Device Management System, Predictive Maintenance System, Device Management Method, and Program

Abstract

A device management system of this disclosure comprises: a parameter reception means for receiving, in a concealed format, a parameter relating to the operation status of a semiconductor manufacturing device, the parameter being used in an analysis relating to indication maintenance of the semiconductor manufacturing device; an indication maintenance analysis means for performing an analysis, by a secret calculation which uses the received parameter in the concealed format and which is related to indication maintenance of a component of the semiconductor manufacturing device; and an output means for outputting the analysis result of the indication maintenance of the component.

Description

Technical Field

[0001] The present disclosure relates to a device management system, a predictive maintenance system, a device management method, and a recording medium.

Background Art

[0002] Semiconductor manufacturing equipment manufacturers remotely monitor the operating status of equipment delivered to semiconductor manufacturers, and quickly respond when detecting signs of failure or malfunction of semiconductor manufacturing equipment to prevent productivity from decreasing.

[0003] For example, Patent Document 1 discloses a system that creates a parameter prediction model for a maintenance part of a semiconductor manufacturing apparatus based on the value of a meta-parameter included in a life prediction model of the maintenance part of the semiconductor manufacturing apparatus, and calculates the predicted life thereof.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, since the invention described in Patent Document 1 above outputs data predicted by a single prediction model, there is a limit to improving the accuracy of the prediction data. The parameters of semiconductor manufacturing equipment monitored for predicting failures or malfunctions are know-how information for semiconductor manufacturers and should be kept confidential. Also, as equipment manufacturers, since they also have transactions with competing semiconductor manufacturers, they do not want to receive know-how information.

[0006] An example of the object of the present disclosure is to provide a system that performs analysis regarding predictive maintenance while concealing know-how information held by semiconductor manufacturers.

Means for Solving the Problems

[0007] The device management system in one aspect of the present disclosure is used for analysis related to predictive maintenance of semiconductor manufacturing equipment, and includes parameter receiving means for receiving parameters related to the operating status of the semiconductor manufacturing equipment in an encrypted form, predictive maintenance analysis means for analyzing predictive maintenance of components of the semiconductor manufacturing equipment by means of secure computing using the received encrypted parameters, and output means for outputting the results of the analyzed predictive maintenance of the components.

[0008] A predictive maintenance system in one aspect of the present disclosure is a predictive maintenance system having one or more semiconductor manufacturer servers and a device management system. Each of the one or more semiconductor manufacturer servers includes a parameter storage unit for storing parameters related to the operating status of the semiconductor manufacturing equipment, an encryption unit for encrypting the parameters stored in the parameter storage unit, and parameter input / output means for transmitting the parameters encrypted by the encryption unit to the device management system in an encrypted form. The device management system is used for analysis related to predictive maintenance of the semiconductor manufacturing equipment, and includes parameter receiving means for receiving parameters related to the operating status of the semiconductor manufacturing equipment in an encrypted form, predictive maintenance analysis means for analyzing predictive maintenance of components of the semiconductor manufacturing equipment by means of secure computing using the received encrypted parameters, and output means for outputting the results of the analyzed predictive maintenance of the components.

[0009] A device management method in one aspect of the present disclosure is used for analysis related to predictive maintenance of semiconductor manufacturing equipment, receives parameters related to the operating status of the semiconductor manufacturing equipment in an encrypted form, analyzes predictive maintenance of components of the semiconductor manufacturing equipment by means of secure computing using the received encrypted parameters, and outputs the results of the analyzed predictive maintenance of the components.

[0010] A recording medium according to one aspect of the present disclosure is used for analysis related to predictive maintenance of a semiconductor manufacturing apparatus, receives parameters related to the operating status of the semiconductor manufacturing apparatus in an encrypted form, analyzes, by means of secure computing, predictive maintenance of components of the semiconductor manufacturing apparatus using the received encrypted-form parameters, and stores a program that causes a computer to output the results of the analyzed predictive maintenance of the components.

Advantages of the Invention

[0011] An example of the effect according to the present disclosure is to provide a system that can perform analysis regarding predictive maintenance while concealing information that is know-how held by semiconductor manufacturers.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0013] Next, embodiments will be described in detail with reference to the drawings.

[0014] [First Embodiment] FIG. 1 is a block diagram showing the configuration of the prognostic maintenance system 10 in the first embodiment. Referring to FIG. 1, the prognostic maintenance system 10 includes an equipment management system 100 of a semiconductor manufacturing apparatus and a semiconductor manufacturer server 200. The equipment management system 100 is implemented by a service provider entrusted with the maintenance and servicing of the semiconductor manufacturing apparatus.

[0015] The equipment management system 100 of the semiconductor manufacturing apparatus includes a parameter reception unit 101, a prognostic maintenance analysis unit 102, and an output unit 103. The semiconductor manufacturer server 200 includes a parameter storage unit 201 for storing parameters of the semiconductor manufacturing apparatus, an encryption unit 202 for encrypting the parameters, and a parameter input / output unit 203 for performing input / output of parameters with the equipment management system 100. The parameter storage unit 201 is connected to each semiconductor manufacturing apparatus in the factory via a network, and stores operating conditions of each manufacturing apparatus, logs related to process parameters, and the like.

[0016] FIG. 2 is a diagram showing an example of a hardware configuration in which the equipment management system 100 of the semiconductor manufacturing apparatus in the first embodiment of the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 2, the equipment management system 100 includes a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, a memory such as a RAM (Random Access Memory) 503, a storage device 505 such as a hard disk for storing a program 504, a communication I / F (Interface) 508 for network connection, and an input / output interface 511 for performing input / output of data. In the first embodiment, information on parameters received from each semiconductor manufacturer server 200 is input to the equipment management system 100 via the communication I / F 508.

[0017] The CPU 501 operates the operating system to control the entire device management system 100 according to the first embodiment of the present invention. Further, the CPU 501 reads programs and data from the recording medium 506 mounted on, for example, the drive device 507 into the memory. Further, the CPU 501 functions as the parameter receiving unit 101, the prognostic maintenance analysis unit 102, the output unit 103, and a part of these in the first embodiment, and executes the processing or instructions in the flowchart shown in FIG. 3 described later based on the program.

[0018] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. A part of the recording medium of the storage device is a non-volatile storage device, and a program is recorded therein. Further, the program may be downloaded from an external computer (not shown) connected to the communication network.

[0019] The input device 509 is realized by, for example, a mouse, a keyboard, a built-in key button, etc., and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or a built-in key button, and may be, for example, a touch panel. The output device 510 is realized by, for example, a display, and is used to confirm the output.

[0020] As described above, the first embodiment shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the realization means of each part included in the semiconductor manufacturing device management system 100 in FIG. 1 is not limited to the configuration described above. Further, the device management system 100 may be realized by a single physically combined device, or may be realized by two or more physically separated devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network. Further, the device management system 100 in the first embodiment shown in FIG. 1 may also be configured by cloud computing or the like.

[0021] In FIG. 1, the parameter receiving unit 101 is a means for receiving, in an encrypted form, parameters related to the operation status of a semiconductor manufacturing apparatus, which is used for analysis related to predictive maintenance of the semiconductor manufacturing apparatus. The semiconductor manufacturing apparatus refers to all apparatuses used in the manufacture of semiconductors. Examples of semiconductor manufacturing apparatuses include, for example, manufacturing apparatuses used in the element formation process on a wafer, which is a pre-process of the semiconductor manufacturing process, such as diffusion / thermal oxidation apparatuses, film formation-related apparatuses (including etching apparatuses), coater / developer apparatuses, exposure apparatuses, cleaning / etching apparatuses, or ion implantation / annealing apparatuses. Examples of film formation-related apparatuses include plasma CVD (Chemical Vapor Deposition), dry etching apparatuses (RIE), RF plasma, sputtering, and CVD. Predictive maintenance is, for example, measuring and monitoring the state of a semiconductor manufacturing apparatus, grasping or predicting the deterioration state of the equipment, and performing component replacement, repair, etc.

[0022] A parameter is a parameter related to the operation status of a semiconductor manufacturing apparatus. More specifically, the parameter changes according to the operation time of the semiconductor manufacturing apparatus and is a parameter that can predict the necessity of maintenance in a specific unit of the semiconductor manufacturing apparatus. Components used in a semiconductor manufacturing apparatus are, for example, components among those used in the semiconductor manufacturing apparatus that particularly affect the yield and the accuracy of the manufactured semiconductors. Examples of components used in a semiconductor manufacturing apparatus include, for example, heating lamps, light sources, ion sources, turbo molecular pumps, vacuum valves, or chambers.

[0023] Parameters are classified, for example, into process parameters and operating condition parameters. Process parameters are, for example, values obtained by measuring physical quantities in a manufacturing apparatus during operation of a semiconductor manufacturing apparatus, and are obtained from sensor values attached to the semiconductor manufacturing apparatus. Examples of sensors include a current sensor, a temperature sensor, a vibration sensor, an acceleration sensor, etc. Examples of process parameters include, for example, current consumption and vibration degree in a specific unit within a semiconductor manufacturing apparatus. Examples of other process parameters in a film formation related apparatus include, for example, gas flow rate, film formation time, substrate temperature, Vpp voltage and Vdc voltage (plasma CVD, dry etching), DC bias (sputtering), pressure. Examples of process parameters of a semiconductor manufacturing apparatus other than those related to film formation include, for example, in a cleaning / etching apparatus, cleanliness and etch depth. In a diffusion / thermal oxidation apparatus, for example, depth, thickness, and sheet resistance of an oxide film. In an ion implantation / annealing apparatus, for example, profile sheet resistance. In a coater / developer, for example, a resist pattern.

[0024] Operating condition parameters are parameters indicating setting conditions during operation of a semiconductor manufacturing apparatus. Examples of each operating condition parameter in a film formation related apparatus include, in plasma CVD, input power, reflected wave → 0 (closeness from 0 of reflection coefficient), achievable vacuum degree in the chamber, heating lamp power. In a dry etching apparatus, achievable vacuum degree, heating lamp power. In RF plasma, incident wave Pf, reflected wave Pr, value of variable capacitor, heating lamp power. In a sputtering apparatus, input power, reflected wave, achievable vacuum degree, heating lamp electrode. In CVD, heating lamp power. Operating condition parameters other than those related to film formation related apparatus include, for example, in an ion implantation / annealing apparatus, for example, vacuum degree and infrared lamp power. In an exposure apparatus, for example, light source output. In a coater / developer, for example, acceleration.

[0025] The encrypted form is, for example, a form encrypted using secure computation. As secure computation methods, there are special encryptions corresponding to specific processes such as homomorphic encryption, a trusted execution environment that processes in an isolated state on hardware, or a multi-party computation method that performs computational processing while keeping secrets distributed across multiple servers (secret sharing computation). When using multi-party computation as a secure computation method, the encryption unit 202 in the semiconductor manufacturer server 200 includes a plurality of servers. According to secret sharing computation, key management and an isolated environment are not required, and the computational processing is faster. When using secret sharing computation (multi-party computation method) as a secure computation method, the parameter receiving unit 101 receives parameters in a decentralized state.

[0026] Specific methods of secure computation for multi-party computation include the following examples. For example, the encrypted data a is secretly shared into distributed values x, y, …, and x, y, … are each sent by the administrator to different servers. Then, while the encrypted data a remains secretly shared, communication is carried out with each other and the computation proceeds. Finally, the distributed values u, v, … of the output, which are the computation results of each server, are collected and restored to obtain the computation result F(a). This computation result is the result of secure computation regarding the prognosis analysis of the components of the semiconductor manufacturing apparatus.

[0027] The parameter receiving unit 101, for example, triggers an operation for analyzing the necessity of maintaining the components of the semiconductor manufacturing apparatus by the service provider, and in the semiconductor manufacturer server 200, receives the stored parameters in an encrypted form through the network via the communication I / F 508. The parameter receiving unit 101 outputs the acquired parameters to the prognosis maintenance analysis unit 102.

[0028] The prognostic maintenance analysis unit 102 is a means for analyzing the prognostic maintenance of components of a semiconductor manufacturing apparatus through secret calculation using the received encrypted-form parameters. The prognostic maintenance analysis unit 102 estimates the necessity for maintenance of components that have a correlation with specific parameters using the parameters input from the parameter reception unit 101. In this embodiment, components include not only individual components used in a semiconductor manufacturing apparatus but also specific units including a plurality of components. For example, when the component to be analyzed for prognostic maintenance is a light source, the prognostic maintenance analysis unit 102 uses the light source output as a parameter.

[0029] The prognostic maintenance analysis unit 102 analyzes the prognostic maintenance of components based on parameters defined by the difference from a reference value. Here, the reference value is a preset parameter value, for example, the initial value parameter value when starting the operation of a semiconductor manufacturing apparatus. The prognostic maintenance analysis unit 102 performs analysis on the prognostic maintenance of components based on differences such as the rate of change from the reference value, and estimates the necessity for maintenance of the components.

[0030] The output unit 103 is a means for transmitting the analysis result of the prognostic maintenance of components analyzed by the prognostic maintenance analysis unit 102 to the semiconductor manufacturer server 200. The output unit 103 transmits the analysis result in a format that allows the semiconductor manufacturer server 200 side to view the analysis result of the prognostic maintenance. The analysis result of the prognostic maintenance is the necessity for maintenance of a specific component. The output unit 103 may output a list of component names that require maintenance. Also, the output unit 103 may output, as additional information, for example, information indicating the replacement time of the component and the time when inspection is required.

[0031] The operation of the device management system 100 configured as described above will be described with reference to the flowchart of FIG. 3.

[0032] FIG. 3 is a flowchart showing an overview of the operation of the device management system 100 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by the aforementioned processor.

[0033] As shown in FIG. 3, first, the parameter receiving unit 101 receives parameters from the semiconductor manufacturer server 200 in an encrypted form (step S101). Next, the prognostic maintenance analysis unit 102 performs an analysis related to the prognostic maintenance of the components of the semiconductor manufacturing apparatus based on the parameters (step S102). Finally, the output unit 103 outputs the analysis result of the prognostic maintenance by the prognostic maintenance analysis unit 102 (step S103). Thus, the apparatus management system 100 of the semiconductor manufacturing apparatus ends the operation of apparatus management.

[0034] The apparatus management system 100 of the semiconductor manufacturing apparatus has the prognostic maintenance analysis unit 102 perform an analysis related to the prognostic maintenance of the components of the semiconductor manufacturing apparatus based on the encrypted parameters. Thereby, it is possible to provide a system that performs analysis regarding prognostic maintenance while concealing parameter information that is know-how held by the semiconductor manufacturer.

[0035] [Second Embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the content overlapping with the above description will be omitted as long as the description of this embodiment is not made unclear. The prognostic maintenance system 11 in the second embodiment is used to provide a system that makes arrangements necessary for prognostic maintenance based on components with a lifespan analyzed by the prognostic maintenance analysis unit. Each component in each embodiment of the present disclosure can be realized not only by hardware for its function in the same manner as the computer device shown in FIG. 2, but also by a computer device based on program control or firmware.

[0036] FIG. 4 is a block diagram showing the configuration of a prognostic maintenance system 11 including an apparatus management system 110 according to a second embodiment of the present disclosure. Referring to FIG. 4, the apparatus management system 110 and semiconductor manufacturer servers 210(210a, 210b) according to the second embodiment will be described, centering on the parts different from the prognostic maintenance system 10 according to the first embodiment. The apparatus management system 110 according to the second embodiment includes a parameter reception unit 111, a parameter integration unit 112, a model generation unit 113, a prognostic maintenance analysis unit 114, a maintenance execution unit 115, and an output unit 116. The plurality of semiconductor manufacturer servers 210(210a, 210b) include parameter storage units 211(211a, 211b), anonymization units 212(212a, 212b), and parameter input / output units 213(213a, 213b).

[0037] The apparatus management system 100 in the first embodiment received parameters indicating the operating status of semiconductor manufacturing apparatuses in a form anonymized using secret computation from a single semiconductor manufacturer server 200. In contrast, the apparatus management system 110 integrates, by secret computation, parameters regarding the operating status of the same type of semiconductor manufacturing apparatuses from a plurality of servers 210a, 210b. The parameters regarding the operating status of the same type of semiconductor manufacturing apparatuses refer to, for example, parameters of the same type of semiconductor manufacturing apparatuses that indicate a similar correlation relationship to a specific component.

[0038] The plurality of semiconductor manufacturer servers 210 are servers owned by a plurality of customers of semiconductor manufacturing equipment manufacturers (for example, competing semiconductor manufacturers). In this case, parameters of competitors can be analyzed while keeping them confidential. Another example of the plurality of semiconductor manufacturer servers 210 is a case where parameters are stored in different servers for each lot even within the same factory. Note that in the present embodiment, the plurality of semiconductor manufacturer servers 200 are located at two places, but this is not limiting. The plurality of semiconductor manufacturer servers 200 are provided in number corresponding to the number of parameters to be integrated. Hereinafter, the apparatus management system 110 of the semiconductor manufacturing apparatus in the present embodiment will be described in detail. Since the parameter reception unit 111 and the output unit 116 have the same configuration and functions as the parameter reception unit 101 and the output unit 103 in the first embodiment, the description thereof will be omitted here.

[0039] <Apparatus Management System> When the parameter integration unit 112 receives the same type of parameters from a plurality of servers, it is a means for integrating the received plurality of parameters by secure computation. In the present embodiment, integration by secure computation means collectively performing computational processing on the encrypted-form parameters received by the parameter reception unit 111 from each semiconductor manufacturer server 210 while keeping them in the encrypted state. The parameter integration unit 112 outputs the integrated parameters to the prognosis preservation analysis unit 114.

[0040] The model generation unit 113 generates a model for estimating the necessity of maintenance of parts of the semiconductor manufacturing apparatus based on the relationship between the parameters acquired in the past and the necessity of maintenance. More specifically, the model generation unit 113 generates a model having information indicating the necessity of maintenance of parts in the semiconductor manufacturing apparatus as the objective variable and information on the parameters of the semiconductor manufacturing apparatus as the explanatory variable. The model generation unit 113 stores the generated model in the storage device 505.

[0041] The prognostic maintenance analysis unit 114 analyzes the prognostic maintenance of components of the semiconductor manufacturing apparatus using the model generated by the model generation unit 113. When the prognostic maintenance analysis unit 114 inputs, for example, the parameters integrated by the parameter integration unit 112 into the model stored in the storage device 505, information about the components correlated with the parameters and the necessity of maintaining those components is output. The prognostic maintenance analysis unit 114 outputs the information about the necessity of maintaining the output components to the maintenance execution unit 115 and the output unit 116.

[0042] The maintenance execution unit 115 is a means for arranging what is necessary for maintaining components of the semiconductor manufacturing apparatus based on the analysis result of prognostic maintenance by the prognostic maintenance analysis unit 114. When information indicating that maintenance is necessary is input from the prognostic maintenance analysis unit 114, the maintenance execution unit 115 arranges what is necessary for maintaining the components. What is necessary for maintenance is, for example, ordering components in the case of component replacement. In the case where what is necessary for maintenance is component repair, it is arranging maintenance personnel to repair the components. When information indicating that maintenance is not necessary is input from the prognostic maintenance analysis unit 114, the maintenance execution unit 115 notifies the semiconductor manufacturer server 210 of that information. In this case, the semiconductor manufacturer server 210 repeats a series of operations after a certain period (for example, one month later).

[0043] <Semiconductor manufacturer server> The semiconductor manufacturer server 210 includes a parameter storage unit 211, an anonymization unit 212, and a parameter input / output unit 213. In the parameter storage unit 211, for example, parameters acquired from the semiconductor manufacturing apparatus are stored for each acquisition time. The acquisition time is the acquisition date and time, lot number, etc. The anonymization unit 212 anonymizes the parameters stored in the parameter storage unit 211 using secret calculation. The anonymization unit 212 may use only specific parameters among the parameters stored in the parameter storage unit 211, or may use the average value of a plurality of parameters. The parameter input / output unit 213 transmits the anonymized parameters to the device management system 110 in an anonymized form.

[0044] The operation of the prognostic maintenance system 11 configured as described above will be described with reference to the flowchart of FIG. 5.

[0045] FIG. 5 is a flowchart showing an overview of the operation of the prognostic maintenance system 11 in the second embodiment. Note that the processing according to this flowchart may be executed based on program control by the aforementioned processor.

[0046] As shown in FIG. 5, first, the anonymization unit 212 of the semiconductor manufacturer server 210 anonymizes the parameters stored in the parameter storage unit 211 (step S201). Next, the parameter input / output unit 213 outputs the parameters in an anonymized form to the device management system 110 (step S202). Next, the parameter reception unit 111 of the device management system 110 receives a plurality of anonymized parameters (step S203). Next, the parameter integration unit 112 integrates the anonymized parameters of a plurality of semiconductor manufacturing devices by performing secret calculation in an anonymized form (step S204). Next, the prognostic maintenance analysis unit 114 analyzes the prognostic maintenance of the components of the semiconductor manufacturing device using the model generated by the model generation unit 113 based on the integrated parameters (step S205). Next, if it is determined as a result of the prognostic analysis that component maintenance is necessary (step S206; YES), the maintenance execution unit 115 makes arrangements necessary for component maintenance (step S207). On the other hand, if it is determined as a result of the prognostic analysis that component maintenance is not necessary (step S206; NO), that information is notified to the semiconductor manufacturer server 210, and a series of operations is repeated. Thus, the prognostic maintenance system 11 ends the operation of prognostic maintenance.

[0047] In the second embodiment of the present disclosure, when it is determined, as a result of prognostic analysis by the prognostic maintenance analysis unit 114, that maintenance of a component is necessary, the maintenance execution unit 115 makes arrangements necessary for the maintenance of the component. Thereby, when maintenance of a component is necessary, prognostic maintenance of the component can be performed without the semiconductor manufacturer making arrangements for maintenance. Also, in the second embodiment of the present disclosure, the parameter integration unit 112 integrates a plurality of encrypted parameters by secret calculation in an encrypted form. In this way, by integrating parameters acquired from a plurality of semiconductor manufacturer servers, the analysis accuracy regarding component maintenance can be improved.

[0048] As described above, the present invention has been described with reference to each embodiment, but the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0049] For example, although a plurality of operations are described in order in the form of a flowchart, the order of the description does not limit the order of execution of the plurality of operations. Therefore, when implementing each embodiment, the order of the plurality of operations can be changed as long as it does not interfere with the content.

[0050] Also, in the present embodiment, when the prognostic maintenance analysis unit 114 inputs specific parameters of the semiconductor manufacturing apparatus into the model generated by the model generation unit 113, information about the component correlated with the parameter and whether maintenance of the component is necessary is output. However, in the present embodiment, when the prognostic maintenance analysis unit 114 inputs specific parameters of the semiconductor manufacturing apparatus into the model generated by the model generation unit 113, the component correlated with the parameter, the timing when maintenance of the component is necessary, the life of the component, etc. may be output. In this case, the model generated by the model generation unit 113 is a model that outputs a predicted value of information indicating the timing when maintenance of a component of the semiconductor manufacturing apparatus is necessary and the life of the component when parameters of the semiconductor manufacturing apparatus are input. In this case, for example, the necessity of maintenance can be determined based on a desired determination criterion.

[0051] Some or all of the above embodiments can be described as follows in the appended claims, but are not limited thereto.

[0052] (Appendix 1) Parameter receiving means used for analysis related to predictive maintenance of a semiconductor manufacturing apparatus, which receives parameters related to the operating status of the semiconductor manufacturing apparatus in an encrypted form; Predictive maintenance analysis means for analyzing predictive maintenance of components of a semiconductor manufacturing apparatus by means of secure computing using the received encrypted-form parameters; Output means for outputting the results of the analyzed predictive maintenance of the components; An equipment management system comprising:

[0053] (Appendix 2) When the parameter receiving means receives the same type of parameters from a plurality of servers, it further comprises parameter integration means for integrating the received plurality of parameters in an encrypted form by means of secure computing; The equipment management system according to Appendix 1, wherein the predictive maintenance analysis means analyzes predictive maintenance of components of a semiconductor manufacturing apparatus using the parameters integrated by the parameter integration means.

[0054] (Appendix 3) The equipment management system according to Appendix 2, wherein the plurality of servers are servers owned by different semiconductor manufacturers respectively.

[0055] (Appendix 4) The equipment management system according to any one of Appendices 1 to 3, wherein the parameter is a parameter defined by a difference from a reference value.

[0056] (Appendix 5) The equipment management system according to any one of Appendices 1 to 4, wherein the parameter is a parameter related to the operating status of a film-forming related apparatus.

[0057] (Appendix 6) The prognostic maintenance analysis means analyzes the prognostic maintenance of the components of the semiconductor manufacturing apparatus using a learned model, and is the apparatus management system according to any one of Appendices 1 to 5.

[0058] (Appendix 7) The learned model is a model that inputs the parameters and outputs the necessity for maintenance of components in the semiconductor manufacturing apparatus, and is the apparatus management system according to Appendix 6.

[0059] (Appendix 8) The apparatus further includes model generation means for generating the learned model. The learned model generates a model for estimating the necessity for maintenance of components of the semiconductor manufacturing apparatus based on the relationship between the parameters acquired in the past and the necessity for maintenance, and is the apparatus management system according to Appendix 6 or Appendix 7.

[0060] (Appendix 9) The secure computation is secure multiparty computation, and is the apparatus management system according to any one of Appendices 1 to 8.

[0061] (Appendix 10) The apparatus further includes maintenance execution means for arranging maintenance of the components based on the result analyzed by the prognostic maintenance analysis means, and is the apparatus management system according to any one of Appendices 1 to 9.

[0062] (Appendix 11) The maintenance execution means places an order for necessary components in the semiconductor manufacturing apparatus, and is the apparatus management system according to claim 10.

[0063] (Appendix 12) A prognostic maintenance system having one or more semiconductor manufacturer servers and an apparatus management system, Each of the one or more semiconductor manufacturer servers includes a parameter storage unit that stores parameters related to the operating status of a semiconductor manufacturing apparatus, and A anonymization unit that anonymizes the parameters stored in the parameter storage unit, Parameter input / output means for transmitting the parameters encrypted by the encryption unit to the device management system in an encrypted form, The device management system, Parameter receiving means for use in analyzing the predictive maintenance of a semiconductor manufacturing apparatus, and receiving parameters related to the operating status of the semiconductor manufacturing apparatus in an encrypted form, Predictive maintenance analysis means for analyzing the predictive maintenance of components of a semiconductor manufacturing apparatus by secret calculation using the received parameters in the encrypted form, Output means for outputting the results of the analyzed predictive maintenance of the components, A predictive maintenance system comprising the above.

[0064] (Appendix 13) Used for analyzing the predictive maintenance of a semiconductor manufacturing apparatus, receiving parameters related to the operating status of the semiconductor manufacturing apparatus in an encrypted form, Analyzing the predictive maintenance of components of the semiconductor manufacturing apparatus by secret calculation using the received parameters in the encrypted form, A device management method for outputting the results of the analyzed predictive maintenance of the components.

[0065] (Appendix 14) Used for analyzing the predictive maintenance of a semiconductor manufacturing apparatus, receiving parameters related to the operating status of the semiconductor manufacturing apparatus in an encrypted form, Analyzing the predictive maintenance of components of a semiconductor manufacturing apparatus by secret calculation using the received parameters in the encrypted form, A recording medium storing a program for causing a computer to execute the steps of outputting the results of the analyzed predictive maintenance of the components.

Explanation of symbols

[0066] 10, 11 Predictive maintenance system 100, 110 Device management system 101, 111 Parameter receiving unit 102, 114 Predictive maintenance analysis unit 103 and 116 Output section 112 Parameter integration section 113 Model generation section 115 Security execution section 200 and 210 Semiconductor manufacturer server 201 and 211 Parameter storage section 202 and 212 Encryption section 203 and 213 Parameter input / output section

Claims

1. A parameter receiving means that is used for analysis related to predictive maintenance of a semiconductor manufacturing apparatus and receives, in an encrypted form, the same type of parameters related to the operating status of the semiconductor manufacturing apparatus from a plurality of servers; A parameter integrating means that integrates the received plurality of parameters by secret calculation in an encrypted form; A predictive maintenance analysis means that analyzes, by secret calculation, predictive maintenance of components of a semiconductor manufacturing apparatus using the parameters integrated by the parameter integrating means; An output means that outputs the results of the analyzed predictive maintenance of the components; comprising: The plurality of servers are respectively servers owned by different semiconductor manufacturers, The parameter is the difference in the rate of change from the initial parameter value when the operation of the semiconductor manufacturing apparatus is started, a device management system.

2. The device management system according to claim 1, wherein the parameter is a parameter related to the operating status of a film forming related apparatus.

3. The device management system according to claim 1 or claim 2, wherein the predictive maintenance analysis means analyzes predictive maintenance of components of the semiconductor manufacturing apparatus using a learned model.

4. The device management system according to claim 3, wherein the learned model is a model that inputs the parameter and outputs the necessity of maintenance of components in the semiconductor manufacturing apparatus.

5. Further comprising a model generation means for generating the learned model, The learned model generates a model for estimating the necessity of maintenance of components of the semiconductor manufacturing apparatus based on the relationship between the parameters acquired in the past and the necessity of maintenance, according to claim 3 or claim 4.

6. The device management system according to any one of claims 1 to 5, wherein the secret calculation is secret sharing calculation.

7. The apparatus management system according to any one of claims 1 to 6, further comprising a maintenance execution means for arranging maintenance of the component based on the result analyzed by the omen maintenance analysis means.

8. The apparatus management system according to claim 7, wherein the maintenance execution means places an order for necessary components in the semiconductor manufacturing apparatus.

9. A prognostic maintenance system having a plurality of semiconductor manufacturer servers and an apparatus management system, Each of the plurality of semiconductor manufacturer servers is a server owned by a different semiconductor manufacturer, and includes a parameter storage means for storing parameters related to the operating status of the semiconductor manufacturing apparatus, A anonymization means for anonymizing the parameters stored in the parameter storage means, Parameter input / output means for transmitting the parameters anonymized by the anonymization means to the apparatus management system in an anonymized form, and The apparatus management system includes Parameter receiving means for receiving, in an anonymized form, the same type of parameters related to the operating status of the semiconductor manufacturing apparatus, which are used for analysis related to prognostic maintenance of the semiconductor manufacturing apparatus, from the plurality of semiconductor manufacturer servers, Parameter integration means for integrating the received plurality of parameters by secret calculation in an anonymized form, Prognostic maintenance analysis means for analyzing, by secret calculation, prognostic maintenance of components of the semiconductor manufacturing apparatus using the parameters integrated by the parameter integration means, Output means for outputting the result of the prognostic maintenance of the analyzed components, and The prognostic maintenance system, wherein the parameter is a difference in the rate of change from the initial value parameter value when the operation of the semiconductor manufacturing apparatus is started.

10. A computer It is used for the analysis related to the predictive maintenance of a semiconductor manufacturing apparatus, and receives, in an encrypted form, the same type of parameters related to the operating status of the semiconductor manufacturing apparatus from servers owned by different semiconductor manufacturers, Integrate the received plurality of parameters by secret calculation in an encrypted form, Using the integrated parameters, analyze the predictive maintenance of the components of the semiconductor manufacturing apparatus by secret calculation, An apparatus management method for outputting the result of the predictive maintenance of the analyzed components, The parameter is the difference in the rate of change from the initial value parameter value when the operation of the semiconductor manufacturing apparatus is started.

11. It is used for the analysis related to the predictive maintenance of a semiconductor manufacturing apparatus, and receives, in an encrypted form, the same type of parameters related to the operating status of the semiconductor manufacturing apparatus from servers owned by different semiconductor manufacturers; Integrate the received plurality of parameters by secret calculation in an encrypted form; Using the integrated parameters, analyze the predictive maintenance of the components of the semiconductor manufacturing apparatus by secret calculation; A program that causes a computer to output the result of the predictive maintenance of the analyzed components, The parameter is the difference in the rate of change from the initial value parameter value when the operation of the semiconductor manufacturing apparatus is started.

Images