Intelligent Equipment Accelerator

This accelerator connects any time-series data feed to your analytics platform so you can screen sensor data, alert to potential problems, improve efficiencies, and prevent down time.  Net result is your company can save millions by monitoring and acting in real-time.  Jump start that savings with this accelerator!

Compatible Products

TIBCO Spotfire® TIBCO® Live Datamart TIBCO StreamBase®

Provider

TIBCO Software

Supported Versions

Software Version
   
TIBCO Spotfire 7.5.0
TIBCO Spotfire Statistics Services 7.5.0
TIBCO StreamBase 7.6.3
TIBCO Live Datamart 2.1.3
TIBCO LiveView Desktop 2.1.3
TIBCO LiveView Web 1.0.3

License

TIBCO Component Exchange License

Overview

The Intelligent Equipment Accelerator's focus is on how to take real-time data and move it into the analytic platform in a consistent manner.  Then the focus shifts to taking the data into bigger blocks where they have semantic meaning.  Given the failure patterns discovered in the analytic phase, turn that knowledge into detection logic to be applied to streaming data.  Given the detection of a potential failure (based on the historical model and applied to the current live stream of data), alert via any number of means to derive operational value.  Alerts can be as simple as an email, or tied into case management, asset management, BPM etc.  Finally, the continuous monitoring of the current stream of data can be fed back into the sytem to refine the predictive model.  Net result: Predict Equipment Failure based on historical analysis in the here and now.  Avoid downtime and loss of production.

Introductory Material

Support Details

The DevZone Forums are a traditional threaded discussion service subscribed to by Accelerator Developers, Practitioners, and Customers with a shared interest in the TIBCO Event Processing and Streaming Analytics platforms.  Accelerators are provided as fast start templates and design pattern examples and are supported as delivered.  For all questions concerning Accelerator use and implementation, please open a new discussion in the DevZone forum here: http://devzone.tibco.com/forums/forums/list.page

License Details

Release(s)

Release v1.1.1

Published: August 2016

Initial Release May 16, 2016

There are currently no reviews for this content.

Why not be the first to review it - click here to login

Intelligent Equipment Accelerator

Changes

2016-08-16 Updated the Quick Start Guide and the IEA Presentation.

The TIBCO NOW presentation for IEA is also available https://d2wh20haedxe3f.cloudfront.net/sites/default/files/wiki_files/508...

To download the Accelerator click on the "Try Now" button on the https://community.tibco.com/modules/intelligent-equipment-accelerator page.

Overview

The Intelligent Equipment Accelerator's focus is on how to take real-time data and move it into the analytic platform in a consistent manner.  Then the focus shifts to taking the data into bigger blocks where they have semantic meaning.  Given the failure patterns discovered in the analytic phase, turn that knowledge into detection logic to be applied to streaming data.  Given the detection of a potential failure (based on the historical model and applied to the current live stream of data), alert via any number of means to derive operational value.  Alerts can be as simple as an email, or tied into case management, asset management, BPM etc.  Finally, the continuous monitoring of the current stream of data can be fed back into the sytem to refine the predictive model.  Net result: predict equipment failure based on historical analysis in the here and now; avoid downtime and loss of production.

Note, For a high-level overview of TIBCO Accelerators in general, see the overarching Accelerator wiki page.

 

Business Scenario

High value capital equipment in industries such as utilities, oil & gas, manufacturing and mining are in general highly instrumented with sensors which measure at frequencies up to and beyond 1 Hz. This equipment is generally not deployed in isolation but is instead part of a network which works together to deliver a business outcome (generation and delivery of electricity, manufacture of X items per day etc). A defining characteristic of such networks is that non-optimal performance or even total failure of a single piece of equipment has a negative effect on the overall performance of the whole network. Examples of such networks are the electrical grid (generating equipment, substations, transformers, lines all connected together in a redundant mesh), an oil field (down-hole pumps, surface pumps, wells, gas-oil separation plant, injectors, valves and storage tanks which all work together to deliver oil production), a rail or road network etc.

For example a wind turbine nacelle has approximately 2000 different sensors reading macro parameters (power output, rotor speed etc.), internal parameters (temperature of cooling fluids, speed of individual gears in the power train etc.) and environmental parameters (wind speed & direction, air pressure, temperature etc).

The data captured by these sensor networks provide insight into the historical and current performance of the equipment. As a result a specialised class of time-series databases have been developed to efficiently store and make query-able this sort of sensor data. These are generally referred to as historians (eg OSISoft’s PI Data Historian, Aspentech IP.21, GE Proficy and others) as they are mainly focused on dealing with long-term storage and analysis of sensor data and are usually used by domain specialists who are motivated to learn these specialised tools. 

Business Analytics tools such as TIBCO Spotfire focus on the democratisation of data analytics making it easy for the more business-focused user to analyse data, finding trends and generating statistical models. They may also provide stronger data governance capabilities which is important in the enterprise.

Streaming Analytics tools such as TIBCO Streambase can be used to apply the heuristics discovered by the citizen data scientist using the business analytics tools to the data being collected in real-time by the sensor network and thus identify optimisation opportunities or incipient failure scenarios which can be remediated immediately. This can increase the overall utilisation or performance over time of the network of equipment being monitored and thus improve business outcomes (more stuff produced for less cost).

Concepts

Benefits and Business Value

The TIBCO Industrial Equipment Accelerator provides a standardised, reusable, configuration-driven framework for integrating sensor data sources with business analytics tools. It consumes time-series data which consists of high volumes of simple context-less data (id, value, timestamp) and populates a LiveDataMart with contextual data which is suitable for analytics tools to consume (wide tables with a column per statistic of interest).

The accelerator provides the following capabilities:

  • Scoring of data coming from a single sensor and assemble all readings from related sensors together in to an array of scored values
  • Aggregation of scored data over one or more time windows
  • Apply statistics to the aggregated data
  • Forward the assembled data to a LiveData Mart using an automatically generated schema

Scoring, aggregation and statistics are implemented via the StreamBase mechanism of extension points which makes it possible for a developer to add new implementations or replace the OOTB ones.

The accelerator provides a simple interface and core functionality for dealing with sensor data analytics so that the developer only needs to

  • Integrate their source of sensor data with the accelerator
  • Define specific condition logic to identify what scores indicate situations of interest
  • Customise the LDM visualisation and alerts in a way that reflects business needs

Technical Scenario

The accelerator is built using the TIBCO StreamBase, TIBCO Live Datamart and a sample JavaScript UI. The sensor data is provided by means of an in built simulator that reads canned data from a CSV file.

Live Datamart is used to capture the current state of each well and display information on an interactive, custom developed HTML5 application. This is all built on top of the Live Datamart JavaScript API, which is fully supported.

Components

Functional Components of the Intelligent Equipment Accelerator include

StreamBase: Streaming Analytics, IoT

StreamBase models for IoT data captured from sensors, filtering and cleaning of data, and communciation with time-series databases and sensor networks

A set of three modular StreamBase projects accomplish these tasks:

  • IntelligentEquipmentAccelerator_Main project:  This project is the core of the accelerator. It defines the accelerator data model and provides modules to implement the handling of sensor data.
  • IntelligentEquipmentAccelerator_DataDistribution project: This project contains the generic Live Data Mart tables used by the accelerator plus the specific LDM tables for the ESP demo UI.  It also hosts all the files that form the HTML5/JS GUI.
  • IntelligentEquipmentAccelerator_ESP project: Integrates the IEA_Main modules with a canned data from Electric Submersible Pump sensors and with the LDM tables used to support the custom GUI.

Live Datamart: Operational Analytics, UI, Alerts

Configure mapping of individual sensors to the model of the world, visualize analytics and rules, control to act on critical business moments.  Provided as open source HTML5 and JavaScript code

Live Datamart/StreamBase: Metadata driven data discovery

Add new sensors to the analytics flow via Web UI.  Assemeble groups of sensors into snapshots for analysis by configuration

Spotfire: Sensor Data Analytics

Identify thresholds and feed back to streaming analytics

 

Documentation

Both a README and a QuickStart guide are available within the package, or you can click on the attachments below.

The slide deck from the Breakout session during TIBCO NOW 2016 is also attached below.

Back to the Accelerators page

View the Wiki Page