Hitachi, Ltd.

Qiyao Wang

Chetan Kumar Gupta

Haiyan Wang

Susumu Serita

Huijuan Shao

Wei Huang

Takashi Saeki

Ahmed Khairy Farahat

Chi Zhang

Hamed Khorasgani

Aniruddha Rajendra Rao

A method for detecting an anomaly in time series sensor data. The method may include identifying a noisiest cycle from the time series sensor data; for an evaluation of the noisiest cycle indicative of the anomaly being detected at a confidence level above a threshold, providing an output associated with the noisiest cycle as being the anomaly; and for the evaluation of the noisiest cycle indicative of the anomaly being detected at the confidence level not above the threshold: identifying a cycle from the time series sensor data having a most differing shape; and providing the output associated with the cycle having the most differing shape as being the anomaly.

Versatile anomaly detection system for industrial systems

In example implementations described herein, there are systems and methods for processing sensor data from an equipment over a period of time to generate sensor time series data; processing the sensor time series data in a kernel weight layer configured to generate weights to weigh the sensor time series data; providing the weighted sensor time series data to fully connected layers configured to conduct a correlation on the weighted sensor time series data with predictive maintenance labels to generate an intermediate predictive maintenance label; and providing the intermediate predictive maintenance label to an inversed kernel weight layer configured to inverse the weights generated by the kernel weight layer, to generate a predictive maintenance label for the equipment.

Predictive maintenance system for spatially correlated industrial equipment

Aspects of the present disclosure are directed to systems and methods for determining execution of failure prediction models and duration prediction models for a sensor system. Systems and methods can involve receiving streaming data from one or more sensors and for a failure prediction model processing the streaming data indicating a predicted failure with a probability higher than a threshold, obtaining a duration of the predicted failure from a duration prediction model configured to predict durations of detected failures based on the streaming data; deactivating the failure prediction model when the predicted failure occurs; and determining a time to reactivate the failure prediction model based on the obtained duration of the predicted failure.

System and methods for failure occurrence prediction and failure duration estimation

Example implementations described herein involve systems and methods involving a plurality of sensors monitoring one or more processes, the sensors providing sensor data, which can include determining a probability map of the sensor data from a database and a functional relationship between key performance indicators (KPIs) of the one or more processes and the sensor data; executing a search on the probability map to determine constrained and continuous ranges for the sensor data that optimize KPIs for the one or more processes based on the functional relationship; and generating a recommendation for the one or more processes that fit within the constrained and continuous range of the sensor data.

Operating envelope recommendation system with guaranteed probabilistic coverage

Example implementations described herein are directed to systems and methods for defect rate analytics to reduce defectiveness in manufacturing. In an example implementation, a method include determining, from data associated with each feature for a manufacturing process, the data feature indicative of process defects detected based on the feature, an estimated condition for the feature that reduces a defect rate of the process defects, the estimated condition indicating the data into a first group and second group; calculating the rate reduction of the defect rate based on a difference in defects between the first group and the second group; for the rate reduction meeting a target confidence level for a target defect rate, applying the estimated condition to the manufacturing process associated with each of the features. In example implementations, the defect rate analytics reduce defectiveness in manufacturing with independent processes and/or dependent processes.

Growing community of inventors

Los Gatos, CA, United States of America

Qiyao Wang