Would you Hire an AI Computer Program instead of a Contractor / Employee?

I was sitting in a meeting with a customer this morning, and a thought kept running through my head: why aren’t more people outsourcing work to computer programs in our industry?

The turbomachinery industry has no shortage of brilliant PhD-level engineers who have a million correct reasons to explain why solving complex flow issues is so complicated; but have they considered how utilizing artificial intelligence may be able to lighten the load?

Our task this morning was to help a customer who is developing an innovative piece of turbomachinery for waste heat recovery as well as their end-customer who will have the pilot machine installed. Our role during the call felt akin to the role of an application engineer; meaning that we did not have to do a complex design on the fly. Instead we answered complex questions about a set of data which we know and have pre-calculated.

It seems that opportunities for leveraging Artificial Intelligence are all around us and are becoming mainstream, but are not as widely used in our industry as if feel they could be, and still seen as an R&D pipe dream rather than a commercial and business engine.

­ ­

It has been about a year since we at SoftInWay started seriously developing and using our AI engine AxSTREAM.AI; it was driven by 3 needs:

1. With a size of 85-90 people and a customer rate growing at about 20-30% a year, how can we offer increasingly better engineering services faster, without sacrificing quality or cost-effectiveness?

2. How can we support the Sales team properly in preparing proposals and engineering concepts without having to use un-billable engineering time?

3. How do we help our external customers who have “one-off" projects to complete them efficiently and NOT have to pay for permanent in-house employee or external consultant rates to do work.

Coming from math/finance background the answer was always simple in my mind: train an AI program to do the work so that our team is maximizing their time thinking about new ideas, and everything that was done before in design and application engineering can be in one way or another reflected in a training network or methodology.

I feel that this can be helpful to large companies trying to capitalize of years of historical experience and counter the losses of workforce turnover due to age, as well as startups that don’t have the budget to hire a full engineering team, or the internal skillset to do all of the work.

Do you agree or disagree?

If this sounds like a familiar problem to you, it might be time to consider “hiring” AxSTREAM.AI to tackle your project before things get “supercritical”. Let me know via private message or email: Valentine@softinway.com

Top 5 Best Practices for Selecting Software for Your Next Turbomachinery Design Project

The airport was bustling with people. The boards were a mixture of delayed and on-time flights. My flight to San Diego for the EUEC Conference was one of the delayed. This happens when you travel as much as I do, so I found a quiet spot to get a few hours of work in while I waited. In the café at JFK, I overheard a conversation between two other detained travelers discussing what they wish they knew before purchasing software tools and/or hiring external consulting companies.

Their pain points were identical to the pain points I’ve encountered in my decade plus years at SoftInWay meeting with design engineers, engineering managers, CxOs, and other non-technical people in my industry (simulation software and R&D of turbomachinery). Over the years, I have used the knowledge gained in my experience to help guide people in making big decisions such as purchasing turbomachinery design software or hiring consultants on a new project and I wanted to share with the blog community as well.

Here are the top 5 Best Practices I suggest everyone use before embarking on their next big software purchase or hiring consultants for their design project.

Read More

A Primer on Compressor Design

As technology has evolved, so has the refrigeration industry. What were once holes in the ground filled with ice and snow have transformed into the modern high-efficiency compression machinery we have become so familiar with today. However, as common as these devices have become, the design process remains a challenge. This is where a combination of scientific knowledge, experience and creative initiative comes into play. While there are, of course, several variations in terms of the application of each design step, the guidelines presented here could be applied not only to refrigeration compressors, but also to compressors used in many other processes and industries.

There are a number of steps to consider throughout the compressor design process, and each step has to relate back to the original design concept. Experience has shown that having a starting concept and an end goal in mind is imperative. Namely, before you can begin the process, you need to know where you are starting and where you want to end up. With this in mind, before we can even get started with preliminary design, blade profiling and analysis of computational fluid dynamics (CFD), it is important to take out a piece of paper and start brainstorming. Consideration of the different refrigeration technologies (cycles), is always a great place to start, so we can ensure we will design the best compressor for the application. The cycle will directly impact the rest of the compressor design decisions, so this is not a step that can be bypassed. This article’s discussion begins with cyclic compression.

Read More

Rotor Dynamics – Importance of Fundamental Understanding & Software tools

Rotor and bearings are the most critical components of any rotating machinery. Rotor lifetime and reliability depend, first of all, on the level of rotor vibrations. In order to meet highest requirements of reliability each step of the rotor design should be based on accurate Rotor Dynamics prediction.

Rotor dynamics is the branch of engineering that studies the lateral and torsional vibrations of rotating shafts, with the objective of predicting the rotor excessive vibrations. Rotor Dynamics is different from structural vibrations analysis because of gyroscopic moments, cross-coupled forces, critical speeds, whirling effect, etc. These difference makers are all due to the rotation of the rotor assembly.

Rotor-Dynamics

Understanding of basic rotor dynamics phenomena and the various types of problems is absolutely mandatory when designing and developing rotor-bearing systems for various applications. Fundamental approach for Rotor Dynamics analysis generally is based on the following steps:

  1.  Predict critical speeds.
  2. Determine design modifications to change critical speeds.
  3. Predict natural frequencies of torsional vibration.
  4. Predict amplitudes of synchronous vibration caused by rotor unbalance.
  5. Predict threshold speeds and vibration frequencies for dynamic instability.
  6. Determine design modifications to avoid dynamic instabilities.
  7. Calculate balance correction masses and locations from measured vibration data.

Another factor that determines accuracy of Rotor Dynamics calculation is rotor system simplification and the adequate modelling for rotor parts such as Impeller/disks, Sleeves, Balance pistons, Seals, Thrust collars, Couplings, Addition of Stiffening Due to Shrink Fits and Irregular Sections etc. Continue reading “Rotor Dynamics – Importance of Fundamental Understanding & Software tools”

Re-inventing the wheel (or perhaps our education system)?

I hope everyone is having a great week. I wanted to write about our education system, as it relates to Turbomachinery, and perhaps some challenges that educators / students face, and some ideas for how things can be improved.

As computation technologies have evolved over the last 30-40 years, it seems that a large number of education institutions are still behind.

Part of my job at SoftInWay, is to make sure that local  & global Universities involved in Turbomachinery have the most advanced software tools, so that the students graduating from undergraduate, as well as Masters and PhD level programs, have some kind of relevant skills to develop / optimize Turbomachinery, as well as know how to use relevant software tools.

From talking to Academia from different countries, it seems that professors (perhaps due to bureaucracy of their positions) are often faced with several challenges / decisions:

1. No budget for software tools thus forced to use free tools

2. Desire to create their own software, to eventually spin off and start a company

3. Lack of deep technical program, thus only picking macro topics as they relate to turbomachinery as general thermodynamics, etc. (which is important also).

What’s the problem with all of these approaches: When students graduate, and want to go into the field of Turbomachinery, a large portion of these students think that “Turbomachinery Design” can be done with CFD.

Looking at the last 5-10 years of CFD as it relates to Turbomachinery, people have been in several “camps”, with the most known names (such as products from Ansys, or CD Adapco (now owned by Siemens), Numeca, and some free open source CFD codes.  Additionally, there has been a plethora of free or academic codes written by 100s of wide-eyed graduates students in hoping of making the next big software company.

Why does this cripple the education system, industry and the general concept of innovation? First of all, in all of these packages, you are going on the assumption that you already have a geometry of the turbomachinery and generally know what the machine looks like. Granted, some advertise that by “partnering” with other vendors they can do 1D or inverse design, when looking at these options closely, they are still very weak.   At the same time, there are lessor known CFD packages (from example our Turbomachinery specific CFD module AxCFD that we offer) that while hasn’t been aggressively marketed, comes at 30% of the cost, and has not only faster computation speed, but is fully integrated in a complete turbomachinery design platform. While this is a great option for students, very few know about it, and we are always stuck with a thought “people need to understand the complete process of design, not just CFD, so let’s focus on teaching that, and sharing that message”.

In addition to working with Universities, another part of my job at SoftInWay is hiring, so what have i learned from looking at 1000s of resumes from masters and PhD students?

If you start to dig deeply, about what candidates have learned about turbomachinery design, how well do they understand, for example, compressor aerodynamics, or gas turbine cooling, quite often the answers come up short. This creates a steep learning curve, not just for our company, but also for major manufacturers and service providers.

We believe, that instead of the next generation of students, trying to re-invent the wheel, and spend their 2,3,4,5,6 years of education  on equations and writing code, for a problem that has been solved, they should use a holistic approach, to advance, Power Generation, Transportation, Propulsion and Advance the clean energy space.

We have created a range of free resources for students in an online university format (learn.softinway.com) and encourage everyone to dig deeply, and together we can create a greener world, for the future generations.

Additionally, our turbomachinery development platform AxSTREAM (r), is the only platform in the world which is wholly integrated and developed in-house, including thermodynamic cycle design, 1D,2D,3D turbomachinery design, analysis and optimization, rotor dynamics and bearing design, stress analysis, advanced optimization and visualization, etc.

** Feel free to fact check this by looking at your current software simulation tools, and see how many modules or features or “tools” are borrowed from other companies.  How can one ever learn and understand how things work and talk to each other, if knowledge is not developed, but rather borrowed.

If  you are a student, or a professor at a college or university, and are interested in improving your turbomachinery program, and giving your students the extra skills (fundamentals and software), to really develop innovations, please write me a message !

Message Me

Crowd Sourcing Innovation – What’s your vision?

Dear Friends,

I hope that you are having a great week. In case that you are not on our mailing list, I wanted to share some updates and discuss innovation.

Typically, every week we send marketing or information emails about our latest customers, case studies, upcoming webinars & seminars, etc.

However, after along product development meeting planning our next 3-9 month, I wanted to reach out to the world and ask: how can we help? What don’t you like about your current engineering process? How can you do what you do faster? What would it take to develop a truly more efficeint machine?

Simulation technology and computers have come a long way in the last 30+ years, and yet there are still many companies, and engineering departments stuck using old designs, and methods.

For those of you who have attended the 2005 Turbo Expo in Montreal, we first publically laid out the idea of “Collaborative Development” and “Crowd Sourcing Innovation”: Watch Video

We are working hard on getting ready the next generation of AxSTREAM Platform, and AxCYCLE, with features and level of integration, that the industry has never seen before.

If you have a few minutes, we would appreciate you answering a few questions, and providing some ideas / or some pains / frustrations you may currently have about your turbomachinery design/analysis process.
**** 10 people will be picked at random, to receive a free access to our online, self-paced, Turbomachinery Course of their choosing.

Please respond by filling out this questionnaire: Questionnaire

We greatly appreciate your help, and feedback.
Warmest Regards,
Valentine Moroz

Summary of the Development of Gas Turbine Industry in China

VM at china conference

On March 18th and 19th I attended a Gas Turbine conference in Beijing, China, where I had been invited as a Chairman and speaker. It was a great learning experience, with many interesting presentations involving energy and modern turbomachinery. I wanted to summarize some topics and ideas which I found particularly interesting.

  1. Supply: Projections for China through 2020 show increases in the Liquefied Natural Gas supply. This LNG will most likely stem from the new agreement between China and Russia. At the same time, still today within China, there is not enough pipe line capacity to efficiently transport it. These two factors make the price very high. In order for Gas Turbine technology to really become economically viable, there needs to be a decrease in the price of fuel, perhaps cheaper locally manufactured machines, and tax & other incentives. Today for most, it is simply a lot more expensive than traditional fossil fuel technology which accounts for more than 60% of all energy being generated today.

Continue reading “Summary of the Development of Gas Turbine Industry in China”

Challenges and Opportunities in the Turbomachinery Industry

Steam turbines have been around for more than a century, and some say the Turbomachinery industry is rather mature. So how does a company decide between competing Turbomachinery producers? Do they go to Siemens or GE? How about Rolls Royce vs. Pratt?

Manufacturers invest millions, if not billions, of dollars (depending on their size) into their sales & marketing to create a perception of having the better technology and lower prices in order to beat the competition. They do so, however, by sacrificing quality and margins.

Last week, we had a very nice dinner with some of our colleagues from a large Japanese manufacturer. They explained to us that, in addition to pricing pressure and brand pressure, the “cost of goods” landscape is changing rapidly with fierce competition from Chinese and Indian companies from the manufacturing perspective. But there exists a “risk” to outsource manufacturing to a cheaper location and lose the quality, or at least the perception of quality, of the turbomachine.

So what is the solution?

At SoftInWay, we are an R&D engineering company and thus consistently feel that the differentiation of our clients from the rest of the market should not just be in price, but rather in truly creating better machines from the perspective of performance, durability, environmental footprint, etc.

However even “R&D” and the design aspects of something as mature as “the steam path” can be a challenge.

Companies have several approaches to designing new machines:

  1. Complete design from scratch based on a new concept: example SCO2 Cycle Technology.
  2. Redesign or improve on existing technologies ( this can often be considered the safest by the larger OEMs with a high level of risk aversion and investor pressure).
  3. Not changing the flow path but adding to the overall machine.

The only approach of these three which can really give a new or existing company any real advantage is the first.

We have also taken a look at another interesting idea: Every “major” manufacturer has at some point taken their designs, models and often software code from academia. The result is that, since they have something that works and has been tested, the engineering R&D teams are often crippled by lack of budget for new tools that will allow them to effectively take approach 1 or even sometimes 2.

Alternatively, some engineering managers upon first meeting us and learning about AxSTREAM ™, our software for design, analysis and optimization, have asked us – why do we need a new approach if we know ours works?

We feel that the answer is quite simple: Although the industry is quite mature, every player does something a little bit different. Our software has been developed and improved over the last 15 years by working with over 200 major players in the Turbomachinery Industry. Because we started as a consulting company, our mission in the beginning was never to be a software player, but rather to make our engineers’ lives easier.  Accomplishing this led us to develop new, innovative software features that would further our capabilities with consulting projects. In 2005, we released our software into the market.

The result became quite interesting: Today in 2015, over 50% of our new feature developments come from our clients’ ideas and requests. What does this mean for a user of software like AxSTREAM as well as for the industry? They can benefit not only from their experience and ours, but also from the experience of the industry as a whole. From a figurative perspective, AxSTREAM has been built and added to by those in the Aerospace, Automotive, Defense, and Power Generation industries, just to name a few. Its capabilities stretch beyond a single field. The ability to innovate using a new approach, such as AxSTREAM, becomes less risky and more attainable. Some might even say the biggest risk in developing new technology is doing so alone, in a room, shut off from the outside world (without AxSTREAM).

Sustainable Turbomachinery

iStock_000015544357MediumThis past Tuesday was the 44th celebrated Earth Day. On Earth Day, more than 100 countries join together to literally stop and smell the roses, appreciate the splendor and beauty of Mother Nature and take extra efforts to be more conscientious for our shared home.

Turbomachinery, though not always the first thing that comes to mind when speaking on the subject of green technology, plays an important role toward our efforts for a more sustainable environment.
Continue reading “Sustainable Turbomachinery”

Let’s Talk About Centrifugal Compressors

centrifugalcompressordesign
Centrifugal Compressor Design

We all know by now that no machine is perfect. Turbines have carryover losses, pumps experience cavitation phenomena, and compressors certainly have their fair share of pros and cons. We’re on the hunt for some common design problems – perhaps problems that you have experienced yourself, with centrifugal compressors. We scoured through our technical papers and presentations and searched the web for some. Here’s a list of frequent concerns and questions we ran into: Continue reading “Let’s Talk About Centrifugal Compressors”