Semiconductor device manufacturing system, server, and method for identifying foreign matter generation factors

Abstract

The present invention provides technology capable of coping with foreign objects caused by an etching process without requiring coating of a member in a processing container.　One semiconductor device manufacturing system according to the present invention comprises a platform on which an application for specifying a factor in generation of foreign objects adhering to a sample to be processed by a semiconductor manufacturing device is implemented, and is characterized in that: the application executes a step for creating a graph in which a process history is set as nodes, and in which set as each edge is the difference between the number of foreign objects in one connected node and the number of foreign objects in the other connected node, a step for inputting an acquired number of foreign objects and a process history and estimating the edges by a neural network using a graph, and a step for using the estimated edges to specify a process history that is a factor in generation of the foreign objects; and the process history includes a manufacturing condition of the semiconductor manufacturing device.

Claims

[Claim 1] In a semiconductor device manufacturing system, which includes a platform equipped with an application for identifying the causes of foreign matter adhering to samples processed by semiconductor manufacturing equipment, A graph is created in which the process history is represented as nodes, and the difference between the number of foreign objects in one connected node and the number of foreign objects in the other connected node is represented as an edge. The steps include: inputting the number of foreign objects obtained and the process history, and estimating the edges using a neural network based on the graph; The application performs the following steps: the process history that causes the foreign matter to be generated is identified using the estimated edge; A semiconductor device manufacturing system characterized in that the process history includes the manufacturing conditions of the semiconductor manufacturing equipment. [Claim 2] In the semiconductor device manufacturing system according to claim 1, The aforementioned graph is a directed acyclic graph, which is a semiconductor device manufacturing system. [Claim 3] In the semiconductor device manufacturing system according to claim 1, A semiconductor device manufacturing system characterized in that the step of estimating the edge is further input of a parts replacement history, which is information indicating the replacement history of parts of the semiconductor manufacturing equipment, and a cleaning execution history, which is information indicating the execution history of cleaning performed by the semiconductor manufacturing equipment, and the edge is then estimated. [Claim 4] In the semiconductor device manufacturing system according to claim 1, A semiconductor device manufacturing system characterized in that the application recommends modifying the manufacturing conditions based on the identified causes of foreign matter generation. [Claim 5] In a server where processing is performed to identify the causes of foreign matter adhering to samples processed by semiconductor manufacturing equipment, A graph is created in which the process history is represented as nodes, and the difference between the number of foreign objects in one connected node and the number of foreign objects in the other connected node is represented as an edge. The steps include: inputting the number of foreign objects obtained and the process history, and estimating the edges using a neural network based on the graph; The process history that causes the foreign matter to be generated is identified using the estimated edge, and the following steps are performed: The server is characterized in that the process history includes the manufacturing conditions of the semiconductor manufacturing equipment. [Claim 6] In a method for identifying the causes of foreign matter that adhere to a sample processed by a semiconductor manufacturing apparatus, The steps include creating a graph where the process history is represented as nodes, and the difference between the number of foreign objects in one connected node and the number of foreign objects in the other connected node is represented as an edge, The steps include: inputting the number of foreign objects obtained and the process history, and estimating the edges using a neural network with the graph; The step includes identifying the process history that causes the foreign matter to be generated using the estimated edge, A method for identifying the cause of foreign matter generation, characterized in that the process history includes the manufacturing conditions of the semiconductor manufacturing apparatus.

Images