Hopper

Quality Optimizer

Increasing product quality

Hopper addresses the product quality created by automated production equipment. The Process Parameter Recommender generates situational recommendations for best-possible machine settings under the prevailing production conditions in order to keep scrap and cycle time as low as possible. With the Recipe Benchmark, the machine settings are identified for producing highest possible output under consideration of the general conditions. Hopper significantly increases the rate of good parts produced per hour, for example in elastomer, thermoplastic and thermoset injection molding and for materials that are difficult to process, e.g. post-consumer plastics, recyclates or highly hygroscopic materials.

Which problems does Hopper tackle?

High scrap rates depending on current raw material

Varying cycle time due to individual machine settings and constant changes

Intransparency of best-fitting SET parameter tuning

Lack of efficiency in 24/7 production

hopper_app
Operators are provided with situational recommendations for best-possible machine settings via mobile devices.

Which benefits does Hopper, the quality optimizer deliver?

Increase in good parts ratio by significant scrap and cycle time reduction

Data analysis on material, production environment and machine

Precise parameter adjustment recommendations based on all influencing factors on the process

Predicted production rate & predicted scrap ratio

Situational and automated recommendations available on smartwatch, smartphone and browser

Features & functions

  • Automated recommendations for optimized process parameters

    Analysis of machine processes on signal-level based on high frequency live data of various sources

  • Independent from machine (type)

    Comparison of similar machines on a very detailed machine component level

  • Already existing data base

    Deduction of optimization actions for each real machine to reduce cycle times

  • Mobile usage on the shopfloor

    Constant monitoring of machine sub-process behavior with notification of anomalies for maintenance department

Letting machines learn from eachother

The AI project “DarWIN”, a cooperation between plus10 and the SKZ, was all about learning detailed behavior models of injection molding machines on the basis of high-frequency machine data. Through the transferability of pre-trained machine learning models, individual machines can learn from each other. This means that behavior models of a specific machine do not have to be completely relearned each time, but are only adapted to the machine and the product currently being run in a small adaptation phase. These behavior models suggest optimized process parameters for the next machine cycle in order to produce in the shortest cycle time and without scrab under the currently prevailing conditions.

From left to right: LTR Dr. Thorsten Thümen of Sumitomo (SHI) Demag, Felix Georg Müller (plus10), Christoph Mussauer (SKZ), Marco Fischer and Melanie Rohde of Sumitomo (SHI) Demag; Source: Sumitomo (SHI) Demag

Interested?
Get a live demo of Hopper!