👋 Welcome to Nexus, a newsletter for people applying analytics and other smart building technology—written by James Dice.
If you’ve been forwarded this email, you can sign up for your subscription here:
This is an experiment, and I’d love your feedback. If you have thoughts, questions, ideas or tips, join the discussion on LinkedIn or hit reply.
We’ve been doing this Nexus thing for 3 months now. If it’s not too much to ask, I would like some feedback so we can keep improving it.
Please take this 2-minute survey so I can get a better sense for:
1. Your direct feedback of what you like/don’t like
2. How to provide more value to you and your business
The form doesn’t collect any personal details (i.e. email, etc.) and I’ve tried to keep it as sparse as possible. It will take no longer than two minutes... five if you want to write a really long love letter.
Oh yeah, one more thing: the survey has a big announcement...
🙏 Thank you for your support. 🙌
+ The latest LinkedIn discussion (with 70+ comments from you wise ones!):
I'd love some input from the experts on this one.
I recently audited the building automation system and analytics software at a local campus. Many of the owner’s #analytics (#KPIs, heat map #visualizations, #FDD, etc) are not fully populating and we wanted to figure out why.
We decided to start with one control loop—zone temperature control—and trace the issue from edge to analytics. Here’s the result of the audit:
Across campus, there are 17 distinct methods for accomplishing the same control loop. The diversity includes varying physical (input/output) and software (variables and programming) configurations.
In some cases, like the fan coil in the image, the points needed for analytics were not even exposed via BACnet as distinct points—they are hardcoded in the BAS programming.
Even if the points are there, the lack of standardization means that some of the identically-named points are actually doing different things— making semantic tagging (Haystack in this case) extremely difficult.
What are your strategies for dealing with this major obstacle to implementing analytics?
Last week, we introduced Tesla’s innovation strategy, explaining why they’ve been able to disrupt the auto industry.
In our industry, we have innovators, sure, but do we have disruptors? Do we have technology that building owners want as much as I want the new Tesla Model Y?
Consider this: when I read that article on Tesla, I only thought of one company attempting something similar—something big: Passive Logic.
Perhaps it was availability bias… because that same day I happened to meet with Troy Harvey, Passive Logic’s CEO. Troy and his team are simply thinking on a different plane. Where everyone else is thinking 1 to N, Passive Logic is thinking Zero to One.
Today we’ll introduce Passive Logic with three points that really stuck out to me:
First, the #1 way Troy has changed my thinking is described in his blog post on the user experience of existing controls solutions:
While we’re seeing a constant stream of band-aid solutions that bolt-on to our automation stack with hopes of fixing this old “black box” foundation, this is probably going to be unsuccessful.
Adding this new functionality, limited by the weak foundation, requires laborious effort — thus we call it “integration” not “installation!” The combination of a weak foundation with a low technology ceiling, together with laborious effort requirements, is a core source of so much dissatisfaction in the marketplace.
This point is obvious when you stop and think about it: most smart building solutions are actually smart overlays over a dumb foundation. The dumbness of the foundation is making everything we’re trying to do more difficult than it should be. Passive Logic wants to replace the weak link: the building automation system as we know it.
What do they want to replace it with? Deep and autonomous digital twins, of course.
Let’s unpack that:
What are deep digital twins? Put simply, the intelligence reaches down into every part of the system.
Functionally, they act as virtualized analogs of real-world objects, like zones, equipment, systems, and the physiological agents of human-comfort.
Because they are built on a physics-based ontology, these analogs aren’t just labeled, but actually understand what ‘kind’ of thing they are. The term ontology comes from the philosophical study of ‘being’, and is used by computer scientists to describe computing systems that can introspect.
Ontology is a framework that comprises the technological ‘nature of existence’ for an object in the world. The ontology, for example, provides a control system with the understanding of the fundamental physics of operation, how that operation interacts with the world around it, how its internal physics is organized, how the object interfaces with controls, the physical parameters of operation, and the meta-semantics of operation. The ‘meta-semantics’ of operation is the ontology translated into language or protocol.
What’s an autonomous digital twin? Picture a fully autonomous vehicle. Most smart building solutions today are analogous to a car’s cruise control. Some even resemble adaptive cruise control. That’s only level 1 out of 8 levels of an autonomous building as proposed by Passive Logic.
And, if Troy is correct, this replacement foundation will replace and render many of today’s smart building services and solutions obsolete.
I’m a little skeptical about this point, but I still haven’t been able to get it out of my mind. How much effort in this industry is simply not needed once the weak foundation is replaced?
I’ll be meeting with Troy again soon for round 2… What questions should I ask him? What are you skeptical about? Hit reply and let me know.
In the meantime, here are some links to dive deeper on Passive Logic:
+ Troy’s Interview with ControlTrends (YouTube version | Podcast version)—"the atom bomb of the industry"
+ How Passive Logic is bringing AI to the Edge (Invidia blog)—An intro to Passive Logic’s Hive supervisory controllers built on the Invidia Jetson chip.
Jetson modules power a range of applications that require various performance levels and prices—from AI-powered Network Video Recorders (NVRs) to automated optical inspection (AOI) in high-precision manufacturing to autonomous mobile robots (AMRs).
Jetson modules pack unbeatable performance and energy efficiency in a tiny form factor, effectively bringing the power of modern AI, deep learning, and inference to embedded systems at the edge.
Compare this to your average building controller… most of which have less horsepower than the flip phone I had in high school.
The AI engine understands at a physics level how buildings components work, and it can run simulations of building systems, taking into account complex interactions, and making control decisions to optimize operation. Next, the Hive compares this optimal control path to actual sensor data, applies machine learning, and gets smarter about operating the building over time.
+ Troy’s (very technical and over my head) presentation on why buildings are a unique application for Machine Learning. He goes deep into how Passive Logic’s platform provides “control by definition”:
You define what a system is and then the system learns to control
And I enjoyed listening to Troy explain our industry to software developers:
If you guys, as computer science professionals, saw what building control looks like you would be terrified.
😂
TRUTH.
OK, that’s all for this week—thanks for reading Nexus!
As a reminder, please take the survey!
👋 Welcome to Nexus, a newsletter for people applying analytics and other smart building technology—written by James Dice.
If you’ve been forwarded this email, you can sign up for your subscription here:
This is an experiment, and I’d love your feedback. If you have thoughts, questions, ideas or tips, join the discussion on LinkedIn or hit reply.
We’ve been doing this Nexus thing for 3 months now. If it’s not too much to ask, I would like some feedback so we can keep improving it.
Please take this 2-minute survey so I can get a better sense for:
1. Your direct feedback of what you like/don’t like
2. How to provide more value to you and your business
The form doesn’t collect any personal details (i.e. email, etc.) and I’ve tried to keep it as sparse as possible. It will take no longer than two minutes... five if you want to write a really long love letter.
Oh yeah, one more thing: the survey has a big announcement...
🙏 Thank you for your support. 🙌
+ The latest LinkedIn discussion (with 70+ comments from you wise ones!):
I'd love some input from the experts on this one.
I recently audited the building automation system and analytics software at a local campus. Many of the owner’s #analytics (#KPIs, heat map #visualizations, #FDD, etc) are not fully populating and we wanted to figure out why.
We decided to start with one control loop—zone temperature control—and trace the issue from edge to analytics. Here’s the result of the audit:
Across campus, there are 17 distinct methods for accomplishing the same control loop. The diversity includes varying physical (input/output) and software (variables and programming) configurations.
In some cases, like the fan coil in the image, the points needed for analytics were not even exposed via BACnet as distinct points—they are hardcoded in the BAS programming.
Even if the points are there, the lack of standardization means that some of the identically-named points are actually doing different things— making semantic tagging (Haystack in this case) extremely difficult.
What are your strategies for dealing with this major obstacle to implementing analytics?
Last week, we introduced Tesla’s innovation strategy, explaining why they’ve been able to disrupt the auto industry.
In our industry, we have innovators, sure, but do we have disruptors? Do we have technology that building owners want as much as I want the new Tesla Model Y?
Consider this: when I read that article on Tesla, I only thought of one company attempting something similar—something big: Passive Logic.
Perhaps it was availability bias… because that same day I happened to meet with Troy Harvey, Passive Logic’s CEO. Troy and his team are simply thinking on a different plane. Where everyone else is thinking 1 to N, Passive Logic is thinking Zero to One.
Today we’ll introduce Passive Logic with three points that really stuck out to me:
First, the #1 way Troy has changed my thinking is described in his blog post on the user experience of existing controls solutions:
While we’re seeing a constant stream of band-aid solutions that bolt-on to our automation stack with hopes of fixing this old “black box” foundation, this is probably going to be unsuccessful.
Adding this new functionality, limited by the weak foundation, requires laborious effort — thus we call it “integration” not “installation!” The combination of a weak foundation with a low technology ceiling, together with laborious effort requirements, is a core source of so much dissatisfaction in the marketplace.
This point is obvious when you stop and think about it: most smart building solutions are actually smart overlays over a dumb foundation. The dumbness of the foundation is making everything we’re trying to do more difficult than it should be. Passive Logic wants to replace the weak link: the building automation system as we know it.
What do they want to replace it with? Deep and autonomous digital twins, of course.
Let’s unpack that:
What are deep digital twins? Put simply, the intelligence reaches down into every part of the system.
Functionally, they act as virtualized analogs of real-world objects, like zones, equipment, systems, and the physiological agents of human-comfort.
Because they are built on a physics-based ontology, these analogs aren’t just labeled, but actually understand what ‘kind’ of thing they are. The term ontology comes from the philosophical study of ‘being’, and is used by computer scientists to describe computing systems that can introspect.
Ontology is a framework that comprises the technological ‘nature of existence’ for an object in the world. The ontology, for example, provides a control system with the understanding of the fundamental physics of operation, how that operation interacts with the world around it, how its internal physics is organized, how the object interfaces with controls, the physical parameters of operation, and the meta-semantics of operation. The ‘meta-semantics’ of operation is the ontology translated into language or protocol.
What’s an autonomous digital twin? Picture a fully autonomous vehicle. Most smart building solutions today are analogous to a car’s cruise control. Some even resemble adaptive cruise control. That’s only level 1 out of 8 levels of an autonomous building as proposed by Passive Logic.
And, if Troy is correct, this replacement foundation will replace and render many of today’s smart building services and solutions obsolete.
I’m a little skeptical about this point, but I still haven’t been able to get it out of my mind. How much effort in this industry is simply not needed once the weak foundation is replaced?
I’ll be meeting with Troy again soon for round 2… What questions should I ask him? What are you skeptical about? Hit reply and let me know.
In the meantime, here are some links to dive deeper on Passive Logic:
+ Troy’s Interview with ControlTrends (YouTube version | Podcast version)—"the atom bomb of the industry"
+ How Passive Logic is bringing AI to the Edge (Invidia blog)—An intro to Passive Logic’s Hive supervisory controllers built on the Invidia Jetson chip.
Jetson modules power a range of applications that require various performance levels and prices—from AI-powered Network Video Recorders (NVRs) to automated optical inspection (AOI) in high-precision manufacturing to autonomous mobile robots (AMRs).
Jetson modules pack unbeatable performance and energy efficiency in a tiny form factor, effectively bringing the power of modern AI, deep learning, and inference to embedded systems at the edge.
Compare this to your average building controller… most of which have less horsepower than the flip phone I had in high school.
The AI engine understands at a physics level how buildings components work, and it can run simulations of building systems, taking into account complex interactions, and making control decisions to optimize operation. Next, the Hive compares this optimal control path to actual sensor data, applies machine learning, and gets smarter about operating the building over time.
+ Troy’s (very technical and over my head) presentation on why buildings are a unique application for Machine Learning. He goes deep into how Passive Logic’s platform provides “control by definition”:
You define what a system is and then the system learns to control
And I enjoyed listening to Troy explain our industry to software developers:
If you guys, as computer science professionals, saw what building control looks like you would be terrified.
😂
TRUTH.
OK, that’s all for this week—thanks for reading Nexus!
As a reminder, please take the survey!
Head over to Nexus Connect and see what’s new in the community. Don’t forget to check out the latest member-only events.
Go to Nexus ConnectJoin Nexus Pro and get full access including invite-only member gatherings, access to the community chatroom Nexus Connect, networking opportunities, and deep dive essays.
Sign Up