Artificial Intelligence, why does it matter in engineering?
I bet most of us has already heard of the term Artificial Intelligence or AI, at least once by now. AI used to be a jargon back when I was in university and all people know about it at that time is robotic future which may start a war with humankind. However, today in every industry people are talking about AI, this includes energy industry and engineering in general.
First question that may come to our mind is the ‘ what is even an AI ’ ? To non-technologist this may still be a mysterious buzzword. According to IBM, artificial intelligence refers to the ability of a computer or machine to mimic the capabilities of the human mind — learning from examples and experience, recognizing objects, understanding and responding to language, making decisions, solving problems — and combining these and other capabilities to perform functions a human might perform, such as greeting a hotel guest or driving a car.
In engineering domain, AI may perform estimations, detections, parameter tuning, simulations, planning and decision making suggestions. The list can go on and on. However, due to the fact that it is only artificial, this intelligent being can only go as far as its design and the lessons they took.
The question now, is how far can AI go in being better than human being within engineering domain? This is a big question that most pro-AI people are trying to solve by implementing AI technologies in their own engineering problems they face. For instance, PETRONAS has been testing AI solution from VROC.AI to identify root cause of some turbomachinery equipment. Many other Proof of Concept projects has now been rolling out to conclude their hypotheses.
As for myself, I am currently going deep into Computer Vision: a branch of AI which emphasize on image recognition and object detections. This branch alone would enable variety of applications such as HSE (Health, Safety & Environment) regulatory compliance camera for detecting unsafe act or attire at site. My current mission (as a starting point) is to implement computer vision technology into data extraction from engineering documents such as P&ID (Piping & Instrumentation Diagram) and Datasheets.
There are many others branch of AI, which the most that are being explored as the following:
- Machine Learning: The study of algorithms that improve automatically through experience and by the use of data. Example: Regression, Classification, Clustering.
- Deep Learning: A specialized study of artificial neural network method Machine Learning. It focuses in structuring algorithms in layers (deep = more than one hidden layer) that can learn and make intelligent decisions on its own.
- Robotics: The study of making intelligent physical robots. Literally.
- Natural Language Processing (NLP): The study of how computers can process texts and languages, such that it can perform classifications or any other tasks from it. Example: Email filters, digital assistant, autocorrect.
- Computer Vision: The study of how computers can process visual-based information, such that it can perform classifications or any other tasks from it. Example: object detection, image recognition, OCR.
- Expert Systems: A computer program that uses artificial-intelligence methods to solve problems within a specialized domain that ordinarily requires human expertise.
Based on above AI subcategories and examples mentioned earlier, I hope this short article can bring light into how Artificial Intelligence can bring value to engineering domain.
That’s all for today! Thanks for reading & see you in the next article which would be about Computer Vision in more specific!
