Uniform Radiant Heating Control Architecture

Abstract

[0005] Embodiments disclosed herein include a method for modeling a rapid thermal processing (RTF) tool. In one embodiment, the method includes developing a lamp model for the RTF tool, the lamp model including a plurality of lamp zones, calculating an irradiance graph for the plurality of lamp zones, multiplying irradiance values ​​of the plurality of lamp zones in the irradiance graph by an existing RTF tool power at a given time during a process recipe, summing the multiplied irradiance values ​​for the plurality of lamp zones to form an exposure graph of the lamp model, using the exposure graph as an input to a machine learning algorithm, and outputting a temperature across a virtual substrate from the machine learning algorithm.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Patent Application No. 17 / 695,619, filed March 15, 2022, the entire contents of which are incorporated herein by reference.

[0002] The embodiments relate to the field of semiconductor manufacturing, and in particular to a process for estimating thermal uniformity across a substrate in a modeled tool. [Background technology]

[0003] In semiconductor processing environments, for example, rapid thermal processing (RTP) tools are used to perform thermal processes (e.g., annealing) and grow material layers (e.g., oxide growth), to name a few applications. In RTP tools, an array of lamps is used to heat a substrate placed under the lamps. Also, in some cases, a reflector may be provided under the substrate. Temperature control across the surface of the substrate is a critical parameter of RTP tools. Often, it is desired that the temperature be substantially uniform across the diameter of the substrate.

[0004] To control temperature, RTP tools often include lamps grouped into zones. Lamps in a single zone may be supplied with the same amount of power, and different zones may have different power levels. For example, the power in a zone near the center of the substrate may be different from the power in a zone toward the edge of the substrate.

[0005] Controlling the temperature across a substrate is a complex engineering challenge. While positioned over one area of ​​the substrate, lamp irradiation can also heat adjacent areas of the substrate. Thermal modeling must also take into account chamber wall temperatures, edge ring temperatures, reflector materials, and substrate materials, among many other parameters.

[0006] Thus, it is very difficult to model an RTP tool. Moreover, the models that are created are computationally intensive and require long periods of time to generate thermal behavior within the system. The complexity of creating such models makes it difficult to model new RTP tool designs. For example, it may be desirable to reduce the number of lamps in an RTP tool (e.g., to reduce manufacturing costs, reduce power consumption, etc.). However, existing solutions limit the ability to test new designs before they are implemented in physical form. Summary of the Invention

[0007] Embodiments disclosed herein include a method of modeling a rapid thermal processing (RTP) tool. In one embodiment, the method includes developing a lamp model of the RTP tool, the lamp model including a plurality of lamp zones, calculating an irradiance graph for the plurality of lamp zones, multiplying irradiance values ​​of the plurality of lamp zones in the irradiance graph by an existing RTP tool power at a given time during a process recipe, summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiation graph of the lamp model, using the irradiation graph as an input to a machine learning algorithm, and outputting a temperature across a hypothetical substrate from the machine learning algorithm.

[0008] The embodiment may also include a non-transitory computer readable medium including program instructions for causing a computer to perform the method. In one embodiment, the method includes developing a lamp model of an RTP tool, the lamp model including a plurality of lamp zones, calculating an irradiance graph for the plurality of lamp zones, multiplying the irradiance values ​​of the plurality of lamp zones in the irradiance graph by the power of the existing RTP tool at a given time during the process recipe, summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiation graph of the lamp model, using the irradiation graph as an input to a machine learning algorithm, and outputting a temperature across the virtual substrate from the machine learning algorithm.

[0009] The embodiments may also include a method of modeling a rapid thermal processing (RTP) tool. In one embodiment, the method includes training a machine learning algorithm with training data including actual temperature data from an existing RTP tool, developing a lamp model of the RTP tool, the lamp model including a plurality of lamp zones, where a number of lamps in the lamp model is different from a number of lamps in the existing RTP tool, calculating an irradiance graph for the plurality of lamp zones, multiplying the irradiance values ​​of the plurality of lamp zones in the irradiance graph by the power of the existing RTP tool at a given time during the process recipe, summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiance graph of the lamp model, using the irradiance graph as an input to the machine learning algorithm, and outputting a temperature across the virtual substrate from the machine learning algorithm. [Brief description of the drawings]

[0010] [Figure 1A] FIG. 1 is a plan view of a lamp array for an existing rapid thermal processing (RTP) tool, according to one embodiment. [Figure 1B]FIG. 1 is a plan view of a lamp array for an RTP tool being investigated in the processing methods described herein, according to one embodiment. [Diagram 2] 1 is a graph of irradiance for a lamp array on a substrate having multiple zones, according to one embodiment. [Figure 3A] 11 is a graph of power applied to lamps in several groups over the duration of a treatment strategy, according to one embodiment. [Figure 3B] 1 is a graph of the temperature of a substrate at different locations over the duration of a processing recipe, according to one embodiment. [Figure 3C] 1 is a graph of temperature over radius of a substrate used as a training data set, according to one embodiment. [Figure 4] 1 is a graph of irradiance over radius of a substrate used as input for a machine learning (ML) algorithm, according to one embodiment. [Diagram 5] 1 is a schematic diagram of an ML algorithm used to convert an input irradiance across a substrate to an output of temperature across the substrate, according to one embodiment. [Figure 6] FIG. 1 is a process flow diagram illustrating a process for determining a temperature profile of a virtual substrate heated in a modeled RTP tool, according to one embodiment. [Figure 7] FIG. 2 is a block diagram of an exemplary computer system that may be used with a processing tool, according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The system described herein includes a process for estimating thermal uniformity across a substrate in a modeled tool. In the following description, numerous specific details are set forth to provide a thorough understanding of the embodiments. It will be apparent to one of ordinary skill in the art that the embodiments may be practiced without these specific details. In other instances, well-known aspects will not be described in detail so as not to unnecessarily obscure the embodiments. Furthermore, it should be understood that the various embodiments illustrated in the accompanying drawings are illustrative representations and are not necessarily drawn to scale.

[0012] As mentioned above, it is currently difficult to model rapid thermal processing (RTP) tools being developed. Therefore, it is currently not feasible to determine the substrate temperature profile on a design without using an overly complex model or actually building an RTP tool. This leads to excessive waste of resources and time. This is especially problematic when a redesign of the RTP tool is required. For example, it may be desirable to reduce the number of lamps in a lamp array to reduce cost and / or to reduce power consumption.

[0013] Thus, embodiments disclosed herein include a method for generating a temperature profile using a machine learning (ML) algorithm. In general, a new lamp design is created. The irradiance of the lamp on the substrate is calculated. This provides a graph of the irradiance delivered by multiple lamp zones. The irradiance can then be multiplied by the power in the recipe delivered to the individual zones. The resulting values ​​for each zone can then be summed together to provide a graph of irradiance across the surface of the substrate. In one embodiment, the irradiance values ​​can then be input into an ML algorithm. The ML algorithm can output a temperature profile for the RTP tool being investigated. Thus, there is no need to extensively model or build the RTP tool to determine the temperature profile.

[0014] 1A, a plan view of a lamp array 150 of an RTP tool is shown, according to one embodiment. As shown, the lamp array 150 includes a plurality of lamps 155 arranged in a given pattern. For example, the pattern can be a honeycomb shaped pattern. Each of the lamps 155 in the lamp array 150 can be powered to heat an underlying substrate (not shown). The substrate can be a semiconductor substrate, such as a silicon wafer. However, it should be appreciated that other substrates can be used (e.g., a glass substrate, etc.).

[0015] In one embodiment, the lamps 155 may be separated into multiple groups (also called zones). The zones may be substantially concentric zones. In a simple case, a first zone may be a central zone and a second zone may be a group of lamps 155 outside the first zone. However, it should be appreciated that in more complex tools, the number of zones may be significantly higher. For example, there may be up to 15 (or more) zones in a given lamp array.

[0016] For convenience, lamp array 150 may be referred to herein as a physical lamp array 150. That is, lamp array 150 may be an existing array that has already been designed and assembled. Lamp array 150 may be used for training purposes to teach machine learning (ML) algorithms to aid in the development of new RTP architectures.

[0017] 1B, a plan view of a lamp array 160 is shown according to an additional embodiment. As shown, the lamp array 160 may include a plurality of lamps 165. The configuration (and / or number) of the lamps 165 in the lamp array 160 may differ from the number and / or configuration of the lamps 155 in the lamp array 150 described above. For example, there are fewer lamps 165 in the lamp array 160 than the number of lamps 155 in the lamp array 150. Additionally, there are voids 166 where there are no lamps 165. Besides the voids 166, the lamps 165 may be arranged in a honeycomb type arrangement. However, it should be appreciated that other configurations (e.g., different packing schemes, different spacing (or pitch), etc.) may be used.

[0018] As described in more detail below, the lamp array 160 may be a theoretical or virtual lamp array 160. That is, the lamp array 160 may not be physically built. However, as a result of an analysis method, such as one described in more detail below, the lamp array 160 may be analyzed to determine the temperature profile that will be implemented on a board. Thus, the output of the RTP tool may be characterized and compared to existing solutions to determine whether the design should be built into an actual product. This saves design time and cost, since faulty lamp arrays 160 may be removed from consideration.

[0019] Referring now to FIG. 2, a graph of the irradiance of the lamps 165 across the surface of a substrate is shown, according to one embodiment. The irradiance shown in FIG. 2 is divided into a set of nine zones. Each zone may include a number of individual lamps 165. Although nine zones are shown in FIG. 2, it should be appreciated that the lamps 165 may be grouped into any number of zones (e.g., two or more zones). In a particular embodiment, there may be 14 zones. The irradiance may be a calculated irradiance. That is, the irradiance may not necessarily be a measured quantity. Thus, the graph shown in FIG. 2 may be generated without having to actually fabricate the lamp array 160. In one embodiment, the irradiance values ​​(Y-axis) are plotted against the radius of the substrate (X-axis). For example, the X-axis may range from 0 mm (i.e., the center of the substrate) to about 150 mm (i.e., the edge of the substrate). In such an embodiment, the substrate is a 300 mm substrate. However, it should be appreciated that substrates having other form factors according to other embodiments may also be used.

[0020] Referring now to FIG. 3A, a graph of power of different lamp groups as a function of time is shown, according to one embodiment. In one embodiment, the graph in FIG. 3A may be a graph of a physical system. That is, the system shown in FIG. 3A may actually be built. For example, a lamp array similar to lamp array 150 may be used to generate the graph in FIG. 3A. Seven groups are shown in FIG. 3A. However, it should be appreciated that any number of groups (e.g., two or more groups) may be used, according to one embodiment. Each group may include two or more lamps, such as lamp 155 described above.

[0021] The graph in FIG. 3A may be a graph of power during the duration of the process recipe. For example, the process recipe may have a duration that is about 225 seconds. However, it should be appreciated that the process recipe may have any duration to provide the desired results for the substrate. As shown, the process recipe may include a thermal ramp up region at about 70 seconds. The thermal ramp up region represents a rapid increase in the temperature of the substrate. After the ramp up region, a thermal soak is implemented. The thermal soak is a period of time during which the substrate is held at a substantially constant elevated temperature. After the desired time of the thermal soak, a thermal ramp down region returns the temperature of the substrate to room temperature.

[0022] In the illustrated embodiment, group 1 (G1) may be at the center of the substrate and group 7 (G7) may be at the edge of the substrate. As shown, group 7 may have the highest power during heat soak and group 1 may have the lowest power during heat soak. The remaining groups (G2-G6) may have powers between group 1 and group 7.

[0023] 3B, a graph of substrate temperature during the duration of a recipe is shown, according to one embodiment. In one embodiment, the temperature graph may include multiple groups (e.g., G1-G7). Groups G1-G7 may be substantially similar to groups G1-G7 described above with respect to FIG. 3A. Thus, although seven groups are shown, it should be appreciated that any number of groups (e.g., two or more groups) may be used, according to one embodiment. As shown, the temperatures of G1-G7 are substantially uniform with respect to one another, despite having significantly different power levels (as shown in FIG. 3A). As shown, there is a thermal ramp at about 100 seconds, which is followed by a thermal soak between about 110 seconds and about 160 seconds.

[0024] 3C, a graph of the temperature of a substrate at a given time is shown, according to one embodiment. The Y-axis may refer to temperature and the X-axis may refer to distance from the center of the substrate. As shown, six locations 3711-3716 are shown. Each of the locations 371 may be a pyrometer location, which measures the temperature of the substrate at that location. In one embodiment, the portion of the curve between the six locations 371 may be a fitted line. That is, there may not be an actual temperature measurement between the locations 371.

[0025] In certain embodiments, the instant in time that the graph in Figure 3C represents may be where dashed line 372 is indicated in Figures 3A and 3B. For example, the temperature snapshot in Figure 3C may be at about 150 seconds into the process recipe, i.e., that time may be around the end of the thermal soak in some embodiments. However, it should be appreciated that a temperature snapshot may be provided at any time during the process recipe.

[0026] In one embodiment, the temperature snapshots in Figure 3C may be used as a training data set. For example, a machine learning (ML) algorithm, described in more detail below, may utilize the temperature snapshots and other data in Figures 3A and 3B as a set of training data. The snapshots in Figure 3C may be output values, and other data from the graphs in Figures 3A and 3B may be used as input data.

[0027] Referring now to FIG. 4, a graph of irradiance versus position across a substrate is shown according to one embodiment. In one embodiment, the graph in FIG. 4 is generated from the data in the irradiance graph of FIG. 2. In particular, the irradiance values ​​in FIG. 2 are multiplied by the power values ​​in FIG. 3A at the time of dashed line 372. After the irradiance values ​​are multiplied, each of the groups is summed together to provide an irradiance value. This irradiance value shown in FIG. 4 can then be used as an input to an ML algorithm to output a temperature snapshot, similar to the embodiment shown in FIG. 3C. In this manner, a prediction of temperature uniformity can be made without having to actually build and test a lamp array. A more detailed description of the process for generating a temperature uniformity plot is described in more detail below with respect to FIG. 6.

[0028] 5, a schematic diagram of an ML algorithm 580 is shown, according to one embodiment. In one embodiment, the ML algorithm may include an input side 581 and an output side 582. A number of hidden layers 583 may be provided between the input side 581 and the output side 582. The hidden layers 583 may each include a number of nodes 584 communicatively coupled to one another (as indicated by the lines between the nodes). In one embodiment, two hidden layers 583 are shown. However, it should be appreciated that any number of hidden layers may be used depending on the complexity of the ML algorithm.

[0029] In one embodiment, the ML algorithm takes as input irradiance values ​​(e.g., similar to the graph shown in FIG. 4) and outputs a temperature uniformity plot (e.g., similar to the graph shown in FIG. 3C). The structure of the ML algorithm can be any type of ML algorithm. For example, the ML algorithm can be a supervised ML algorithm, a semi-supervised ML algorithm, an unsupervised ML algorithm, an enhanced ML algorithm, etc.

[0030] 6, a process flow diagram is shown illustrating a process 690 for modeling an RTP tool, according to one embodiment. In one embodiment, the process 690 may begin with operation 691, which includes training an ML algorithm with training data including actual temperature data from an existing RTP tool. For example, the training data may be obtained from an RTP tool with a lamp array, similar to the lamps, lamp array 150, described in more detail above. The training data may include information about the power supplied to various lamp zones in the lamp array, the temperature of the various zones over time, and a snapshot of the temperature across the substrate at a given time. For example, the snapshot of the temperature across the substrate may be similar to the snapshot graph shown in FIG. 3C. The snapshot of the temperature across the substrate may be an output value of the ML algorithm, and other data may be fed as input data to the ML algorithm. In some embodiments, there may be more than one training data set used. For example, there may be up to 25 or more training data sets to adequately train the ML algorithm.

[0031] In one embodiment, process 690 may continue with operation 692, which includes developing a lamp model for the RTP tool. In one embodiment, the lamp model for the RTP tool may have a different configuration than the lamp array of the existing RTP tool used for the ML algorithm training process. For example, the lamp model may have a lamp array with a different layout of individual lamps and / or a different number of lamps therein. In certain embodiments, it is desired that the RTP tool being investigated has the same or similar performance as the existing RTP tool, but includes fewer lamps to allow for cost and power reduction.

[0032] In one embodiment, process 690 may continue with operation 693, which includes calculating an irradiance graph for multiple zones for the lamp model. In one embodiment, the irradiance graph may be similar to the graph shown in FIG. 2 above. That is, multiple different zones across the surface of the substrate and the irradiance for those zones are provided. The irradiance may be calculated. Since the value is calculated, there is no need to physically build the lamp model.

[0033] In one embodiment, process 690 may continue with operation 694, which includes multiplying the irradiance values ​​of the lamp zones in the irradiance graph by the power of the existing RTP tool at a given time during the process recipe. For example, the power values ​​may be provided by a graph, such as the graph shown in FIG. 3A. The given time may refer to dashed line 372. For example, the power level may be during a heat soak. In other embodiments, the power level used may be during a heat lamp. In yet another embodiment, the power at multiple different times is multiplied by the irradiance value.

[0034] In one embodiment, process 690 may continue with operation 695, which includes summing the multiplied irradiance values ​​for multiple lamp zones to form an irradiance graph of the lamp model. The irradiance graph of the lamp model may be similar to the graph shown in Figure 4, i.e., irradiance across the surface of the substrate may be provided. In embodiments, where power at multiple different times is multiplied with irradiance values, there may be multiple irradiance graphs provided.

[0035] In one embodiment, process 690 may continue with operation 696, which includes using the irradiation graph (or graphs) as input to an ML algorithm. The irradiation graph (or graphs) may be input to the ML algorithm trained in operation 691. In one embodiment, process 690 may continue with operation 697, which includes outputting temperatures across the virtual substrate from the machine learning algorithm. Thus, the performance of the RTP tool may be determined without having to build a model of the RTP tool. Thus, many different models may be easily investigated using a similar process to select the best candidate for further consideration regarding minimum cost and development time.

[0036] Referring now to FIG. 7, a block diagram of an exemplary computer system 700 of a processing tool is shown, according to one embodiment. In one embodiment, the computer system 700 is coupled to the processing tool and controls processing in the processing tool. The computer system 700 may be connected (e.g., networked) to other machines in a local area network (LAN), an intranet, an extranet, or the Internet. The computer system 700 may operate in the capacity of a server machine or a client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The computer system 700 may be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a web appliance, a server, a network router, a switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by the machine. Further, although only a single machine is illustrated for computer system 700, the term "machine" is also intended to include any collection of machines (e.g., computers) that individually or together execute a set (or multiple sets) of instructions to perform any one or more of the methodologies described herein.

[0037] The computer system 700 may include a computer program product, or software 722, having a non-transitory machine-readable medium having instructions stored thereon that may be used to program the computer system 700 (or other electronic devices) to perform a process according to an embodiment. A machine-readable medium includes any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer). For example, a machine-readable (e.g., computer-readable) medium includes a machine (e.g., computer) readable storage medium (e.g., read-only memory ("ROM"), random access memory ("RAM"), magnetic disk storage media, optical storage media, flash memory devices, etc.), a machine (e.g., computer) readable transmission medium (electrical, optical, acoustic or other form of propagated signal (e.g., infrared signal, digital signal, etc.)), etc.

[0038] In one embodiment, computer system 700 includes a system processor 702, a main memory 704 (e.g., read only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM), etc.), a static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory 718 (e.g., a data storage device), which communicate with each other via a bus 730.

[0039] The system processor 702 represents one or more general-purpose processing devices, such as a microsystem processor, a central processing unit, etc. More specifically, the system processor may be a complex instruction set computing (CISC) microsystem processor, a reduced instruction set computing (RISC) microsystem processor, a very long instruction word (VLIW) microsystem processor, a system processor implementing other instruction sets, or a system processor implementing a combination of instruction sets. The system processor 702 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 system processor (DSP), a network system processor, etc. The system processor 702 is configured to execute processing logic 726 for performing the operations described herein.

[0040] The computer system 700 may further include a system network interface device 708 for communicating with other devices or machines. The computer system 700 may also include a video display unit 710 (e.g., a liquid crystal display (LCD), a light emitting diode display (LED), or a cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and a signal generating device 716 (e.g., a speaker).

[0041] The secondary memory 718 may include a machine-accessible storage medium 732 (or more specifically, a computer-readable storage medium) having stored thereon one or more sets of instructions (e.g., software 722) embodying any one or more of the methodologies or functions described herein. The software 722 may also reside, completely or at least partially, within the main memory 704 and / or within the system processor 702 during execution of the software 722 by the computer system 700, with the main memory 704 and the system processor 702 also constituting machine-readable storage media. The software 722 may further be transmitted or received over the network 720 via the system network interface device 708. In one embodiment, the network interface device 708 may operate using RF, optical, acoustic, or inductive coupling.

[0042] While the machine-accessible storage medium 732 is shown to be a single medium in the exemplary embodiment, the term "machine-readable storage medium" shall be interpreted to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more sets of instructions. The term "machine-readable storage medium" shall also be interpreted to include any medium capable of storing or encoding a set of instructions for execution by a machine, causing the machine to perform any one or more of the methodologies. The term "machine-readable storage medium" shall therefore be interpreted to include, but not limited to, solid-state memories and optical and magnetic media.

[0043] In the foregoing specification, certain exemplary embodiments have been described. It will be apparent that various modifications may be made thereto without departing from the scope of the following claims. The specification and drawings are therefore to be regarded in an illustrative rather than a restrictive sense.

Claims

1. 1. A method for modeling a rapid thermal processing (RTP) tool, comprising: developing a lamp model for an RTP tool, the lamp model including a plurality of lamp zones; calculating an irradiance graph for the plurality of lamp zones; multiplying the irradiance values ​​of the lamp zones in the irradiance graph by an existing RTP tool power at a given time during a process recipe; summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiance graph of the lamp model; using the illumination graph as an input to a machine learning algorithm; outputting a temperature across the virtual substrate from the machine learning algorithm; A method comprising:

2. Training the machine learning algorithm with training data including actual temperature data from the existing RTP tool. The method of claim 1 further comprising:

3. The method of claim 2 , wherein the training comprises at least 25 sets of different training data.

4. The method of claim 1 , wherein the plurality of lamp zones comprises up to 15 lamp zones.

5. The method of claim 1 , wherein a lamp configuration of the lamp model is different from a lamp configuration of the existing RTP tool.

6. The method of claim 5 , wherein a number of lamps in the lamp configuration of the lamp model is different from a number of lamps in the lamp configuration of the existing RTP tool.

7. The method of claim 1 , wherein the machine learning algorithm includes two or more hidden layers.

8. The method of claim 1 , wherein the illumination graph includes data points for at least 15 different locations on the virtual substrate.

9. The method of claim 1 , wherein the given time during a process recipe is during a heat soak.

10. The method of claim 1 , wherein the given time during the process recipe is during a heat lamp.

11. The method of claim 1 , wherein the temperatures across the virtual substrate substantially match a set of training data.

12. On the computer, developing a lamp model for an RTP tool, the lamp model including a plurality of lamp zones; calculating an irradiance graph for the plurality of lamp zones; multiplying the irradiance values ​​of the lamp zones in the irradiance graph by an existing RTP tool power at a given time during a process recipe; summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiance graph of the lamp model; using the illumination graph as an input to a machine learning algorithm; outputting a temperature across the virtual substrate from the machine learning algorithm; A non-transitory computer readable medium comprising program instructions for carrying out a method comprising:

13. Training the machine learning algorithm with training data including actual temperature data from the existing RTP tool.

13. The non-transitory computer-readable medium of claim 12, further comprising:

14. 14. The non-transitory computer-readable medium of claim 13, wherein the training comprises at least 25 sets of different training data.

15. 13. The non-transitory computer-readable medium of claim 12, wherein the plurality of lamp zones comprises up to 15 lamp zones.

16. The non-transitory computer-readable medium of claim 12 , wherein a lamp configuration of the lamp model is different from a lamp configuration of the existing RTP tool.

17. 20. The non-transitory computer-readable medium of claim 16, wherein a number of lamps in the lamp configuration of the lamp model is different from a number of lamps in the lamp configuration of the existing RTP tool.

18. The method of claim 1 , wherein the given time during a process recipe is during a heat soak and / or during a heat ramp.

19. 1. A method for modeling a rapid thermal processing (RTP) tool, comprising: Training a machine learning algorithm with training data including actual temperature data from an existing RTP tool; developing a lamp model for an RTP tool, the lamp model including a plurality of lamp zones, the number of lamps in the lamp model being different than the number of lamps in the existing RTP tool; calculating an irradiance graph for the plurality of lamp zones; multiplying the irradiance values ​​of the lamp zones in the irradiance graph by the power of the existing RTP tool at a given time during a process recipe; summing the multiplied irradiance values ​​for the plurality of lamp zones to form an irradiance graph of the lamp model; using the illumination graph as an input to the machine learning algorithm; outputting a temperature across the virtual substrate from the machine learning algorithm; A method comprising:

20. 20. The method of claim 19, wherein the given time during a process recipe is during a heat soak and / or a heat ramp.

Images