Anomaly detection from aggregation statistics using neural networks

• Main Authors: ISKANDER JIMMY, ARMACOST MICHAEL D
• Format: Patent
• Language: Chinese; English
• Published: 16.05.2023
• Subjects: CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

The disclosed embodiments describe a method and system to perform a method of obtaining a simplified representation of a plurality of sensor statistics representative of data collected by a plurality of sensors associated with a device manufacturing system that performs manufacturing operations. The method further includes generating a plurality of outlier scores using a plurality of outlier detection models, each of the plurality of outlier scores being generated based on a simplified representation of the plurality of sensor statistics using a respective outlier detection model of the plurality of outlier detection models. The method further includes processing the plurality of outlier scores using a detector neural network to produce an anomaly score indicating a likelihood of an anomaly associated with a manufacturing operation. 所公开的实施描述一种方法及系统，用以执行获得代表由与执行制造操作的器件制造系统相关联的多个传感器收集的数据的多个传感器统计的简化表示的方法。所述方法进一步包括使用多个离群值检测模型产生多个离群值得分，所述多个离群值得分中的每一个使用所述多个离群值检测模型中的相应离群值检测模型基于所述多个传感器统计的简化表示产生。所述方法进一步包括使用检测器神经网络处理所述