Standard operating procedures (SOPs) for the manufacturing industry are created to optimize product quality and cycle time, as well as to protect workers from dangers. However, human error is the major failure factor of complying SOPs. Thus, continuous procedure auditing and improvement are the keys for implementing SOPs successfully.
Traditionally, industrial manufacturers audit SOP compliance by manual monitoring. Keeping track of every step performed by each operator is too time-consuming to implement through all the production lines. This has led manufacturers to seek automated solutions.
“Display assembly requires high standardization to ensure the product quality. We need a solution to keep an eye on every movement on the assembly line all the time. ADLINK utilizes AI smart cameras and behavior analysis deep learning algorithms to take care of these requirements.” said by the assembly supervisor of a worldwide leading display manufacturer.
MonitoringConsistency
The judgement of manual monitoring varies among different production managers. Being a human, managers may lose focus on monitoring repeated assembly procedures over time.
MonitoringConsistency
The judgement of manual monitoring varies among different production managers. Being a human, managers may lose focus on monitoring repeated assembly procedures over time.
MonitoringFrequency
A production manager can only monitor a few operators at a certain workstation during a limited time period. Incomplete data of the workflow may impair the optimization of production procedures.
MonitoringFrequency
AI vision can continuously monitor every step of assembly, all the time. Production managers can shift their valuable time to do more productive tasks. The comprehensive monitoring is also helpful for identifying the operators who need further training to improve cycle time.
ComplianceAnalysis Time
Manual monitoring means it takes time to consolidate all the observed data and then conduct analysis. The delayed response to amend incorrect procedures may lead to quality issues, lower productivity or even workplace accidents.
ComplianceAnalysis Time
Real-time analysis of AI vision helps production managers respond to incorrect procedures immediately, saving rework costs and material losses. Additionally, it also can prevent operators from dangers when operating with incorrect procedure.
NEON integrates Intel® Movidius™ or NVIDIA® Jetson™ AI vision processing cores, a wide range of image sensors, optimized OS, and rich I/O for vision applications in a palm-sized chassis to minimize cabling complexity and installation space requirements.
In addition to strict validation tests for EMC, ESD, shock, vibration and thermal dissipation, NEON also supports IP67 for harsh industrial environments.
NEON is pre-installed with optimized operating system, software, and Edge Vision Analytics (EVA) SDK. EVA SDK supports NVIDIA® TensorRT™ and Intel® OpenVINO™ AI inference engines, as well as field-ready application plugins for streamlining AI vision project development time.
ADLINK has verified the performance of all possible combinations of neural networks and AI accelerators. The performance benchmarks are available upon requests to optimize customers’ applications.
|
NEON-1000-MDX 
|
NEON-2000-JT2 
|
NEON-2000-JT2-X 
|
NEON-2000-JNX 
|
|
| Computing Platform |
Intel® Movidius™ Myriad™ X MA2485 |
Navid® Jetson™ TX2 | Navid® Jetson™ Xavier NX | |
| Processor | Intel Atom® x5-E3930 | ARM® Cortex-A57 and NVIDIA Denver 2 |
6-core NVIDIA Carmel ARM®v8.2 64-bit CPU |
|
| GPU | - | 256-core NVIDIA Pascal™GPU | 384-core NVIDIA Volta™GPU with 48 Tensor Cores |
|
| VPU | Intel® Movidius™ Myriad™X MA2485 |
- | - | - |
| Memory / Storage |
4GB / 32GB eMMC | 8GB LPDDR4 / 32GB eMMC (integrated with TX2 module) |
8GB LPDDR4 / 32GB eMMC (integrated with TX2 module) |
8GB LPDDR4 / 16GB eMMC (integrated with NX module) |
| Image Sensor |
ON Semiconductor AR0134, 1.2M resolution, H1280 x V960, 54 FPS e2v EV76C570, 1.9M resolution, H1600 x V1200, 60 FPS ON Semiconductor MT9P031, 2M resolution, H1920 x V1080, 30 FPS ON Semiconductor MT9P031, 5M resolution, H2592 x V1944, 14 FPS |
|||
| Ingress Protection |
- | - | IP67 with M12 connector |
- |
| Dimension (H x W x D) |
123.3x77.5x66.81mm | 123.3x77.5x66.81mm | 137.7x79.5x122.85mm | 123.3x77.5x66.81mm |
