Milacron, a leading industrial technology company serving the plastics processing industry, is announcing its latest data-driven developments in Industrial Internet of Things (IIoT) predictive capabilities available to M-Powered users later this year.
M-Powered is an industry-leading suite of IIoT applications for operators, managers, and service technicians. The new applications take M-Powered predictive capabilities yet one step further. Focusing not just on point-failure prediction, next-generation of machine learning algorithms is used to continuously quantify the impact of wear-and-tear. Three applications will be made available to manufacturers beginning in June 2020 with the assistance of the data science partners, ei3.
“Our data science team has crafted algorithms that give operators valuable insights into the inner workings of the Milacron machine; for the first time, it allows us to quantify the impact of wear and tear as it progresses,” said Dr. Stefan Hild, Director of Data Science at ei3. “Operators can then take smart decisions by weighing that cost against the cost of maintenance. This was only possible by close collaboration between our data scientist and the engineering team from Milacron. This is a true milestone for the industry.”
Predictive analytics provides unlimited pathways to leverage data science to track machine condition and advise operators on providing actionable knowledge when it comes to triggering maintenance actions. Three new applications are being adapted from extensive research and testing on Milacron machinery in hopes to go beyond the typical break-fix methodology currently happening at scale in injection molding and extrusion.
“One of the most important movements in the last few decades is the evolution toward lean manufacturing. As manufacturers evaluate and reform their operations to reduce waste, efficiency can reach new heights,” said Edward Jump, M-Powered IIoT Digital Analytics Leader at Milacron. “In real-world applications, true maintenance requirements are based on many variables. Through the adoption of machine learning and advanced analytics and AI, M-Powered can now monitor signals of impending failure. When combined, these are key indicators that allow manufacturers to deploy maintenance resources; improvements accrue to manufacturing in the form of cost savings and added efficiency.”
Three new applications are being adapted from extensive research and testing on Milacron machinery in hopes to go beyond the typical break-fix methodology currently happening at scale in injection molding and extrusion.
Screw Efficiency Analysis
 |
The plasticizing screw is an essential component that conveys a resin while generating and utilizing the mechanical and conductive energy necessary to melt the polymer and build a homogenous melt necessary to mold an acceptable part. With each unique application, this highly engineered component can be expensive and often comes with a long lead time. As wear of this component occurs and the flight diameters of the screw begin to deteriorate, the screw’s ability to efficiently convey material is reduced, consequently leading to increased recovery time, energy consumption, and increased melt temperatures.
As a result, productivity can be impacted as these conditions can translate into increased cycle times as well as potentially impacting part quality. For most manufacturers, wear occurs slowly and over a period of time, consequently, the deterioration of the process is also slow and over a period of time, therefore, making it oftentimes difficult to immediately detect and challenging to observe.
Our patent-pending system adopts an innovative energy-based assessment to provide awareness in the process. Its touch-free functions can yield insight on the screw’s health without adding sensors to the screw or barrel. This allows M-Powered users to proactively order a new screw and replace it before wear and tear has a great impact on each cycle.
This application is expected to be available to all M-Powered users this month.
Fill Case Analysis
 |
Another key component is the feed screw tip, based on its essential role as the link between the machine and the mold, containing a check ring or non-return valve critical to the molding process. For manufacturers, screw tips are a high wear item that often catches the brunt of the molding application but provides challenges to understanding and actively measuring wear-and-tear. This leading contributor has a direct impact on processing quality and repeatability, thus demands frequent replacement when compared to other injection end components.
M-Powered utilizes a proprietary shot-by-shot multivariate analysis to understand the state of the screw tip and indicate the effect of wear and tear on part quality, cycle time, and operating costs. This application will display and alarm when issues impact repeatability. Like our screw analytics, this is an evolving machine learning process, that accounts for distinct parts and operator adjustments.
This application is expected to be available to all M-Powered users in August.
Efficiency Report
 |
Intentional solutions can be derived from aggregated machine data and quantified wear-and-tear for manufacturers to summarize the operational efficiency of the machine to understand the impact on energy cost shot by shot. This resourceful application presents the leading variables in a single platform that increase the cost of production such as increased heating energy, extruder or injection energy, cooling time or recovery.
Using the application, operators can view a summary of their machine efficiency for each machine or their entire fleet in real-time. From this, costly offenders of cycle deviations can be corrected.
This application is expected to be available to all M-Powered users in September.
Milacron’s goal is to reduce unplanned downtime by providing solutions to assess wear and tear and predicting failures proactively. This ensures plastics processors operate at the highest levels of cost efficiency, quality and sustainability.
