Mitsubishi Electric > Case Studies > Mitsubishi Electric’s Fast Stepwise-learning AI Shortens Motion Learning

Mitsubishi Electric’s Fast Stepwise-learning AI Shortens Motion Learning

Technology Category

Analytics & Modeling - Machine Learning

Applicable Functions

Discrete Manufacturing

Use Cases

Manufacturing System Automation

Services

Software Design & Engineering Services

The Challenge

Due to declining workforces in ageing societies such as Japan, securing sufficient human resources is becoming increasingly difficult, which in turn is raising the demand for AI that can support efficient mechanized operations. New production facilities, however, present special challenges due to differences in pre-learned and actual shop environments, resulting in huge amounts of time devoted to teaching AI before it can be implemented on a full scale.

Log in to view content

The Solution

Mitsubishi Electric’s new AI automatically creates control programs for actual environments after short learning to support optimized operations.

Mitsubishi Electric has developed an artificial intelligence (AI) technology capable of fast stepwise learning using a simulator to efficiently complete motion learning in a relatively short time. The new technology combines the company’s latest proprietary Maisart compact AI technology and reinforcement learning, which enables machines to explore optimal actions through highly efficient trial and error. Supported with the company’s smart-control AI technology that adapts rapidly and nimbly to changing conditions, the new AI technology learns and responds to changes in actual environments in real-time to enable smooth machine operation.

Log in to view content

Operational Impact

[Efficiency Improvement - Productivity]
Productivity is equal to or higher than that of equipment adjusted by a skilled worker.

Log in to view content

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Plastic Spoons Case study: Injection Moulding

In order to meet customer expectations by supplying a wide variety of packaging units, from 36 to 1000 spoons per package, a new production and packaging line needed to be built. DeSter wanted to achieve higher production capacity, lower cycle time and a high degree of operator friendliness with this new production line.

Robot Saves Money and Time for US Custom Molding Company

Injection Technology (Itech) is a custom molder for a variety of clients that require precision plastic parts for such products as electric meter covers, dental appliance cases and spools. With 95 employees operating 23 molding machines in a 30,000 square foot plant, Itech wanted to reduce man hours and increase efficiency.

Fully Automated Visual Inspection System

Tofflon has developed a fully automatic machine that uses light to inspect vials, medicine bottles, or infusion containers for glass fragments, aluminum particles, rubber grains, hairs, fibers, or other contaminants. It also detects damaged containers with cracks or inclusions (microscopic imperfections), automatically removing faulty or contaminated products. In order to cover all production processes for freeze-dried pharmaceuticals, Tofflon needed to create an open, consistent, and module-based automation concept.

SAP Leonardo Enabling Rocket Science

At times, ULA has as many as 15 different operating systems dedicated to overlapping processes, such as rocket design, testing, and launch. Multiple systems created unnecessary costs and unwanted confusion among workers at offices, factories, and launch sites in different location. In order to improve collaboration and transparency during vital activities that directly influence mission success, ULA wanted to improve data sharing and streamline manufacturing processes.

IIC Smart Manufacturing Connectivity for Brown-field Sensors

The discrete manufacturing domain is characterized by a strictly hierarchical structure of the automation systems, commonly referred to as the automation pyramid. Data acquired by a sensor typically flows through an IO-module into a Programmable Logic Controller (PLC) which manages the local real-time control system. As all process data are concentrated in the PLC, re-programming the PLC and thus, implementing interfaces to access these data appear to be the natural choice to transfer them to the IT system. However, for brownfield installations this choice has proven impracticable for the following two reasons:In brownfield facilities, PLC usually operate within a once-specified environment and are rarely re-programmed. That is why the active staff is often not familiar with the code and lacks of the competence to modify the existing implementation in a reasonable amount of time.Furthermore, for cost reasons, any PLC was selected to exactly match the requirements of the environment within which it was intended to operate. That is why it cannot be assumed that a PLC will be able to support additional tasks such as communicating data through additional interfaces.

Human–Robot Control

Industry 4.0 is changing the way manufacturing industry operates. Increasingly more manufacturers are leveraging advanced technologies such as robotics and automation systems to improve productivity and efficiency. As a result, human–machine interfaces (HMIs) are becoming more important in their role in the digital connectedness of humans and machines. However, using the wrong HMI can lengthen development times and increase implementation costs.

© 2015-2024 IoT ONE Limited | Privacy Policy

Contact us

Let's talk!

Thank you for your message!
We will contact you soon.