Author Contributor: E Tech Group Director, Manufacturing Intelligence & Advanced Services Pradeep Paul
Overview
Today’s industrial manufacturing data analytics platforms offer powerful ways to analyze and resolve complex engineering and operations challenges. Using critical process parameters, quality attributes, KPIs, and event data, these SaaS-based tools apply artificial intelligence (AI) methodologies to mathematically model a production system. A well-constructed model can reveal how process parameters relate to outcomes including product quality, production efficiency, throughput, and energy use.
In E Tech Group’s experience, these tools offer significant potential, and the numbers speak for themselves. As an example, when E Tech Group selected and implemented a partner’s data analytics platform for a recent client, they saw a plant-wide overall improvement in OEE of 21%, with a 5x ROI within six months.
However, implementing an effective manufacturing intelligence solution requires careful evaluation of the targeted goal or production challenge to pair it with the most technically compatible analytics solution. These analytics platforms use data to complete their system modeling computations in the cloud, and the quality of their insights is directly related to the selection of the most appropriate datasets.
As discussed in my earlier article Don’t Be Data Rich but Information Poor, many facilities collect vast amounts of process data but struggle to convert it into actionable intelligence. Choosing the right datasets is essential for obtaining the full value of a manufacturing intelligence platform. Implementation requires these datasets to be made accessible for secure and reliable streaming to the selected cloud-based platform. This article provides a summary of E Tech Group’s manufacturing intelligence partners and solutions, and then describes E Tech Group’s process for helping clients implement an effective solution.
Selecting the Best-Fit Analytics Platform
As shown in Table 1, E Tech Group partners with several manufacturing analytics providers that have demonstrated success in specific process types and industries. This breadth allows E Tech Group to help manufacturers choose a solution that is both technically compatible and well suited to the intended application, and then handle its integration so the tools quickly deliver insights and value.
| Platform/Solution | Best Suited For | Typical Use Case |
| Oden Technologies | Discrete or mixed-mode manufacturing focused on OEE improvement | Plant-wide performance tracking and process optimization |
| Quartic | Regulated industries and batch processing | Batch quality tracking, compliance reporting, and process analysis |
| Automation Intellect | Plants seeking fast OEE monitoring with minimal infrastructure changes | Tracking machine performance and downtime trends in smaller operations |
| Rockwell Automation Pavilion8 | A point solution for continuous processes that require advanced closed loop control | Model predictive control for chemical, oil and gas, or water treatment facilities |
| Rockwell Automation PlantPAx Analytics (Alarm & Events) | Facilities using PlantPAx 5.0+ with alarm flooding issues | Alarm rationalization and prioritization to improve operator effectiveness |
| Rockwell Automation Energy Manager | Facilities seeking to monitor and reduce energy consumption | Capturing and analyzing energy usage data from across plant systems to identify inefficiencies and track trends |
Note only Pavillion8 supports closed loop control, allowing the tool to make direct changes to the process without operator intervention. All other solutions provide open loop feedback, including insights, alerts, or recommendations, but do not directly adjust process parameters.
Once the best-fit platform has been selected, the facility’s infrastructure must be prepared so the chosen solution can securely and reliably access the right datasets.
Preparing a Facility for Manufacturing Intelligence: E Tech Group’s Process
E Tech Group follows a structured process for implementing a manufacturing intelligence solution that includes reviewing and upgrading a facility’s infrastructure as needed. It is described below.
1. Identification of Necessary Datasets
Using the requirements of the selected analytics platform, identify the most important process parameters, quality attributes, KPIs, and event data that’s relevant to the targeted problem. These datasets are prioritized for their impact on modeling accuracy and must be in a form, at a resolution, and with enough context that the analytics platform can run calculations effectively and present the results in a meaningful way.
2. Evaluation of Data Accessibility
Assess the targeted machines to confirm that their sensors and instrumentation are producing the necessary data and review the control systems (PLCs, DCS, SCADA) to verify that this data is being collected and can be accessed. Evaluate other systems that may already store the relevant datasets including historians, MES, ERP, or quality systems. Identify any protocol limitations, driver gaps, licensing restrictions on tag counts, or network bandwidth / security weaknesses that could affect reliable data transfer to the cloud.
3. Gap Analysis and Remediation
Resolve issues that block the flow of necessary data to the analytics platform. This may include upgrading obsolete PLCs or outfitting them with gateways to extract needed data. Sometimes OT network improvements are required to increase bandwidth or improve security.
4. Establish Secure Network Access
Configure the OT network so that data can flow reliably and securely from the plant systems to an aggregation point or unified namespace (UNS) through an edge device, and ultimately to the cloud-based analytics platform. Ensure the path is protected from unauthorized access while maintaining uninterrupted streaming. For additional best practices on secure IT/OT networking, see the article Core Architecture Strategies for IT/OT Network Integration.
5. Set up Data Aggregation or a Unified Namespace (UNS)
Establish a single point where all required data is collected and made available to the analytics platform. For smaller solutions, this can be accomplished with a data aggregation server using a platform such as Ignition or FactoryTalk Optix.
For larger systems with multiple applications that need to share information, setting up a UNS is often the best way to simplify integration since it allows each application to connect to this central source for all required data. This architecture reduces the total number of system connections since all data-consuming applications connect to the singular UNS. It minimizes the number of open firewall ports, simplifies adding additional data sources or applications, and reduces protocol conversions needed before sending data to the analytics platform. As an aside, a UNS can also support advanced digital twin implementations as described in our article, Unity Gaming Engine Powers Digital Twin Technology.
6. Install and Configure the Edge Device
Deploy the edge device in the demilitarized zone (DMZ) network zone as a secure bridge between the OT network and the cloud-based analytics platform. Connect it to the aggregation point or UNS. Configure it for secure communication and perform any required protocol conversions so the data is in the correct format for the platform. Verify continuous, reliable streaming of all datasets to the platform.
Turning Data into Measurable Improvements
Manufacturing intelligence solutions offer novel approaches to solving complex production problems and improving OEE metrics. To benefit from these solutions, the best-fit platform must be selected based on the targeted challenge and the facility’s operational goals. The state of its infrastructure must be evaluated and upgraded to accommodate secure and reliable data transfer to the selected cloud-based platform. Whether the solution provides open-loop feedback for operators or closed-loop control that adjusts processes automatically, the goal is the same: data-driven process optimization and decision-making, better performance, and a strong return on investment. With the right foundation in place, manufacturers stand poised to move from struggling with isolated data to obtaining remarkable insights and improvements through connected intelligence.
Talk to an Expert
Reach out to us here and someone will respond within 24 hours.
"*" indicates required fields