It is becoming a reality that artificial intelligence (AI) are starting to change the traditional role of the control engineer. There are some benefits, but there also potential barriers to its adoption in the industrial environment.

Jos Martin, senior engineering manager at MathWorks, said the biggest impact of artificial intelligence (AI) on control engineering in the coming years will be on the workers themselves. He said: “As demand for data science skills grows and the tech skills gap widens, everyday engineers and scientists, as well as data scientists, will be expected to fill the gap, undergoing training on how to design and deploy machine learning systems to become ‘citizen data scientists.’ To be able to make the most of AI in their work, engineering professionals will need to possess skills such as the ability to deal with large datasets, build and train AI models and understand how to use new development tools and software. Companies need to support their workers to upskill and be willing to invest in adequate training to make this a reality.”
Hartmut Pütz, president factory automation EMEA at Mitsubishi Electric Europe, agrees AI will affect the control engineering role. “Control engineers will need to change their daily task list,” he said. “Their role will start to include much more data analysis activities. When users start to implement more self-learning and self-optimizing technology in processes a big part of the control engineering objectives will change and this will mean that engineering skillsets will also need to change. I believe that the job profile will become more aligned with that software engineering and data engineering.”
He added, “In around 10-15 years it is very likely that process optimization will be handled entirely by AI technologies and the ability to program PLCs will become much less important. Even today we are seeing PLC programs being generated automatically by higher level systems in the simulation space and then downloaded into the PLC.”
Improving efficiencies
AI algorithms are starting to improve the efficiency of the entire factory production line, reducing energy consumption and waste, enabling organizations to meet important corporate social responsibility targets as well as deliver cost-savings. Traditionally, to achieve good AI accuracy levels and easy training of models, use of high-performance computing systems such as GPUs, clusters and data centers that use 32-bit floating-point math have been vital. However, developments in software tools now mean AI inference models, which use a range of fixed-point math, can enable engineers to capitalize on devices such as electronic control units and other embedded industrial applications that run on lower power.
AI is helping to improve the accuracy of predictive maintenance applications – such as those for predicting the remaining useful life for an industrial site pump. However, one of the biggest barriers to its adoption in the industrial space is having enough high-quality data to properly train AI models.
“Lots of failure data is needed to ensure the AI model is accurate, but it is expensive and inefficient to create data from real, physical equipment,” Martin said. “Fortunately, improvements in software now make it easier to recreate data from critical failure conditions and anomalies by generating simulations representing failure behavior and synthesizing it to train a model. We are seeing AI being used to transform design in everything from industrial plants to wind turbines to autonomous vehicles to aircraft. However, another barrier to adoption of AI for smart design is the complexity of multi-domain, AI-driven systems. To get around this, engineers are turning to model-based design tools that provide an end-to-end workflow to reduce complexity. These tools can simulate, integrate and continuously test systems, allowing designers to trial ideas in complete context, identify weaknesses in the data and spot flaws in component design before they become a problem.”
Reinforcement learning (RL) – a form of AI famous for beating human players in chess and Go – is being employed to improve engineering design. It works by learning to perform a task through repeated trial-and-error interactions within a dynamic environment. Martin predicts engineers will deploy RL agents into AI models to optimize performance very soon.
Where and how?
An important question facing industry today is where and how to leverage AI and the data that drives it, to capture as much value as possible. Andrew McCloskey, chief technology officer, EVP of R&D at AVEVA, believes this offers a huge opportunity for modern control engineers as when properly implemented AI will make them more effective than ever before, enabling them to implement huge savings for their companies. “AI-enhanced predictive maintenance of industrial equipment can generate a 10% reduction in annual maintenance costs, up to 20% reduction in downtime and a 25% reduction in inspection costs,” said McCloskey.
Predictive maintenance will leverage both supervised and unsupervised learning – the two primary methods of machine learning that essentially describe the ‘training’ required for artificial intelligence algorithms to ‘get smart’ and provide these savings. Supervised learning enables knowledge transfer from the control engineer in a very short time while unsupervised learning is able to automatically recognize disparities in data that may have significant consequences if left unchecked. Together, these algorithms develop high probability predictions that are often not intuitive or otherwise easily identified.
“This frees up more time for the control engineer to take on even bigger challenges and drive a flow of continuous improvement, not just a singular event of improvement,” McCloskey said. “For example, equipped with predictions of impending failures, it is no longer necessary to perform inspections and maintenance based on a pre-determined time schedule. Instead, we maximize the lifespan of equipment parts and replace them as and when necessary – in this case, just before the impending problem occurs. With tight capital and operating budgets, manufacturers are looking to ‘sweat’ existing assets, and this predictive maintenance approach translates into significant savings in inspection and maintenance costs while keeping unplanned downtime to minimum.”
There is no denying AI is making waves in the control engineering sector, but it’s not a magic bullet. While there are still barriers to its adoption of the technology, it is vital manufacturers start engaging with the technology because the benefits are too great to ignore.
Suzanne Gill is editor, Control Engineering Europe. This article originally appeared on the Control Engineering Europe website. Edited by Chris Vavra, production editor, Control Engineering, CFE Media, [email protected]