Smart manufacturing is expected to gain insights from sensors deployed in large numbers in modern factories. Because of the ability to reduce lag, edge computing can enable manufacturing processes to respond and change more quickly, enabling real-time insights and real-time actions from data analysis. This may include turning the machine off before it overheats.
A factory can use two robots to accomplish the same task. Two robots are equipped with sensors and connected to an edge device. Edge devices can predict whether one of the robots will fail by running a machine learning model. If the edge device concludes that the robot is likely to fail, it triggers an action to stop or slow down the robot. This will allow the plant to assess potential failures in real time. If robots can process the data themselves, they may also become more self-sufficient and responsive.
At the end of 2017, there will be 18 million state monitoring connections worldwide, which will grow to 88 million in 2025. Global industrial robot shipments will also increase from 360,000 units to 1.05 million units. It is estimated that by 2020, the global manufacturing connection will reach 12.5 billion, and the market size of the factory network is close to 50 billion US dollars.
In the industrial automation scenario, 5G can provide a delay of less than 1ms, a reliability of more than 99.9999%, and a connection of 100,000 devices per square kilometer, which can better meet industrial control needs. 5G features low latency, high reliability, and large connections. 5G network slicing and MEC enable mobile operators to offer a variety of value-added services, providing enterprises with remote control centers and data flow management tools to manage a large number of devices and software updates to these devices over the wireless network.