Fisher-rosemount Systems, Inc

Paul Richard Muston

Mark J Nixon

Terrence L Blevins

Ken J Beoughter

Daniel Dean Christensen

Wilhelm K Wojsznis

Noel Howard Bell

Alper Turhan Enver

Joshua Brian Kidd

Eric Darrell Rotvold

J Michael Lucas

Peter Zornio

Gary Keith Law

Deji Chen

Christopher J Worek

Song Han

Robert Burke Havekost

Ling Zhou

Michael J Lucas

Paul Kenneth Daly

Randolf Reiss

Distributed industrial process monitoring and analytics systems and methods are provided for operation within a process plant. A plurality of distributed data engines (DDEs) may be embedded within the process plant to collect and store data generated by data sources, such as process controllers. Thus, the data may be stored in a distributed manner in the DDEs embedded throughout the process plant. The DDEs may be connected by a data analytics network to facilitate data transmission by subscription or query. The DDEs may be configured as a plurality of clusters, which may further include local and centralized clusters. The local clusters may obtain streaming data from data sources and stream selected data to a data consumer. The centralized cluster may register the local clusters, receive data therefrom, and perform data analytic functions on the received data. The analyzed data may be further sent to a data consumer.

Distributed industrial performance monitoring and analytics

A big data network or system for a process control system or plant includes a big data apparatus including a data storage area configured to store, using a common data schema, multiple types of process data and/or plant data (such as configuration and real-time data) that is used in, generated by or received by the process control system, and one or more data receiver computing devices to receive the data from multiple nodes or devices. The data may be cached and time-stamped at the nodes and streamed to the big data apparatus for storage. The process control system big data system provides services and/or data analyses to automatically or manually discover prescriptive and/or predictive knowledge, and to determine, based on the discovered knowledge, changes and/or additions to the process control system and to the set of services and/or analyses to optimize the process control system or plant.

Big data in process control systems

Techniques for streaming big data in a process plant are disclosed. Generally, these techniques facilitate storage or communication of process control data, including alarms, parameters, events, and the like, in near real-time. Receivers of big data, such as big data historians or devices requesting specific data, are configured via an initial set of metadata, and thereafter receive updated metadata upon requesting it from the transmitting device, such as when the receiving device encounters an identifier in the data, which identifier was not defined in the metadata previously received.

Streaming data for analytics in process control systems

Techniques for requesting and providing process plant data using a source-independent standardized query are provided. A requesting device generates a standardized query to obtain data from one or more data sources, such as relational or non-relational databases. The query utilizes a standardized format that does not depend upon the data source, which query may be generated as a JSON file. The standardized query may not be directly usable for any data sources. Instead, a data device generates one or more source-specific queries upon receipt of the standardized query. The source-specific queries utilize syntax native to each data source to obtain data. In some instances, the received data must be further processed to adjust for different sample times or sampling rates, such as by interpolation. The resulting data from all data sources may be aggregated into a data frame prior to being returned to the requesting device.

Source-independent queries in distributed industrial system

A data analytics service for performing data analytics functions within a distributed process control environment is provided. The service may provide a user interface for creating a first diagram, representing a data model. The first diagram may be configured, compiled, and evaluated using off-line (i.e., historical) data from a distributed process control system, which may include data stored in distributed data engines (DDEs). Following evaluation, the first diagram may be automatically converted into a second diagram that is bound to on-line (i.e., real-time) data sources within the process control environment, which may then be compiled and executed to generate performance or predictive analytics data for the process. The diagrams may comprise a plurality of configurable function blocks or modules, connected logically via wires conveying outputs or inputs of the blocks or modules.

Data analytic services for distributed industrial performance monitoring

A big data network or system for a process control system or plant includes a data storage device configured to receive process control data from control system devices and store the process control data. The big data network or system identifies various parameters or attributes from the process control data, and creates and uses rowkeys to store the parameters according to various combinations, such as combinations using timestamps. The big data network or system may also store certain aggregate data analyses associated with time periods specified by the timestamps. Accordingly, the big data network or system efficiently stores real-time data having measurements within a database schema, and users or administrators can leverage the aggregate data to analyze certain data associated with certain time periods.

Managing big data in process control systems

A technique is provided for providing early fault detection using process control data generated by control devices in a process plant. The technique determines a leading indicator of a condition within the process plant, such as a fault, abnormality, or decrease in performance. The leading indicator may be determined using principal component analysis. A process signal indicating a process variable corresponding to the leading indicator is then obtained and analyzed. A rolling fast Fourier transform (FFT) may be performed on the process signal to generate time-series data with which to monitor the process plant. When the presence of the leading indicator is detected in the time-series data, an alert or other prediction of the condition may be generated. Thus, process faults may be identified using fluctuations and abnormalities as leading predictors.

Techniques for determining device-specific information such as commissioning data, location information, images, and other data descriptive of a process device installed in a plant include obtaining the device-specific information at a local device during the process device's commissioning. Based on this information, the local device determines the relative order of the process device within a process flow, and may determine a process element alignment map indicating the activation order of a plurality of process elements within the flow. A user may modify the map at the local device. The map is transmitted to a process control big data network for use in discovery and learning analytics. The device-specific information and/or the map may be utilized to generate, at the local device, representations/views of the process flow, which may include real-time operational data. A user may zoom in or out on these views for more or less detail.

Commissioning field devices in a process control system supported by big data

A system for monitoring and analyzing data in a distributed process control system is provided. The system includes a user interface having a set of user controls for selecting and configuring data blocks to create a data diagram representing a data model. The data blocks are associated with data operations, such as data analytics functions, and may be configured by the user for particular instances of general blocks. The data blocks are interconnected by wires conveying outputs or inputs of the blocks, which may also connect data sources to the data blocks. The data sources may include on-line data (i.e., data streams) or off-line data (i.e., stored data) from the process control system. Additional user controls may be used to evaluate the data diagram or convert the data diagram from an off-line to an on-line version.

Distributed industrial performance monitoring and analytics platform

A distributed big data device in a process plant includes an embedded big data appliance configured to locally stream and store, as big data, data that is generated, received, or observed by the device, and to perform one or more learning analyzes on at least a portion of the stored data. The embedded big data appliance generates or creates learned knowledge based on a result of the learning analysis, which the device may use to modify its operation to control a process in real-time in the process plant, and/or which the device may transmit to other devices in the process plant. The distributed big data device may be a field device, a controller, an input/output device, or other process plant device, and may utilize learned knowledge created by other devices when performing its learning analysis.

Distributed big data in a process control system

A data modeling studio provides a structured environment for graphically creating and executing models which may be configured for diagnosis, prognosis, analysis, identifying relationships, etc., within a process plant. The data modeling studio includes a configuration engine for generating user interface elements to facilitate graphical construction of a model and a runtime engine for executing data models in, for example, an offline or an on-line environment. The configuration engine includes an interface routine that generates user interface elements, a plurality of templates stored in memory that serve as the building blocks of the model and a model compiler that converts the graphical model into a data format executable by the run-time engine. The run time engine executes the model to produce the desired output and may include a retrieval routine for retrieving data corresponding to the templates from memory and a modeling routine for executing the executable model.

Data modeling studio

Techniques for automatically or autonomously performing signal processing-based learning in a process plant are disclosed. Generally, said techniques automatically or autonomously perform signal processing on a real-time signal that is generated based on the process plant controlling a process. Typically, the signal corresponds to a parameter value that varies over time, and the signal is processed as it is generated in real-time during on-line plant operations. Results of the signal processing may indicate characteristics of the signal, and one or more analytics functions may determine the sources of the characteristics, which may include a process element or device, a piece of equipment, and/or an asset of the process plant that is upstream, within the process, of the source of the signal. An autonomous signal processor may be integrated with or included in a process control device and/or a big data node of the process plant.

Automatic signal processing-based learning in a process plant

A device supporting big data in a process plant includes an interface to a communications network, a cache configured to store data observed by the device, and a multi-processing element processor to cause the data to be cached and transmitted (e.g., streamed) for historization at a unitary, logical centralized data storage area. The data storage area stores multiple types of process control or plant data using a common format. The device time-stamps the cached data, and, in some cases, all data that is generated or created by or received at the device may be cached and/or streamed. The device may be a field device, a controller, an input/output device, a network management device, a user interface device, or a historian device, and the device may be a node of a network supporting big data in the process plant. Multiple devices in the network may support layered or leveled caching of data.

Collecting and delivering data to a big data machine in a process control system

A data pipeline is used as a fundamental processing element for implementing techniques that automatically or autonomously perform signal processing-based learning in a process plant or monitoring system. Each data pipeline includes a set of communicatively interconnected data processing blocks that perform processing on one or more sources of data in a predetermined order to, for example, clean the data, filter the data, select data for further processing, perform supervised or unsupervised learning on the data, etc. The individual processing blocks or modules within a data pipeline may be stored and executed at different devices in a plant network to perform distributed data processing. Moreover, each data pipeline can be integrated into one or more higher level analytic modules that perform higher level analytics, such as quality prediction, fault detection, etc. on the processed data. The use of data pipelines within a plant network enables data collected within a plant control or monitoring system to be processed automatically and used in various higher level analytic modules within the plant during ongoing operation of the plant.

Growing community of inventors

Narborough, United Kingdom

Paul Richard Muston