Machines producing precision components use factory automation equipment (FA) for their control. For example, computerised numerical control cutting machines (CNC) , electrical discharge machines (EDM), and industrial robotics. Yet to optimise agile production, operating parameters often need precise changes in response to workplace conditions. Integrating AI technology enables these micro adjustments and brings performance advantages.
In conventional manufacturing, skilled workers adjust the operating parameters according to various specifications like the required level of accuracy. But performing such manual adjustments requires labour and time, resulting in decreased productivity. Moreover, declining birth rates and ageing populations in many developed countries are resulting in a shortage of skilled workers capable of adjusting FA equipment.
In response, Mitsubishi Electric and Japan’s AIST developed a technology that uses AI to predict various changes in manufacturing processes during machining. Besides ending the need for time-consuming manual adjustments, the AI estimates the confidence level of ‘inference’ factors like machining errors. (An ‘inference’ is the prediction from the AI algorithm in use). After indexing the confidence levels of the AI inferences, it adjusts the FA equipment to ensure high reliability and productivity.
In-process learning adapts to changing work factors
The shapes of workpieces change during manufacturing, and this can lengthen manufacturing times or lower processing quality. Also, changes can vary by workpiece, making it difficult for FA equipment to learn in advance. Mitsubishi Electric’s innovative technology allows the AI to learn work factors during operation and then make real-time adjustments as needed. The technology also formulates physical phenomena, such as friction, and incorporates these mathematical expressions to enable learning during operation. This makes it possible to adapt to changing processing factors.
Improved Reliability
AI inferences must be dependable to ensure that real-time control of FA equipment leads to stable product quality and efficient processing. The new algorithm calculates the confidence level of inferences by learning the machine characteristics for each process and target device. By using this algorithm to control FA devices, the new AI ensures high reliability.
Early Beneficiaries of AI Technology
Robotics
As an example of the high-speed inference of Mitsubishi Electric’s AI control technology, the company developed a solution to estimate loads on robotic arms. The system uses various load parameters to calculate acceleration and deceleration speeds. From these, the AI function infers load values using information about the robot, such as motor current, joint angle, etc. As a result, robot operating time fell by 20% when using inferences. Moreover, the robot achieved more stable operation by adjusting motions when the confidence level was high.
Electric discharge machining (EDM)
Mitsubishi Electric adapted the algorithm to make automatic adjustments to an EDM engraving machine. The EDM positions an electrode close to the workpiece and generates an electric discharge to perform engraving. Debris produced during machining needs ejecting with the electrode. The volume of debris increases as processing proceeds. In the new solution, AI learns the state of debris collection and then adjusts the frequency of ejecting it. Tests have confirmed that machining time falls by up to 23% compared to processing without AI correction.
CNC cutting machines
They then developed an AI error-correction solution for CNC cutting machines. The AI estimates the changing machining error, or the difference between the cutting machine’s current position and the command value. This enables corrections even during dynamic machining, although only if the confidence level is high enough. Tests confirmed that machining accuracy improves by 51% compared to using error correction not supported with AI.
Mitsubishi Electric plans to incorporate its proprietary Maisart AI technology in factory automation equipment to improve manufacturing productivity. They expect the technology will lead to more stable, dependable, and productive operations, particularly in agile manufacturing.
