (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and / or a secondary memory (e.g., a data storage device such as a disk drive (e.g., data store 312 or cloud data)). The main memory and / or secondary memory can store instructions (e.g., processing recipe 308) for performing various types of manufacturing processes.

[0057] In one embodiment, the system controller 306 can determine the actual environmental efficiency characteristic value associated with the manufacturing apparatus 304 based on the first common charge data associated with the manufacturing apparatus 304 and the first utility usage data associated with the manufacturing apparatus 304. The first utility usage data and the first usage data can be determined, for example, by the system controller 306. In other embodiments, the first utility usage data and the first usage data are received from an external source (e.g., server 320, cloud service, and / or cloud data store). The system controller 306 can compare the actual environmental efficiency characteristic value with the first environmental efficiency characteristic value (e.g., the first estimated environmental efficiency characteristic value) associated with the manufacturing apparatus 304. If values of utility usage data and usage data different from the actual values associated with the operating manufacturing apparatus 304 are used to calculate the first environmental efficiency characteristic value, the environmental efficiency characteristic value may be different.

[0058] In one embodiment, the system controller 306 can determine that a first environmental efficiency characteristic evaluation indicating that it is possible to adjust the settings of the manufacturing apparatus 304 to better optimize the manufacturing apparatus 304 for environmental efficiency is higher in environmental efficiency than the actual environmental efficiency characteristic evaluation. In some embodiments, the manufacturing apparatus 304 can control and adjust the settings of sub-components to better optimize environmental efficiency.

[0059] System controller 306 can also determine that the actual utility usage data or actual utilization data is not the same as the utility usage data and utilization data associated with the first environmental efficiency characteristic value, based on the actual utility usage data, actual utilization data, and environmental efficiency characteristic values. This can be the case where nominal data values or estimated data values are used to determine the first environmental efficiency characteristic value, and different actual recorded data values are used while the manufacturing apparatus 304 is operating. In such a scenario, an adjustment to one or more settings associated with the manufacturing apparatus 304 may be beneficial to optimize the environmental efficiency of the manufacturing apparatus.

[0060] Data store 312 can be another type of component or device capable of storing data, such as a memory (e.g., random access memory), a drive (e.g., hard drive, flash drive), a database system, or a store provided by a cloud server and / or a processor. Data store 312 can store one or more past sensor data. Data store 312 can store one or more environmental efficiency data 314 (e.g., including past and / or current environmental efficiency data), sensor and processing recipe data 316 (e.g., including past and / or current sensor and processing recipe data 316), modification and optimization data (e.g., including past and / or current modification and optimization data 318), and digital replica data 319. Sensor and processing recipe data 316 can include various processing steps, processing parameter windows, alternative processing steps, and process queuing instructions for executing multiple processes on duplicate manufacturing apparatuses. Sensor and processing recipe data 316 can be linked or otherwise associated with environmental efficiency data 314 to track environmental efficiency across various processing steps, recipes, etc. Modification and optimization data 318 can include past modifications made to previous processing recipes (including adjustments to individual processing steps or multiple processing recipes) and associated changes in environmental efficiency resulting from the modifications.

[0061] The environmental efficiency data 314 can include various consumed resources used in the environmental efficiency characteristic evaluation. In one embodiment, the environmental efficiency data 314 incorporates one or more of water usage, emissions, electrical energy usage, and any combination thereof. In other embodiments, the environmental efficiency data 314 can include resource consumption amounts in other categories such as gas usage, heavy metal usage, and the potential for eutrophication.

[0062] The digital replica data 319 can include data associated with the digital replica. The digital replica data 319 can include data associated with the digital twin. As used herein, the digital twin can include a digital replica of a physical asset such as the manufacturing apparatus 304. The digital twin includes the characteristics of the physical asset at each stage of the manufacturing process, where the characteristics include, but are not limited to, dimensions of the coordinate axes, weight characteristics, material characteristics (e.g., density, surface roughness), electrical characteristics (e.g., conductivity), optical characteristics (e.g., reflectivity), and the like.

[0063] As described above, a digital replica may include a physics-based model of one or more physical assets of a substrate manufacturing system. Digital replica data 319 may encapsulate relationships, parameters, specifications, etc. associated with one or more perspectives of the physics-based model. For example, the physics-based model may show the relationship between the size and outer shape of a substrate processing chamber and the environmental resource consumption. An update may be associated with a modification to at least one of the size or shape of the substrate processing chamber. The physics-based model may show the relationship between the type of purge gas used within the substrate manufacturing system and the environmental resource consumption. An update may be associated with how the environmental resource consumption changes by modifying the type and amount of gas used to purge the system. For example, an update to a particular resource consumption may include how the environmental resource consumption is affected by changing the purge gas used from a first purge gas such as nitrogen to CDA. The physics-based model may show the relationship between at least one of the heat removal procedures from the substrate manufacturing system and the environmental resource consumption. The update may be associated with a modification to at least one of an exhaust heat device, a gas removal device, a water cooling device, or a gas venting structure.

[0064] Server 320 may include a component integration tool 322, a digital replica tool 324, an optimization tool 326, a recipe builder tool 328, a resource consumption tool 330, and / or an investigation tool. The component integration tool 322 can determine the cumulative consumption per device (e.g., per individual manufacturing device). The various tools of server 320 can communicate data with each other to perform their respective functions as described herein.

[0065] The component integration tool 322 can receive manufacturing data (such as recipes, recipe selections, manufacturing equipment, processes between and within recipes, etc.) and perform an analysis of environmental efficiency across various parts of the data. In some embodiments, the component integration tool 322 can determine environmental efficiency characteristic values across multiple processing steps from an individual processing recipe. For example, the component integration tool 322 can determine environmental efficiency characteristic values across all steps from the start to the end of a chip manufacturing process. For example, each manufacturing step can include one or more manufacturing steps (such as hundreds of manufacturing steps), each of which has an environmental efficiency characteristic evaluation, and together they have an overall environmental efficiency characteristic evaluation value. In other examples, selections from the above manufacturing process can be used to determine the environmental efficiency of a subset of manufacturing processing steps.

[0066] In other embodiments, the component integration tool 322 can perform an environmental efficiency characteristic evaluation of the process between recipes. For example, the environmental efficiency characteristic evaluation can be associated with a manufacturing device that performs multiple different processing steps from multiple different manufacturing processes (such as processing recipe 308) (for example, of the manufacturing system 302). In other examples, the order of various processing steps (such as within or between recipes) can affect the overall environmental efficiency. The component integration tool 322 can perform an overall environmental efficiency characteristic evaluation across the system of manufacturing devices and / or a series of processes. For example, the component integration tool 322 can perform a comparison of environmental efficiency between sub-components (such as multiple processing chambers) that perform similar functions.

[0067] In an exemplary example, each processing step, such as epitaxial growth or etching, can be performed by a processing chamber. Each of the above processing steps is performed using a processing recipe. There can be various processing recipes for performing a process such as epitaxial growth. For example, a processing recipe can include a plurality of steps such as 1) purging the chamber, 2) pumping, 3) flowing with gas, 4) heating the chamber, etc. These steps can be associated with one or more processing recipes.

[0068] In other embodiments, the component integration tool 322 can perform an environmental efficiency characteristic evaluation including the environmental efficiency of auxiliary equipment. Auxiliary equipment can include equipment that is not directly used for manufacturing but supports the execution of various processing recipes. For example, auxiliary equipment can include a substrate transfer system designed to move wafers between various manufacturing apparatuses. In other examples, auxiliary equipment can include a heat sink, a shared exhaust port, a power supply system, etc. The component integration tool 322 can consider the resource consumption of the auxiliary equipment and combine the resource consumption of the auxiliary equipment with the manufacturing resource consumption to determine the resource consumption of a processing recipe (e.g., a subset or the entire recipe), or a combination of recipes (e.g., a subset or the entire recipe).

[0069] In other embodiments, the component integration tool 322 can perform an environmental efficiency characteristic evaluation considering a series of processes or recipes. For example, when processing step B is executed following processing step A, a first resource consumption can be obtained, and when processing step A is executed following processing step B, a second resource consumption different from the first resource consumption can be obtained. The component integration tool 322 integrates environmental efficiency across multiple mechanical devices and / or processing steps and considers the sequence of processing steps of a processing recipe (e.g., a subset or the entire recipe) or a combination of recipes (e.g., a subset or the entire recipe).

[0070] In some embodiments, there are different manufacturing apparatuses for each processing step. For example, a film on a wafer can have multiple layers. A first machine can perform a first process (e.g., deposition), a second machine can perform a second process (e.g., etching), a third machine can perform a third process (e.g., deposition), and so on. The component integration tool 322 can instruct the resource consumption tracker to track multiple processing steps across multiple machines to generate a data stash report. As previously mentioned, the consumption report can depict the selection of a processing recipe, including the lifespan of the wafer from start to finish.

[0071] In some embodiments, the component integration tool 322 can perform a comparison of environmental resource consumption between chambers. The component integration tool can utilize the digital replica tool 324 to provide one or more physical data indicating the basis for the difference in environmental efficiency between two chambers.

[0072] The digital replica tool 324 receives manufacturing data from the manufacturing system 302 and / or the client device 350 and generates a digital replica associated with the manufacturing data. The manufacturing data can include the selection of the machining device 304 and the processing steps to the processing recipe 308. The digital replica tool 324 generates a digital twin of the physical system structure of the manufacturing system or a virtually input system (e.g., generated by the user on the client device 350).

[0073] The digital replica generated by the digital replica tool 324 may include one of a physical model, a statistical model, and / or a hybrid model. The physical model may include physics-based constraints and control algorithms designed to estimate the physical conditions of the input manufacturing data (e.g., exhaust temperature, power supply requirements, and / or other conditions indicating the physical environment associated with environmental resource consumption). For example, a user can generate a processing recipe on the client device 350. The processing recipe may include the parameters of the process or recipe and instructions for using the mechanical device in a particular manner. The digital replica tool 324 will obtain the above manufacturing data and determine the physical constraints of the system (e.g., operating temperature, pressure, exhaust parameters, etc.). For example, the physical model can specify the physical conditions of the system based on the hardware configuration of the chamber (e.g., use of device material of type A vs. device material of type B) and / or recipe parameters. In other examples, the physical conditions can be determined from parts of the associated mechanical device that affect heat loss to water, air, and / or heating ventilation and air conditioning (HVAC) equipment. The digital replica tool 324 can cooperate with other tools (e.g., the component integration tool 322 and / or the resource consumption tool 330) to predict the environmental efficiency characteristics of the received manufacturing data. It should be noted that the digital replica tool 324 can predict the environmental efficiency of the selection of the manufacturing process and manufacturing equipment without receiving empirical data from the execution of the processing recipe by the manufacturing device 304. Therefore, using the digital replica of the manufacturing device, the environmental efficiency of the device design and / or the processing recipe can be predicted without actually constructing a specific device design or executing a specific processing recipe.

[0074] In some embodiments, the digital replica tool 324 can operate in conjunction with the digital twin. As used herein, a digital twin is a digital replica of a physical asset such as a manufactured part. The digital twin includes the characteristics of the physical asset at each stage of the manufacturing process, which include, among other things, the dimensions of the coordinate axes, weight characteristics, material characteristics (e.g., density, surface roughness), electrical characteristics (e.g., conductivity), and optical characteristics (e.g., reflectivity), but are not limited thereto.

[0075] In some embodiments, the physical models used by the digital replica tool 324 can include fluid flow modeling, gas flow and / or consumption modeling, chemistry-based modeling, heat transfer modeling, electrical energy consumption modeling, and plasma modeling.

[0076] In some embodiments, the digital replica tool 324 can utilize statistical modeling to predict the environmental efficiency of manufacturing data. The statistical model can be used to process manufacturing data based on past environmental efficiency data (e.g., environmental efficiency data 314) that has been previously processed, using statistical operations to verify, predict, and / or transform the manufacturing data. In some embodiments, the statistical model is generated using statistical process control (SPC) analysis to determine the control limits of the data and identify whether the data is reliable or unreliable based on those control limits. In some embodiments, the statistical model is associated with univariate and / or multivariate data analysis. For example, various parameters can be analyzed using the statistical model, and patterns and correlations can be determined through statistical processing (e.g., range, minimum value, maximum value, quartiles, variance, and standard deviation). In other examples, regression analysis, path analysis, factor analysis, multivariate statistical process control (MCSPC), and / or multivariate analysis of variance (MANOVA) can be used to confirm the relationships between multiple variables.

[0077] The optimization tool 326 receives the selection of the process recipe 308 and the machine device 304, identifies a modification to the selection, and can improve environmental efficiency (e.g., reduce resource consumption, resource cost consumption, and / or environmental impact (e.g., gas species or particulate species flowing into the atmosphere)). The optimization tool 326 can incorporate the use of a machine learning model (e.g., model 390 of the machine learning system 370). The machine learning model can receive the selection of the process recipe and / or the machine device as input and determine one or more modifications to the selection that improve the overall environmental efficiency of the selection when executed by the manufacturing system 302. In some embodiments, the machine learning model can use a digital replica tool to generate synthetic manufacturing data for training. Alternatively or additionally, the machine learning model can use past data (e.g., environmental efficiency data 314, sensor and process recipe data 316, and / or modification and optimization data 318) to train the machine learning model.

[0078] The modifications identified by the optimization tool 326 can include changes to processing steps, changes to the order of processes, changes to parameters executed by a part of the machine device, changes to the interaction between the first process recipe and the second process recipe (e.g., order, simultaneous processing, delay time, etc.). In some embodiments, the optimization tool 326 can send instructions to the manufacturing system 302 to directly execute the optimization. However, in other embodiments, the optimization tool can display the modifications on a graphical user interface (GUI) so that an operator can act accordingly. For example, the digital replica tool 324 can send one or more modifications to the client device 350 for display on the browser 352 and / or the application 354.

[0079] In some embodiments, the optimization tool 326 can adjust the hyperparameters of the digital twin model generated by the digital replica tool 324. As described in later embodiments, the optimization tool 326 can incorporate reinforcement learning and / or deep learning by executing simulated modifications on the digital replica and evaluating the environmental efficiency results output from the digital replica.

[0080] In some embodiments, the optimization tool 326 can perform an environmental efficiency characteristic evaluation and an optimization that prioritizes one or more types of environmental resources. For example, as previously described, the environmental efficiency characteristic evaluation can be based on various resource consumption amounts such as water usage, gas usage, and energy usage. The optimization tool 326 can perform an optimization that prioritizes the first resource consumption amount (e.g., water usage) over the second resource consumption amount (e.g., gas usage). In some embodiments, the optimization tool 326 can perform an optimization that uses a weighted priority system. For example, when optimizing environmental efficiency and / or identifying modifications to environmental efficiency for a manufacturing process, weights indicating optimization priorities for the resource consumption amount per relevant unit can be assigned to one or more resource consumption amounts.

[0081] The recipe builder tool 328 can receive a selection of a manufacturing process and / or a machine device, and dynamically and gradually determine and predict the environmental efficiency after each addition, each deletion, and / or each modification to the selection of the virtual manufacturing process and / or device. When the manufacturing recipe is updated, the recipe builder tool 328 can use other tools (e.g., the component integration tool 322, the digital replica tool 324, the optimization tool 326, and the resource consumption amount tool 330) to dynamically update the determined environmental efficiency. For example, a user can generate a manufacturing recipe. The recipe builder tool 328 can output the current environmental efficiency of the current iteration of the processing recipe. The recipe builder tool 328 can receive a modification for the current iteration that has updated the processing recipe. The recipe builder tool 328 can output the updated environmental efficiency characteristic value.

[0082] In some embodiments, the recipe builder tool 328 and the optimization tool 326 can be used to identify one or more recipes as being more environmentally efficient than other recipes. For example, the recipe builder tool 328 can cause one or more (e.g., the top three) of the most energy-efficient recipes associated with a processing tool to be presented on a GUI (e.g., the client device 350) or provided in some other way. The recipe builder tool 328 can use the digital replica tool 324 to provide detailed information indicating the basis for why one or more energy-efficient recipes are being executed with the corresponding high environmental efficiency.

[0083] The resource consumption tool 330 can track various resource consumptions. For example, as described above, the environmental characteristic evaluation can be based on a broader range of resources such as energy consumption, gas emissions, water usage, etc. However, the resource consumption tool 330 can track the resource consumption more specifically. In some embodiments, the selection of the processing recipe and / or manufacturing apparatus is received by the resource consumption tool 330. The resource consumption tool 330 can determine the lifetime data of components associated with the selection of the manufacturing apparatus and / or processing recipe. For example, a mechanical device wears out during use and, in some cases, improvement measures such as component replacement and / or repair are required. This improvement measure is also associated with the environmental consumption (e.g., resource consumption for performing the improvement measure). The resource consumption tool 330 can track the lifetime data of components individually and provide the environmental resource consumption per unit and / or environmental impact based on improvement measures predicted to be performed in the future.

[0084] In some embodiments, the environmental resource consumption can be monitored, tracked, and / or otherwise determined over various failures. In some embodiments, the resource consumption tool 330 can perform live monitoring of energy, gas, and water consumption. The resource consumption tool 330 can determine the consumption at the chamber level (e.g., per wafer, per day, per week, per year, etc.), including calculating the total consumption of electricity, gas, and water in the chamber. The resource consumption tool 330 can determine the consumption at the tool level (e.g., per wafer, per day, per week, per year, etc.), including determining the total consumption of electricity, gas, and water of the tool. The resource consumption tool 330 can determine the individual gas consumption, including determining the breakdown of the individual gas consumption (e.g., per wafer, per day, per week, per year, etc.). The resource consumption tool 330 can generate a standard report including the energy, gas, and water consumption at the chamber and tool levels.

[0085] In some embodiments, the resource consumption tool 330 can determine the total consumption of electricity, gas, and water for all subfab components (e.g., per wafer, per day, per week, per year, etc.). The resource consumption tool can determine the consumption at the recipe level, including the total consumption of electricity, gas, and water for the corresponding chambers and / or recipes executed on the tools. The resource consumption tool can determine the consumption at the component level, including the breakdown of the energy consumption of all energy-consuming components within the chamber. The resource consumption tool 330 can execute on-demand customized reports, which includes determining on-demand customized information and on-demand customized environmental efficiency reports. The resource consumption tool 330 can perform comparisons between energy consumption for various recipes and / or points in time, which includes using recipe optimization (e.g., using the optimization tool 326) to quantify energy savings and opportunities for energy savings.

[0086] The investigation tool 332 can communicate with the digital replica tool 324 when determining the impact of one or more updates to the manufacturing apparatus 304. The investigation tool 332 can utilize the digital replica tool 324 to generate a digital replica, including a digital replication of the substrate manufacturing system (e.g., the manufacturing apparatus 304). The investigation tool can receive an update to the manufacturing apparatus and enable a user to investigate, among other things, various alternative arrangements to the apparatus being used, apparatus settings, and process parameters associated with the performance of the apparatus. The investigation tool 332 can use the resource consumption tool 330 to determine environmental resource usage data corresponding to the execution of one or more processing procedures by the substrate manufacturing system incorporating the updates described herein. The environmental resource usage data can be provided for display on a graphical user interface (GUI) (e.g., on the client device 350).

[0087] In some embodiments, an update to the manufacturing system can include replacing a first hardware subsystem device with a second hardware subsystem device having one or more operating specifications different from those of the first hardware subsystem device. In an exemplary embodiment, an update to the manufacturing system can include changing a first setting of a manufacturing apparatus to a second setting of the manufacturing apparatus. In an exemplary embodiment, an update to the manufacturing system can include changing a scheduled operating mode of a physical asset of the substrate manufacturing system, where the scheduled operating mode includes a power reduction mode. In an exemplary embodiment, the update includes changing a scheduled operating mode of a support asset of the substrate manufacturing system to a shared operating mode, where a support asset operating in the shared operating mode alternately performs support functions for a plurality of physical assets of the substrate manufacturing system that execute one or more processing procedures.

[0088] In some embodiments, a digital twin can be used to estimate the lifetimes of some consumables associated with manufacturing process steps. Lifetime data can be used to estimate the lifetime period and predict future improvement measures to be taken according to the predicted lifetime. For example, by using lifetime data to notify in advance an order for replacement parts to a supply chain, an optimized environmental efficiency performance can be maintained.

[0089] In some embodiments, environmental resource usage data determined by other tools of a server can include the environmental resource consumption and / or environmental impact associated with either an exchange procedure or a maintenance procedure of a consumable part of a first manufacturing apparatus. In some embodiments, an optimization tool 326 can determine a modification to the manufacturing process, and the modification can include performing a corrective measure associated with a component of a mechanical device (e.g., mechanical device 304).

[0090] The investigation tool 332 can perform an ownership cost analysis associated with the manufacturing system. The ownership cost analysis can include a comprehensive analysis regarding the interoperability (interworking) of the manufacturing system for calculating the total cost of owning and / or operating the system. The investigation tool 332 can calculate the cost for a customer to perform a specific manufacturing procedure. The investigation tool 332 can determine the cost of a wafer, the cost corresponding to the gas used by the system, the cost associated with the tools in use (e.g., lifetime degradation data), and the power for the manufacturing system to perform one or more processing procedures. The ownership cost can be calculated per unit (e.g., per wafer).

[0091] In some embodiments, the machine learning system 370 further includes a server machine 372, a server machine 380, and / or a server machine 392. The server machine 372 includes a dataset generator 374, and the dataset generator 374 can generate a dataset (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing the machine learning model 390.

[0092] Server machine 380 includes a training engine 382, a verification engine 384, and / or a test engine 386. An engine (e.g., training engine 382, verification engine 384, and / or test engine 386) can refer to hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (e.g., instructions executed on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 382 can train the machine learning model 390 using one or more sets of features associated with the training set from the dataset generator 374. The training engine 382 can generate one or more trained machine learning models 390, where each trained machine learning model 390 can be trained based on a distinct set of features of the training set and / or a distinct set of labels of the training set. For example, the first trained machine learning model may be trained using the resource consumption data output by the digital replica tool 324, and the second trained machine learning model may be trained using past environmental efficiency data (e.g., environmental efficiency data 314), and so on.

[0093] The verification engine 384 can verify the trained machine learning model 390 using the verification set from the dataset generator 374. The test engine 386 can test the trained machine learning model 390 using the test set from the dataset generator 374.

[0094] The machine learning model 390 may refer to one or more trained machine learning models generated by the training engine 382 using a training set that includes data inputs and, in some embodiments, corresponding target outputs (e.g., correct answers for each training input). Patterns that cluster the data inputs and / or map the data inputs to the target outputs (correct answers) are found within the data set, and the machine learning model 390 is provided with a mapping that captures the patterns and / or the machine learning model 390 learns the mapping. The machine learning model 390 may include an artificial neural network, a deep neural network, a convolutional neural network, a recurrent neural network (e.g., an LSTM (long short term memory) network, a convLSTM network, etc.), and / or other types of neural networks. Additionally or alternatively, the machine learning model 390 may include other types of machine learning models such as those that use one or more of linear regression, Gaussian regression, random forest, and support vector machine.

[0095] One type of machine learning model that can be used to perform some or all of the above tasks is an artificial neural network such as a deep neural network. Artificial neural networks generally include a feature representation component, which includes a classifier or a regression layer that maps features to a desired output space. A convolutional neural network (CNN) hosts, for example, multiple layers of convolutional filters. In lower layers, pooling is performed and non-linearity can be addressed. Above the lower layers, a multi-layer perceptron is generally added. At the top layer, the features extracted by the convolutional layer are mapped to produce a decision (e.g., a classification output). Deep learning is a class of machine learning algorithms that uses a cascade of multiple layers of non-linear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. Deep neural networks can learn in supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) forms. Deep neural networks include a hierarchy of layers, and different layers learn different levels of representation corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into a slightly more abstract composite representation. For example, in an image recognition application, the raw input is a matrix of pixels, the first representation layer can abstract the pixels to encode edges, the second layer can synthesize and encode the arrangement of the edges, the third layer can encode higher-level shapes (e.g., teeth, lips, gums, etc.), and the fourth layer can recognize the role of the scan. It should be noted that the deep learning process can learn for itself which features to optimally place at which level. The "deep" in "deep learning" refers to the number of layers that transform the data. More precisely, a deep learning system has a relatively deep CAP (credit assignment path). The CAP is a chain of input-to-output transformations. The CAP describes the potential causal relationship between the input and the output.In the case of a feed-forward neural network, the depth of the CAP can be the depth of the network and can be the number of hidden layers plus one. For a recurrent neural network where a signal can propagate through a layer multiple times, the depth of the CAP is potentially unlimited.

[0096] The training of a machine learning model can be broadly classified into supervised learning and unsupervised learning. In an embodiment, both techniques can be used to train a machine learning model. In one embodiment, the training of a neural network can be realized in the form of supervised learning, which involves supplying a training data set consisting of labeled inputs through the network, observing its output, defining an error (by measuring the difference between the output and the label value), and using techniques such as deep gradient descent and backpropagation to adjust the weights of the network across all its layers and nodes so that the error is minimized. In many applications, by repeating this process over multiple labeled inputs in the training data set, a network can be obtained that can generate correct outputs even when presented with inputs different from those present in the training data set. In high-dimensional settings such as large images, this generalization is achieved when a sufficiently large and diverse learning data set is provided.

[0097] For model training, a training dataset containing hundreds, thousands, tens of thousands, hundreds of thousands, or more data inputs should be used to train the dataset. In embodiments, cases of up to thousands, tens of thousands, hundreds of thousands, or millions of past data (e.g., processes executed within a processing chamber and associated labels of resource consumption) may be available for forming the training dataset, where each case may include various labels of one or more types of useful information. Each case may include data indicating, for example, a processing chamber, a recipe, and the utilization of various resources. The above data is processed to generate one or more training datasets for training one or more machine learning models. The machine learning model is trained to estimate, for example, resource consumption and / or environmental efficiency, and to propose modifications to the recipe and / or processing chamber based on the input processing chamber and / or recipe information. Such a trained machine learning model can be added to an environmental efficiency dashboard and applied to provide detailed information about resource consumption and environmental efficiency, as well as ways to reduce resource consumption and / or improve environmental efficiency before, during, and / or after the execution of a process in a processing chamber.

[0098] The processing logic unit can collect a training dataset including past process execution information having one or more associated labels (such as, for example, resource consumption, environmental efficiency values, recommendations for improving processing recipe parameters, etc.). The training dataset can be augmented additionally or alternatively. For training large neural networks, generally tens of thousands of inputs are used, but such inputs are not easily obtained in many real-world applications. It is possible to artificially increase the effective sample size using data augmentation.

[0099] To perform training, the processing logic unit inputs a training dataset into one or more untrained machine learning models. The machine learning models can be initialized before the first input is provided to them. The processing logic unit trains the untrained machine learning models based on the training dataset and generates one or more trained machine learning models that perform the various processes described above.

[0100] Training can be performed by inputting one or more data inputs into the machine learning model one by one. Each input can include data from past process executions in the training data items from the training dataset. The machine learning model processes the input and generates an output. An artificial neural network includes an input layer consisting of values at data points (e.g., the intensity value and / or height value of a pixel in a height map). The next layer is called a hidden layer, and each node in the hidden layer receives one or more input values. Each node includes parameters (e.g., weights) to apply to the input values. Thus, each node basically inputs the input values into a multivariate function (e.g., a non-linear mathematical transformation) to generate an output value. The next layer can be another hidden layer or an output layer. In either case, the nodes in the next layer receive the output values from the nodes in the previous layer, and each node applies weights to the value and then generates its own output value. This is done for each layer. The last layer is the output layer, where there is one node for each class, prediction, and / or output that the machine learning model can generate. Thus, the output can include predicted or estimated resource consumption amounts for one or more types of resources and can include environmental efficiency values, etc.

[0101] Thereafter, the processing logic unit can compare the generated output with the known label included in the training data item. The processing logic unit determines an error (i.e., classification error) based on the difference between the output and the provided label. The processing logic unit adjusts the weights of one or more nodes in the machine learning model based on the above error. An error term or delta can be determined for each node in the artificial neural network. Based on the above error, the artificial neural network adjusts one or more of its own parameters (weights for one or more inputs of the nodes) of one or more of its own nodes. The parameters can be updated in the way of backpropagation such that the topmost nodes are updated first and subsequently the nodes of the next layer are updated. The artificial neural network includes multiple layers of "neurons", and each layer receives values as inputs from the neurons of the previous layer. The parameters for each neuron include weights associated with the values received from each neuron of the previous layer. Therefore, adjusting the parameters can include adjusting the weights assigned to each input for one or more neurons in one or more layers within the artificial neural network.

[0102] Once the model parameters are optimized, model validation can be performed to determine whether the model has improved and to determine the current accuracy of the deep learning model. After one or more rounds of training, the processing logic unit can determine whether the stopping criterion is met. The stopping criterion can be a target level of accuracy, a target number of processed images from the training dataset, a target amount of change to the parameters for one or more previous data points, combinations of these, and / or other criteria. In one embodiment, the stopping criterion is met when at least a minimum number of data points have been processed and at least a threshold accuracy has been achieved. The threshold accuracy can be, for example, 70%, 80%, or 90% accuracy. In one embodiment, the stopping criterion is met when the accuracy of the machine learning model no longer improves. If the stopping criterion is not met, further training is performed. If the stopping criterion is met, the training can be completed. Once the machine learning model is trained, a reserved portion of the training dataset is used to test the model.

[0103] The modification identification component 394 can provide current data to the trained machine learning model 390 and can execute the trained machine learning model 390 on the input to obtain one or more outputs. The modification identification component 394 can make a determination and / or execute processing from the output of the trained machine learning model 390. The output of the ML (Modification identification) model is confidence data, which can include confidence data indicating that the output of the ML model (e.g., modification and optimization parameters), if applied, corresponds to a modification that improves the overall environmental efficiency of the selection of the manufacturing process and / or manufacturing equipment. The modification identification component 394 can, in some embodiments, execute a modification of the processing recipe based on the ML model output. The modification identification component 394 can provide the output of the ML model to one or more tools of the server 320.

[0104] Confidence data can include or indicate the confidence that the output of the ML model is correct (e.g., the output of the ML model corresponds to a known label associated with a training data item). In one example, the confidence is a real number between 0 and 1, where 0 indicates no confidence that the output of the ML model is correct and 1 indicates absolute confidence that the output of the ML model is correct. Depending on the confidence data indicating a confidence below a threshold for a given number of instances (e.g., a percentage of instances, a frequency of instances, a total number of instances, etc.), the server 320 can retrain the trained machine learning model 390.

[0105] By way of illustration and not limitation, in aspects of the present disclosure, to determine the output of an ML model (such as process modification and optimization parameters like a target environmental efficiency for a particular resource consumption), it is described to train a machine learning model using process recipe data and input the current selections of the manufacturing process and / or manufacturing equipment into the trained machine learning model. In other embodiments, a heuristic model or a rule-based model is used to determine the output (e.g., without using a trained machine learning model).

[0106] In some embodiments, the functionality of the manufacturing system 302, the client device 350, the machine learning system 370, the data store 312, and / or the server 320 can be provided by fewer machines. For example, in some embodiments, the server machines 372 and 380 can be integrated into a single machine, and in some other embodiments, the server machine 372, the server machine 380, and the server machine 392 can be integrated into a single machine. In some embodiments, the server 320, the manufacturing system 302, and the client device 350 can be integrated into a single machine.

[0107] Generally, the functions described as being performed by the manufacturing system 302, the client device 350, and / or the machine learning system 370 in one embodiment can also be performed on the server 320 as appropriate in other embodiments. Further, the functions belonging to a particular component can be performed by different components or by multiple components operating together. For example, in some embodiments, the server 320 can receive manufacturing data and perform machine learning processing. In other examples, the client device 350 can perform processing of manufacturing data based on the output from a trained machine learning model.

[0108] Further, the functions of a particular component can be performed by different components or by multiple components operating together. One or more of the server 320, the manufacturing system 302, or the machine learning system 370 can be accessed via an appropriate application programming interface (API) as a service provided to other systems or devices.

[0109] In an embodiment, a "user" can be represented as a single individual. However, other embodiments of the present disclosure include the case where a "user" is an entity controlled by multiple users and / or automated sources. For example, a collection of individual users formed as a group of administrators can be regarded as a "user".

[0110] FIG. 4 is a block diagram showing a structure 400 of an environmental efficiency sustainability system in which embodiments of the present disclosure can function. The above system structure 400 includes the selection of a processing tool 402 that includes one or more sub-components 404 (e.g., processing chambers). The system structure may further include support equipment that supports one or more sub-components, such as a power supply, a pump, an air flow, and a coolant flow. As described above, the processing tool 402 includes various manufacturing tools used to process substrates. In line 406, sensors (including sensors in the processing chamber and external sensors) measure manufacturing data (e.g., energy consumption sensor data, gas and water consumption data, etc.) and transmit it to the common infrastructure structure 408. The common infrastructure structure 408 may include one or more control algorithms configured to execute manufacturing process steps and manage processing parameters (e.g., critical processing parameters, machine diagnosis parameters, or parameters indicating the manufacturing process otherwise).

[0111] The common base structure 408 can send sensor data (from, for example, wired sensors and / or wireless sensors such as IoT sensors) to a data management algorithm (for example, the integration algorithm 410). The integration algorithm 410 can analyze the manufacturing data received from the processing tool 402 and select a part of the data for performing an environmental efficiency characteristic evaluation. The integration algorithm 410 extracts data to perform a cumulative environmental efficiency characteristic evaluation across the selection of manufacturing process steps and / or manufacturing apparatuses. The selected data can be used in association with the physical-based model 414 to determine the physical conditions of the processing tool 402 (for example, of each sub-component 404). The above data can be combined with scheduling information from, for example, on-board sequencers and / or planners or from operators (for example, at line 418). The scheduling information can include data indicating future recipes, tool idle states, and maintenance, etc. In some embodiments, one or more of the data and / or models described herein can be incorporated into one or more of a manufacturing central scheduler network or a software system or a manufacturing execution system.

[0112] The selection of manufacturing data combined with scheduling data can be input to the physical-based model 414. In some embodiments, the physical-based model is a mechanistic model. The mechanistic model examines the behavior of individual data points of manufacturing data and scheduling information and the form in which the individual data points are combined to determine a physical / mechanistic representation of the data combination. In some embodiments, the mechanistic model can include processing data to determine a prediction of resource consumption. For example, the mechanistic model can process manufacturing data to determine a prediction of resource consumption (such as water, energy, gas, etc.) and / or environmental impacts (such as gas species or particulate species flowing into the atmosphere). The mechanistic model can be generated using past manufacturing data and later used for current data to determine predictions.

[0113] In some embodiments, the physics-based model 414 can incorporate various physical relationships such as thermodynamics, fluid dynamics, energy conservation, gas laws, mechanical systems, transportation, and distribution. For example, a processing tool can include a cooling water flow to a part of a manufacturing apparatus device for performing a cooling process. The physics model can incorporate fluid dynamics including heat transfer to determine a model for converting raw manufacturing data into system process data that can characterize its environmental efficiency. In some embodiments, the physics model can be used to determine whether threshold resource consumption conditions are met. Along the same example, the physics model can be used to determine the flow rate of a fluid and then the heat transfer rate within a sub-component. If this heat transfer rate is below a threshold rate, additional energy may be diverted to exhaust. Thus, the physics model can determine that the fluid flow rate is operating below a desired flow rate level to maintain a desired environmental efficiency level.

[0114] In some embodiments, the physics-based model 414 incorporates the operating resource consumption of auxiliary or peripheral devices. For example, the energy consumption for powering a processing device to provide a control algorithm to a processing tool 402 (e.g., using a common infrastructure 408). The auxiliary devices are located in the vicinity of the manufacturing apparatus or not directly associated with a single manufacturing process, but can be allocated as a contribution to various manufacturing process steps (or individual manufacturing processes) using the physics-based model 414.

[0115] In some embodiments, in addition to or instead of using a physical model, a statistical model is used on the manufacturing data. The statistical model can be used to process the data based on statistical procedures to validate, predict, and / or transform the manufacturing data. In some embodiments, the statistical model is generated using statistical process control (SPC) analysis to determine control limits for the data and identify whether the data is reliable or unreliable based on the control limits. In some embodiments, the statistical model is associated with univariate and / or multivariate data analysis. For example, various parameters can be analyzed using the statistical model, and patterns and correlations can be determined through statistical procedures (e.g., range, minimum, maximum, quartiles, variance, standard deviation, etc.). In other examples, regression analysis, path analysis, factor analysis, multivariate statistical process control (MCSPC), and / or multivariate analysis of variance (MANOVA) can be used to identify relationships between multiple variables.

[0116] In some embodiments, system architecture 400 includes an adaptive optimization algorithm 416. The adaptive optimization algorithm 416 cooperates with physics-based model 414 to determine modifications to the selection of manufacturing equipment to perform the manufacturing process and / or related processes. In some embodiments, the adaptive optimization algorithm outputs automatic optimization commands to the control software (e.g., at line 424). In other embodiments, the adaptive optimization algorithm can output performance optimization suggestions to an operator (e.g., at line 420). In some embodiments, the adaptive optimization algorithm outputs automatic optimization commands targeted to hardware components (e.g., at line 422).

[0117] In some embodiments, the adaptive optimization algorithm 416 uses a machine learning model to determine modifications to the manufacturing process and / or manufacturing apparatus. The machine learning model can be a trained machine learning model (e.g., trained and executed using methods 700A - C). As described in further embodiments, the machine learning model can operate with a physics - based model to identify modifications to the manufacturing process and / or apparatus received as input.

[0118] The system architecture 400 can include an integrated dashboard GUI 412. The integrated dashboard GUI can be designed to display relevant manufacturing data (e.g., sensor data, machine diagnostics, machine status, manufacturing process status, etc.). In some embodiments, the integrated dashboard GUI includes a way to receive input from a user. For example, the user can input manufacturing data (e.g., using the recipe builder tool 328) to generate a recipe. This additional manufacturing data can be used as input to one or more of the physics - based model and the adaptive optimization algorithm 416. In embodiments, the dashboard includes a fleet view, a tool view, a device view, and a system schematic that illustrate various data, which include graphical displays indicating corresponding environmental resource consumption. Figures 9A - 9E illustrate further features, aspects, and / or details related to the integrated dashboard GUI.

[0119] Figure 5 shows a flowchart of an exemplary method 500 for monitoring, maintaining, and / or optimizing a manufacturing process. The exemplary method can be divided into two parts, namely, first, training a machine learning model 524 and second, executing a manufacturing process 504. The exemplary method 500 includes, in one embodiment, a machine learning model 502, tool software 506, tool hardware 508, and a physics model 512.

[0120] In some embodiments, a machine learning model receives a selection of a manufacturing process and / or a manufacturing apparatus and outputs one or more modifications to the manufacturing process and / or the manufacturing apparatus to improve environmental efficiency (e.g., reduce resource consumption). In some embodiments, a physical model 512 is used to generate simulated training / validation data 520. In response to the received simulated training / validation data 520, a machine learning model 502 generates simulated modifications 518, which can be fed back to the physical model 512 for verification. The machine learning model 502 is trained on various simulated and / or real training / validation data 520. Once trained, the machine learning model 502 can receive a selection of an empirical manufacturing system and / or a processing recipe executed by the system. The machine learning model 502 outputs manufacturing process instructions and / or modifications 504 to a system controller (e.g., system controller 128) implementing tool software. With the above modifications, environmental efficiency can be improved. Tool software 506 provides manufacturing process instructions 514 to tool hardware 508. The tool hardware 508 executes the manufacturing process. The tool hardware includes sensors, which report sensor data back to a system controller implementing the tool software 506.

[0121] In some embodiments, a system controller identifies that one or more physical states of the tool hardware violate threshold conditions (e.g., high temperature, overpressure, gas leak, power shortage, etc.). The system controller can modify the manufacturing process instructions to correct the violated threshold state (e.g., based on the output from the machine learning model 502).

[0122] A manufacturing system that includes tool hardware 508 reports empirical training / validation 510 back to the physical model 512. The physical model can then be updated, and the physical model can generate and update simulated training / validation data 520 that can be used for further training of the machine learning model.

[0123] In some embodiments, the physical model 512 generates simulated training / validation data, and in other embodiments, the physical model outputs a modification to the manufacturing process. In such embodiments, the machine learning model can be used as an optimization model to adjust hyperparameters (e.g., manufacturing data parameters) to identify modifications for further optimizing the manufacturing process. For example, the manufacturing process can be used as an input to the physical model 512. The machine learning model can then process the output of the physical model 512 to identify possible changes (i.e., hyperparameters) to the manufacturing process. The identified changes can be executed on the physical model to determine the corresponding updated environmental efficiency. This can be repeated in an iterative process for fine-tuning the design of the machine and the design of the recipe. In one example, the optimization model can be generated and / or implemented using an instance of the BFGS (Broyden-Fletcher-Goldfarb-Shanno) algorithm, a conjugate gradient (CG) algorithm, an instance of the Nelder-Mead algorithm, and / or a model predictive control (MPC) algorithm.

[0124] FIG. 6 shows an exemplary digital replica according to some embodiments of the present disclosure. The digital replica 600 can include a digital twin of a manufacturing system selection, and can include, for example, a digital replica of a manufacturing system including the same chamber, valves, gas supply lines, materials, and chamber components. The digital replica 600 can receive, as input, manufacturing apparatus process data, which can include first sensor data 602-604 output by an integrated sensor of a processing chamber and second sensor data 606-608 output by an external sensor that is not a component of the processing chamber. The input can further include a processing recipe of a manufacturing system including the processing chamber and / or can output physical conditions of the manufacturing system. In some embodiments, the digital replica 600 can include a physics-based model that can incorporate various physical relationships such as thermodynamics, fluid dynamics, energy conservation, gas laws, mechanical systems, transport, and distribution. The digital replica 600 processes the input data and generates an output 610. The output can include one or more physical conditions of the processing chamber and / or other systems or devices. The output can alternatively or additionally include environmental resource usage data.

[0125] In one example, the digital replica 600 can receive, as input, a first gas flow of a first gas, a second gas flow of a second gas, and a third gas flow of a third gas, and a first processing recipe. The digital replica can use the physics-based model to estimate the amount of energy exiting the chamber due to the gas flow. For example, the model determines the temperature of the exhaust and the total energy flow through the exhaust. In other examples, the same digital replica 600 can output a modification for environmental efficiency optimization such as different hardware configurations of the chamber (e.g., use of a first line type A vs. use of a second line type B). The digital replica can identify related parts of the system that affect heat loss to water, air, and HVAC and identify proposed optimization solutions to improve energy savings.

[0126] In some embodiments, the digital replica 600 can determine the exhaust for one or more gas panels or gas boxes containing gases used at one or more locations throughout the manufacturing system. For example, each gas box can use dedicated negative pressure exhaust to efficiently exhaust the gas (e.g., to prevent toxins from entering the manufacturing facility or an undesirable location in the manufacturing system) in the event of a gas line leak or more general failure. The digital replica is a digital twin and can be part of the digital twin that utilizes information about the assumed type and amount of gas in the gas box to determine the adjustments to the exhaust flow required for proper final disposal of the gas (e.g., to vent the leak). The exhaust flow rate can be determined taking into account the exhaust pressure and flow. The exhaust flow can include the determination of relevant parameters to optimize environmental efficiency while maintaining a minimum safety threshold and / or standard.

[0127] In some embodiments, the digital replica 600 can indicate the temperature of the exhaust and the total energy flow through the exhaust based on heating within the processing chamber. For example, the processing chamber can include one or more processing devices such as a substrate pedestal during a substrate processing procedure. Excess heat from within the chamber can be removed via the exhaust. The operation of the pedestal can be changed to reduce the heat lost via the exhaust. Several methods have been reported for controlling heat transfer in a pedestal that includes both a heating element and a cooling element that circulates a cooling medium such as a gas or liquid coolant inside the pedestal or between the substrate and the pedestal to remove excess heat. When the temperature of the substrate rises above the set range during the process, the heating element is turned off and the cooling element is activated to remove the excess heat, thereby controlling the temperature. One or more parameters associated with the above process are used as inputs to the digital replica 600, and it can be determined how much excess heat is lost via the exhaust.

[0128] In some embodiments, digital replica 600 may represent an energy flow and / or a chemical substance including a precursor or by-product of a reaction that exits a decontamination system or a scrubber system. For example, the gaseous effluent from the manufacture of electronic materials, devices, products, solar cells, and memory products (hereinafter, "electronic devices") may include various chemical compounds, organic compounds, oxidants, decomposition products of photoresists and other reagents, and other gases and particulates that may desirably be removed from the effluent before it is vented from the processing facility into the atmosphere.

[0129] The effluent to be excluded may include chemical species generated by the electronic device manufacturing process and / or chemical species that are transferred through the electronic device manufacturing process and passed through the processing chamber without chemically changing. As used herein, the term "electronic manufacturing process" is intended to be broadly construed to include any and all processes and unit operations in the manufacture of electronic devices, as well as any operations involving the processing or machining of materials used in or manufactured by electronic device and / or LCD manufacturing facilities, and any operations performed in connection with electronic device and / or LCD manufacturing facilities that do not involve active manufacturing (examples include conditioning of processing equipment, purging of chemical supply lines during start-up, etching cleaning of processing tool chambers, removal of toxic or harmful gases from emissions generated by electronic device and / or LCD manufacturing facilities, etc.).

[0130] In some embodiments, the digital replica 600 takes into account the exhaust stream of the leaked gas or as part of the cleaning procedure. For example, the gas is periodically flushed from the manufacturing asset to extend the life of the manufacturing asset, improve the performance of the product, or prepare the product for other functions that have been imposed. The digital replica 600 can determine the environmental consumption (e.g., energy consumption, gas consumption) associated with the execution of this purge procedure. For example, the digital replica 600 can indicate the energy consumption and / or gas consumption used to flush the system (e.g., continuously supply a gas stream to the system to maintain dynamic gas movement within the system). The digital replica 600 can indicate how the energy and / or gas consumption is changed by adjusting one or more gas flow rates (e.g., purge gas) within the processing system.

[0131] In some embodiments, the digital replica 600 can utilize the processing recipe to determine what gas is entering the processing chamber, what reactions are occurring on the substrate placed within the processing chamber, and what utilization of the gas occurs due to the reaction of the substrate. The digital replica 600 can further determine how much gas remains and in what quantity after the reaction has occurred on the substrate surface. The digital replica 600 can further determine the amount and type of gas lost by exclusion. The digital replica 600 can further determine what the final by-product of the excluded material is and the overall impact of the final by-product on the environment.

[0132] In some embodiments, one or more substrate processing procedures may require a constant gas flow to and / or from a processing chamber to process a substrate that meets target processing result conditions. The substrate processing system can perform a stable gas flow procedure by performing one or more transitions from a flow-to-vent to a flow-to-chamber to reduce transient air flow due to turning the air flow to the chamber on and off. For example, an initial gas flow can be started and vented, and once that gas flow stabilizes, a stable gas flow can be provided to the chamber by introducing the vented air into the processing chamber. The digital replica 600 can determine the gas consumption as a result of the above process (e.g., gas lost through the vent). For example, the digital replica can identify the transition time and the amount of gas lost through the gas vent during the transition period of the start or end of the gas flow. The digital replica can determine an optimization for the transition between the gas vent and the introduction of gas into the chamber. By optimizing the transition time, the time for the gas to reach a stable state can be identified while reducing the gas lost through the vent. In some embodiments, the transition frequency of the gas flow can be determined based on the processing result requirements. For example, the transition time of the gas flow can be determined (e.g., optimized) to include a flow rate that does not adversely affect the processing result in the corresponding processing chamber.

[0133] The digital replica 600 can be used to determine environmental efficiency data associated with one or more operating states of the physical assets of the manufacturing system. As an example, the digital replica 600 can receive data associated with one or more operating states of the physical assets of the manufacturing system. For example, the digital replica 600 can receive reduced power data, sleep mode data, shared operation mode data, and / or processing recipe data indicating one or more processing procedures performed by the manufacturing system, and these data are represented by the digital replica 600.

[0134] When one or more physical assets operate in various operating states during processing time and idle time, energy savings can be achieved. For example, in various steps of a manufacturing process, various elements of a sub-fab device may not be needed, and thus can be put into a sleep state, idle state, standby state, or off state according to how soon the element will be needed. Examples of power-saving low-power states include the idle state, sleep state, and hibernation state. The main differences between the three power-saving states are the duration and the amount of energy consumption. In energy savings in deeper levels of idle mode such as sleep or hibernation, it takes longer to return from the energy-saving mode to realize full production without affecting the quality or yield of the manufacturing process. To restore the processing chamber and related sub-fab devices to the BKM (best known method) temperature and pressure, it may take seconds, minutes, or hours depending on the degree of deviation from the BKM chamber conditions related to the power-saving states of the sub-fab devices and the processing chamber. The idle state usually lasts for several seconds, the sleep state usually lasts for several minutes, and the hibernation state usually lasts for several hours.

[0135] The digital replica 600 can identify one or more operating states / power states of the physical assets of a manufacturing system and determine the effect of using that power state in a given scenario (such as the hardware structure of the system, the hardware structure of the subsystem, the processing of one or more processing recipes, and the execution of a specific scheduled process, etc.). For example, the digital replica 600 can be a digital twin and can be part of a digital twin that determines the impact of such power states and scenarios for idle or full power or modulation before actually performing power adjustment in a manufacturing system.

[0136] Processing tools and related manufacturing systems can have various different power settings based on operational requirements. For example, while the processing tool is in the "off" state, there can be power settings where various airflow and decontamination systems are fully operational and a shutdown operation is performed after the manufacturing process is completed. For the purposes of this application, the term "low power configuration" refers to a state where one or more elements of the processing tool and / or the manufacturing system sub-fab are in a power-saving mode, commanded by one or more controllers, and are in any state that operates in a power-saving mode, such as, for example, steps of a particular processing recipe, or non-productive idle operation modes such as the idle states, sleep states, and hibernation states described above, or various levels of energy consumption between the off state.

[0137] In some embodiments, one or more support assets can provide support functions to one or more other physical assets. For example, the pumping of two processing chambers can be performed by one pump. By leveraging support assets to alternate the operation between two physical assets, energy can be saved and the overall environmental cost can be reduced.

[0138] The digital replica 600 can identify environmental resource consumption data associated with one or more physical assets operating in one or more corresponding operation modes. The digital replica 600 can provide recommendations for reducing environmental consumption costs when one or more physical assets are in a power reduction state, sleep mode state, hibernation state, and / or by recommending shared operation mode data during periods when the corresponding tool is in an idle state or when the demand on the physical asset is low.

[0139] In other examples, the digital replica 600 can be configured to determine environmental efficiency data associated with the execution of preventative maintenance (PM) and / or cleaning of the physical assets of the manufacturing system. The digital replica 600 can receive purge gas data, cleaning process data, preventative maintenance data, chamber recovery data, and / or a process recipe to determine the environmental resource consumption.

[0140] Substrate processing can include a series of processes that form an electrical circuit within a semiconductor, such as within a silicon wafer, according to a circuit design. The above processes can be executed within a series of chambers. The successful operation of current semiconductor machinery can aim to facilitate the movement of wafers in a stable flow from one chamber to another in the process of forming an electrical circuit within the wafer. In many processes that execute substrate processing, the conditions of the processing chamber degrade, and as a result, the processed substrate may not meet the desired conditions or processing results (e.g., critical dimensions, process uniformity, thickness dimensions, etc.).

[0141] The cleaning process data can indicate one or more parameters related to the cleaning process, such as the cleaning period, frequency, and / or etchant flow. The cleaning process can utilize specific environmental resources, such as cleaning materials, precursors, etchants, and / or other substances used to perform the cleaning procedure. For example, the cleaning procedure can be performed at a certain cadence or frequency (e.g., after a certain amount of wafers have been processed) for the sake of a processing result where the processing result of a future substrate meets threshold conditions (e.g., process uniformity, critical dimensions, etc.). The frequency of the process chamber cleaning can be adjusted (e.g., optimized) to identify a cleaning frequency where the results of the substrates processed by the chamber operating on the cleaning frequency schedule still meet the threshold conditions (e.g., minimum process result requirements). For example, a multi-wafer cleaning procedure that conserves environmental resources such as cleaning substances, precursors, etchants, and / or other substances used to perform the cleaning procedure can be realized. The digital replica 600D can receive the cleaning data and determine the optimization of the cleaning, such as updates to the cleaning period, frequency, amount of cleaning agent used, etc.

[0142] The preventive maintenance data indicates one or more of the types, frequencies, periods, etc. of one or more preventive maintenance procedures associated with one or more physical assets of the manufacturing system. Preventive maintenance procedures (e.g., chamber cleaning) are often used as part of the chamber recovery process to return the state of the process chamber to a state suitable for entering the substrate processing production mode (e.g., mass processing of substrates). Recovery procedures are often used following preventive maintenance procedures to prepare the chamber for the production mode (e.g., "warm up" the chamber).

[0143] Chamber recovery data indicates one or more of the type, frequency, duration, etc. of one or more chamber recovery procedures associated with one or more physical assets of the manufacturing system. A commonly used conventional recovery procedure is the seasoning of the processing chamber. Chamber seasoning is a procedure that includes processing a series of substrates (e.g., blank silicon wafers) to restore a chamber state suitable for a production substrate process (e.g., a substrate processed in the chamber having a processing result that meets a desired threshold criterion) (e.g., coating the walls of the chamber). After chamber seasoning, the chamber can operate in production mode for a certain period until the preventive maintenance needs to be re-implemented and further chamber seasoning is required or recommended to restore the state of the processing chamber.

[0144] Purge gas data can indicate the type, amount, frequency, flow rate, and cleaning duration of the purge gas. The digital replica can determine the impact of changing one or more process parameters related to the purge gas used. For example, the digital replica 600 can determine an update of the environmental resource consumption based on a switch to a purge procedure using alternative purge gas species such as H2, N2, and CDA.

[0145] In other examples, the digital replica 600 can be configured to determine environmental efficiency data associated with one or more operating states of the physical assets of the manufacturing system. The digital replica 600 can receive coolant loop configuration data, process chilled water (PCW) data, ambient air data, and / or a process recipe and determine environmental resource consumption data therefrom.

[0146] The processing chamber used during substrate processing typically includes several internal components that are repeatedly heated and cooled during and after the execution of the process. In some examples, for instance, when periodic inspections or maintenance are required after a process has been executed within the processing chamber, the above components are cooled to around room temperature. For temperature-controlled components such as a processing chamber showerhead having coolant channels, the heat source heating the component can be stopped in order to cool the component from a typical operating temperature (e.g., about 90 degrees Celsius), and coolant is flowed through the coolant channels to remove heat from the component.

[0147] Coolant loop configuration data indicates the shape of one or more coolant loops configured to remove heat from one or more physical assets of a manufacturing system. The one or more coolant loops can function in parallel, with multiple loops cooling a shared area of the physical asset. The one or more coolant loops can continuously cool multiple physical assets relative to each other. Process cooling water (PCW) data indicates one or more parameters of the cooling substance, such as the type, flow rate, and temperature of the coolant (e.g., example process cooling water (PCW)). The digital replica can include a heat flow model showing where energy is transferred within the environment of a manufacturing system that utilizes one or more coolant loops. The digital replica 600 can identify modifications to the physical assets (e.g., chambers, chamber walls, chamber systems) that direct heat to the coolant loops and the associated environmental efficiency ensured by directing heat to the coolant loops. The digital replica 600 can further determine the impact on process results while adjustments to the PCW are being made. Adjustments to the PCW can involve changing the flow rate within the cooling loop to vary heat exchange within the physical assets of the manufacturing system.

[0148] FIG. 7 is an exemplary diagram of process parameter limits 700 for manufacturing process steps according to some embodiments of the present disclosure. Various manufacturing process steps can include the process parameter limits 700, which are a process parameter window 710, or a set of values (e.g., a combination of values), that when satisfied, indicate a set of values to a corresponding set of parameters that result in meeting a threshold condition (e.g., a minimum quality condition). For example, the process parameter window 710 can include a first parameter 702 (e.g., a first flow rate of a first gas) and a second parameter 704 (e.g., the temperature of the gas). A process parameter value window 710 is determined that identifies a combination of parameter values that, when the manufacturing process is executed, results in a product that is likely to meet the threshold condition (e.g., a minimum quality standard, a statistical process control (SPC) limit, a specification limit, etc.). As shown in FIG. 7, the process parameter window 710 includes a lower limit value 706B and an upper limit value 706A for the first parameter 702, and a lower limit value 708B and an upper limit value 708A for the second parameter.

[0149] Optimization identified by the manufacturing process system (e.g., using the adaptive optimization algorithm 416 and / or the physics-based model 414) includes determining an eco-optimized process parameter window 712 within the process parameter window 710, which results in a manufacturing process that consumes a reduced amount of resources compared to process parameter values outside of the eco-optimized process parameter window 712.

[0150] Note that in FIG. 7, a simplified processing parameter window 710 and an eco-optimized processing parameter window 712 that depends only on two parameters 702, 704 are illustrated. Both the processing parameter window 710 and the eco-optimized processing parameter window 712 form simple rectangles. The processing parameter window can include more than two parameters and can include more diverse parameter dependencies. For example, non-linear processing parameter windows and eco-optimized processing parameter windows can be brought about by non-linear, physics-based, statistical, and / or empirical relationships between parameters.

[0151] FIG. 8 is a flowchart of a method 800 for monitoring environmental usage data of a processing chamber based on internal sensor data and external sensor data of the processing chamber, according to some embodiments of the present disclosure. For simplicity of explanation, method 800 is illustrated and described as a series of operations. However, the operations according to the present disclosure can occur in various orders and / or simultaneously with other operations not presented or described herein. Further, not all of the illustrated operations may be executed to perform method 800 according to the disclosed subject matter. Further, those skilled in the art will understand and recognize that method 800 can alternatively be represented as a series of interrelated states or events through a state diagram. Method 800 can be executed by processing logic that can include hardware (e.g., circuits, dedicated logic units, programmable logic units, microcode, etc.), software (e.g., instructions executed by a processing device to perform hardware simulation), or a combination thereof. In an embodiment, method 800 can be executed by system controller 128 of FIG. 1 and / or computing device 1000 of FIG. 10. Alternatively, method 800 can be executed by other devices such as computing device 250 of FIG. 2.

[0152] In block 805 of method 800, the processing logic unit receives first sensor data generated by a sensor in the processing chamber. In block 810, the processing logic unit receives second sensor data generated by an external sensor such as an IoT sensor (e.g., a sensor including an embedded system). In block 812, the processing logic unit can preprocess some or all of the first sensor data and / or the second sensor data. Such preprocessing can include any of the aforementioned preprocessing operations.

[0153] In block 815, the processing logic unit determines environmental resource usage data based on the first sensor data and the second sensor data. This can include, in block 820, inputting the first sensor data and the second sensor data into one or more models such as a digital replica, a digital twin, a physics-based model, a statistical model, and / or a machine learning model. In block 825, one or more models can output physical conditions associated with the manufacturing process executed on the chamber model. In block 830, the processing logic unit determines environmental resource usage data based on the physical conditions and / or the first sensor data and the second sensor data. This can include inputting the physical conditions, the first sensor data, and / or the second sensor data into a second model (e.g., a machine learning model) that can output environmental resource usage data. In some embodiments, in block 825, the above model outputs environmental resource usage data instead of or in addition to the physical conditions associated with the execution of the manufacturing process.

[0154] In block 835, the processing logic unit can determine whether the processing chamber is in an idle state or executing a manufacturing process (for example, the manufacturing process in which the environmental resource usage data in block 815 is determined). In block 840, the processing logic unit can output the status regarding whether the processing chamber is in an idle state or executing a manufacturing process on the GUI. In one embodiment, a graphical representation of the manufacturing system including the processing chamber is displayed on the GUI. The graphical representation can include icons for each processing chamber of the manufacturing system. A first visualization (for example, a first color such as red, and / or a first texture and / or fill pattern) is used for the icon associated with the processing chamber in the idle state, and a second visualization (for example, a second color such as green, and / or a second texture and / or fill pattern) is used for the icon associated with the processing chamber currently executing the process.

[0155] In block 845, the processing logic unit can provide environmental resource usage data for display on the GUI. As used herein, environmental resource usage data can include data regarding the consumption amount of resources and / or chemicals, the environmental impact of the resources and / or chemicals used / consumed, the energy consumption amount, and / or the environmental impact of the consumed energy. The environmental resource usage data can be output in real time or near real time while the process is being executed within the processing chamber, and can also include the current environmental resource usage (for example, environmental resource consumption amount, environmental impact of the resources / chemicals used, energy consumption amount, etc.) and the accumulated environmental resource consumption amount for the process being executed so far. Additionally or alternatively, the environmental resource usage data can be output after the process is completed and can indicate the total environmental resource consumption amount of that process.

[0156] In one embodiment, at block 850, the processing logic unit generates a set of one or more graphs, tables, and / or menus based on the environmental resource usage data. At block 855, the processing logic unit can output the set of graphs, tables, and / or menus on the GUI.

[0157] Figures 9A - E show various views of integrated environmental resource usage (e.g., environmental resource consumption, environmental impact of used resources / chemicals, energy consumption, etc.) dashboard graphical user interfaces (GUIs) 1000A - E according to some embodiments.

[0158] Figure 9A shows view 900A of an environmental resource usage (e.g., environmental impact of used resources / chemicals, energy consumption, etc.) dashboard GUI. View 900A can be the landing page or main page of the environmental efficiency platform.

[0159] As shown in Figure 9A, view 900A includes a system diagram 902. The system diagram 902 can include a schematic or mapping of one or more processing chambers and / or other processing tools. The system diagram 902 can be a live image or a video, and for each processing chamber, it can indicate whether the processing chamber is in an idle state or an active state. Additionally, in an embodiment, basic environmental resource usage data such as total or average or current electricity consumption and / or gas consumption can be shown above or beside each tool icon. Above the system diagram 902, there is an explanation of the manufacturing system such as tool type, serial number, manufacturing system name, and / or version number.

[0160] On the right side of the system diagram 902, there is a menu of components or tools of the manufacturing system (for example, including processing chambers). Selecting any of the components or tools in the menu can further display a view showing the environmental resource usage data of the selected tool or tools. As shown in the figure, A12, and C11, C12, C13 are all processing chambers. X1 is a transfer chamber. D11, D12, LD111, LD121 are load locks, and FI is a factory interface.

[0161] A report button is also shown in the upper right corner of the GUI. The user can click or select this report button to generate a report on the environmental resource usage of the manufacturing system. The report includes, for example, a detailed table of electricity consumption during a certain period and gas consumption during that period.

[0162] Figure 9B shows the second view 900B of the environmental resource usage dashboard GUI. The second view 900B can be displayed after the user selects one of the above tools (for example, processing chamber C11). The second view 900B shows the date range breakdown of the illustrated environmental resource usage data. In one embodiment, the second view 900B includes an electricity consumption breakdown 904 and a gas consumption breakdown 906. The electricity consumption breakdown 904 shows the contribution of one or more of the sub-components of the specified system to the electricity consumption. Sub-components can include items such as pumps, power supplies, HVAC, gas flows, heaters, and coolers.

[0163] The breakdown of chemical consumption 906 (e.g., the breakdown of gases, liquids, solids, etc. used) is similar to the breakdown of electrical consumption 904 and provides the consumption or loss of chemical substances attributable to one or more sub-components of a specified system. The consumed chemical substances include one or more gases, liquids, and / or solids. For example, some precursors for a process may be gases, while other precursors may be liquids and are converted to a vapor and / or gaseous state via a bubbler, injection, or atomization process before being injected into the processing chamber. View 900B can include a time-segmented representation of the electrical consumption of the system and / or the gas consumption of the system. For example, a 7-day history of electrical consumption can be illustrated. In one embodiment, the electrical consumption and gas consumption are shown in one or more pie charts.

[0164] View 900B shows an "All Recipes" button and a "Recipe Comparison" button in the upper right region of the GUI. Selecting the Recipe Comparison button can display the view shown in FIG. 9E. Selecting the "All Recipes" button can display the view shown in FIG. 9D.

[0165] View 900B shows a date window and a chamber window. The user can select the chamber window to display a drop-down menu from which any tool (e.g., a processing chamber) can be selected. A second View 900B will, in this case, be updated by replacing the environmental resource data associated with the previously selected tool with the environmental resource data associated with the newly selected tool in response to the selection of the new tool. Selecting the date window will display the view shown in FIG. 9C.

[0166] In some embodiments, the environmental resource usage dashboard GUI includes interfaces (e.g., buttons, dropdown menus, text input boxes, etc.) for launching, applying, and / or using one or more models such as the trained machine learning models and / or physics-based models described herein. For example, via the environmental resource usage dashboard GUI, a user can interact with, input, and select input information to be processed by a model (e.g., a physics-based model and / or a trained machine learning model) (e.g., via a dropdown menu, a text input window, a date selection window, etc.). Further, via the environmental resource usage dashboard GUI, a user can select a particular model or set of models (e.g., via a dropdown menu). The environmental resource usage dashboard GUI can display the output of one or more models on a display. The above output can include, for example, any of the outputs described above herein. Based on such output, a user can interact with the environmental resource usage dashboard GUI to perform actions such as scheduling maintenance and changing recipes.

[0167] FIG. 9C shows a second view 900B with a popup window 908 overlapping the second view 900B. The popup window 908 includes a calendar from which a user can select a start date and an end date for environmental resource usage data.

[0168] FIG. 9D shows a third view 900C of the GUI. In the third view 900C, it is possible to show, for each recipe, the electricity consumption, gas consumption, etc. The electricity consumption per recipe indicates the electricity cost resulting from the execution of one or more specified processing recipes. The electricity consumption per recipe may further indicate one or more quantities indicating the number of times the corresponding recipe has been executed. The gas consumption per recipe may indicate the gas usage or gas loss resulting from the execution of one or more specified processing recipes. The gas consumption per recipe may further indicate one or more quantities indicating the number of times the corresponding recipe has been executed. As shown in FIG. 9D, the GUI may include a navigation panel (e.g., interactive buttons) that enables the user to access various views of the GUI (e.g., including different representations of environmental efficiency data).

[0169] FIG. 9E shows a recipe comparison view 900D of the integrated environmental resource consumption dashboard GUI. As shown in FIG. 9E, view 900D shows a comparison of the electricity consumption, chemical consumption, and carbon footprint for two selected recipes over a certain date range. The user can select the first and second recipes to be compared via the recipe window, select the type of recipe via the recipe type window, select a chamber or tool via the chamber window, and select the date range for comparison via the date window. The types of recipes include cleaning recipes, inspection recipes, deposition recipes, and etching recipes, etc.

[0170] FIG. 10 shows a block diagram of an exemplary computing device operating in accordance with one or more aspects of the present disclosure. In various exemplary examples, the various components of computing device 1000 may represent various components such as a system controller 128, a computing device 250, a device executing a web client 220, etc.

[0171] An exemplary computing device 1000 can be connected to other computing devices in a LAN, intranet, extranet, and / or the Internet (e.g., using cloud environments, cloud technologies, and / or edge computing). The computing device 1000 can operate as a server in a network environment between a client and a server. The computing device 1000 can be a personal computer (PC), a set-top box (STB), a server, a network router, a switch or bridge, or any device capable of (sequentially or otherwise) executing a set of instructions (or a set of operations performed by such a device) that specify actions to be taken. Further, although only a single exemplary computing device is illustrated, the term "computer" should also be understood to include any collection of computers that individually or jointly execute a set of instructions (or multiple sets of instructions) to perform any one or more of the methods described herein.

[0172] The exemplary computing device 1000 can include a processing device 1002 (also referred to as a processor or CPU), a main memory 1004 (e.g., dynamic random access memory (DRAM) such as read-only memory (ROM), flash memory, synchronous DRAM (SDRAM)), a static memory 1006 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., data storage device 1018), which can communicate with each other via a bus 1030.

[0173] The processing device 1002 represents one or more general-purpose processing devices such as a microprocessor or a central processing unit. More specifically, the processing device 1002 can be a complex instruction set computing (CISC) micro-system processor, a reduced instruction set computing (RISC) micro-system processor, a very long instruction word (VLIW) micro-system processor, a processor that executes other instruction sets, or a processor that executes a combination of instruction sets. The processing device 1002 can also be one or more special-purpose processing devices such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal system processor (DSP), or a network processor. According to one or more aspects of the present disclosure, the processing device 1002 can be configured to execute instructions that implement the methods 600-800 illustrated in FIGS. 6-8.

[0174] The exemplary computing device 1000 can further include a network interface device 1008, which can be communicatively connected to a network 1020. The exemplary computing device 1000 can further include a video display 1010 (e.g., a liquid crystal display (LCD), a touch screen, or a cathode ray tube (CRT)), an alphanumeric input device 1012 (e.g., a keyboard), a cursor control device 1014 (e.g., a mouse), and an acoustic signal generating device 1016 (e.g., a speaker).

[0175] The data storage device 1018 may include a machine-readable storage medium (more specifically, a non-transitory machine-readable storage medium) 1028 in which one or more sets of executable instructions 1022 are stored. For example, the data storage may be on-premises physical storage or remote storage such as a cloud storage environment. According to one or more aspects of the present disclosure, the executable instructions 1022 may include executable instructions related to the execution of method 800 of FIG. 8. In one embodiment, the instructions 1022 include the instructions of the environmental efficiency module 129 of FIG. 1.

[0176] The executable instructions 1022 may also be present, in whole or at least in part, within the main memory 1004 and / or within the processing device 1002 while being executed by the exemplary computing device 1000, and the main memory 1004 and the processing device 1002 also constitute a computer-readable storage medium. The executable instructions 1022 may further be transmitted or received over the network via the network interface device 1008.

[0177] In FIG. 10, the computer-readable storage medium 1028 is shown as a single medium, but the term "computer-readable storage medium" should be understood to include a single medium or multiple media (e.g., a centralized database or a distributed database, and / or associated caches and servers) that store one or more sets of processing instructions. The term "computer-readable storage medium" should also be interpreted to include any medium that can store or encode a set of instructions for causing a machine to execute any one or more of the methods described herein. Thus, the term "computer-readable storage medium" should be interpreted to include, but not be limited to, solid-state memory, optical media, and magnetic media.

[0178] Certain portions of the detailed descriptions are presented from the perspective of algorithms and symbolic representations of operations on data bits within a computer memory. The above algorithmic descriptions and representations are means used by those skilled in the data processing arts to most effectively convey the substance of their work to other such skilled artisans. An algorithm is here, and generally, considered to be a consistent sequence of steps leading to a desired result. The above steps are steps that require physical operations of physical quantities. Usually, but not necessarily so, the above physical quantities take the form of electrical or magnetic signals that can be stored, transferred, combined, compared, or otherwise manipulated. It has proven convenient, mainly for reasons of common usage, to represent the above signals in terms of bits, values, elements, symbols, characters, terms, or numbers, etc.

[0179] However, it should be noted that all of these terms and similar terms should be associated with appropriate physical quantities and are merely convenient labels applied to such physical quantities. Unless otherwise specifically stated, throughout this specification, descriptions using terms such as "providing", "determining", "storing", "adjusting", "causing", "receiving", "comparing", "creating", "stopping", "loading", "copying", "throwing", "replacing", or "performing" are to be understood as referring to the actions and processes of a computer system or similar electronic computing device that manipulates data represented as physical quantities (electrical quantities) in the registers and memories of the computer system and converts such data into other data similarly represented as physical quantities in the memory or registers of the computer system, or other storage devices, transmission devices, or display devices for such information.

[0180] Embodiments of the present disclosure also relate to an apparatus for executing the methods described herein. The apparatus can be specially configured for the required purpose or can be a general-purpose computer system selectively programmed by a computer program stored in the computer system. Such a computer program can be selectively stored on a computer-readable storage medium such as, but not limited to, any type of disk including optical disks, CD-ROMs, and magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk storage media, optical storage media, flash memory devices, other types of machine-accessible storage media, or any type of medium suitable for storing electronic instructions.

[0181] The methods and displays presented herein are not inherently related to any particular computer or other device. It will be appreciated that various general-purpose systems may be used in conjunction with the programs in accordance with the teachings herein, or that it may prove more convenient to construct a more specialized device to perform the required method steps. The structure of various such systems will become apparent from the description below. Further, the scope of the present disclosure is not limited to any particular programming language. It is understood that various programming languages may be used to implement the teachings herein.

[0182] It should be understood that the description in the previous specification is for illustrative purposes and not for limitation. Reading and understanding the description in the previous specification will make many other embodiments apparent to those skilled in the art. Although specific examples are described in this disclosure, it will be understood that the systems and methods of this disclosure are not limited to the embodiments described herein and can be implemented with modifications within the scope of the appended claims. Correspondingly, this specification and the drawings should be regarded as illustrative rather than limiting in meaning. Therefore, the scope of this disclosure should be determined in relation to the appended claims, together with the full scope of equivalents to which the claims are entitled.

Claims

1. A method comprising: receiving, by a processing device, first sensor data generated by a plurality of sensors of a processing chamber of a manufacturing system during execution of a manufacturing process; receiving, by the processing device, second sensor data generated by one or more external sensors that are not components of the processing chamber during execution of the manufacturing process; determining, by the processing device, environmental resource usage data indicating an environmental resource consumption amount of the manufacturing process executed in the processing chamber based on the first sensor data and the second sensor data; providing, by the processing device, the environmental resource usage data for display on a graphical user interface (GUI). A method as described above.

2. Determining the environmental resource usage data includes: inputting the first sensor data and the second sensor data into a trained model that outputs the environmental resource usage data, according to the method of Claim 1.

3. Determining the environmental resource usage data includes: inputting the first sensor data and the second sensor data into a digital replica of the processing chamber, where the digital replica outputs physical conditions associated with the manufacturing process; determining the environmental resource usage data based at least in part on the physical conditions associated with the manufacturing process. A method as described in Claim 2.

4. The digital replica includes a physics-based model of one or more physical assets of the manufacturing system, the physics-based model showing: one or more gases entering the processing chamber; one or more reactions occurring on a substrate disposed within the processing chamber; one or more relationships between the one or more gases and the one or more reactions occurring on the substrate. A method as described in Claim 2.

5. The environmental resource usage data includes at least one of an energy consumption amount, a gas consumption amount, a carbon footprint, or a water consumption amount associated with the processing chamber executing the manufacturing process, according to the method of Claim 1.

6. The first sensor data includes measurements of at least one of current, voltage, power, flow rate, pressure, concentration, velocity, acceleration, or temperature. The method according to claim 1, wherein the second sensor data includes at least one measurement value of current, flow rate, temperature, eddy current, concentration, vibration, voltage, or power factor.

7. The method according to claim 1, wherein the one or more external sensors include IoT sensors that provide the second sensor data to an IoT (Internet-of-Things) hub, and the second sensor data is received by the processing device from the IoT hub.

8. The method according to claim 1, wherein the processing device is a processing device of the manufacturing system, the one or more external sensors include IoT sensors that provide the second sensor data to an IoT (Internet-of-Things) hub, the IoT hub transmits the second sensor data to a remote computing device connected to the IoT hub via a network, and the processing device receives the second sensor data from the remote computing device.

9. The method according to claim 1, wherein the processing device is a processing device of the manufacturing system.

10. generating a set of graphs, tables, and menus based on the environmental resource usage data; displaying the set of graphs, tables, and menus via the GUI; The method according to claim 1, further comprising.

11. determining whether the processing chamber is in an idle state or executing the manufacturing process or an alternative manufacturing process; displaying a representation of the manufacturing system via the GUI, the representation of the manufacturing system including a representation of the processing chamber, the representation of the processing chamber including a first visualization when the processing chamber is in an idle state and a second visualization when the processing chamber is executing the manufacturing process or the alternative manufacturing process; The method according to claim 1, further comprising.

12. Before determining the environmental resource usage data based on the first sensor data and the second sensor data, preprocessing the first sensor data and the second sensor data, wherein preprocessing the first sensor data and the second sensor data includes at least one of: a) labeling at least one of the first sensor data or the second sensor data; b) synchronizing at least one of the first sensor data or the second sensor data based on a timestamp; c) normalizing at least one of the first sensor data or the second sensor data; or d) changing the measurement unit of one or more measurement values of at least one of the first sensor data or the second sensor data. The method according to claim 1.

13. Using at least one of the environmental resource usage data or a recipe used for the manufacturing process as an input to a trained machine learning model; Obtaining one or more outputs of the trained machine learning model, wherein the one or more outputs indicate modifications to the manufacturing process that reduce the environmental resource consumption of the manufacturing process executed in the processing chamber. Obtaining one or more outputs. The method according to claim 1, further comprising.

14. The method according to claim 1, wherein the first sensor data and the second sensor data are received in parallel.

15. A system, A manufacturing system, One or more processing chambers for processing a substrate, the one or more processing chambers including a first plurality of sensors; A transfer chamber coupled to the one or more processing chambers, the transfer chamber including a robot for transferring the substrate between the one or more processing chambers; and A system controller for controlling the one or more processing chambers and the transfer chamber A manufacturing system including; A second plurality of sensors that are external sensors that are not components of any of the one or more processing chambers; A hub communicating with the second plurality of sensors; Comprising, The system controller is Receiving first sensor data generated by the first plurality of sensors during execution of a manufacturing process in a first processing chamber of the one or more processing chambers; Receiving second sensor data generated by the second plurality of sensors associated with the first processing chamber; Determining environmental resource usage data indicative of an environmental resource consumption amount of the manufacturing process executed in the first processing chamber based on application of the first sensor data and the second sensor data to one or more models; Providing the environmental resource usage data for display on a graphical user interface (GUI); A system for.

16. The one or more models include a digital replica of a processing chamber among the one or more processing chambers, and determining the environmental resource usage data is Inputting the first sensor data and the second sensor data into the digital replica of the processing chamber, wherein the digital replica outputs physical conditions associated with the manufacturing process, inputting the first sensor data and the second sensor data; Determining the environmental resource usage data based at least in part on the physical conditions associated with the manufacturing process; The system according to claim 15, comprising:

17. The environmental resource usage data includes at least one of an energy consumption amount, a gas consumption amount, a carbon footprint, or a water consumption amount associated with the first processing chamber that executes the manufacturing process, The first sensor data includes at least one measurement value of current, voltage, power, flow rate, pressure, concentration, speed, acceleration, or temperature, The system according to claim 15, wherein the second sensor data includes at least one measurement value of current, flow rate, temperature, eddy current, concentration, vibration, voltage, or power factor.

18. The system according to claim 15, wherein the hub includes an IoT (Internet of Things) hub that wirelessly receives the second sensor data from the second plurality of sensors, and the second plurality of sensors include IoT sensors.

19. A remote computing device, Receiving the environmental resource usage data from the system controller; Storing the environmental resource usage data in a database; Outputting the environmental resource usage data to the GUI; The system according to claim 15, further comprising a remote computing device for.

20. A non-transitory machine-readable storage medium containing instructions which, when executed by a processing device, cause the processing device to receive, by the processing device, first sensor data generated by a plurality of sensors of a processing chamber of a manufacturing system during execution of a manufacturing process; receive, by the processing device, second sensor data generated by one or more external sensors that are not components of the processing chamber during execution of the manufacturing process; determine, by the processing device, environmental resource usage data indicating an environmental resource consumption amount of the manufacturing process executed in the processing chamber based on the first sensor data and the second sensor data; provide, by the processing device, the environmental resource usage data for display on a graphical user interface (GUI). A non-transitory machine-readable storage medium that causes the above to be performed. **Claim 21** Determining the environmental resource usage data includes inputting the first sensor data and the second sensor data into a trained model that outputs the environmental resource usage data. The non-transitory machine-readable storage medium according to claim 20.

Images