
Mitsubishi Electric announced today that it has developed what is believed to be the world’s first diagnostic technology based on the company’s proprietary Maisart artificial intelligence (AI) technology that uses machine learning to analyze sensor data and then generate a model of a production machine’s transition between various operational states, thereby enabling the technology to detect machine abnormalities rapidly and accurately for improved productivity in factories and plants. The new AI technology eliminates complicated manual settings to simplify the introduction of abnormality-detection systems.
Unlike conventional diagnostic technology, which uses the same conditions for abnormality detection regardless of a machine’s current operational state, the new AI technology analyzes sensor data to automatically generate a model of the machine’s transition between various operational states, and then uses the model to set optimal conditions for detecting abnormalities during each operation. Signs of machinery failure can be detected accurately prior to actual breakdowns using the new AI technology and thus helping to reduce the labor associated with performing maintenance and dealing with downtime in factories and plants.