Mtelligence's mVision machine learning platform determines predictors of equipment failure and then continuously monitors for them
Mtelligence's mVision machine learning platform features turnkey integration with several operations and maintenance systems used in manufacturing. mVision is designed to apply a combination of supervised and unsupervised learning techniques to determine predictors of equipment failure and then continuously monitors for them.
The platform includes pre-built adapters for maintenance, automation and condition monitoring systems, converting all data into the MIMOSA open standard data model. MIMOSA (Machinery Information Management Open Systems Alliance) is a mature open standard for modeling asset, maintenance and condition monitoring data. The use of an open standard data model and messaging protocol is engineered to enable mVision to integrate with a variety of data sources.
The platform includes a library of intelligent processing filters for sensor data, including statistical process control (SPC) and signal processing algorithms, to improve the signal-to-noise ratio prior to training the mVision agent. The agent is engineered to learn to differentiate normal operating context from abnormal conditions, and recognize patterns that represent symptoms of impending failure. mVision is also designed to correlate sensor data with equipment assembly and transactional data coming from EAM/CMMS systems.