A framework for industrial artificial intelligence

Modern technologies enable the application of artificial intelligence (AI) to machine and operational process data to gain better insights.

By Wael William Diab June 29, 2022
Courtesy: Industry IoT Consortium

The Industrial Internet of Things (IIoT) integrates the industrial assets and machines—the things—with enterprise information systems, business processes and people who operate or use them.

With these connections to the industrial assets and machines, modern technologies enable the application of artificial intelligence (AI) to machine and operational process data to gain insights into the operations, optimize them intelligently to boost productivity, increase quality, reduce energy and material consumption, increase flexibility and ultimately create new business value.

All this must be done while maintaining commitments to safety, reliability, resilience, security and data privacy as the trustworthiness of the systems and addressing ethical considerations and societal concerns.

AI-enabled IoT applications

Artificial intelligence is enabling the next generation of IoT applications and services within industry, in areas like smart manufacturing, robotics, predictive maintenance, diagnosis of infectious disease with machine learning and autonomous vehicles.

The use of AI is pervasive in the enterprise, helping organizations achieve significant benefits in terms of better insight, faster decisions and more effective operations. Industrial AI is major enabler of digital transformation and is making next-generation Industrial IoT systems a reality.

In a new publication entitled “Industrial IoT Artificial Intelligence Framework (IIAIF),” the IIC has developed a first of its kind framework intended to be a blueprint for how technology and business decision-makers can deploy AI-enabled IIoT systems. The publication looks at the considerations that must be addressed during an AI implementation’s full lifecycle within an IIoT system, from business value creation to architecture to design to implementation and operation.

Architecture viewpoints

IIoT systems are complex system-of-systems. To better understand and provide guidance, a variety of perspectives are used. For each, a set of stakeholders is identified along with their concerns and from which, issues are highlighted along with proposed guidance. The IIAIF uses the same viewpoints as the IIC Industrial Internet Reference Architecture (IIRA) and also used by the Industrial IoT Analytics Framework (IIAF):

  1. Business,
  2. Usage,
  3. Functional, and
  4. Implementation
To better understand and provide guidance, a variety of perspectives are used. Courtesy: Industry IoT Consortium

To better understand and provide guidance, a variety of perspectives are used. Courtesy: Industry IoT Consortium

A sample of what is discussed under each of the perspectives in the framework is summarized below:

  • Business Perspective: This perspective maximizes value through:
    • Direct ROI improvement, such as improved insights, faster decision-making and improved efficiencies.
    • Indirectly by improving societal aspects, which in turn lead to a better utilization of labor and capital. Examples include disease diagnosis and cure formulation, disaster prediction, education, and career guidance.
    • Value is generated from data-intensive environments by transforming problematic data environments into valuable insights.
  • Usage Perspective: Ensuring confidence in the AI system is paramount to successful usage and adoption. For instance, a discussion is provided on addressing trustworthiness, ethical considerations, and societal concerns. In addition, a discussion about using AI as a force for good is presented.
  • The Functional and Implementation Perspectives are focused on architecting, integrating, and deploying the technology. Examples discussed include:
    • Architecting the system to ensure oversight to achieve intended organizational goals and KPIs, monitor effectiveness, identify operational issues, and apply risk mitigation techniques.
    • AI-specific considerations and tradeoffs such as mapping the AI subsystem inputs and outputs to IIoT system, addressing the AI data ecosystem over all phases such as quality, lifecycle, governance, and balancing architecture, implementation, and resource tradeoffs.

The framework also provides treatment on where industrial IoT systems enabled by AI are headed and the emerging industry ecosystem is evolving. For instance, a number of emerging technologies are discussed, regarding how they could amplify the benefits of AI.

– This originally appeared on the Industry IoT Consortium’s (IIC) website. The IIC is a CFE Media and Technology content partner.

Original content can be found at Industry IoT Consortium (IIC).


Wael William Diab
Author Bio: Wael William Diab (on behalf of the IIC Industrial AI Task Group) Chair, IIC Industrial AI Task Group