Home / Case Studies / Casting Machine
CASE STUDY / ALUMINUM COMPONENT MANUFACTURING
Casting Machine Monitoring in Aluminum Component Manufacturing
How can aluminum component manufacturers make cycle deviations and hidden production losses visible in high-pressure die casting? In this project, Novo AI WatchMen was used within a 147-machine production environment. The detailed casting scope covered 2 monitored HPDC machines, while the customer reported a 25.87% productivity improvement. Machine-state and cycle data helped make slower cycles, idle time, die changes, melt waiting, microstops and downtime visible.
Free PDF · No registration
High-pressure die casting: making cycle performance and hidden production losses visible.
+25.87%
higher productivity
Customer-reported result
147
production machines
Build years 2006–2019
15 min
sensor installation
Per machine in the project
In this case study Project · Implementation · Measures · Results · FAQ
THE PROJECT
At a Glance
Industry
Aluminum component manufacturing
Machine fleet
147 production machines
Machine generations
Build years 2006–2019
Operations
Operating model: 3 × 8-hour shifts
Technology
External Novo AI retrofit sensors + WatchMen
Focus
Cycle performance, idle time, die changes, melt waiting, microstops and downtime
THE CHALLENGE
Stable Casting Requires More Than a Running Machine
High-pressure die casting is cycle-based production. A machine can continue running while slower cycles, idle periods, die changes, material or melt waiting, microstops, automation delays and downtime reduce usable production capacity.
The challenge was therefore not only to determine whether the machine was running, but to understand whether it was producing stable cycles and where recurring time and cycle losses were occurring.
Cycle Performance
Compare actual productive cycles with realistic product- and die-specific targets.
Idle Time & Changeovers
Make waiting periods, die changes and product changeovers visible and consistently comparable.
Interruptions & Downtime
Reveal recurring microstops, melt waiting, automation delays and longer machine faults.
FROM MACHINE TO ANALYSIS
Sense. Interpret. Add Context.
Monitoring provides the physical machine and cycle timeline. Reliable casting analysis comes from validated machine states and cycles combined with the die, alloy, order and quality context needed to interpret deviations correctly.
01
Capture machine behavior
External Novo AI sensors capture physical machine behavior on existing die-casting equipment without requiring basic PLC or machine-control intervention.
02
Validate cycles and machine states
Edge processing and validation support cycle detection and the distinction between productive casting, idle periods, changeovers, microstops and downtime.
03
Add production context
WatchMen links machine states with order and production information. Component family, die, alloy, cavity configuration, automation and quality requirements can then be considered when investigating deviations.
EXTERNAL SENSORS
Casting Data Without PLC Access
External retrofit sensors capture physical machine behavior without requiring direct intervention in the machine control system for the basic monitoring layer.
WatchMen turns validated signals into machine-state and cycle information. This makes productive casting, cycle deviations, idle periods and recurring interruptions visible over time.Order, die, alloy, automation and quality context can then help explain why a particular deviation or production loss occurred.
TURNING DATA INTO ACTION
Turn Casting Deviations Into Practical Improvements
Monitoring shows where productive casting capacity is being lost. The next step is to investigate recurring cycle and time losses and verify whether process changes release usable casting capacity.
01
Improve cycle performance
Compare actual productive cycles with realistic targets for the relevant component, die and alloy. Repeated deviations can then be investigated in the context of machine behavior, automation and production conditions.
02
Reduce idle time and improve changeovers
Improve material readiness and next-order preparation while staging dies, programs, tooling and supporting tasks before the machine becomes available. This helps separate avoidable waiting from necessary changeover activity.
03
Reduce melt waiting, microstops and downtime
Separate material-supply delays, technical faults, automation-related interruptions and recurring short stops. Use the machine timeline together with production and maintenance context, implement corrective actions and then compare the same indicators again.
RESULTS IN CONTEXT
What Improved During the Project
REPORTED PROJECT RESULT
−34.72%
less idle time
In the modeled production scenario, idle time was reduced by 34.72%. The detailed before-and-after values and calculation basis are included in the complete case study PDF.
+1,300.46
additional productive machine-hours per year
Reported result: The customer reported a 25.87% productivity improvement. WatchMen helped make productive casting, cycle deviations and recurring losses such as idle time, die changes, melt waiting, microstops and downtime visible for systematic investigation.
Annual capacity estimate: The modeled improvement corresponds to approximately 1,300.46 additional productive machine-hours per year across the two monitored die-casting machines. This represents released casting capacity within the existing machine schedule rather than a full year of directly measured additional casting output.
Context: These figures relate to the project described. Starting conditions, product mix, shift model and the measures implemented affect the result. A reduction in time losses does not automatically mean an equally large increase in OEE.
GOOD TO KNOW
Questions About Casting Machine Monitoring
What was the scope of the project?
The broader production environment contains 147 production machines. Machine generations span 2006 to 2019.
What productivity improvement was reported?
The customer reported a 25.87% productivity improvement. Detailed cycle, idle-time and annual-capacity figures are modeled values used to interpret the reported project result.
How much idle time was reduced?
In the modeled production scenario, idle time was reduced by 34.72%. Detailed before-and-after values and the calculation basis are included in the complete case study PDF.
How much additional productive capacity was calculated?
The model estimates approximately 1,300.46 additional productive machine-hours per year across the two monitored die-casting machines. This is an annualized capacity estimate rather than a complete year of directly measured additional output.
Can cycle performance be monitored?
Yes. The case-study model evaluates productive cycle behavior against a defined target and uses cycle deviations together with machine states to identify where further investigation is required.
Can existing die-casting machines be monitored without PLC access?
Novo AI uses external sensors to capture physical machine behavior. The basic monitoring layer can therefore be implemented without requiring deep intervention in the existing machine control system.
THE COMPLETE CASE STUDY
Details to Support Your Decision
Download the English PDF with the project description, results and measurement notes.
Download the free PDF ↓APPLYING IT TO YOUR PRODUCTION
What Would You Like to Make Visible?
Tell us how many die-casting machines you operate, their approximate years of manufacture and your most important production question: cycle performance, idle time, die changes, melt waiting, microstops or downtime?
Together, we can identify suitable pilot machines and determine which machine states, cycle deviations and production losses should be made visible first.
Further reading: CNC Monitoring in Precision Tool Manufacturing · Understanding machine data acquisition: data and system boundaries · All Case Studies
Publisher: Novo AI GmbH. Source of the project information: the corresponding case study PDF. Definition and calculation: OEE based on availability, performance and quality.