These 3 steps will bring you to Condition-based Maintenance
Updated: Jun 19
As an item of Industry 4.0, ‘condition-based’ tooling maintenance (CBM) -- also known as ‘predictive’ maintenance (PdM) -- might seem daunting to manufacturers who aren’t prepared yet to implement it.
However, what companies need to fundamentally understand is that CBM boils down to 3 separate steps. You achieve these steps, you arrive at a CBM model. Easy, right?
1. Data Acquisition
First, you need to acquire the ‘right’ data; automatedly, and in real-time.
‘Right data’ means data regarding your toolings’ condition or health status. Condition data could be any number of things: the number of shots completed, cycle times, the duration of active operation, scrap rate output, temperature levels, pressure levels, and so on.
REQUIRES: IoT sensors for tracking and transmitting data to appropriate systems.
2. Data Analysis
Now that you’ve acquired your data, you need to analyze it to forecast tooling failure.
A fast and easy way of doing CBM data analysis is to compare the acquired data with predefined parameters. First, consult with your engineers and establish the known causes of tooling failure. Based on these consultations, create ‘IF X, THEN Y’ rules; if the acquired data exceeds these thresholds, then you receive an alert, helping you catch potential tooling failures early-on.
In the future, you could supplement this solution with Big Data analytics. AI and machine learning algorithms could crunch massive quantities of both real-time and history data, creating more accurate predictions.
REQUIRES: Dedicated analytics software that can accommodate AI and machine learning applications through future patches.
3. Automated Alerts and Dashboards
Analytics aren’t useful unless you can view them in an automated, visible way.
The analytics predictions should alert all parties related to toolings, in order to quickly resolve problems. Alerts should be sent out to factory managers, engineers, suppliers, etc. These alerts need to be automated and sent over a cloud or web-based dashboard for clear, informative viewing.
REQUIRES: A comprehensive alerts and dashboard system, accessible to tooling-related parties.
Why Should I Care?
“Better predictive maintenance using IoT can reduce equipment downtime by up to 50 percent and reduce equipment capital investment by 3 to 5 percent … In manufacturing, these savings have a potential economic impact of nearly $630 billion per year in 2025.” - Manyika, James, et al., “Unlocking the potential of the Internet of Things.” McKinsey & Company, 2015
Condition-based predictive maintenance is a hair’s breadth away. With three steps, manufacturers could benefit from the efficiency of CBM and transform their practices across the board.
Find out how eMoldino will guide OEMs to condition-based monitoring, guiding them step-by-step through all 3 of the steps outlined above. Contact us to begin the conversation today.