Due to the proliferation of Industrial IoT applications, a staggering number of industrial devices are connected to the Internet and this number continues to grow year after year. According to an International Data Corporation report in 2019, the number is expected to reach 41.6 billion endpoints in 2025. What’s even more mind-boggling is how much data each device produces. A Harvard Business Review study has concluded that “less than half of an organization’s structured data is actively used in making decisions and less than 1% of its unstructured data is analyzed or used at all”. Consequently, businesses and industry experts are turning to artificial intelligence (AI) and machine learning (ML) solutions for their IIoT applications to gain a holistic view and make smarter decisions more quickly.
The Artificial Intelligence of Things (AIoT) refers to the adoption of AI technologies in IoT applications for the purposes of improving operational efficiency, human-machine interactions, and data analytics and management. For example, computer vision or AI-powered video analytics are being adopted by more and more businesses for classification and recognition capabilities in their applications. From data reading in remote monitoring and preventive maintenance, to identifying vehicles for controlling traffic light signals in intelligent transportation systems, to indoor/outdoor patrol robots and agricultural drones, to automatic optical inspection (AOI) of tiny defects in golf balls and other products, computer vision and video analytics are unleashing greater productivity and efficiency for industrial applications.
In many real-world situations, especially highly distributed systems located in remote areas, constantly sending large amounts of raw data to a central server might not be possible. In order to reduce latency, reduce data communication and storage costs, and increase network availability, solution providers and application architects are moving AI and machine learning capabilities to the edge of the network to enable more powerful preprocessing capabilities directly in the field. Indeed, by connecting your field devices to edge computers equipped with powerful local processors and AI, you no longer need to send all of your data to the cloud for analysis.
Choosing the Right Edge Computer Makes All the Difference
AIoT edge computing essentially enables AI inferencing in the field rather than sending raw data to the cloud for processing and analysis. In order to effectively run AI models and algorithms, industrial AIoT applications require a reliable hardware platform at the edge. When choosing your edge computing solution for AIoT, you may need to consider the processing requirements for different phases of the AI implementation and the environment in which the computers are deployed.
Since the three phases in building an AI edge computing application—Data Collection, AI Model Training, and AI Inferencing—use different algorithms to perform different tasks, each phase has its own set of processing requirements. Depending on the complexity of the data collected, the computing platforms used in data collection are usually based on Arm® Cortex® or Intel® Atom®/Core™ processors. AI model training requires advanced neural networks and resource-hungry machine learning or deep learning algorithms and hence are typically done using cloud-based services and tools. However, they must be deployed on edge computers that have a conversion tool to convert the trained model to run on specialized edge processors/accelerators, such as Intel® OpenVINO™ or NVIDIA® CUDA®. AI inferencing includes several different edge computing levels, each with its own set of requirements.
You will also need to consider the physical location where your application will be implemented. Industrial applications deployed outdoors or in harsh environments—such as smart city, oil and gas, mining, power, or outdoor patrol robot applications—should have a wide operating temperature range and appropriate heat dissipation mechanisms to ensure reliability in blistering hot or freezing cold weather conditions. Certain applications also require industry-specific certifications or approvals, such as fanless design, explosion proof construction, and vibration resistance. And since many real-world applications are deployed in space-limited cabinets and subject to size limitations, small form factor edge computers are preferred. Moreover, highly distributed industrial applications in remote sites may also require communications over a reliable cellular or Wi-Fi connection. Another consideration is that redundant wireless connectivity with dual SIM support may also be needed to ensure that data can be transferred if one cellular network signal is weak or goes down.
To learn more about deploying edge-computing platforms for AIoT in real-world industrial applications and for example cases, download our AIoT white paper.