Honeywell International Inc.

Meenakshi Sundaram Krishnaswamy

Andrew John Trenchard

Sanjoy Saha

Qing Zhao

Venkata Naresh Kumar Boggarapu

Bahador Rashidi

Srikanth Pothakamuri

An Asset Performance Monitoring (APM) based-system includes an APM workflow engine receiving measured data values for dependent process variables from a process. A process and control simulator includes a dynamic operator training simulations (OTS) model. The APM workflow engine initializes the OTS model at a defined operating point at values for independent process variables from the measured data values to synchronize to the OTS model. The OTS model simulates at the defined operating point to generate model predicted values for key dependent process variables used to generate a trained data model that generates trained model predicted values for the key dependent process variables. The trained model predicted values are compared to the measured data values to generate symptom inputs processed by fault models to identify a suspected fault with the processing equipment/process. The APM workflow engine triggers an alert relating to inspection or maintenance action regarding the processing equipment/process.

Extended dynamic process simulation

An apparatus, method, and non-transitory machine-readable medium provide for improved feature extraction and fault detection in a non-stationary process through unsupervised machine learning. The apparatus includes a memory and a processor operably connected to the memory. The processor receives training data regarding a field device in an industrial process control and automation system; extracts a meaningful feature from the training data; performs an unsupervised classification to determine a health index for the meaningful feature; identifies a faulty condition of real-time data using the health index of the meaningful feature; and performs a rectifying operation in the industrial process control and automation system for correcting the faulty condition of the field device.

Feature extraction and fault detection in a non-stationary process through unsupervised machine learning

A method includes associating multiple real-time applications with a framework. The real-time applications include applications for monitoring or controlling equipment in at least one industrial facility. Each application has at least one input variable and at least one output variable. The method also includes identifying relationships between the input and output variables of the applications to identify data dependencies. The method further includes receiving data updates at the framework and notifying at least one of the applications of the data updates based on the data dependencies to support data-driven operation of the framework. The data-driven operation of the framework provides data to the applications to support performance monitoring of the equipment, analysis of the equipment's operation, and/or identification of abnormal equipment conditions.

Growing community of inventors

Edmonton, Canada

Meenakshi Sundaram Krishnaswamy