As mentioned, self optimising algorithms based on AI and neural networks are simply not yet suitable for every machine builder. For most machine builders (and customers) the focus is on creating a smooth and fast running machine with a high OEE. In addition, touching the PLC software on optimised equipment and machines is considered a no-go for most, as their motto probably is: 'never touch a running system'. However, a realistic step for every machine builder is to learn from your machines. New machines are like a new car, they have failures in the beginning and need to be optimised.

A digital transformation (DX or less commonly DT) is the application of software, programmable hardware, and operational technologies (OTs) to fundamentally transfigure a company's operations and end products for the better. DX programs can be undertaken by industrial organizations, machine builders, or a vast array of other businesses; the involved OTs typically include machine-monitoring systems, connectivity, and online web and cloud access --especially that via tools with internet of things, IIoT, or Industrie 4.0 functionalities. The most successful digital transformations engage every employee at the organization from management to seasonal plant personnel and continually evolve in response to quantified results and personnel feedback. But whether instituted by a team internal to an organization or hired consultants, digital-transformation initiatives can face pushback at established companies -- especially from naturally skeptical engineers. Exacerbating this issue is the way in which products supporting DXs are inherently reliant on the adoption of complementary elements to work … so a given smart sensor (to give one example) can require adoption and integration of dozens of other disparate components and elements to support a grander initiative.

They often focus almost exclusively on machine learning (ML)--sometimes even using "ML" as a synonym for "AI."

Traditional machine control technologies are based on the work of application-specific engineers. To tackle a certain task a control engineer would need to understand it in terms of physical requirements, work on a traditional physics-based solution for it and transfer the knowledge obtained into source code. In an AI-based approach, the engineer will be more focused on data. The challenge to be solved is first described through data collection and then the engineer works with an abstract data-based representation of the physical problem. Therefore, the data engineer may not need to understand the physical details of a problem to generate a data-based solution for it.

Last year, advisory firm Forrester noted that, "The honeymoon for enterprises naively celebrating the cure-all promises of artificial intelligence (AI) technologies is over… AI and all other new technologies like big data and cloud computing still require hard work." Given that 70 percent of enterprises expect to implement AI this year, including Schneider Electric, I would like to offer three concrete ways companies can seize the business value that I strongly believe AI promises. Integrating an AI strategy can seem like a daunting task as Forrester analysts point out, so we recommend that any company embarking on this journey start with a pragmatic, practical approach to individual AI projects. Ask upfront: "Which problem can I solve with an AI-enabled digital solution?" This question always prompts our R&D process to lead with the customer challenge in mind.

Last year, Forrester noted that, "The honeymoon for enterprises naively celebrating the cure-all promises of artificial intelligence (AI) technologies is over: …AI and all other new technologies like big data and cloud computing still require hard work."[1] Given that 70% of enterprises expect to implement AI this year[2], including Schneider Electric, I would like to offer 3 concrete ways companies can seize the business value that I strongly believe AI promises. Integrating an AI strategy can seem like a daunting task as Forrester analysts point out, so we recommend that any company embarking on this journey start with a pragmatic, practical approach to individual AI projects. Ask upfront: "Which problem can I solve with an AI-enabled digital solution?" This question always prompts our R&D process to lead with the customer challenge in mind.

Powered by smart machines, the new industrial revolution is changing how manufacturers operate today and plan for the future, influencing a significant transformation in manufacturing, engineering and factory-floor industries. Adding to this, manufacturers are under pressure to meet the demand for faster delivery of new products, coupled with shorter production lifecycles. Organizations are adopting agile, flexible production plant systems and processes to adapt and evolve, so as to remain competitive and profitable. Going forward plants and machines will have to be smarter, better connected, more efficient, flexible, and safe. Over the past several years, innovation frameworks have emerged in industry organizations worldwide, such as Industry 4.0 (Europe), the Industrial Internet Consortium (America), and the Made-in-China initiative, to name a few.

Dave Perkon is technical editor for Control Design. He has engineered and managed automation projects for Fortune 500 companies in the medical, automotive, semiconductor, defense and solar industries. Put simply, the IoT provides the connection, the cloud provides online storage and convenient applications, and big data provides analysis, management and maintenance of information, which, when combined, can overwhelm the data users and decision makers. Fortunately computers and specifically machine-learning applications, although in their early stages, can help. From the industry or manufacturing side of business, machine learning can be applied to just about any control system that is smart enough to actually alter how it controls a machine in response to changing conditions, but there is much more to it than that.