China Railway Design Group Co., Ltd. (CRDC), formerly China Railway Third Survey and Design Institute Group Co., Ltd. (CRTSDI), is the sole design enterprise affiliated with China State Railway Group Co., Ltd. Established in 1953 and headquartered in Tianjin, it is a large enterprise group primarily engaged in engineering survey, design, consulting, supervision, EPC (Engineering, Procurement, and Construction) contracting, and product industrialization for railways, urban rail transit, highways, and other projects. It holds a Class A comprehensive engineering design qualification certificate and is one of the first high-tech enterprises recognized by the state. Its comprehensive strength ranks among the top in the industry. In the 2022 ENR rankings, it was ranked 37th among the Top 150 Global Design Firms, 103rd among the Top 225 International Design Firms, 35th among the Top 80 Chinese Contractors, and 5th among the Top 60 Chinese Engineering Design Firms.

Bridge structure safety monitoring involves collecting key parameters such as deformation, stress, and environmental factors at critical structural points of the bridge. These are transmitted to a platform via an edge computer with a 5G/4G industrial wireless gateway BMG700, enabling real-time monitoring, statistical analysis, anomaly alarming, and remote management of bridge structure safety. It achieves 24-hour real-time monitoring: fully automated online monitoring of bridge deformation, stress, environment, etc., to grasp the overall operational status of the bridge in real-time. Automatic Report Push: Monitoring results are released in real-time, and monitoring reports are regularly pushed to users. Multi-level Tiered Warning: When data is abnormal, the system triggers a corresponding three-level alarm mechanism, notifying users immediately via SMS, fax, broadcast, and other forms. Emergency Response Handling: Relevant solutions are directly retrieved from an expert database, and measures such as personnel intervention and road closures are promptly taken to eliminate safety hazards in their infancy. Structural Trend Analysis: Quantitative safety evaluation of bridge structures and safety analysis of monitoring indicator data enable structural stability trend analysis. Provision of Reference Basis: Long-term stable storage of monitoring data provides analogous references for future engineering design and construction of similar projects.

1. Product Overview

The XM-AIBOX-16 Smart Edge Analysis All-in-One Machine is a high-performance, low-power edge computing product. Equipped with the domestic TPU chip BM1684, its INT8 computing power reaches up to 17.6 TOPS. It can process 16 channels of high-definition video simultaneously and supports hardware decoding of 32 channels of 1080P HD video and 2 channels of encoding.

This product highly integrates high-precision AI intelligent algorithms based on computer vision and deep learning networks, as well as a video intelligent comprehensive management platform. The AI intelligent algorithms cover various scenarios such as parks, communities, construction sites, and campuses, and can be combined and configured on demand according to the scene. The video intelligent comprehensive management platform supports front-end device management, real-time video preview, alarm push, evidence capture, online algorithm loading and optimization, data situational analysis large screen display, etc. The device is easy to operate and plug-and-play. It also has rich northbound API interfaces, enabling upper-layer business application platforms.

1. Product Features

Ultra-High Performance Computing and Codec Capabilities

Supports up to 17.6 TOPS INT8 peak computing power or 2.2 TFLOPS FP32 high-precision computing power;
Supports full-process processing of up to 16 channels of 1080P HD video;
Supports hardware decoding of up to 32 channels of H.264/H.265 1080P@25FPS video;
Supports hardware encoding of up to 2 channels of H.264/H.265 1080P@25FPS video.

Rich Built-in AI Algorithms

Built-in with over 30 AI algorithms, supporting free matching and custom combinations;

(Supports Person Structuring / Face Recognition / Vehicle Structuring / License Plate Recognition / Flame Detection / Smoke Detection / Smoking Detection / Phone Call Detection / Mobile Phone Usage Detection / Mask Non-compliance Detection / Personnel Absenteeism Detection / Personnel Sleeping on Duty Detection / Person Fall Detection / Personnel Electrostatic Discharge (ESD) Detection / Area Occupancy Counting / Insufficient Area Occupancy / Area Over-occupancy / Abnormal Area Occupancy / Area Intrusion Detection / Work Uniform Detection / Hard Hat Detection / Reflective Vest Detection / Electric Bicycle Detection / Standardized Parking (Illegal Parking) / Entrance/Exit Passenger Flow Statistics / Perimeter Crossing Intrusion / Personnel Cross-border Detection / Loitering Detection / Fire Lane Occupancy / Fire Escape Route Occupancy / Waste Not in Bin Detection / Overflowing Bin Detection / Waste Disposal Reminder / Camera Abnormal Displacement Detection, and other algorithms)

Each video channel supports up to 3 AI analysis tasks running simultaneously;
Supports up to 16 video AI analysis tasks running simultaneously; if more than 16 AI analysis tasks, they can be analyzed in a polling manner.

Rich Interfaces, Flexible Deployment

Supports rich interfaces: 1000M Ethernet port, USB3.0/USB2.0, HDMI, RS-485, RS-232;
Supports wide operating temperature environment from -20℃ to +60℃;
Supports IP30 protection level, and fanless heat dissipation (subject to specific models);
Adapts to and supports SATA storage, with up to 2TB storage capacity (subject to specific models);
Optional support for LTE wireless backhaul function (subject to specific models);
Northbound Interfaces: Supports HTTP protocol, MQTT protocol, GB28281
Southbound Interfaces: Supports GB28281, Onvif, RTSP

High Reliability, Encryption Protection

High-capacity eMMC supports development of master/backup partitions;
Supports abnormal fault alarm and protection handling mechanisms;
Supports programmable encryption chip for privacy information protection.

Easy-to-Use Toolchain, Flexible Development

One-stop deep learning development toolkit, Sophon SDK;
Supports mainstream deep learning frameworks such as Caffe/DarkNet/TensorFlow/PyTorch/MXNet/ONNX/PaddlePaddle;
Supports mainstream network models for classification and detection, and custom operator development;
Supports Docker containerization for rapid deployment of algorithm applications.

1. Technical Specifications

Specifications

Model

XM-AIBOX-16

Technical Specifications

Chip

TPU

BM1684

CPU

8-core A53@2.3GHz

AI Computing Power

INT8

17.6 TOPS

FP32

2.2 TFLOPS

Video/Image Codec

Video Decoding Capability

H.264/H.265: 1080P @960fps

Video Decoding Resolution

8K / 4K / 1080P / 720P / D1 / CIF

Video Encoding Capability

H.264/H.265: 1080P @50fps

Video Encoding Resolution

4K / 1080P / 720P / D1 / CIF

Image Encoding/Decoding Capability

480 frames/sec@1080P

Max Image Decoding Resolution

32768 * 32768

Memory and Storage

Memory

12 GB

eMMC

32 GB

External Interfaces

Network Port

10/100/1000Mbps Adaptive *2

USB

USB3.0 *2

N/A

Storage

MicroSD *1

Display

HDMI *1

N/A

Serial Port

RS232 *1 / RS485 *1 / Custom I/O

Extended Storage

SSD (Optional)

2TB (Optional)

N/A

Wireless Functionality

4G/5G Wireless Module (Optional)

Mini-PCIe 4G Module

Antenna (Optional)

SMA Female *2 (Wi-Fi)

SMA Female *4 (5G)

SIM

Standard SIM Card Slot

Wireless Functionality (Non-Optional)

5G Wireless Module

M.2 5G Module

Physical Specifications

Dimensions

LWH

188 mm * 148 mm * 44.5 mm

Power Supply and Consumption

Power Supply

DC 12V

Typical Power Consumption

≤23.5W

≤19W

Note: Hard drive and wireless functionality are optional features, not standard product configurations. Typical power consumption does not include the power consumption of the hard drive or wireless module.