advanced manufacturing environment

Tools you can use today to build the plastics processing plant of tomorrow

Advanced technologies such as Artificial Intelligence (AI), Big Data and high-tech sensors are changing the dynamics of plastics processing by providing tools that learn from each other and make decisions to improve processes.

Plastics processing equipment with automated technology allows the equipment to communicate and process data with little or no human intervention. These embedded systems integrate operating technologies and information technologies to monitor and control physical processes.

A joint study by the Manufacturer’s Alliance for Productivity and Innovation and Deloitte published in September 2019 found that more than 85% of industrial manufacturers believe that smart factory initiatives using advanced technologies will be the main driver of manufacturing competitiveness. over the next five years. IDTechEx Research estimates that companies will spend more than $250 million by 2032 on industrial applications of printed and flexible sensors.

Sensitive material, process behavior

An example of advanced sensor applications in plastics processing is SensXPERT technology from Netzsch Process Intelligence in Germany. The technology analyzes material behavior with in-mold sensors that enable dynamic and adaptive production by reacting to material deviations, the company said. Customers can connect sensXPERT to existing manufacturing and control systems with standard interfaces, or use it as a cloud-based service.

Image courtesy of Netzsch Process IntelligenceSensXPERT Technology
SensXPERT technology analyzes material behavior with in-mold sensors that enable dynamic and adaptive production.

“The sensXPERT package is designed to handle all machines using modern industrial interfaces such as OPC-UA, PROFIBUS, PROFINET and, in the case of retrofitting older machines, analog and digital I/O.” SensXPERT Managing Director and CTO Dr. Alexander Chaloupka said plastics today. “Hardware connection is usually the easiest process and end-to-end communication must be defined in software to allow sensXPERT and machines to communicate with each other.

The system consists of several pieces of hardware, including two dielectric sensors installed in the mold and an Edge Device, which is hardware external to the press that collects the data measured by the sensors inside the mold and the process parameters of the press. herself.

Simulate, predict, analyze

The Edge Device evaluates hardware and software to produce models that capture minute deviations in materials and processes. The resulting algorithms simulate, predict and analyze the behavior of materials on individual machines. The algorithms’ ability to analyze huge amounts of data from molds in real time helps the system get smarter over time. If the algorithms flag a data set as different, the machine learning software alerts the technician monitoring the press that something is changing. This allows the operator to decide if action is required.

Key parameters such as glass transition temperature, pressure and cure requirements “drive” these process models, which are continually refined. This data-driven model is designed to improve the quality and efficiency of manufacturing processes.

SensXPERT said its technology will work with a wide range of materials – including thermosets, thermoplastics and elastomers – and methods – injection, compression and transfer molding; thermoforming; vacuum infusion; and hardening in an autoclave. A web application allows users to access the system remotely.

“We have historically grown our business with thermosets,” Chaloupka said. plastics today. “Due to the complexity of the chemical reaction, there is a strong demand for process transparency and automated control to avoid scrap production and work at process limits. In thermoplastic processing, similar to what we observe when thermosets solidify, we can see the crystallization and temperature behavior in the mold and use third-party sensors to also measure the pressure in the mold.

AI allows operators to see into the future

Trying to manually identify a plastics processing problem requires a focused team effort to pull data from many different sources, including oil analysis, vibration analysis, sensor data, and electrical tests. This data needs to be analyzed, which is a labour-intensive, tedious and time-consuming reactive exercise.

Harnessing AI to collect and analyze data in multivariate analysis can reduce the time it takes to discover problems, according to Dominic Gallello, CEO of SymphonyAI Industrial. Instead of reacting to a problem, operators can examine data in real time, which is more beneficial than looking at data after the fact. AI’s ability to assess a variety of factors and produce a comprehensive view of operations and processes also gives operators the insight they need to see the future, he said.

A key aspect of the factory of the future is the increased use of sensors capable of measuring all aspects of plastics processing, including temperature, vibration, speed, time, pressure, proximity, smoke and humidity. “But the data is not enough,” Gallello wrote. in a recent plastics today article. “It takes AI to gather, analyze, combine and evaluate data to produce meaningful and actionable insights. Together, AI and wireless sensors can collect and study enough data over days, weeks, and months to accurately predict hard-to-detect gear wear, early bearing wear, and other faults criticisms long before they occur. They can make accurate predictions using multidimensional models that far exceed what engineers can do with univariate models. And as advances in computer technology, sophisticated artificial intelligence, and machine learning provide more accurate results with consistent data, they also dramatically reduce the burden on people to act as detectives.

Processors apply only about 2% of available data

Plastics processors aren’t leveraging about 98% of the data they have about their operations, Gallello says. By using sensors, AI, physics, and embedded domain expertise, they can better understand their operations and processes.

According to Prashant Srinivasan, Director of AI Products at SymphonyAI Industrial, although standard in-line sensors are built into most plastic manufacturing machinery today, they are not always sufficient to obtain the highest levels of benefit from the machine. process optimization.

“As melting pressures exceed 150 MPa and temperatures frequently exceed 300°C, in-mold pressure sensing elements are exposed to harsh conditions in a corrosive and abrasive medium,” Srinivasan said. plastics today. “A number of new technologies, such as wireless thin-film piezoelectric sensors, are now available on the market. For temperature sensing, standard shielded thermocouples are subject to significant offset, making it desirable to consider installing IR-based temperature sensors. Likewise, for in-line quality measurements, advanced AI-based automated vision systems are now available and can be installed to achieve the highest quality control capability.

Programming robots without code

Sepro Group, a leader in the integration of injection molding machines and robots, is now working on “no-code” programming, with a robot controller using AI to optimize trajectories and manage obstacles.

At K 2022 in Germany, Sepro allowed stand visitors to reposition a simulated mold and other peripherals, then challenge Sepro’s artificial intelligence solution to calculate the best possible trajectory based on one of three objectives. main ones – maximum energy savings, minimum wear or fastest cycle time – is selected. The system calculates the ideal trajectories before the start of the cycle, without any code written by the operator.

Image courtesy of Seprointeractive cell at K 2022
Interactivity was a key focus for Sepro at K 2022 in Düsseldorf, Germany in October. Here is a demonstration cell that allowed visitors to choose the best human-machine interface to pilot a Sepro S5-15 Speed ​​robot through a series of movements.

Power saving mode reduces power consumption by up to 25% on certain paths, which is ideal for processors looking to reduce their carbon footprint. Minimal wear mode reduces stress on system components, extending life and reducing maintenance.

Also at K 2022, Sepro’s new centralized control software, Visual+, was at the center of a multi-stage production process that included a 110-tonne Milacron injection molding machine and two Sepro robots. The process included assembling toy sailboat components, inkjet printing, collecting production data, dimensional checking, packing the trays and delivering the finished boats to visitors from the stand at the using an autonomous mobile robot.

The new controller uses an open communication system that allows better synchronization of complex movements, integrated peripherals, data management and traceability. It can also communicate seamlessly with almost any brand of molding machine or secondary unit, the company said.

As an open system, it connects to the controls of molding machines and peripheral equipment using a single centralized and intuitive human-machine interface for more intuitive machine operation and improved user experience, said the society. It can collect large amounts of data from all connected systems, which can be used for process optimization, traceability and analytics to calculate overall equipment efficiency and other metrics, locally or in the cloud.

Don’t be left behind

Using sensors, AI, multivariate analysis and machine learning, manufacturers can harness the power of vast amounts of data to create models to predict product quality based on conditions. and process parameters. These models can be used to optimize and recommend settings for a given product to achieve the optimum quality and avoid scrap. They can also automatically learn from new data and adapt to aging machines and changing operating conditions. Manufacturers who can effectively utilize these high-tech tools will achieve new levels of efficiency.

#Tools #today #build #plastics #processing #plant #tomorrow

Leave a Comment

Your email address will not be published. Required fields are marked *