AI insights

• Artificial intelligence (AI)-driven tools like predictive maintenance and advanced process control are transforming operational efficiency in industrial manufacturing.
• Integration of AI with automation systems addresses challenges, enhances flexibility and drives innovation across the industry.

There can be little doubt that the world — and industrial manufacturing in particular — is in a state of rapid transformation and artificial intelligence (AI) is at the center of that change. AI has been embedded in select industrial manufacturing technology for years, helping power early automation and emerging data analytics solutions. However, technology has finally reached an inflection point.

Improvements in machine learning and cloud computing have been combined with technological advances in natural language processing, data analytics and generative AI. These advances have dramatically increased the scope and scale of AI solutions, delivering technologies that are more powerful, personalized and efficient.

The possibilities are both broad and complex. AI-driven automation and predictive maintenance solutions are forming an increasingly powerful foundation upon which organizations can improve their processes and workflows to promote operational excellence. Simultaneously, AI is the driving force behind robust analytics tools that compare, combine and even coordinate production and market data to drive better financial choices and mitigate risk across an organization’s entire enterprise. Such capabilities are only a small sampling of the existing and emerging benefits of modern AI solutions (see Figure 1).

Figure 1: Cloud-powered artificial intelligence will unleash augmented tools and workflows. Courtesy: Emerson and AspenTech

Ultimately, businesses will increasingly adopt new AI solutions to improve how they operate, whether those solutions are fit-for-purpose and standalone or embedded elements of existing automation solutions.

However, in both cases, doing so effectively will mean finding ways to navigate an increasingly broad and complex landscape of solutions, each with its own capabilities and requirements. Therefore, it is worthwhile to consider how AI technologies can be implemented as part of a seamlessly integrated holistic solution across operations and the enterprise.

AI creates challenges for a changing environment

The world has seen dramatic change in just the past two decades and the manufacturing industry has changed along with it. Technology advances, increasing mobility and globalization, geopolitical shifts and more have created a volatile, uncertain, complex and ambiguous environment that has increased competitive pressures. As demand, supply chains, workforces and other key enablers of efficient operations continue to evolve, manufacturing organizations are shifting their strategies to an approach focused on flexibility, monitoring demand and changing production as necessary to meet changing marketplace needs (see Figure 2).

Figure 2: Industry challenges have not changed; they have become more complex and connected. Courtesy: Emerson and AspenTech

Demographic change is creating significant challenges for the manufacturing industry. As an entire generation of expert personnel leaves the workforce, decades of institutional knowledge depart with them. Gone are the days of operators and technicians with decades of experience walking through the plant and identifying a worn bearing from an unusual sound or flagging a lubrication issue due to a strange smell.

AI and automation meet new challenges

As manufacturing organizations rise to meet the new challenges of a changing world and shifting demographics, they will increasingly rely on automation to develop pathways for increased performance and profitability. AI tools at the heart of these automation solutions will help companies unlock new production efficiencies to drive continual optimization — both of personnel and processes — helping them capture operational excellence and competitive advantage.

Increasing agility: As organizations cope with an increasing need to adapt to shifting business conditions and opportunities, they will leverage AI tools to increase their agility, both at the individual plant level and across the enterprise. Many plants will move away from the traditional model of producing one blockbuster product 24/7, opting instead for a more flexible approach focused on monitoring demand and changing production lines as necessary to meet those needs. Doing so — particularly with fewer experienced operators in the control room — will drive an increased reliance on automation as teams safely move production from state to state.

Tools like advanced process control, predictive maintenance, dynamic and state-based alarming and more will be essential to guide operators through transitions in their flexible environments. Supported with embedded AI, these tools will help teams lock in best practices and ensure safer and more efficient execution of their complex operations, regardless of who is in the control room. In addition, closed-loop planning and scheduling will tightly integrate with advanced process control and AI-driven forecasting tools to continually optimize operations across both plants and the enterprise.

In-context guidance: It can take years or even decades to bring operators and technicians up to expert levels. But when a plant experiences a complex operational state — such as a startup, shutdown or unexpected process deviation — safety and efficiency needs require workers who can make fast, wise decisions. To close the ever-increasing experience gap and enable personnel to quickly perform at a higher level, many organizations will look to advanced AI tools to provide expert guidance, assisting operators, technicians and engineers through complex decisions to drive the best results.

To meet this need, many automation suppliers are already employing process performance modeling with a network of online models to provide automated, 24×7 insights to propose critical adjustments to human operators for their review and implementation. Moreover, automation solutions providers are increasingly building intelligent virtual advisers into automation systems to help enhance decision making with natural language insights into closed-loop relationships, making it easier to maintain optimum process performance and safety.

Automation-enhanced productivity: The challenges of a shrinking pool of expertise are not limited to the plant floor but also associated with engineering. Those organizations retaining expert personnel are finding them quickly overtaxed, so they are looking for ways to help operators understand what actions are required and what the automation is doing at any given stage of the process. In addition, organizations are looking to help engineers work more efficiently and effectively using expert guided creation of models to quickly optimize plants both offline and online.

AI-enabled adaptive process control can help simplify process transitions in both routine and emergency situations, while helping operators better understand exactly what is happening. In addition, engineering tools with embedded machine learning help engineers develop more accurate and sustainable advanced process control models. Leveraging embedded AI, users can more quickly manage configuration, monitoring and optimization.

Holistic solutions deliver greater success

AI tools are an increasingly critical element of a successful industrial manufacturing business strategy in a changing marketplace. However, as teams start implementing a wide array of disparate AI tools from a variety of suppliers, they often quickly discover challenges to effective deployment. To get the most out of any AI solution, organizations should seek out technological offerings that deliver AI tools as part of a holistic automation package.

The organizations using AI most effectively have discovered that the most valuable tools are those deployed as an integrated part of their end-to-end automation solutions. Such solutions leverage deep industry expertise to help cut through the challenges of deploying and integrating AI into operational technology (OT) environments and to drive increased benefits and faster return on investment. The best AI tools are seamlessly integrated into software operations because operations teams already trust their automation software to help them deliver operational excellence.

That trust, in turn, leads to faster adoption and a seamless user experience — operators and technicians continue using the tools they know and trust, gaining AI enhancement without the need for additional knowledge or training. At the heart of this powerful, embedded-AI automation is an enterprise operations platform built on a boundless automation vision providing seamless data mobility from the intelligent field through the edge and into the cloud.

The importance of an enterprise operations platform for AI tools

AI-ready automation will require a rich OT data ecosystem that not only drives copious amounts of data to and from any automation technology across the enterprise, but does so while preserving rich context, broad and secure connectivity and layered analytics.

If data is trapped in various silos across the enterprise or is delivered without the rich context necessary to turn large data into smart data, AI tools will struggle to generate trustworthy, actionable insights. An enterprise operations platform designed as part of a boundless automation vision delivers the data mobility — with rich context — necessary to power embedded AI tools. Built on an OT data ecosystem, seamlessly integrated enterprise operations platforms help overcome data silos by allowing contextualized data to move freely without the need for complex, custom engineering between solutions.

Yet, even among embedded AI solutions, not just any software will provide the game-changing results industrial manufacturers require to compete in a more complex marketplace. Purpose-built industrial AI solutions leverage engineering fundamentals, deep asset knowledge and industry experience to drive better experiences and results. The most powerful tools combine the speed and flexibility of a data-driven approach with first principles models to provide guardrails, robustness and trusted results.

Under such practical constraints, options that are not practically possible in the plant are prevented. Hybrid models can run simulations thousands of times, but still ensure key constraints are obeyed. Such a solution helps reduce the time users spend validating because models are constrained by reality.

In fact, one of the key differentiators of fit-for-purpose industrial AI is that the tools are already trusted by users to help them work more effectively on their highest-value tasks. The most advanced industrial AI tools offer a robustness that no generic AI solution can match because they have been embedded in key automation tools for years — generating design examples in engineering, enhancing models in digital twin simulation software, tracking equipment performance and predicting breakdowns as part of predictive maintenance solutions and more (see Figure 3).

Figure 3: Industrial artificial intelligence tools drive value by increasing automation, improving agility and providing guidance to support and upskill personnel of all experience levels. Courtesy: Emerson and AspenTech

When combined by design, automation tools and embedded industrial AI naturally deliver a holistic solution by enhancing automation of business processes while providing seamless integration of AI automation infrastructure. Such solutions deliver end-to-end functionality that provides value not just in an individual stage, but across the entire technology life cycle.

For example, in the earliest stages, instead of requiring users to drag and drop control elements or to prepare spreadsheets to be imported to engineering automation systems, AI tools are gradually gaining the capacity to use natural language to present configurations that users can approve or modify. Later, during operations, AI guidance can help users combine real-time data, historical data — and unstructured information like documents, control narratives and more — to help operators understand what is happening in the plant.

AI tools can easily monitor hundreds of displays simultaneously and then use natural language to help operators understand what is going on behind the scenes of the automation — such as when an advanced process control algorithm automatically changes states or setpoints for a reason that is not immediately clear. And even at end of life, embedded AI technologies can help convert legacy code to new control system logic to simplify and streamline modernization (see Figure 4).

Figure 4: Modern artificial intelligence tools can automate configuration, coding and testing to drive faster modernization. Courtesy: Emerson and AspenTech

Building the right foundation for AI and automation

As they increase in power and capability, AI tools will fundamentally redefine the way industrial manufacturers operate. AI will unlock unimagined flexibility, safety, sustainability and performance, helping organizations navigate the market and demographic challenges that are barriers to operational excellence.

The same industrial AI tools that have been embedded in automation solutions for years will be a key part of those solutions, evolving and scaling alongside key automation tools to provide users with an intuitive, trustworthy way to continue leveraging AI for increased efficiency and decision support. It will be tightly integrated technologies, delivered as part of an organization’s seamless and comprehensive enterprise operations platform that will truly unlock a step-change in operation.

The foundation for such a technological leap is already available today and it will continue to improve and scale in the coming years. Now is the time to get on board and capture the innovation capabilities that will drive competitive advantage for years to come.

Do you have experience and expertise with the topics mentioned in this content? You should consider contributing to our WTWH Media editorial team and getting the recognition you and your company deserve. Click here to start this process.