The goal of the project is to keep the manufacturing process for recognized European automotive manufacturer running smoothly and preventing problems that often arise with the robots moving pallets around.
Most manufacturing processes are automated with minimal human involvement. Machines have limitations, though, and cannot detect or fix anomalies such as incorrect pallet placement.
Our work in preventing these errors saves the customer money on repairing broken parts caused by these accidents. Artificial intelligence provides continuous monitoring for the robots in place of human supervision.
Our technology allows our operators to detect machine incidents in time, preventing further loss and making sure the manufacturing process runs smoothly.
At its core, this project primarily involves monitoring the robots automatically picking up pallets and moving them from place to place. Sometimes the pallets get stuck together, which the robot cannot detect, causing damage to the pallet or robot.
Neuron soundware technology prevents this damage and avoids the need to replace expensive robots. We installed microphones at certain locations to record data and industrial IoT devices (nBoxes) to send incident warnings as well as visual and acoustic signals on-site.
“In order to provide the customer with information for instant decisions, we opted for neuron networks, which learn from acoustic data to recognise the noise made by a falling pallet. The longer the neuron network continues learning, and the more times it captures this noise, the more data will be available for improving the learning process and error detection accuracy,” says Pavel Konečný, CEO of Neuron soundware.