Skill Level: Intermediate

High-value asset-based industries need to be aware of the performance of their components in a real-time mode. Learn to integrate IBM® Predictive Maintenance and Quality with Telit deviceWISE to receive data from remote sources.


See this DeveloperWorks

 Key Products:

  • IBM Predictive Maintenance and Quality(PMQ)
  • Telit deviceWISE IoT Platform
  • Matrikon OPC

Asset-intensive industries, such as oil and gas, mining, and energy and utilities, use complexequipment, such as compressors, haul trucks, and turbines, in their day-to-day operation. Anyunplanned downtime or major unforeseen failure of this equipment has a direct impact onproduction downtime, which affects the financial performance of the organization.

Potential component and equipment failure, plus machine health of in-service equipment needs tobe monitored by identifying early signs of possible downtime. The goal is to maximize the uptimeof the component/equipment.

The IBM Predictive Maintenance and Quality (PMQ) solution helps you monitor, analyze, andreport on information that is gathered from high-value assets and recommend maintenanceactivities for them. With this integrated solution, you can:
• Predict the failure of a monitored asset in order to fix it and avoid costly downtime.
• Search stored maintenance logs to determine the best repair procedures and cycles.
• Identify the root causes of asset failure to take corrective actions.

The integration bus layer within PMQ helps to transform external events (received from monitoredhigh-value assets) into the format that is required by the PMQ analytics solution's data model.One way to receive external low-level events, such as the discharge pressure of a compressoror the inlet temperature of compressor, is to use the ILS deviceWISE Machine to Machine (M2M)Application Platform. (For more information about Telit deviceWISE, see Resources.) This platform helps:
• Connect assets to applications.
• Collect and process data from a variant of assets, in various locations.
• Integrate that data into existing enterprise IT systems or to a custom dashboard to drive betterbusiness decisions.
• Remotely access and manage assets.

This recipe explains how to onboard data from an OLE for Process Control (OPC) source, whichstands for Object Linking and Embedding (OLE) for Process Control, and the step-by-stepconfiguration to onboard data into PMQ to perform analytics on the asset data.

Use case
A typical oil and gas industry involves various rotating equipment, such as turbines, pumps,compressors, generators, and motors. Each gas turbine has an upstream rotating compressor,which generates pipeline data, such as compressor unit suction and discharge pressures, gastemperatures, unit flow, ambient temperature, and more. The data that is received from low-levelsource systems acts as a data store to perform analytics, like the health monitoring of turbines.The data is captured in the form of events from field-level systems in a real-time mode thatuses a protocol and format that is called OLE for Process Control (OPC). OPC event sourcesare integrated by using an external adapter, ILS deviceWISE, which pushes the data into theIntegration Bus layer within PMQ by using the WebSphere® MQ (IBM MQ) transport. After deviceevents are received in a queue, the event-processing component transforms them into the PMQevent format that is required by the solution.

Tags are often used in the process industry and are normally assigned to a piece of information. Atag consists of a name by describing a single point of information, so a process system can consistof hundreds and even thousands of tags.

For demonstration of integration capabilities, this article uses MatrikonOPC Simulator, whichprovides equipment data connectivity by using these tags, which are an item database for adevice. Simulated tags are OPC-timestamped with range and OPC quality. Based on the qualityset, a tag can either be "good" or "bad."


Solution architecture
Figure 1 shows the integration of Telit deviceWISE with IBM Predictive Maintenance and Quality solution, a packaged, preconfigured cross-industry business analytics solution.

Figure 1. Architecture of the solution when you integrate Telit deviceWISE with PMQ



Technical summary of the solution workflow

  1. Integration with historians: Equipment tags and online analyzers are configured in DCS,SCADA, and historian systems. Telit deviceWISE is configured to read the values of all theonline and offline tags in a real-time mode. Thus, Telit deviceWISE integrates with level 2systems and historians to fetch sensor, alarm, monitoring, and diagnostic data that is injectedfrom equipments. This integration results in continuous raw event data capture and a nearreal-time analysis of the captured data.
  2. Real-time data integration: Triggers are created in Telit deviceWISE workbench to put the tagdata in the integration bus layer within PMQ by using a message queue. This data is receivedon the queue in the form of XML.
  3. Onboard operational data store: Event data that is received from historian systems isconverted to the format expected by PMQ, which is eventually populated in the analytical datastore. This onboarded data is aggregated data and includes key performance indicator (KPI)and profile information.
  4. Predictive model: IBM SPSS® executes pre-built analytical models, resulting in scores. KPI's are analyzed by the system on a continuous basis. In response to the scores and the currentKPI values, SPSS generates recommendations by using the pre-configured business rules.
  5. Enterprise Asset Management (EAM) systems: The received recommendation can beused to initiate or modify a work order in EAM (Maximo) systems for maintenance of thecompressor. This event also provides an automatic email alert in all such instances


  1. Configure MatrikonOPC to simulate tag values for a compressor

    Create an alias group in the MatrikonOPC Simulation Server, with the required alias for each
    parameter, as shown in Figure 2. (For more information about MatrikonOPC, see Resources.)

    1. Open the Matrikon OPC Server for Simulation.
    2. Right-click on Alias Configuration and select Insert Alias Group from the pop-up menu.
    3. Provide a suitable name for the alias group.
    4. In the Contents of alias group frame for the newly created group, right-click and select Insert New Alias from the pop-up menu.
    5. Provide a suitable name for the alias/parameter.

    Figure 2. Alias group and its contents in Matrikon OPC


  2. Configure Telit deviceWISE

    1. Create a device of type DA CLIENT in Telit deviceWISE and specify the required OPC serverURL. (The OPC server URL field differs per your setup. It is not a generic URL to be used byall.)

    Figure 3. Device of type DA Client, pointing to the correct OPC server



    After the device is connected, it displays the items n the Variable tab as in Figure 4.

    Figure 4. DA Client with a list of available alias groups and their aliasesthat are configured in Matrikon OPC



    2. Create a WebSphere MQ transport and provide the required queue manager, queue, channel,and host name.

    Figure 5. WebSphere MQ transport that is created in deviceWISE



    3. Create a transport map for each tag by selecting the previously created IBM MQ transport.Repeat this step for each tag.

    Figure 6. Transport map



    Figure 7 provides a screen capture of the XML message that is generated.

    Figure 7. XML message that is generated after the map is successfullycreated



    4. Create a project within the node, as shown in Figure 8.
    a. In the NEW NODE tree in deviceWISE, expand NEW NODE.
    b. Right-click on the projects item, and select New from the menu.

    c.Provide a new project name in the wizard. A new project then appears in the Projects tab, as shown in Figure 8.

    Figure 8. A new project that is created under Node section in deviceWISE


    5. Create a trigger for each tag within the project by using the Canvas editor.
    Figure 9. Canvas editor, depicting a new trigger for a tag


    After the trigger definition is validated and saved, it appears within the project, along with allthe other triggers, as shown in Figure 10.

    Figure 10. Project with a list of all available triggers in deviceWISEworkbench



  3. Configure IBM PMQ

    Master data is the type of resource that you want to manage, such as people, parts, assets,pieces of equipment, and processes. Master data is normally loaded by using one of the suppliedconnectors or the Flat File API. The connectors and the Flat File API use IBM Integration Busflows to transform the data into the required form and to update the data in the IBM PredictiveMaintenance and Quality database.

    Explore master data and other concepts in the PMQ solution guide.

    The following master data files must be loaded in PMQ data store to populate the master tables:

    • location_upsert.csv
    • measurement_type_upsert.csv
    • profile_variable_upsert.csv
    • resource_upsert.csv
    • source_system_upsert.csv

    The resource master data sheet contains a list of all compressors and their attributes, as shown inFigure 11.
    Figure 11. Sample master data sheet for a resource in IBM PMQ


    Test the solution
    Start the trigger that is created in ILS deviceWISE.

    1. Right-click on the trigger present in a project under “Node” in deviceWISE.
    2. Select Start to start the trigger.

    Figure 12. Starting trigger in ILS deviceWISE workbench


    Starting the trigger sends a message into the queue that was defined in the transport section. The message is of the format defined in the transport map definition. Data that is pushed from ILS isreceived in XML in a WebSphere message queue.
    You can browse for the XML message received from ILS.

    Figure 13. List of messages that are received in WebSphere MQ


    You can double-click any one of the XML messages to see a detailed view of the data present inthe XML, as shown in Figure 14.

    Figure 14. Detailed view of XML message


    The event data that is received from historian systems is converted to the format expectedby PMQ, which is eventually populated in the analytical data store. This onboarded data isaggregated data and includes KPI and profile information.

    You can see a screen capture of the event observation table in PMQ data store, as shown inFigure 15.

    Figure 15. Data onboarded in the PMQ data store


  4. Conclusion

    The IBM Predictive Maintenance and Quality solution helps you monitor, analyze, and report oninformation that is gathered from devices and other assets and recommend maintenance activities. PMQ uses Telit deviceWISE to integrate seamlessly with level 2 systems and historians to performpredictive and business analytics on the operational data. This analysis provides the hot spotidentification of a problem and the corresponding resolution to avoid a forced outage.

  5. Resources

    • “Real-time data analytics using IBM Predictive Maintenance and Quality” (developerWorks,May 2014): Understand how to use IBM PMQ to onboard production data in real time andperform analytics on the data to predict production in near future.
    • IBM Predictive Maintenance and Quality Information Center: Learn more about the solution inthe IBM Predictive Maintenance and Quality Information Center.
    • “Predictive Maintenance and Quality 1.0 Solution Guide” (IBM, 2013): Gain an understandingof how the IBM Predictive Maintenance and Quality solution works. Know what tasks areinvolved when you plan to implement IBM Predictive Maintenance and Quality. (The solutionasset that is used in this article is based on PMQ 1.0.)
    • “IBM Predictive Maintenance and Quality 2.0 Solution Guide” (IBM Redbooks, May 2014):Learn how Predictive Maintenance and Quality enables companies to identify whenmanufacturing assets need maintenance, not just according to the manufacturer”s scheduledrepair guide but also based on how the asset is used every day. This information helps tokeep critical production lines running while also saving money because repairs are always,and only, performed when truly necessary.
    • “Predict the future to keep your production line running” (IBM): View a demo on how IBM Predictive Maintenance and Quality helps spot problems before they happen so you can planfor, rather than react to asset failure.
    • ILS deviceWISE: Learn more about ILS deviceWISE and how to seamlessly connect yourassets with your enterprise systems and databases.
    • MatrikonOPC: Learn more about MatrikonOPC and MatrikonOPC Simulation Server.

    Get products and technologies
    • IBM Predictive Maintenance and Quality solution: Explore the IBM Predictive Maintenance and Quality solution, which helps you maximize asset productivity and operationalperformance.
    • Evaluate IBM products in the way that suits you best: Download a product trial, try a productonline, use a product in a cloud environment.

    • PMQ Practitioners Community: Get involved in the PMQ Practitioners Community to shareknowledge, ideas, solutions, and experiences around IBM Predictive Maintenance andQuality.
    • Get involved in the developerWorks community. Connect with other developerWorks userswhile you explore the developer-driven blogs, forums, groups, and wikis.

Join The Discussion