The invention belongs to the technical field of
rail transit intelligent monitoring, and particularly relates to an intelligent monitoring method and device for a
rail transit air conditioning system. According to the method, the
sensor array with the self-adaptive sampling frequency is used for collecting the multi-
modal operation data, then the collected multi-
modal operation data is preprocessed, the feature degradation track atlas is established, powerful data support is provided for subsequent fault early warning and diagnosis, and the fault diagnosis accuracy is improved. Historical abnormal events are introduced to dynamically correct the health state evaluation
base line, the timeliness and accuracy of the evaluation
base line are ensured, in comparative analysis of real-time operation data and the dynamic evaluation
base line, a health degree scoring and dynamic threshold mechanism is adopted, quantitative evaluation of the health state of the air conditioner
system is achieved, and the evaluation accuracy of the health state of the air conditioner
system is improved. According to the method, a
decision graph containing fault diagnosis and
predictive maintenance suggestions is generated by analyzing the propagation path and
time sequence relevance of abnormal parameters in the
air conditioning system and combining an equipment topological
relation graph, so that the
troubleshooting and repairing efficiency is improved.