The Impact of Artificial Intelligence on Injection Molding | Technology and Business

The Impact of Artificial Intelligence on Injection Molding | Technology and Business
The Impact of Artificial Intelligence on Injection Molding 

How AI is changing injection moulding

By harnessing the vast amount of data produced in modern plastics processing facilities, artificial intelligence can improve the performance of machines.

The Industry 4.0 era of manufacturing relies so heavily on data-driven precision that artificial intelligence (AI) is playing an increasingly important role in harnessing that data to improve the performance of machines, including injection molders. 

AI in manufacturing encompasses a variety of technologies that allow machines to function with intelligence that emulates that of humans. Machine learning and natural language processing help machines approximate the human ability to learn, make judgments, and solve problems. Improved data efficiency keeps processes moving faster and more cost effectively.

AI is becoming more important as processors turn to automation

“AI is becoming increasingly important in mechanical engineering, not least because of the need to automate injection molding processes efficiently and flexibly despite ever smaller batch sizes and longer life cycles. product shorts,” said Werner Faulhaber, Director of Research and Development at Arburg. “Examples of AI application include automatic programming of robotic systems, repair of specific faults, and a 'smart' image processing spare parts system. Arburg is working to make injection molding smarter, step by step, ensuring that the machine continuously learns, remains stable and can even be optimized in the future.”

Arburg forms flexible and controllable production systems by combining machines, automation and patented IT solutions. The company's Gestica control system, with its intelligent assistant functions, is an integral part of those systems. “All Kuka six-axis robots, for example, have been equipped with the new Gestica user interface as standard,” Faulhaber noted. "This simplifies programming as well as monitoring, storage and evaluation of process data."

One application Arburg is working on is the automatic programming of its Multilift linear robotic systems. “The idea is that the operator simply enters the destination, like with a car navigation device, and the system automatically calculates the optimal route. For robotic systems, this means the operator simply enters the desired start and end positions, and the control system takes care of the rest.”

Wittmann Battenfeld, which has fully embraced Industry 4.0 connectivity in its injection molding and auxiliary machine portfolio in recent years, employs AI with its robots to monitor cycle times and control robot speeds outside the machine. of molding

The company's machine learning capabilities (HiQ Flow and CMS technology) will be on display at this year's K show from October 19-26 in Düsseldorf, Germany. The speed of return on investment can be as short as a few cycles with HiQ Flow, and the software can often be retrofitted to older injection molding machines equipped with a B8 machine control. A CMS Pro version will be available at a later date.

“The technology draws new conclusions from current parameters and thus gets smarter as it monitors performance,” said Christian Glueck, Product Manager. “We limit it to a methodical determination of parameters. Therefore, the time required to use the technology is minimal, as is the price.”

AI versus Machine Learning 

Comparing AI and machine learning, Glueck said, “AI actually requires a much higher time investment and consequently a higher financial investment. A large number of parameters of a running process must be recorded and the relevant parameters are determined on the basis of deviations. These are compared with the measurement data of the product.”

Based on factors such as material changes, ambient temperature, machine wear, tool wear, and other influences, “AI can determine which machine parameters need to be changed so that the product can be produced within of their quality tolerances. This can take months, as mistakes must first occur in order to learn from them.”

Wittmann co-financed such an evaluation program with the Montanuniversität Leoben university in Austria, "but we found that the time needed to make it viable for production had to be questioned because in addition to long-term investigation of the process, you also need the hand of necessary work to handle it.”

The company's eco-mode prevents wear and tear on the robot by ensuring it doesn't run faster than necessary, ultimately saving energy and maintenance costs. Offered as standard on many Wittmann robots, Eco-Mode "does not require special programming or interface with the IMM or operator/programmer," said Jason Long, National Sales Manager for robots and automation at Wittmann USA. "All the end user has to do is tell the robot how many seconds to return to the IMM before the mold opens."

Another Wittmann feature, Eco-Vac conserves energy by setting some parameters on the robot and allowing the robot to turn its vacuum circuits off and on. “The robot monitors the vacuum level of the circuit used to extract the part from the mold. If the robot detects that the vacuum has dropped to a level that could drop the part before being told, the robot will turn the vacuum on until it reaches the safe level again and then turn off.” This feature reduces the amount of compressed air each robot uses "and could save customers hundreds of dollars per year per robot."

Simply collecting data is not enough

As AI and machine learning are further harnessed to improve injection molding operations, simply collecting data is not enough to optimize processes, Faulhaber warned. “You also need the process expertise and domain knowledge. In the future, the evaluation of a lot of data directly in the control unit will offer additional added value.”

Arburg uses AI "to develop master models using the experience and data collected over the years on processes, materials and machinery," Faulhaber continued. “The client could then tune the provided master model ‘to the limit’ and optimize their processes. The in-house developed Gestica control system, the Arburg central computer system and the arburgXworld customer portal offer an advantage here.

“One of Arburg's medium-term goals is to develop a system for digital twins of custom injection molding machines. This will open up completely new possibilities for simulating the cycle and making energy predictions. Furthermore, the 3D views and installation drawings of the machine, stored in the arburgXworld customer portal and in the control system, help the operator,” said Faulhaber.

Source: plasticstoday.com, directnews99.site