For a number of years, IBM‘s Research Group has been striving to find solutions to some of these problems. By approaching the issue differently, they have just started to have success in industrial settings like the production of automobiles.
It is far more difficult than it first looks to try to divide computer work across several sites and then coordinate those different efforts into a coherent, useful whole. This is especially true when trying to scale up little proof-of-concept ideas into big productions.
Successful edge computing deployments are now the exception rather than the rule due to problems like the need to move massive amounts of data from one location to another, which ironically was supposed to be unnecessary with edge computing. These issues are just two of many that have contributed to this.
The business has been rethinking how data is evaluated at different edge locations and how AI models are shared with other sites in particular.
For instance, most businesses have begun to deploy AI-powered visual inspection models at auto production facilities to find manufacturing problems that may be difficult or expensive for humans to detect.
Utilizing tools properly, such as IBM’s Visual Inspection Solution with Zero D (Defects or Downtime) from the Maximo Applications Suite, may help automakers prevent defects and save a lot of money while maintaining the efficiency of their production lines.
That point has grown increasingly important lately, especially in light of the supply chain-related challenges that many auto companies have recently encountered.
To read our blog on “Three months after stopping operations in Russia, IBM initiates laying off workers,” click here.
