Industry challenges are driving manufacturers to focus on improving efficiency, optimizing production and quality, and reducing unplanned downtime. Leveraging data and analytics technologies, such as industrial artificial intelligence (AI) and predictive analytics, can transform a company’s assets and systems by capturing data more accurately from different sources to increase business insights and strengthen predictive capabilities.

It’s tempting to focus on immediate needs – meeting the growing or shrinking demand for products. However, those decisions will have a long-term impact on the brand and ultimately your competitive position, so it’s critical to make those decisions with as much insight as possible.

Industrial AI, predictive analytics, and machine learning (ML) are critical in modeling the actions and consequences in a way that’s always valuable. It’s important to understand an operation and be able to break it down granularly to take productive action that’ll make a difference.

There are many benefits to deploying solutions that help use the power of Industrial AI in your operation. By breaking down information and data silos, aerospace manufacturers can tap into previously unused or under-utilized data, speeding operations and producing finished products and parts faster and with greater precision. Tracking the performance and health of equipment optimizes maintenance and safety on the shop floor, making critical manufacturing assets more reliable and available for use. Production lines are up and running and end production is increased and reliable.

Speeding production also allows improved on-time delivery performance, quicker response to late state changes, clearer views of work-in-progress orders, and shortened production cycles.

With a lack of real-time information from the shop floor to the C-suite, it can be difficult to see critical information in time to accommodate market shifts or customer demands. By implementing effective industrial applications with AI and analytics technologies, shop-floor personnel gain deep visibility into complex work processes enabling more data-driven insights along with tighter control of production quality, staffing, and predictive maintenance scheduling.

Graphics courtesy of GE Digital

Getting started

There are barriers and risks to expanding and using digital touchpoints.

The first hurdle is understanding business processes that could be improved using data. Determine how that data is used in the current process and how that process would be modified to get improved business results. Understanding the process tells you the data you need, where to get it, the AI models used to make the decision of whether to change the process, and justification for that decision.

Another key hurdle is acceptance of AI’s output. Many AI systems are black boxes in which the logic of their output cannot be readily understood by the layperson. It’s important to construct AI models that correspond to physical models.

Keep in mind that scale and implementation may not be easy at first, but as more industrial assets are digitized, the opportunity to use data to improve business processes and business value grows exponentially.

In addition, companies often deal with obsolete systems, multiple systems on the floor, low machine connectivity, and the inability to analyze end-to-end data sets.

With data that’s already available, teams don’t need to be in a constant state of reactivity. Combine data across industrial data sources to rapidly identify problems, discover root causes, predict future performance, and automate actions to continuously improve quality, utilization, productivity, safety, and delivery of operations.

For example, to improve quality, you can automatically import process-relevant data from various sources and apply AI/ML models to predict quality before and during production runs – improving quality while reducing waste and costs.

Graphics courtesy of GE Digital

Drive continuous improvement

Approximately 70% of companies worldwide know they need to implement industrial analytics to remain competitive. With ML and analytics, aerospace manufacturers can capitalize on the Internet of Things (IoT) opportunity, optimize operations, and generate greater profitability.

Additionally, engaging in the latest analytics technologies also helps attract and retain the best talent. Today’s digital plant and its mobile, connected workforce accelerate and sustain continuous improvement to drive greater productivity and efficiency.

The journey to success with ML and analytics doesn’t mean engineers and shop floor workers must become data scientists. Seamless connectivity, rich visualization, and predictive analytics enable engineers to analyze operating scenarios, quantifying the impact operational changes will have on key performance metrics and identifying causes for performance variation.

A comprehensive analytic solution-development environment provides visual analytic building blocks to build and test calculations, predictive analytics, and real-time optimization and control solutions with connectivity to real-time and historical data sources and drag-and-drop access to rich functional libraries.

The solution-development environment can provide visual analytic building blocks, allowing users to build and test calculations, predictive analytics, and real-time optimization and control. Solutions are enhanced with real-time and historical data sources and drag-and drop access to rich functional libraries. Solutions are saved as reusable templates for easy deployment to similar assets or process units and permanently deployed into production.

To support the full IoT value journey, look for capabilities from simple calculations to predictive ML models to real-time optimization and advanced-control algorithms. The best solutions provide rapid wizard-driven data mining for engineers for fast time-to-insight; an easy visual drag-and-drop environment for subject matter experts and engineers; and analytic solution templates without programming for simple calculations, data cleaning, math, statistics, ML models, real-time optimization, and advanced process control. These solutions can go a long way to deploy AI for efficiency improvements.

GE Digital

GE Digital is a partner member of the Control System Integrators Association (CSIA). For more information, visit the company profile on the Industrial Automation Exchange.

About the author: Cobus van Heerden is senior product manager, analytics and machine learning at GE Digital. He can be reached at cobus.vanheerden@ge.com.

Online tools for product evaluation, ordering

Photo credit Portescap

Two new online tools are now available to streamline the process of evaluating and buying miniature motors.

MotionCompass: Users input operating points such as torque, speed, and voltage, along with key application parameters and gearbox and position feedback requirements. MotionCompass then generates a list of motor recommendations that users can prioritize in ascending or descending order according to their speed, efficiency, power, or current needs. It also immediately displays prices and availability so users can proceed to the eStore, confirm the order quantity, and complete their purchase.

eStore: Portescap customers can browse or search for off-the-shelf products to fit desired configuration, environment, or envelope. When a customer selects a motor, they can download its specifications as well as 2D drawings and 3D CAD models, check its availability and, if the product isn’t available for immediate shipment, request a quote. Users can also customize a motor for a hard-to-satisfy application by reviewing options for gearheads and encoders. And checkouts are even faster with an e-store account.

These online tools offer designers a resource to guide motor selection decisions throughout product development, allowing design iterations and implementing any changes based on off-the-shelf motor options. Customers will also be able to test designs in a virtual setting, saving time and helping get end products to market faster.

Portescap