Dr Sia Doshvarpassand is the Lead Data Scientist at VROC. Sia has a unique background that includes both engineering as well as data science, and he is now applying that experience to further develop the VROC Artificial Intelligence platform as well as deliver exceptional results for our clients.
We thought it was time to sit down with Sia and get an insight into how this blend of data science, asset reliability and artificial intelligence works together, and what he sees is the future for data scientists and asset realibility engineers.
It would have certainly come across contradictory and to some extent weird if ten years back you would introduce yourself like: “Hi, I am mechanical engineer, I work for an IT firm as a data science consultant and AI solution architect”. But not anymore.
The impact of industrial data has become huge, thanks to cheap availability and significant reliability of sensors, IIoT and broad and remote sensing and communications. The resource and energy industries focus on benefiting from their data has been long overdue. Sectors like retail, finance and marketing have been using AI and advanced analytics for quite sometime.
After working a decade in oil and gas downstream design and integrity departments, I began to realise, that using design codes and practice set based on statistical and mathematical modelling of certain case studies is no longer best practice. The design process has been significantly affected by reliability studies during recent years. In fact, the reliability as the key exercise during asset after-design life and during operation has had a significant impact on optimising the design process. So not only the reliability and more importantly the asset condition monitoring will increase the asset life cycle but also will optimise the design process through focusing on hotspot and risk points.
As part of a transformation journey I began a couple of years back, AI and some of its subsections such as machine vision, machine/deep learning became mandatory to my evolution and transition from an engineer to an analyst. Despite being present in academic environment for a quite some time, which generally drives the candidates’ mindset towards theoretical contributions, I never intended to use my two masters and PhD achievements in order to expand my career contributing to the mathematics behind the AI. However, it was very exciting for me to solve problems using AI as a tool.
There is a misconception out there that data scientists are able to work on any type of data and extract insights out of them. This can be true if as a data scientist you spend quite sometime understanding the physics and foundation behind the data you are working on to make sure you are not looking at the data at face. Working on industrial (sensor) data has always been fairly straightforward, as well as exciting for me according to my background. However, the impact of interaction with client’s SME and being benefited by their experience and subject matter expertise to validate AI models results was a key success factor in my multiple projects in VROC.
After working on multiple projects as an AI solution architect and asset analyst, a mentor introduced me to VROC. As a data scientist who spends a major portion of his time on developing solutions through hard coding, VROC suddenly came across as a scalable and powerful tool which removed a significant amount of time spent on developing solutions. I internally participate in developing AI solutions while using my engineering insights and capabilities alongside VROC as a powerful tool in a client facing position, I help clients to get the full benefit of using AI for the long-term monitoring of their assets’ health.
Data science as a career will be eventually divided into two less pronounced categories. The evolution of customised and industry-specific AI tools such as VROC predictive maintenance platform will require hybrid breed of engineers and data scientist to look after AI models and client asset health, account management, client training and conducting PoCs. The second group are hybrid breed of people with DevOps, data engineering, mathematics and statistics skills contributing to optimising solution and developing off-the-shelf tools.
Life is short. Make positive impact no matter how small.
If you would like more information on how VROC’s platform can help you with your asset reliability and maintenance get in-touch with our team, we can set up a demo or get you started with your own POC.
With so many Industrial Analytics solutions on the market how do you know what the best solution is, to ensure you get results quickly and cost effectively?Read Article
Interested in a demo of one of our data solution products?
DataHUB4.0 is our enterprise data historian solution, OPUS is our Auto AI platform and OASIS is our remote control solution for Smart Cities and Facilities.
Book your demo with our team today!
Ready to embark on a pilot project or roll-out AI innovation enterprise wide? Perhaps you need assistance integrating your systems or storing your big data? Whatever the situation, we are ready to help you on your digital transformation.
The efficient deployment, continuous retraining of models with live data and monitoring of model accuracy falls under the categorisation called MLOps. As businesses have hundreds and even.
Learn more about DataHUB4.0, VROC's distributed enterprise data historian. Complete the form form to download the product sheet.
Discover how you can connect disparate systems and smart innovations in one platform, and remotely control your smart facility. Complete the form to download the product sheet.
'OPUS, an artistic work, especially on a large scale'
Please complete the form to download the OPUS Product Sheet, and discover how you can scale Auto AI today.
Interested in reading the technical case studies? Complete the form and our team will be in touch with you.
Subscribe to our newsletter for quarterly VROC updates and industry news.