Why do we emphasize the importance of data ownership in the journey of digital transformation? Where’s why
Only with data figures, can we see the room for improvement, and only after we improved, can we make dynamic adjustments in the future.
In the post-COVID era, companies are paying more attention to data reliability, and the transformation should be based on data management. Last week, we mentioned the importance of data collection under the topic of data ownership. Now, let’s dive into the discussion of data application, through the perspective of 4M1E.
4M1E refers to Men, Machines, Materials, Methods, and Environment. These are the five key elements of manufacturing management. Through proper configuration and control, factories need to avoid errors in these five major areas, including long cycle time, machine malfunction, wrong materials, poor SOP, and high-risk working environments. AI Vision provides a complete and well-understood integration platform and helps IE engineers collect data accurately in every moment of ate production line so that factories have the most intuitive and useful data in these five major areas.
Men: Cycle Time Recording
AI vision captures each cycle time more accurately than an IE engineer. The start-to-start or end-to-end technology, recording individual workstation cycle times also better meets the needs of engineering teams.
Knowing the exact timing of each station allows for better management of production line personnel.
If the AI registers a single excessive operating time, we can assist the operator by providing training, or expanding headcount of the line.
A more advanced application is to set up a system that records the cycle time of each operator. In this case, when someone is absent, the IE engineer can find a substitute with the same ability, to ensure the production line will run smoothly as usual.
Machine: Downtime Analysis
Factory managers can know whether an operator has left his post or not through the alert, but what does this have to do with the machine?
Humans and machines have to cooperate to create value.
An idle machine will not only be in danger of breaking down, but more importantly, it will only increase energy waste. Through vision, AI can identify the working & unworking times of the machine to avoid the situation.
Material: Raw Material Management
AI vision can be further integrated with IoT and upgraded to AIoT. In this way, we can have a well-established management platform for raw material inspection and ordering.
Method: SOP Management
The engineering team can take the accurate values provided by AI as a strong reference when it comes to SOP optimization.
IE team can also review the process in a single station. What is causing a long operation time? Is the SOP itself not human-friendly enough, or other issues?
Having accurate values also means that there is a more favorable reference in hand. This help assists future roadmap setup and decision-making.
Environment: The “Health Check”
Environment refers to everything related to the workspace, and the information provided by AI not only benefits the production line but also improves the quality of the entire work environment.
The round-the-clock operation of the AI is a blessing to the 24-hour production line. IE engineers do not have to schedule multiple shifts to supervise the production line.
Through AI vision, we can also understand how to improve the working environment. For example, to see if there is external interference disturbing operators.
After implementing digital tools
In the aforementioned applications, especially in the Man and Method aspects of 4M1E, from the management of the operator to the line balancing, these can all make full use of data. There are too many digital transformation tools for companies to choose from, and the key to success is to introduce the right one and use them “as your support.”
Meanwhile, in a highly competitive environment, time is precious, and “result-oriented” is how manufacturers play the game. After the imputment of digital tools, what kinds of goals can we achieve?
Next week, we will discuss how high-performance, high-yield, and high-resilience smart factories include AI vision as a “factory manager” to build data ownership and achieve lean manufacturing.