THANK YOU FOR SUBSCRIBING
Manufacturing Technology Insights | Monday, October 25, 2021
For a fully mature Industry 4.0 implementation in the metal fabrication industry, the fabricators must go through some steps and create a solid foundation.
FREMONT, CA: For years, the terms Industrial Internet of Things, machine learning, artificial intelligence, and Industry 4.0 have circulated in the trade and public press. They appear to be the future. Automation will become autonomous, self-learning, and self-correcting, while humans will manage exceptions—process difficulties and rework-and feed that knowledge back into the system, which will learn, improve, and make errors increasingly fewer.
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
To implement Industry 4.0 in metal fabrication, the industry must go through six steps. Each step is built based on the previous one. The more solid the foundation, the more effective, even revolutionary, the final steps may be.
Step 1: Lean manufacturing
The first stage is to develop lean production and quality standards. This encompasses not only 5S but also end-to-end process inspection. Fabricators are paid for the products they ship, not for machine uptime. As a result, the faster those products move from raw materials to the loading dock, the better. Raw material handling, material inspection, and even vendor interactions should all be part of lean processes and procedures. When a shop begins to acquire and analyze process data without adhering to the standards of lean manufacturing, the result is an essentially inconclusive and extremely broad bell curve.
Step 2: Connectivity and digitization
Step 2 will go into the specifics of process monitoring and the path to autonomous operation. Multiple sites for OEE measurement exist on automated devices, dividing a bigger process into its constituent components. This could involve material loading and unloading, as well as other aspects of the laser cutting head's behavior, in the case of a laser FMS. The more effective the upper levels become, the more robust step 2 is. If the measures are incorrect or insufficient, everything else becomes difficult, if not impossible.
Step 3: Information
The analysis can relate good-part and bad-part information to other process information after the data has been processed, contextualized and converted into actionable knowledge. The goal is to reduce the number of unknown parts, raise the number of good parts, and reduce the number of poor parts.
Step 4: knowledge
Step 4 begins as a manual process that becomes more automated as a result of machine learning. Information can be recorded in a database or other system so that others can access it and apply the solution to similar challenges. Eventually, the automated operation takes on autonomous characteristics. The more knowledge a system has, the more machine learning can be used to automate it.
Step 5: Prognosis
Once a production unit has achieved machine learning, it will be able to observe the curves of its own progress. A decent prognosis will tell the manufacturer if the situation is growing worse, and if so, when it will get bad enough that parts will start to fail.
Step 6: complete autonomy
This stage provides a concept of what a fully mature Industry 4.0 implementation may look like in a fabrication facility. Popular depictions of a smart manufacturing plant with connected machinery include fabrication equipment interacting across their whole value streams, with data flowing from laser cutting to bending to hardware insertion and final assembly.
More in News