US 2019/0094108 A1 · System And Method For Detecting Anomaly Of A Machine Tool

Abstract

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

Claims20

Dependent claims

A system for detecting an anomaly of a machine tool, comprising:

a server comprising a processor and configured to execute code, comprising:
a collection module configured to collect a stream of operational data comprising positional parameters and movement parameters of machining processes performed by the machine tool;
a detection module configured to detect one or more outliers from the stream of the operational data by a plurality of anomaly detection methods that are based on different failure models and assumptions;
a determination module configured to determine the number of the outliers present in the anomaly detection methods;
an adjustment module configured to adjust a threshold of the outliers based on cost of failure or impact on workflow;
and
a notification module configured to send a notification when the number of the outliers exceeds the threshold,
wherein maintenance of the machine tool is performed based on the notification.

5 more elements

A method for detecting an anomaly of a machine tool, comprising:

collecting a stream of operational data comprising positional parameters and movement parameters of machining processes performed by the machine tool;
detecting one or more outliers from the stream of the operational data by a plurality of anomaly detection methods that are based on different failure models and assumptions;
determine the number of the outliers present in the anomaly detection methods;
adjusting a threshold of the outliers based on cost of failure or impact on workflow;
and
sending a notification when the number of the outliers exceeds the threshold,
wherein maintenance of the machine tool is performed based on the notification.

4 more elements

Dependencies are inferred from the claim text.

System And Method For Detecting Anomaly Of A Machine Tool

Life of this patent

System And Method For Detecting Anomaly Of A Machine Tool

Life of this patent

Abstract

Claims20