Refinery of the Future Podcast - Episode 3

[Podcast] Delivering Next Gen IIoT: Refinery of the Future

Episode 3 – Video as a Sensor

Series Description:

With a robust team of industry-leading partners like Hewlett Packard Enterprise (HPE), Aruba and PTC, CB Technologies is helping Texmark Chemicals modernize their business with advanced Industrial IoT (IIoT). This Refinery of the Future (RotF) podcast series is about the creation of the Refinery of the Future and the development of its five core solutions: Predictive Maintenance & Analytics, Video as a Sensor, Worker Safety, Connected Worker, and Asset Integrity Management. Throughout the series, we’ll discuss how RotF delivers improved process analytics, up-time, customer satisfaction, and worker safety.

Episode 3:

Listen in as host Daniel Newman, Principal Analyst at Futurum Research discusses Video as a Sensor with Linda Salinas of Texmark Chemicals, Stan Galanski of CB Technologies, and HPE’s Tripp Partain. A key element of the Refinery of the Future, Video as a Sensor combines video sensor technology, edge computing devices, Artificial Intelligence (AI) and Machine Learning (ML) to bring enhanced, real-time data to Internal Plant Operators so they are better positioned to address the most strategic aspects of their job. The solution is led by CB Technologies, with critical technologies provided by HPE and Intel.

Full Transcript:

Daniel Newman, Host: Welcome to the Refinery of the Future Podcast, Episode 3. I’m this edition’s host Daniel Newman. I’m the Principal Analyst at Futurum Research, Forbes and MarketWatch contributor and seven times bestselling author, including my most recent book, “Human Machine”. I’m excited to be here today with three esteemed guests, partners and participants in one of the most interesting projects that I’ve come across as an analyst in a long time.

And I’m going to quickly introduce them before I give you guys all a quick reminder of what’s been covered in the first two editions of the Refinery of the Future Podcast. So joining me today is Linda Salinas. Linda is the Vice President of Operations at Texmark Chemicals. Tripp Partain, Tripp is the CTO for Edge & IoT at HPE. And Stan Galanski. Stan is the Senior Vice President of Customer Success at CB Technologies (CBT).

Welcome to the show.

I’m excited to have you all with me today. So before I jump into the feature, which is a big part of our show, we want to take a moment and talk a little bit about the past and I want to get everybody up to speed on the first two episodes of the refinery of the future podcast. In the first two episodes, we discussed CB Technologies’ work with Texmark Chemicals and the work they did to launch the Refinery of the Future as well as CBT’s Connected Worker solution.

Some of this included featuring advanced IoT capabilities, and various HPE solutions. The Refinery of the Future addresses some of the most pressing issues facing the highly competitive oil and gas industry, including marketplace volatility, stringent environmental standards, competitive pressures, and workplace safety.

For Texmark, a chemical processing facility that manufactures hazardous materials in the petroleum product supply chain, the Refinery of the Future has sparked heightened performance via uninterrupted productivity, increased uptime, and better process analytics while also delivering a safer environment for employees. In this podcast, we’re going to turn our attention to another key element of the Refinery of the Future: how it’s cultivated a more connected and enterprising workforce, and we’re going to talk about the Video as a Sensor solution.

But we’re also going to talk about something that I think is really important as I reviewed the first two episodes and had a chance to talk with our guests today. And that’s the critical importance of the relationships in developing solutions and partnering on complex integrations, and how important the relationship is between the integrator, the customer, and the strategic partners. And that’s where I want to start off today’s conversation with you, Stan, I want to talk a little bit about how the process took place for you.

How did you gain an understanding of the needs of Texmark? Sure, you’re an integration firm, but their needs are very specific and very unique. How did that whole process take place?

Stan Galanski, SVP of Customer Success, CBT:

We were invited to come work on this project with our strategic partners, HPE and Intel. And they said that they needed to find a way to relieve the burden, significant burden of activities on their operations control staff, and they wanted to deploy Video as a Sensor capability. To make sure that we understood what they needed and that we did not leave any stone unturned, we felt it necessary to utilize our methodology called Innovation Delivery as a Service (IDAAS).

That methodology kicked off with a discovery series that we call Jumpstart, where we sat down with the customer at length for a couple of days and fully understood and inspected their processes, how they do their jobs, who they work with (both interior and exterior to the company) and mark that out and architected it. We’ve said it back to them, ask them further questions until we converge on a very clear understanding of what their business was, and how they needed to change in order to insert more safety and security into their workforce, specifically out in the rail yards.

DN:

Linda, it sounds like it was a fairly exciting and probably challenging process of finding the right partners to accomplish what you set out to accomplish. You know your business better than any tech company on the planet. And while technology can certainly enable your innovation, you had some things in mind. So Stan did a great job of framing how CBT ended up helping to deliver it. But it sounds like the story of how they were brought into the situation and how you guys basically even mapped out what you needed, has had quite a history.

Can you tell us a little bit about how you came to that? And how you came to, you know, how did you start with HPE, with Intel, to ultimately lead you to this process that got you to where you are today?

Linda Salinas, VP of Operations, Texmark Chemicals:

So the history began about three years ago, Texmark identified a need to upgrade its mechanical integrity program. And we were also looking for partners to upgrade or enhance our distributed control system (DCS). And it was at that point that Doug Smith, our CEO, and I reached out to some of our partners, our technology partners at HPE and said, we’ve got these two challenges, how can technology help us? That’s when HPE introduced Texmark to IoT (Internet of Things). We took a tour of their IoT lab, and from that was born the Refinery of the Future. The Refinery of the Future consists of five solutions. And the solution that we’re discussing today, Videos as a Sensor, is one of those five.

Very quickly, the others are Predictive Maintenance and Analytics, where we have censored a couple of our critical pumps in the plant. Another is Worker Safety and Security. The fourth one is Connected Worker which CB Technologies is leading. And then Asset Integrity Management. So that gives you a little bit of the history of Texmark and our Refinery of the Future.

DN:

And if I can dig one layer deeper, Linda, because that all is really fascinating. But when you’re pulling this many collective resources together, you have CBT, you have HPE, you have Intel, there are probably several other technology vendors. This is an industry, oil, and gas, that’s very compliance-driven or governance driven, regulation, safety-driven. What made Texmark feel good, feel safe, about the partners you selected? What was it that they were telling you that really gave you that comfort to proceed forward with the partners?

LS:

Well, I think right off the bat, when one might think of Hewlett Packard Enterprise as an IT company. And the same thing with CB Technologies, as a system integrator. Or Intel, they’re a computer chip company. However, what we learned very quickly, as we formed our partnership is that within each of these organizations is an oil and gas vertical.

There are people inside their organizations that understand my business, that understand our organization, understand our challenges in the plant, physical challenges with working in a hot, dirty, dusty environment, working in Class 1, Division 1 situation.

They understand that you just can’t grab a computer off the shelf and plug it into the control room and have it perform the way that it would in a nice clean data center. So it was very useful and helpful to us that each of the partners – Intel, CB Technologies, and HPE, and others – had that internal knowledge about chemical manufacturing.

DN:

Which transitions me perfectly to the next question. And, Stan, I’m going to bring you back into this. But it sounds like the courting process went very well, you felt very comfortable that these companies understood your environment. And that it is not, it’s much more ruggedized. It’s not just taking the boxes that have been put into a data center and making them work in your environment. And, and I think that certainly is important, but the solution itself.

You guys had an idea, Linda, in your mind of what you wanted. But this is where Stan, your group really had to come in and help figure out how do we put all this together? So how did you arrive here? Because there’s probably endless configurations and possibilities of how you could have done it? How did you arrive at the final solution?

SG:

Well, we started with: what is the situation today? And we planted ourselves right into the Operations Control Room. And we lived with them for several days, watching how they did their job, what resources they had, the demands on their time, the interruptions, where they were having a difficult time being able to fully provide safety observation and direction to their teams throughout the day. Because what IoT brings to the table is a chance to automate and reduce those pressures, and actually fulfill some of those functions, such that they can make decisions faster and quicker.

So by working with them on a daily basis, we saw that not only did they care about possible intruders coming into their plant through their rail yard, they also were concerned that maybe there might be a safety problem if some of their equipment got dislodged that was normally supposed to be still, or if one of their workers may have become fatigued and was not in an upright position, but had fallen, or somebody was wearing the improper safety attire and that person needed to be identified.

We ended up expanding the requirements based on this cyclic discussion with them and decided on a baseline the scope of the mission. And that was to give them the ability to sense something was abnormal in this part of the plant and provide an artificial intelligence-based program, running on state of the art computers that would alert them and save them the time of having to do a manual intervention.

DN:

So talk a little bit about that process, because what you call Video as a Sensor started as a proof of concept. And now it’s being scaled up. But you guys have a fairly well-determined process that you follow for… I think it’s a capture, categorize and analyze. And I think it’s important to spell that out. Because if I can frame this just a little, many IoT projects that people hear about out there are quite simply sensors collecting data.

And people don’t hear a lot about projects like this that integrate something so complex with video, machine learning, and AI. And if they do hear about it, they don’t get practical, real-world examples in real workplace environments. And that’s exactly what you’ve done, so talk a little bit about how that process was determined and how it’s working now.

SG:

Yes, by all means. This is not a lab that we were dealing with, we are actually working in an operational plant, which makes it all the more unbelievable. So, we were able to capture data like anybody else can through video cameras. And once that data was captured, we then had to categorize it to determine what’s a good situation, what’s a normal situation, and what’s an anomaly.

And the only way to do that takes that data, go back, share it with the customer, and have them start to make the judicious decisions. This is good, or this is bad, etc. Once we have that categorization, then we’re able to feed it into the software. And the software starts its first cycle of learning. And it determines what indicates something as abnormal. And then as we take more data, the software was able to assess it and come up with a smaller set of anomalies. We share that with the customer. They categorized it again. And through several cycles, we were able to hone the application down.

This is what I would consider the machine learning aspect, to the point that it could now distinguish key features that would prevent calamity or potential safety infractions.

DN:

So Linda, as the group at CBT and the partners at HPE and Intel came back to you after discussions, planning, analysis, data collection, they probably presented to you, “Hey, here are our findings. Here’s what the results look like, here’s what it’s going to look like when we leave at least from a being here all the time.” You must have felt like they really nailed it or how did that work? At that point, was that it? Or was there a lot of tweaking? Or do you think that after that time spent on site that they really figured it out and were able to dial it in? And how much have you seen a change since?

LS:

I think the answer to that question is all of the above. From the time that we have the IDAAS workshop with CB Technologies, to the time that they rolled out the first demo, until now, the process and the ideation and that whole iterative process with our employees have been fantastic.

In the sense that it has helped build trust between the employees and CBT’s team, and trust between the employees and the software package itself. I feel like if CBT and HPE and Intel all got in a room together and said, “Hey, this is going to be something great, we’re going to roll it out to your employees. Here you go, here’s your new video as a sensor package. Click this button and an alarm will go off as needed.”

I’m not sure that the employees would have accepted it as readily as they have now since they’ve been in it since the beginning. Now there is trust in the system because they gave the input from the beginning as they were developing the program. And they continue to provide what I think of as machine learning because our employees are teaching the system: What is a hit? And what is a false alarm? As it is detecting railcars or workers or a fallen worker or an intruder and so forth.

DN:

Yeah, it sounds like it is an ongoing process. It does have a lot of iteration. But I think that’s the key because you even see, like the example of the employee that identified an anomaly that wasn’t part of the plan, becomes an opportunity to say, “Hey, can we innovate, iterate, improve the process going forward? This could be something that uses machine learning?”

LS:

Absolutely. In fact, we had a recent example where a railcar was delivered to Texmark and our operator detected a leak from the gasket around the top of the railcar. This was particularly important to us because you don’t want any hazardous materials leaking. And immediately the operators knew hey, we’ve got the cameras down there at the railcar loading area, can we roll the tape and find out if it was leaking upon arrival?

And when did it start to leak? All of that footage became of interest to the railroad operator and for the railcar product supplier. They’ll be using that information as part of their investigation. So what did that trigger? It had our operators coming to me and saying, “Well, hey, we detected the leak upon inspection. However, can those cameras help detect those leaks?”

DN:

That example was so perfect. You would have thought we planned it! So, Tripp, you haven’t had much of a chance to hop in but your part’s coming here. Throughout this conversation, both Stan and Linda have mentioned Intel, they’ve mentioned HPE, you’ve talked about partnerships with these technology leaders, as well as obviously the integrator and customer relationship. Tripp, you are the CTO of HPE, working on Edge and IoT. So, while a lot of times you’re involved in very high-level strategy, sometimes you get into these specific opportunities, applications that end up building product categories, solutions that get scaled out globally.

Talk a little bit about your involvement in this strategic partnership and the involvement, you know, in the case of HPE, everything from the comfort of the partners that you’ll bring into opportunities like this, to how important it is that you guys are intimately involved in these unique use cases in terms of continuing to develop products and solutions.

Tripp Partain, CTO Converged Servers, Edge and IoT Systems, HPE:

Yeah, and as Linda mentioned a little bit earlier in the podcast, you know, within HPE we’ve had vertical focuses, so that we could take what a lot of folks would consider, you know, generic data center technologies and some of the other technologies that HPE has had over the years, and really be able to focus those to solve problems that are a little more vertical-centric. So that at least the way you use it, the way you explain it, the way you align, it really goes to focus toward what makes sense for that vertical. When you start to look at Edge and IoT, because it’s a much newer technology, and while it’s been talked about a lot, I would say you’re probably still early.

Maybe not early in the hype curve, but definitely early in the adoption and real value generation curve. And so, when you have that happening and the technologists themselves really have to be very close to the problem sets, being able to really understand, maybe even get closer to the vertical than we would have in the past to make sure that the way we’re developing the technologies and the way that we’re enabling them to be used is actually going to be adoptable by the end-user and fit for that problem.

And so, it’s one thing to have a customer that’s willing to take that journey with you, and to allow you to get close enough, but it’s also even more critical to have the right provider, the solution provider, the system integrator, the partner that can say, “Okay, so HPE you’re bringing some really cool technologies to the forefront here.

But it’s going to take a combination of that, plus a number of other pieces to really solve the problem.” And so, having a key partner like CB Technologies to work with, so that we can then go and focus these new Edge and IoT solutions toward the Texmark use cases and the problems they presented, really is the only way for us to make sure that these newer solutions are fit for purpose and have the right adaptability to a very different environment than what a company with a data center background is used to.

Now granted, we started in a garage, so you would think we would have the ability to work outside of a data center. But over the years, we’ve really sort of migrated to much more pristine data center environments. And now with the emergence of Edge and IoT, we’re kind of working ourselves back toward the garage again.

DN:

Yeah, I always wonder why every company starts in a garage, not in the basement and not in a home office, or a dining room, it’s always a garage! But in tech and in Silicon Valley, I just don’t think there’s another story that’s more relatable than that. I wanted you to go one layer further though. And so as an analyst, I’ve been tracking IoT very closely. Of course, we work with HPE, but we work across the industry with many IoT companies building systems that they say are hardened for the Edge.

But one of the areas I’ve definitely given a lot of credit to HPE has been truly building hardened Edge solutions that consider these environments and that are really redesigned to run at the Edge. Not a repurposed box or a box with slightly different wrappers around it. There was a product out of the box that was almost like it was designed for this application. The Edgeline 300, I believe it was, the Converged System. How quickly did you guys come to realize, and I’d love Stan to weigh in on this too, but how quickly, Tripp and Stan, did you guys come to realize that this was the right product to help give Texmark what they needed?

TP:

Yeah, well, categorically, when you start to look at very complex environments involving artificial intelligence, involving machine learning, involving video as a sensor, what you end up with is really the key tenants around the whole reason HPE created the Edgeline Converged Edge System. And so out of the box, you have to make sure that whatever fits in Edgeline description has to be rugged enough and compact enough to be able to work in a non-data center environment.

Take that a step further: this is not just a non-data center environment, this is a hazardous plant environment. So you’re taking it to that next extreme. But when you start talking about using AI and machine learning and video as a sensor or video analytics, in general, you’re talking about a very high level of computing, right? If you look at the way a lot of companies approach IoT today, it’s a gateway focus. It’s a very small device that has a minimal amount of compute power, not much expandability, and the whole idea is to grab data and send it somewhere else.

Well, in the case of worker safety and plant safety, that doesn’t work. You can’t wait for the time for that to happen. So, when when you have one of the key tenants of Edgeline is not only to meet the ruggedization requirements but have the most compute capabilities that are in the marketplace.

But also the ability to expand with industry-standard VPUs and GPUs and other accelerators that are really fit for purpose. So in the case of Texmark, and with CB Technologies, looking at video as a sensor, the ability to have the right size device with the right level of ruggedization, the right level of compute, but also the ability to take some special capabilities from Intel, and have those embedded directly into that device to really handle specific video sensor analytics, you know, you really start to see that the vision HPE had for Edgeline and the way that we’re now adapting that toward Edge and IoT solutions, you know, it was a pretty good fit for what CB Technologies and Texmark were looking for.

SG:

Daniel, we looked across the entire industry. And we pretty much found that the Edgeline compute platform by HPE was far and above most all the competition. That’s why we used it on Connected Worker. That’s why we used it on Predictive Maintenance and Analytics and on other solutions at Texmark. But when it came to putting the compute power way out, into the field, right there in the railyard, and knowing that we’re going to have to process streaming video, and do it quickly,  do it fast.

We found that Intel and HPE had collaboratively designed this EL300 to do just that. So it became a perfect fit. And that’s why when we deployed this and tested it, we brought the Intel engineers, we brought the HPE engineers to make sure we were tuning this correctly and optimizing it for just what it was made for. And that was one of the beauties of this solution, the way it works.

DN:

Stan that absolutely would have been my question if you hadn’t just jumped right in and started talking was, did you look beyond HPE? Obviously, you were brought in to some extent. And sometimes as an integrator you don’t, you know, have the chance or, you feel like you don’t want to maybe look beyond so that’s really exciting. And also obviously for HPE sitting here, to hear that you did that type of diligence. You looked at everything out there and determined in the end that that was the right solution.

So we’re coming towards the end of this conversation. And it’s been a pleasure for me to hear about this, certainly. And I hope everybody out there has really enjoyed this as well. We started the show talking about partnerships. And I’d love to end it just on a slightly personal note from each of you. And Linda, I’m going to start with you. So let’s start queuing it up as I asked the question, but was there anything in this process that you learned with having this many partners involved in a collaboration?

Maybe a technology that’s not part of what you’re thinking about every day? Was there any really valuable lesson as a user, as a customer, that you could pass on to the listeners, that they could, you know, a tidbit of knowledge to take away? And then I’ll let you two (Stna and Trip) also have a chance at this one.

LS:

I think through this experience, it has really reinforced the value of including our team from the beginning, on any sort of solution. They’re the ones that are bringing us the problems, so why not include them in the solution. And this one, in particular, was really exciting though, again, the ideation process. And from that emerged some champions within our organization, you know, I think about Ben and Carlos and Charlie that was there through the meetings and really had a voice and now they feel ownership of the finished product. And so they want to see it through the end. They want to see that it will be a successful and useful tool.

They want to be there side by side with Stan and his team and continuing to tweak until we have this finished product that will continue to add value going forward. They also come to me and come to Stan directly with ideas on how to improve it, you know, with the railcar situation, for example. And so I want that to continue. My vision for the Refinery of the Future is that the next time we have a podcast is that you’ll have Ben, or Carlos, or Charlie, or one of our employees sitting here in the podcast, telling you about their direct experience. Rather than having my report on their behalf. They are where the rubber meets the road.

DN:

It’s such a great testament to digital transformation as a whole. We always talk about culture and people and getting everyone involved. But so often, that’s followed up with a bunch of speeds and feeds and technologies. And so hearing you advocating for your team to be part of this process and actually recognizing it, and its importance. And that’s for everybody out there, so important too as you’re considering projects: who are those key stakeholders that are going to be intimately involved with this technology?

Stan, what about you? Any real, key takeaways?

SG:

Very much similar to Linda, she was very impressed with the dynamic relationship between our two teams and I feel the same way. In fact, when we were designing the system, we were contemplating where we were going to store the data for a month, are we going to do playbacks at certain intervals? Did we have to re-position the cameras to get glare out in certain quadrants of the picture?

And when we thought we knew because we’re the experts at some of this. As far as the technology is concerned, we sit down with the customer and they say, “Nope don’t need that much data. This is how much I need. The glare is not important here. This is what’s important.” And that allowed us to really hone in on what were the strategic features. It saved us a lot of time. We started learning, we started thinking like an operator versus a technologist. And so the next project that we’re on, I think we’re going to converge a lot faster.

DN:

Absolutely. And Tripp, again, you had to wait for the longest but I’ll give you the final word here. Any really interesting or exciting findings? And as a strategic tech partner, kind of being the cloud over this Edge, what really intrigued you?

TP:

Yeah, and I wouldn’t say it’s necessarily an authentic finding I didn’t expect, but it definitely confirmed it much stronger. And it was good because it helped resonate to some parts of our organization that maybe weren’t there yet. And that is technology, which is what HPE provides (some of the world’s best technology), technologies are enablers to solving problems, but solutions are what really solve problems. And in order to get a solution, you have to have the right buy-in from the customer, the end customer.

But probably even more critical is having the right partner, an integrator to really take the components and turn it into the right solution. And it’s still early days around Edge and IoT. And, you know, CB Technologies is really uniquely positioned to solving these kinds of problems and really being the hands-on system integrator that’s required for these types of solutions. And so it really just sort of brought home that HPE has a very important role to play. But there are critical partnerships to getting the right solutions created to really solve the end customer’s problems.

DN:

Linda, Stan, Tripp, I want to thank each of you for your participation. It was a great discussion. I hope everybody out there, those that are thinking about deployments, those that are integrators or technology providers, all found some value in hearing about this, not just the tech itself, but the whole story of how it’s come together and how strategic partnerships can really add a tremendous amount of value in delivering a solution. It drives performance and productivity and helps companies move their digital transformation forward. So Stan, for anybody out there that wants to get in touch with CB Technologies to learn more, or to see how their projects could be helped by your solutions, how should they reach you?

SG:

Sure, they can go to our website, where this solution and other solutions related to Refinery the Future are captured, at cbtechinc.com.

DN:

Great. Well, for the Refinery of the Future Podcast. I’m Daniel Newman. And I want to thank everybody once again for tuning in. We’ll see you soon.

RotF, Refinery of the Future Podcast, CBT, CB Technologies

 

If you enjoyed that episode, check out the previous installments in our series:

Let's Innovate Together

Just ask us how we can make a difference for you today.