Manufacturing system for semiconductor light emitting elements

Abstract

To provide a manufacturing system for semiconductor light emitting elements with which it is possible to predict optical output of the semiconductor light emitting elements.SOLUTION: The present invention comprises a film forming device 10, a terminal 11 for management, and an optical output prediction device 1 for semiconductor light emitting elements. The optical output prediction device 1 for semiconductor light emitting elements comprises: a data acquisition unit 21 for acquiring data corresponding to a composition parameter and / or a physical property parameter and optical output data of a semiconductor light emitting element 100 from the film forming device 10 or the terminal 11 for management and creating data 31 for training; a model creation unit 22 for creating a trained model 32 when the data 31 for training is updated using the data 31 for training as teaching data, with the composition parameter and / or the physical property parameter adopted as an explanatory variable and the optical output adopted as an objective variable; and an optical output prediction unit 23 for predicting the optical output using the trained model 32. The model creation unit 22 is constituted to be capable of selecting the parameter used for the explanatory variable.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a manufacturing system for a semiconductor light-emitting device. [Background technology]

[0002] Group III nitride semiconductors made of compounds of aluminum (Al), gallium (Ga), indium (In) and nitrogen (N) are used as materials for ultraviolet light emitting devices. Among them, group III nitride semiconductors made of AlGaN with a high Al composition are used for ultraviolet light emitting devices and deep ultraviolet light emitting devices (for example, see Patent Document 1).

[0003] Prior art document information related to the invention of this application includes Patent Document 2. Patent Document 2 proposes a prediction method using machine learning to efficiently predict the properties of a film formed by a film forming apparatus. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6001756 [Patent Document 2] Patent No. 6959191 Summary of the Invention [Problem to be solved by the invention]

[0005] Nitride semiconductor light-emitting devices require chipping and packaging after film formation, and it takes a long time to produce a product. For this reason, there is a problem that, for example, when reviewing the design at the time of film formation, it takes a very long time to repeat prototyping and evaluation. Therefore, there is a demand for predicting the light output of nitride semiconductor light-emitting devices before prototyping. However, nitride semiconductor light-emitting devices require control of a large number of parameters, and it was unclear what parameters should be used to predict the light output.

[0006] SUMMARY OF THE PRESENT DISCLOSURE In view of the above, an object of the present invention is to provide a manufacturing system for a semiconductor light-emitting device that is capable of predicting the optical output of the semiconductor light-emitting device. [Means for solving the problem]

[0007] A manufacturing system for a semiconductor light-emitting element according to an embodiment of the present invention includes a film formation apparatus for a semiconductor light-emitting element, a management terminal for managing the film formation apparatus, and a light output prediction apparatus for a semiconductor light-emitting element for predicting a light output of the semiconductor light-emitting element, the light output prediction apparatus for the semiconductor light-emitting element being configured to obtain data corresponding to at least one of a composition parameter that is a parameter defining a composition of a layer constituting the semiconductor light-emitting element, or a physical property parameter that is a parameter defining a physical property of a layer constituting the semiconductor light-emitting element, and data on the light output of the semiconductor light-emitting element from the film formation apparatus or the management terminal, and to create learning data by linking the obtained data corresponding to at least one of the composition parameter or the physical property parameter with the light output data, and to store the data in a storage unit; the optical output prediction unit includes a learning algorithm that uses at least one of the composition parameters or the physical property parameters as explanatory variables and the optical output as an objective variable, and that learns by itself through machine learning a correlation between each parameter of the explanatory variables and the objective variable, when the learning data stored in the storage unit is updated, iteratively executes learning based on a data set of each parameter of the explanatory variables and the objective variable, automatically interprets the correlation between the two, creates a learned model, and stores the learned model in the storage unit; an optical output prediction unit that uses the learned model stored in the storage unit to predict the optical output corresponding to prediction source data, which is data of the values ​​of each parameter used for the explanatory variables, and stores the predicted data in the storage unit; and a prediction result presentation unit that presents the predicted data, wherein the model creation unit is configured to be able to select a parameter to be used for the explanatory variables. Effect of the Invention

[0008] According to the present invention, it is possible to provide a semiconductor light-emitting device manufacturing system capable of predicting the light output of the semiconductor light-emitting device. [Brief description of the drawings]

[0009] [Figure 1] 1 is a schematic diagram illustrating a configuration of a nitride semiconductor light-emitting device. [Diagram 2] 1 is a schematic configuration diagram of an optical output prediction device for a nitride semiconductor light-emitting element according to an embodiment of the present invention. [Figure 3A] FIG. 11 is a diagram illustrating an example of learning data. [Figure 3B] FIG. 11 is a diagram illustrating an example of learning data. [Figure 4] 1A and 1B are graphs showing the change in emission wavelength and the change in optical output when the deposition temperature of the well layer is changed while the Al composition ratio of the well layer is kept constant. FIG. [Diagram 5] 1A and 1B are graphs showing the change in the thickness of the buffer layer and the change in the optical output when the film formation temperature of the buffer layer is changed while the thickness of the buffer layer is kept constant. FIG. [Figure 6] FIG. 1 is a diagram illustrating a model creation process. [Figure 7] FIG. 13 is a diagram illustrating a light output prediction process. [Figure 8] 1 is a diagram illustrating a control flow of a method for predicting the optical output of a nitride semiconductor light-emitting device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] [Embodiment Mode] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

[0011] (Nitride semiconductor light emitting element 100) First, a nitride semiconductor light-emitting element 100 (hereinafter, simply referred to as "light-emitting element 100") whose light output is to be predicted in this embodiment will be described. Fig. 1 is a schematic diagram showing the configuration of the nitride semiconductor light-emitting element 100. Note that in Fig. 1, the dimensional ratio of each layer in the stacking direction of the light-emitting element 100 does not necessarily match the actual one, and each layer may have a multi-layer structure.

[0012] The light emitting element 100 is a light emitting diode (LED) and emits light with a wavelength in the ultraviolet region in this embodiment. The light emitting element 100 is, for example, a deep ultraviolet LED that emits ultraviolet light with a central wavelength of 200 nm or more and 365 nm or less, and is used, for example, for sterilizing water or air.

[0013] 1, the light emitting device 100 includes a buffer layer 102, an n-type semiconductor layer 103, an active layer 104, an electron blocking layer 105, and a p-type semiconductor layer 106, which are arranged in this order on a substrate 101. A p-type electrode 107 and a p-side pad electrode 108 are arranged in this order on the p-type semiconductor layer 106, and an n-type electrode 109 and an n-side pad electrode 110 are arranged in this order on the n-type semiconductor layer 103. A passivation film (protective film) 111 is arranged on the side surfaces of the p-type electrode 107 and the n-type electrode 109, and on the surface of the light emitting device 100 between the p-type electrode 107 and the n-type electrode 109. The active layer 104 has a multi-quantum well structure (Multi Quantum Well: MQW) formed by alternately stacking barrier layers 104a and well layers 104b.

[0014] Each of the layers 102 to 106 on the substrate 101 can be formed using a well-known epitaxial growth method such as Metal Organic Chemical Vapor Deposition (MOCVD), Molecular Beam Epitaxy (MBE), or Hydride Vapor Phase Epitaxy (HVPE).

[0015] The semiconductor constituting the light emitting device 100 is, for example, Al. x Ga y In 1-x-y A binary to quaternary III-N nitride semiconductor represented by 0≦x≦1, 0≦y≦1, 0≦x+y≦1 can be used. In deep ultraviolet LEDs, Al containing no indium is used. z Ga 1-z In many cases, N-based (0≦z≦1) is used. In addition, a part of the group III elements of the semiconductors constituting the light emitting device 100 may be replaced with boron (B), thallium (Tl), etc. In addition, a part of the nitrogen may be replaced with phosphorus (P), arsenic (As), antimony (Sb), bismuth (Bi), etc. In this embodiment, each of the layers 102 to 106 is made of Al. z Ga 1-z It is composed of N (0≦z≦1).

[0016] It should be noted that the structure in FIG. 1 is merely an example, and the specific structure of the light-emitting element 100 is not limited to that shown in the figure, and can be modified as appropriate.

[0017] (Light output prediction device for nitride semiconductor light emitting device 1) FIG. 2 is a schematic diagram of an optical output prediction device 1 for a nitride semiconductor light-emitting element (hereinafter, simply referred to as "optical output prediction device 1"). FIG. 2 shows an apparatus 10 (film formation device) for manufacturing a nitride semiconductor light-emitting element and a management terminal 11 together with the optical output prediction device 1. The apparatus 10 for manufacturing a nitride semiconductor light-emitting element is an apparatus for forming layers 102 to 106 of a light-emitting element 100 by using a known epitaxial growth method such as metal organic chemical vapor deposition, molecular beam epitaxy, or halide vapor phase epitaxy. The management terminal 11 is a terminal device for managing the apparatus 10 for manufacturing a nitride semiconductor light-emitting element, and is composed of, for example, a personal computer. The management terminal 11 can be omitted, and the optical output prediction device 1 may be equipped with a function as the management terminal 11.

[0018] 2, the optical output prediction device 1 includes a control unit 2, a storage unit 3, a display unit 4, and an input device 5. The optical output prediction device 1 is configured from a calculation device such as a personal computer or a server device.

[0019] The control unit 2 has a learning data acquisition unit 21, a model creation unit 22, an optical output prediction unit 23, and a prediction result presentation unit 24. Details of each unit will be described later. The control unit 2 is realized by appropriately combining a calculation element, a memory, an interface, a storage device, etc. The storage unit 3 is realized by a predetermined storage area of ​​a memory or a storage device, and stores data etc. used for various controls by the control unit 2 described later. The input device 5 is composed of, for example, a keyboard, a mouse, etc. The display unit 4 is composed of, for example, a liquid crystal display, etc.

[0020] (Learning data acquisition unit 21) The learning data acquisition unit 21 performs a process of acquiring various data used for learning (machine learning) from the outside and storing it in the storage unit 3 as learning data 31. The various data may be acquired directly from the nitride semiconductor light-emitting device manufacturing apparatus 10 via wired or wireless communication, or may be acquired from the management terminal 11 via wired or wireless communication. The various data may be input from the input device 5, or may be input using a medium such as a USB memory. In this way, the method of acquiring the learning data 31 is not particularly limited.

[0021] (Learning data 31 and parameters used in machine learning) Here, an example of the learning data 31 used in machine learning will be described. FIGS. 3A and 3B are diagrams showing an example of the learning data 31. As shown in FIGS. 3A and 3B, the learning data 31 stores data corresponding to the composition parameters, physical property parameters, and manufacturing condition parameters of each of the layers 102 to 106, and data on the light output, which are linked to each other. The composition parameters are parameters that define the composition of each of the layers 102 to 106 constituting the light-emitting device 100. The manufacturing condition parameters are parameters that define the physical properties (and physical structure, etc.) of each of the layers 102 to 106 constituting the light-emitting device 100. The manufacturing condition parameters are parameters that define the manufacturing conditions of the light-emitting device 100.

[0022] The specific parameters of the composition parameters, physical property parameters, and manufacturing condition parameters are not limited to those shown in the drawings, and other parameters may be used. The learning data 31 may include parameters other than the composition parameters, physical property parameters, and manufacturing condition parameters, and may include, for example, equipment state parameters representing the state of the manufacturing equipment 10 of the nitride semiconductor light-emitting device. Examples of the equipment state parameters include the height of the pile on the tray and the number of pockets, the temperature and flow rate of the chiller and cooling water, the number of film formations, and furnace dimensions. The learning data 31 may also include, in addition to the above, substrate parameters representing the state of the substrate 101, electrode parameters representing the states of the electrodes 107 to 110, and the like. The manufacturing condition parameters are not essential and can be omitted. The learning data 31 may also include only one of the composition parameters and the physical property parameters.

[0023] Although details will be described later, in this embodiment, the relationship between each of the composition parameters, physical property parameters, and manufacturing condition parameters and the optical output is machine-learned. Therefore, it is desirable to select parameters that have a large effect on the optical output as the composition parameters and physical property parameters used in the machine learning. When the manufacturing condition parameters are used in the machine learning, it is desirable to select parameters that are changed when adjusting the values ​​of the composition parameters and physical property parameters used in the machine learning.

[0024] More specifically, in the buffer layer 102, it is preferable to use the Al composition ratio as the composition parameter, and it is preferable to use the film thickness, transmittance, and mix value as the physical property parameters for machine learning. The mix value is the half-width (arcsec) of the X-ray rocking curve obtained by ω-scanning of X-ray diffraction for the (10-12) plane (Mixed plane) of the crystal, and is a representative index indicating the crystal quality of each layer in a nitride semiconductor light-emitting device. When the manufacturing condition parameters of the buffer layer 102 are used for machine learning, it is preferable to use the film formation temperature (heater temperature or substrate temperature), TMA (trimethylaluminum) flow rate, and TMG (trimethylgallium) flow rate as the manufacturing condition parameters.

[0025] In addition, in the n-type semiconductor layer 103, it is preferable to use the Al composition ratio and doping concentration as the composition parameters, and the mix value, transmittance, and film resistance as the physical property parameters. In particular, in the n-type semiconductor layer 103, the mix value, which is a physical property parameter, is considered to have a large effect on the light output, so it is preferable to use it for machine learning when there is variation in the data that cannot be considered constant. In addition, when the manufacturing condition parameters of the n-type semiconductor layer 103 are used for machine learning, it is preferable to use the TMA flow rate, the TMG flow rate, and the TMSi (tetramethylsilane) flow rate as the manufacturing condition parameters.

[0026] In the barrier layer 104a of the active layer 104, it is preferable to use the Al composition ratio and doping concentration as the composition parameters, and the film thickness as the physical property parameter. Since the Al composition ratio, doping concentration, and film thickness parameters of the barrier layer 104a have a large effect on the optical output, it is preferable to use them for machine learning when the data has a variation that cannot be considered constant. When the manufacturing condition parameters of the barrier layer 104a are used for machine learning, it is preferable to use the film formation temperature (heater temperature or substrate temperature), film formation time, TMA flow rate, and TMG flow rate as the manufacturing condition parameters.

[0027] In the well layer 104b of the active layer 104, as in the barrier layer 104a, it is preferable to use the Al composition ratio and doping concentration as the composition parameters, and the film thickness as the physical property parameter. Since the parameters of the Al composition ratio, doping concentration, and film thickness of the well layer 104b have a large effect on the optical output, it is preferable to use them for machine learning when the data has a variation that cannot be considered constant. When the manufacturing condition parameters of the well layer 104b are used for machine learning, it is preferable to use the film formation temperature (heater temperature or substrate temperature), film formation time, TMA flow rate, and TMG flow rate as the manufacturing condition parameters.

[0028] In the electron block layer 105, it is preferable to use an Al composition ratio as the composition parameter, and a film thickness and a transmittance as the physical property parameters. Since the parameters of the Al composition ratio, film thickness, and transmittance of the electron block layer 105 have a large effect on the optical output, it is preferable to use them for machine learning when the data has a variation that cannot be considered constant. When the manufacturing condition parameters of the electron block layer 105 are used for machine learning, it is preferable to use the heater temperature, film formation time, TMA flow rate, and TMG flow rate as the manufacturing condition parameters.

[0029] In the p-type semiconductor layer 106, as in the above-mentioned electron block layer 105, it is preferable to use an Al composition ratio as the composition parameter, and a film thickness and a transmittance as the physical property parameters. Since the parameters of the Al composition ratio, film thickness, and transmittance of the p-type semiconductor layer 106 have a large effect on the optical output, it is preferable to use them for machine learning when the data has a variation that cannot be considered constant. When the manufacturing condition parameters of the p-type semiconductor layer 106 are used for machine learning, it is preferable to use the film formation temperature (heater temperature or substrate temperature), film formation time, TMA flow rate, and TMG flow rate as the manufacturing condition parameters.

[0030] In this embodiment, the optical output was the optical output of the light-emitting element 100 in a state where the film was formed, chipped, and packaged to become a product. The optical output varies depending on various conditions in the chipping and packaging processes, but here, the chipping and packaging were performed under the same conditions, and were not used for machine learning. However, it is also possible to perform machine learning including the conditions during chipping and packaging.

[0031] (Regarding combined use of manufacturing condition parameters) Furthermore, the inventors have found through their research that even when the composition parameters and physical property parameters are constant, the light output may change when the manufacturing condition parameters change. This will be specifically described below.

[0032] First, the deposition temperature of the well layer 104b was changed while keeping the Al composition ratio of the well layer 104b constant. As described above, the Al composition ratio of the well layer 104b has a large effect on the optical output, and changing the Al composition ratio of the well layer 104b changes the optical output. The change in the emission wavelength at this time is shown in FIG. 4(a). As shown in FIG. 4(a), the emission wavelength of the well layer 104b is almost constant, and the Al composition ratio is almost constant regardless of the deposition temperature. The change in the optical output at this time is shown in FIG. 4(b). As shown in FIG. 4(b), the optical output decreases as the deposition temperature of the well layer 104b increases, and it can be seen that the optical output changes depending on the deposition temperature of the well layer 104b, even though the Al composition ratio, which is a composition parameter of the well layer 104b, is constant.

[0033] Similarly, the deposition temperature of the buffer layer 102 made of AlN was changed while maintaining the thickness of the buffer layer 102 constant. As described above, the thickness of the buffer layer 102 has a large effect on the optical output, and changing the thickness of the buffer layer 102 changes the optical output. The change in the thickness of the buffer layer 102 at this time is shown in FIG. 5(a). As shown in FIG. 5(a), the thickness of the buffer layer 102 is almost constant regardless of the deposition temperature. The change in the optical output at this time is shown in FIG. 5(b). As shown in FIG. 5(b), the optical output decreases as the deposition temperature of the buffer layer 102 increases, and it can be seen that the optical output changes depending on the deposition temperature of the buffer layer 102, even though the thickness, which is a physical property parameter of the buffer layer 102, is constant.

[0034] Thus, there are cases where the light output cannot be predicted with sufficient accuracy only by the physical property parameters and the composition parameters. In this case, in addition to at least one of the physical property parameters and the composition parameters, it is necessary to predict the light output by further considering the manufacturing condition parameters that are changed when adjusting the value of the composition parameter or the physical property parameter. From the results of FIG. 4 and FIG. 5, when at least one of the composition parameters or the physical property parameters of a predetermined layer (the well layer 104b in the example of FIG. 4 and the buffer layer 102 in the example of FIG. 5) of the nitride semiconductor light emitting device is used for learning, it is possible to accurately predict the light output of the nitride semiconductor light emitting device 100 by using the film formation temperature of the predetermined layer (the well layer 104b in the example of FIG. 4 and the buffer layer 102 in the example of FIG. 5) as a manufacturing condition parameter for learning. The active layer 104 (the barrier layer 104a and the well layer 104b) and the electron block layer 105 generally have a thin film thickness of 100 nm or less, and it is difficult to predict the light output only by the composition parameters and the physical property parameters, so it is desirable to include the film formation temperature in the explanatory variables. It is more preferable to use the substrate temperature as the film formation temperature, which can be calculated, for example, by measuring infrared rays generated from the substrate surface with a pyrometer.

[0035] (Model Creation Part 22) The model creation unit 22 performs a process of creating a trained model 32 using the training data 31. The process performed by the model creation unit 22 corresponds to a model creation step of the present invention. In this embodiment, the model creation unit 22 creates the trained model 32 by learning (machine learning) a correlation between at least one of the composition parameters or physical property parameters of the layers 102 to 106 constituting the light-emitting element 100, the manufacturing condition parameters changed when adjusting the values ​​of the composition parameters or physical property parameters, and the light output of the light-emitting element 100. In this embodiment, the model creation unit 22 is configured to create the trained model 32 by using both the composition parameters and the physical property parameters for machine learning.

[0036] The model creation unit 22 may be configured to perform machine learning of correlations between the composition parameters, physical property parameters, and manufacturing condition parameters and the optical output of the nitride semiconductor light-emitting device to create the trained model 32. This enables prediction of the optical output taking into account the manufacturing conditions in addition to the composition and physical properties, and can further improve the prediction accuracy of the optical output.

[0037] The model creation unit 22 includes a learning algorithm that uses the composition parameters, physical property parameters, and manufacturing condition parameters of the layers 102 to 106 that are preset as explanatory variables, and the optical output as an objective variable, and learns the correlation between each parameter of the explanatory variables and the objective variable by machine learning. The learning algorithm is not particularly limited, and a known learning algorithm called, for example, deep forest or deep neural network can be used.

[0038] As shown in Fig. 6, learning data 31 is input to the model creation unit 22. Using the input learning data 31, the model creation unit 22 repeatedly executes learning based on a data set of parameters used as explanatory variables and optical output, which is a target variable, and automatically interprets the correlation between the two to create a learned model 32. The model creation unit 22 stores the created learned model 32 in the storage unit 3. The model creation unit 22 may be configured to allow the user to appropriately select parameters (composition parameters, physical property parameters, manufacturing condition parameters) to be used as explanatory variables.

[0039] (Optical output prediction unit 23) The optical output prediction unit 23 performs a process of predicting an optical output using the trained model 32. The process performed by the optical output prediction unit 23 corresponds to an optical output prediction step of the present invention. As shown in FIG. 7, the trained model 32 created by the model creation unit 22 and prediction source data 33 are input to the optical output prediction unit 23. The prediction source data 33 is the value of each parameter used as an explanatory variable, and is input, for example, by the input device 5. The optical output prediction unit 23 predicts an optical output corresponding to the prediction source data 33 by applying the value of each parameter of the prediction source data 33 to the trained model 32. The predicted optical output is stored in the storage unit 3 as prediction data 34.

[0040] (Prediction result presentation unit 24) The prediction result presentation unit 24 performs a process of presenting the prediction data 34 predicted by the light output prediction unit 23. The prediction result presentation unit 24 presents the prediction data 34, for example, by displaying the prediction data 34 on the display 4. The format of the presentation is not particularly limited, and the prediction data 34 may be presented in an appropriate format such as numerical values ​​or graphs. However, the present invention is not limited to this, and the prediction data 34 may be presented, for example, by outputting the prediction data 34 to an external device.

[0041] (Method for predicting optical output of nitride semiconductor light-emitting device) Fig. 8 is a flow diagram showing a control flow of a method for predicting the light output of a nitride semiconductor light-emitting device according to this embodiment. The control flow of Fig. 8 is executed when predicting the light output. Prior to the control flow of Fig. 8, the learning data acquisition unit 21 acquires learning data 31, and the acquired learning data 31 is stored in the storage unit 3 as needed.

[0042] As shown in FIG. 8, in the method for predicting the light output of a nitride semiconductor light-emitting device according to this embodiment, a model creation step in step S1, a light output prediction step in step S2, and a prediction result presentation step in step S3 are performed in this order.

[0043] In the model creation process of step S1, first, in step S11, the model creation unit 22 determines whether the learning data 31 has been updated since the previous time the trained model 32 was created. The determination in step S11 can be made by comparing the creation date and time of the trained model 32 with the update date and time of the training data 31. In addition, in step S11, if the trained model 32 has not been created (first time), it is determined that the learning data 31 has been updated (Yes). If the determination in step S11 is No (N), the process proceeds to the light output prediction process of step S2. If the determination in step S11 is Yes (Y), in step S12, the model creation unit 22 machine-learns the correlation between each parameter of the explanatory variable set in advance and the target variable, the light output, based on the updated training data 31, and creates the trained model 32.

[0044] In this embodiment, the parameters used as explanatory variables in the machine learning in step S11 include at least one of composition parameters and physical property parameters of the layers 102 to 106 constituting the light emitting device 100, and manufacturing parameters of the layers 102 to 106. More preferably, the following parameters are used: Al composition ratio of each layer 102 to 106 Transmittance of each layer 102, 103, 105, 106 other than the active layer 104 Doping concentrations of the barrier layer 104a, the well layer 104b, and the n-type semiconductor layer 103 Mix value of n-type semiconductor layer 103 The thicknesses of the buffer layer 102, the barrier layer 104a, the well layer 104b, the electron blocking layer 105, and the p-type semiconductor layer 106 Regarding the parameter, since the influence on the optical output is very large, when the data has a variation that cannot be regarded as constant, it is desirable to include it in the explanatory variables. In addition, it is desirable to use the deposition temperature of the layer using the composition parameter or the physical property parameter as a manufacturing parameter. As described in FIG. 4, when at least the Al composition ratio of the well layer 104b is used as an explanatory variable, it is desirable to also include the deposition temperature of the well layer 104b in the explanatory variables. Also, as described in FIG. 5, when at least the film thickness of the buffer layer 102 is used as an explanatory variable, it is desirable to also include the deposition temperature of the buffer layer 102 in the explanatory variables. Although not shown in FIG. 8, a step of selecting which parameter to use as an explanatory variable may be added before step S12.

[0045] After creating the trained model 32 in step S12, in step S13, the model creation unit 22 stores the created trained model 32 in the memory unit 3, and the process proceeds to the optical output prediction step of step S2.

[0046] In the optical output prediction process of step S2, first, in step S21, the prediction source data 33 is input. At this time, for example, an input screen for the prediction source data 33 may be displayed on the display 4 so that the prediction source data 33 can be input by the input device 5. In addition, when the prediction source data 33 is input in a file format, a display prompting the input of the file may be displayed on the display 4. Thereafter, in step S22, the optical output prediction unit 23 predicts the optical output corresponding to the prediction source data 33 using the trained model 32 stored in the storage unit 3. Thereafter, in step S23, the optical output prediction unit 23 stores the predicted optical output value in the storage unit 3 as prediction data 34, and proceeds to the prediction result presentation process of step S3.

[0047] In the prediction result presentation process of step S3, in step S31, the prediction result presentation unit 24 of step S3 presents the prediction result of the light output by presenting the prediction data 34 stored in the storage unit 3 on the display 4. Thereafter, the process ends.

[0048] In the present embodiment, a case has been described in which the trained model 32 is updated when predicting the optical output, but the present invention is not limited to this. The model creation unit 22 may be configured to monitor the update status of the training data 31 and update the trained model 32 every time the training data 31 is updated. The model creation unit 22 may also be configured to update the trained model 32 at predetermined intervals (for example, every week or every month).

[0049] (Functions and Effects of the Embodiments) According to the embodiment described above, the following actions and effects can be obtained.

[0050] (1) By using a trained model 32 that has been machine-learned to correlate at least one of the composition parameters or physical property parameters of the layers constituting the light-emitting element 100, the manufacturing condition parameters that are changed when adjusting the values ​​of the composition parameters or physical property parameters, and the light output, and by using the film formation temperature of a predetermined layer that is used for training the composition parameters or physical property parameters as a manufacturing condition parameter for training, it becomes possible to accurately predict the light output of the light-emitting element 100. As a result, it becomes possible to predict the light output of the light-emitting element 100 without making a prototype, and it becomes possible to carry out development in a short period of time without the need for trial and error through repeated prototyping and evaluation over a long period of time.

[0051] (2) In particular, when the Al composition ratio of the well layer 104b is used as the composition parameter, the deposition temperature of the well layer 104b is further used as a manufacturing condition parameter for learning, thereby improving the prediction accuracy of the optical output.

[0052] (3) Similarly, when the thickness of the buffer layer 102 is used as a physical property parameter, the deposition temperature of the buffer layer 102 is further used as a manufacturing condition parameter for learning, thereby improving the prediction accuracy of the optical output.

[0053] (Summary of the embodiment) Next, the technical ideas grasped from the above-described embodiment will be described by using the reference numerals and the like in the embodiment.

[0054] [1] A method for predicting an optical output of a nitride semiconductor light-emitting element (100), comprising: a model creation step of learning a correlation between at least one of a composition parameter, which is a parameter defining a composition of layers (102-106) constituting the nitride semiconductor light-emitting element (100), or a physical property parameter, which is a parameter defining a physical property of the layers (102-106) constituting the nitride semiconductor light-emitting element (100), a manufacturing condition parameter, which is a manufacturing condition of the nitride semiconductor light-emitting element (100) that is changed when adjusting the value of the composition parameter or the physical property parameter, and the optical output of the nitride semiconductor light-emitting element (100), to create a trained model (32); and an optical output prediction step of predicting optical output using the trained model (32), wherein in the model creation step, at least one of the composition parameter or the physical property parameter of a predetermined layer of the nitride semiconductor light-emitting element (100) is used in the learning, and a deposition temperature of the predetermined layer is used as the manufacturing condition parameter in the learning.

[0055] [2] The method for predicting light output from a nitride semiconductor light-emitting element according to [1], wherein the nitride semiconductor light-emitting element (100) has an active layer (104) formed by alternately stacking barrier layers (104a) and well layers (104b) made of AlGaN, the predetermined layer is the well layer (104b), and at least the Al composition ratio of the well layer (104b), which is the composition parameter, and the deposition temperature of the well layer (104b), which is the manufacturing condition parameter, are used for the learning.

[0056] [3] The method for predicting the light output of a nitride semiconductor light-emitting element according to [1], wherein the specified layer is a buffer layer (102) made of AlN, and at least a thickness of the buffer layer (102), which is the physical property parameter, and a deposition temperature of the buffer layer (102), which is the manufacturing condition parameter, are used in the learning.

[0057] [4] An apparatus for predicting an optical output of a nitride semiconductor light-emitting device (100), comprising at least one of a composition parameter that is a parameter defining a composition of layers (102-106) constituting the nitride semiconductor light-emitting device (100) or a physical property parameter that is a parameter defining a physical property of the layers (102-106) constituting the nitride semiconductor light-emitting device (100), and manufacturing condition parameters that are manufacturing conditions of the nitride semiconductor light-emitting device (100) to be changed when adjusting the value of the composition parameter or the physical property parameter; The light output prediction device (1) for a nitride semiconductor light-emitting element includes a model creation unit (22) that learns a correlation with the light output of the nitride semiconductor light-emitting element (100) and creates a trained model (32), and a light output prediction unit (23) that predicts the light output using the trained model (32), wherein the model creation unit (22) uses at least one of the composition parameters or the physical property parameters of a specified layer of the nitride semiconductor light-emitting element (100) for the learning, and uses the film formation temperature of the specified layer as the manufacturing condition parameter for the learning.

[0058] (Additional Note) Although the embodiment of the present invention has been described above, the invention according to the claims is not limited to the embodiment described above. It should be noted that not all of the combinations of features described in the embodiment are essential to the means for solving the problems of the invention. The present invention can be modified appropriately without departing from the spirit of the invention. [Explanation of symbols]

[0059] 1...Light output prediction device for nitride semiconductor light emitting device 2...Control section 21…Learning data acquisition section 22…Model Creation Section 23...Light output prediction unit 24…Prediction result display section 3...Storage section 31…Learning data 32…Trained model 33…Source data for prediction 34…Prediction data 100...Nitride semiconductor light emitting element (light emitting element) 101...Substrate 102...Buffer layer 103...n-type semiconductor layer 104…Active layer 104a...Barrier layer 104b...Well layer 105...Electron blocking layer 106...p-type semiconductor layer

Claims

1. A film forming apparatus for a semiconductor light emitting device; a management terminal for managing the film forming apparatus; a semiconductor light emitting device optical output prediction device for predicting an optical output of the semiconductor light emitting device, The optical output prediction device for a semiconductor light emitting device comprises: a data acquisition unit that acquires data corresponding to at least one of composition parameters, which are parameters that define the composition of a layer constituting the semiconductor light emitting device, or physical property parameters, which are parameters that define the physical properties of a layer constituting the semiconductor light emitting device, and data on the optical output of the semiconductor light emitting device from the film forming apparatus or the management terminal, and creates learning data by linking the acquired data corresponding to at least one of the composition parameters or the physical property parameters with the optical output data, and stores the data in a storage unit; a model creation unit that includes a learning algorithm that uses the learning data stored in the storage unit as teacher data, sets at least one of the composition parameters or the physical property parameters as explanatory variables, sets the optical output as an objective variable, and learns by itself a correlation between each parameter of the explanatory variables and the objective variable by machine learning, and when the learning data stored in the storage unit is updated, iteratively executes learning based on a data set of each parameter of the explanatory variables and the objective variable, automatically interprets the correlation between the two, creates a learned model, and stores the model in the storage unit; an optical output prediction unit that predicts the optical output corresponding to prediction source data, which is data of values ​​of each parameter used in the explanatory variables, by using the trained model stored in the storage unit, and stores the predicted data in the storage unit; A prediction result presentation unit that presents the prediction data, The model creation unit is configured to be able to select parameters to be used as the explanatory variables. A manufacturing system for semiconductor light-emitting devices.

2. The model creation unit determines whether the learning data has been updated by comparing a creation date and time of the trained model with an update date and time of the learning data, and when it is determined that the learning data has been updated, creates the trained model based on the updated learning data. The manufacturing system for the semiconductor light-emitting device according to claim 1 .

3. The model creation unit monitors an update status of the learning data, and updates the trained model every time the learning data is updated. The manufacturing system for the semiconductor light-emitting device according to claim 1 .

Images