Line 25: Line 25:
The cloud or on-premise backend will include standard backend compute resources, plus specialized compute resources for AI model training. These can be, for examples, GPUs (Graphics Processing Unit used for AI), TPUs (Tensor Processing Unit), or other AI accelerators.
The cloud or on-premise backend will include standard backend compute resources, plus specialized compute resources for AI model training. These can be, for examples, GPUs (Graphics Processing Unit used for AI), TPUs (Tensor Processing Unit), or other AI accelerators.


Setting up the supply chain for such a wide breath of different IT and other hardware components can be quite challenging. This will be discussed in more detail in the [[Sourcing_and_Procurement|sourcing]] section.
Setting up the supply chain for such a wide breadth of different IT and other hardware components can be quite challenging. This will be discussed in more detail in the [[Sourcing_and_Procurement|sourcing]] section.


[[File:HW Product Example.png|800px|frameless|center|Hardware for smart, connected product]]
[[File:HW Product Example.png|800px|frameless|center|Hardware for smart, connected product]]

Revision as of 20:45, 28 August 2021

More...More...More...More...More...More...AIoT Framework

AIoT hardware (& physical product components)

AIoT hardware includes all the physical components required to build an AIoT product or retrofit solution. For the retrofit solution, this will usually include sensors, as well as edge and cloud (or on-premise) compute resources. Most retrofit solutions will not include actuators. Products, on the other hand, must not only provide the IT-related hardware plus sensors, actuators and AI compute resources, but also all the mechanical components for the product, as well as the product chassis, body and housing. Finally, both AIoT products and solutions will usually require specialized IT hardware for AI inferencing and AI training. The concepts developed for Cyber Physical Systems (CPS) will also be of relevance here. The following will look at both, the AIoT product and retrofit solution perspective, before discussing details of the hardware requirements and options for edge/cloud/AI.

Smart, connected products

The hardware for a smart, connected product must include all required physical product components. This means that it will not only include the edge/cloud/AI perspective, but also the physical product engineering perspective. This will include mechatronics, a discipline combining mechanical systems, electronic systems, control systems and computers.

In the example shown here, all hardware aspects for a vacuum robot are depicted. This includes edge IT components like the on-board computer (including specialized edge AI accelerators), connectivity modules, HMI (Human-Machine Interaction), antennas, sensors and actuators like the motors, plus the battery and battery charger. In addition, it also includes the chassis and body of the vacuum robot, plus the packaging.

The cloud or on-premise backend will include standard backend compute resources, plus specialized compute resources for AI model training. These can be, for examples, GPUs (Graphics Processing Unit used for AI), TPUs (Tensor Processing Unit), or other AI accelerators.

Setting up the supply chain for such a wide breadth of different IT and other hardware components can be quite challenging. This will be discussed in more detail in the sourcing section.

Hardware for smart, connected product

Smart, connected (retrofit) solutions

Hardware for smart, connected solution (retrofit)

Edge node platforms

Edge Node Platforms

Sensor edge nodes

Edge sensor nodes

AI edge nodes

AI Edge Nodes

Putting it all together

Putting it all together