Abnormality detection system, semiconductor device manufacturing system and semiconductor device manufacturing method

Abstract

To provide an abnormality detection system capable of reducing work load of an engineer. An algorithm storage unit stores therein a detection algorithm corresponding to identification information of a detection target. An abnormality detection unit detects an abnormality in a detection target signal obtained from a monitor signal of the detection target using a corresponding detection algorithm in the algorithm storage unit. A detection target identification unit determines whether the detection algorithm corresponding to the identification information of the detection target is stored in the algorithm storage unit, and issues a generation request when it is not stored therein. An algorithm generation unit generates the detection algorithm using a corresponding detection target signal according to the generation request.

What is claimed is: 
     
         1 . A method for manufacturing of devices comprising:
 processing the devices in accordance with a manufacturing configuration;   receiving a monitoring signal obtained by electrically sensing the status of the processing;   generating an abnormality detection algorithm based on the monitoring signal; and   detecting an abnormality of the processing based on the abnormality detection algorithm.   
     
     
         2 . The method according to  claim 1 ,
 wherein the generating includes updating the abnormality detection algorithm.   
     
     
         3 . The method according to  claim 1 ,
 wherein the receiving, the generating and the detecting are performed while the processing.   
     
     
         4 . The method according to  claim 1 ,
 wherein the abnormality detection algorithm comprises parameters for neural network.   
     
     
         5 . The method according to  claim 4 ,
 wherein the parameters are repeatedly updated by feeding back learning results of the neural network.   
     
     
         6 . The method according to  claim 1 , further comprising:
 identifying the manufacturing condition from a plurality of manufacturing conditions;   selecting the abnormality detection algorithm corresponding to the identified manufacturing condition from a plurality of abnormality detection algorithms,   the generating is performed when the abnormality detection algorithm corresponding to the identified manufacturing condition is not found at the selecting.   
     
     
         7 . The method according to  claim 6 ,
 wherein the generating includes updating the abnormality detection algorithm.   
     
     
         8 . The method according to  claim 6 ,
 wherein the receiving, the generating, the detecting, the identifying and the selecting are performed while the processing.   
     
     
         9 . The method according to  claim 6 ,
 wherein the abnormality detection algorithm comprises parameters for neural network.   
     
     
         10 . The method according to  claim 9 ,
 wherein the parameters are repeatedly updated by feeding back learning results of the neural network.   
     
     
         11 . A computing device comprising:
 a network interface circuit configured to input identification information which identifies a configuration of processing;   a signal input circuit configured to input a monitoring signal which corresponds to the configuration;   a storage circuit configured to store a detection algorithm which corresponds to the configuration; and   a detection execution circuit configured to detect the status of the processing by executing the detection algorithm with the monitoring signal,   wherein the detection algorithm is obtained by receiving from an external algorithm generation device via the network interface.   
     
     
         12 . The computing device according to  claim 11 ,
 wherein the detection algorithm comprises parameters for neural network.   
     
     
         13 . The computing device according to  claim 12 ,
 wherein the parameters for neural network are learned at the external algorithm generation device.   
     
     
         14 . The computing device according to  claim 11 ,
 wherein the detection algorithm comprises parameters for statistic algorithm.   
     
     
         15 . The computing device according to  claim 14 ,
 wherein the parameters for statistic algorithm are collected at the external algorithm generation device.   
     
     
         16 . The computing device according to  claim 11 ,
 wherein the computing device is configured to send a request for generating of the detection algorithm to the external algorithm generation device via the network interface, when the detection algorithm which corresponds to the configuration is not stored in the storage device.