Advantech AIR-030
AI Inference System Based on NVIDIA® Jetson™ AGX Orin
Les caractéristiques
Présentation
Plus d'information
Voir les produits similaires
Imprimer la fiche produit
Demander votre devis
Votre liste de demandes de devis
PDF
Les caractéristiques
Présentation
Plus d'information
PDF
- Compact and high performance AI box
- NVIDIA® Jetson AGX Orin 64GB and 32GB Modules
- Wide range power inpute and wide operating temperature
- Multiple IO ports: LAN, DIO, COM, USB 3.2 and USB type C
- Versatile expansions with M.2 B key, M.2 E key, SD, PCIe x16(optional) support
- Support Linux Ubuntu 20.04 LTS and JetPack 5.0.1
- WISE-DeviceOn supported for quick AI deployment at scale
Powered by NVIDIA Jetson family and RTX, AIR series provides scalable AI inference performance or efficient retraining on a large scale at the edge.
Specifications
- Processor System
- CPU
JAO 64GB: 12-core NVIDIA Arm® Cortex A78AE v8.2
JAO 32GB: 8-core NVIDIA Arm® Cortex A78AE v8.2
GPU
JAO 64GB: 2048-core NVIDIA Ampere GPU with 64 Tensor Cores| Maximum Operating Frequency: 1.3GHz
JAO 32GB: 1792-core NVIDIA Ampere GPU with 56 Tensor Cores, Maximum Operating Frequency: 939 MHz
AI Performance Reference
JAO 64GB: Up to 275 Sparse TOPS (INT8)
JAO 32GB: Up to 200 Sparse TOPs (INT8)
Memory
JAO 64GB: 64GB 256-bit LPDDR5 DRAM
JAO 32GB: 32GB 256-bit LPDDR5 DRAM
Flash
64GB eMMC 5.1
Ethernet
- Interface
RJ-45
Controller
Intel® i225
Speed
3 x Gigabit Ethernet (10/100/1000 Mbps, LAN1&2 optional PoE support)
Display
- HDMI
1 x HDMI (Max. resolution 3840 x 2160 @ 60Hz)
IO Ports
- USB
4 x USB 3.2 Type A
1 x USB 3.2 Type C
OTG USB
1 x Micro USB (for system recovery only)
CANBus
1 x DB9
DI/DO
16 bit
COM
4 x RS-232/RS-422/RS-485
Audio
1 x Line-out
Expansion
- M.2
1 x M.2 2230 (E Key)
PCIe
1 x PCIex16 (Optional, signal: PCIe x 8)
Storage
- M.2
2280 1 x M.2 2280/3052 (B Key, signal: PCIe x2, USB3.0)
SD
1 x SD 3.0 slot
Power
- Power Supply voltage
9~36V
Power Type
ATX/AT mode, ATX default
Environment
- Operational Temperature
JAO 64G: -10 ~ 50 °C with 0.7 m/s air flow (non-throttling)
JAO 32G: -10 ~ 60 °C with 0.7 m/s air flow (non-throttling)
Operating Humidity
95% @ 40 °C (non-condensing)
Vibration
3 Grms @ 5 ~ 500 Hz, random, 1 hr/axis
Mechanical
- Dimensions (W x D x H)
200 x 220 x 74 mm
Weight
-
Mounting Support
Wall mounting
Operating System
- Linux
Ubuntu 20.04 LTS with JetPack 5.0.1
Software Support
- Software API
Edge AI Suite compatible
Certifications
- EMC/Safety
CE/FCC Class B, CB, UL, CCC and BSMI (No RED Certificate)
Ordering Information
| Part No. | CPU | VPU | Memory | Storage | HDMI | GbE | USB | CANBus | RS-232/422/485 | DIO | Power input | Operating Temperature |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AIR-030-B90A1 | Arm Cortex-A78AE | 1792 NVIDIA ® CUDA® cores and 56 Tensor cores | 32GB | 64GB eMMC 5.1 | 1 | 3 | 5 | 2 | 4 | 1 | 9 - 36 VDC | -10 ~ 60 °C |
| AIR-030-S30A1 | Arm Cortex-A78AE | 2048 NVIDIA® CUDA® cores and 64 Tensor cores | 64GB | 64GB eMMC 5.1 | 1 | 3 | 5 | 2 | 4 | 1 | 9 - 36 VDC | -10 ~ 50 °C |
Packing List
| Part Number | Description | Quantity |
|---|---|---|
| - | NVIDIA AI Inference System | 1 |
| - | Micro USB cable 40cm for system recovery | 1 |
| - | Simplified Chinese User Manuel | 1 |
| - | China RoHS | 1 |
Optional
| Part Number | Description |
|---|---|
| 96PSA-A230W24P4-3 | AC to DC adapter, DC 24V 230W, -20 ~ 60 °C |
| 1702002600 | Power cable 3-pin 183cm, USA type |
| 1702002605 | Power cable 3-pin 183cm, EU type |
| 1702031801 | Power cable 3-pin 183cm, UK type |
| 1700000237 | Power cable, 3-Pin 183cm, PSE type |
Clients qui ont dájà consulté cet article ont également vu