Artificial intelligence in manufacturing
Ask Control Engineering: What does artificial intelligence have to do with control engineering?
Answer: One way artificial intelligence (AI) relates to control engineering is when embedded software helps with situational awareness. The software algorithm looks at feedback from a situation, then actuates the decision (closed-loop control) without human consultation, or the software recommends a course of action with human consultation (open-loop control).
Suppose a car were left running in a parking garage. (Presumably, within range of the auto-start key fob, something else in the driver’s pocket or purse accidentally started the car.) Embedded AI code might send a text message alert to the driver’s phone 5 minutes after remote startup without driving. If there’s no response, programming might tell the car to shut off after 7 minutes. If the car were in a closed space without ventilation, a CO sensor combined with an area sensor could automatically shut down a running vehicle (remote started or not) within a very short period, potentially saving lives.
In manufacturing, a machine running a web-based process may have similar situational awareness. There may be a perfectly good reason to leave the machine running when the last material runs through the rollers and an operator is standing in a certain location. If the machine is unattended at that particular moment, embedded code may begin an orderly shutdown as the best response.
See related articles linked below on artificial intelligence and situational awareness.
Control Engineering contributor Dennis Brandl talks about the next big thing (TNBT) is the second generation of smarphones, which have the software capacity to provide situational awareness. TNBT devices will be able to recognize what is going on inside your area or site and determine when something is out of normal but not yet in alarm. Information for this awareness may come from traditional fixed sensors or even by listening for sound patterns such as hisses, whistles, clangs, and bangs. TNBT devices will become true operator assistants; always watching and always listening for out-of-normal conditions or for events that require manual intervention.
David A. Sanders outlines seven AI tools have proved to be useful with sensor systems: Knowledge-based systems, fuzzy logic, automatic knowledge acquisition, neural networks, genetic algorithms, case-based reasoning, and ambient-intelligence. Applications of these tools within sensor systems have become more widespread due to the power and affordability of present-day computers. The appropriate deployment of the new AI tools will contribute to the creation of more competitive sensor systems and applications.
Sanders and co-author Alexander Gegov also explain in another article how robotics, cars, and wheelchairs are among the beneficiaries of artificial intelligence. These developements, as a result are making control loops smarter, adaptive, and able to change behavior, hopefully for the better. Ideally, AI helps computing in four ways:
- Natural language understanding to improve communication.
- Machine reasoning to provide inference, theorem-proving, cooperation, and relevant solutions.
- Knowledge representation for perception, path planning, modeling, and problem solving.
- Knowledge acquisition using sensors to learn automatically for navigation and problem solving.
Artificial intelligence’s ability to function as a safety measure and provide another set of eyes, so to speak, can be extremely beneficial to worker safety in manufacturing. It can also enhance our ability to understand what’s happening around us and offer solutions that might not be readily available.
– Mark T. Hoske is content manager, Control Engineering, CFE Media, firstname.lastname@example.org.
– See the Control Engineering cyber security page.