Research And Application Of Elevator Safety Monitoring Method Based On Big Data

With the development of the economy and the improvement of people’s living standard,elevators have become an indispensable equipment of transportation for people’s lives.Elevator safety becomes more and more important.How to effectively reduce or avoid elevator accidents has become a hot topic in the industry and academia.On the other hand,the sensors of elevator collect a large amount of data.These data provide the data basis for analyzing the running status of the elevator.In this context,this thesis proposes an elevator safety monitoring method based on big data,and uses big data technology to solve the problem of elevator real-time fault detection and elevator abnormal status warning.The main research contents as follows:(1)A platform architecture of elevator safety monitoring based on big data is designed.The platform includes a data integration and distribution layer,a data transmission layer,a data processing layer,a data storage layer and a data application layer.The platform can simultaneously analyze and detect the running data of a large number of elevators in real time,and it has high performance,high extensibility and high available.(2)An elevator fault detection method based on streaming big data is proposed.The finite state machine is used to model the elevator operation process.And an elevator fault detection algorithm is designed in this thesis,which can detect the transfer process of elevator running state in real time,and bind the abnormal state transfer to the corresponding fault so that It can judge elevator fault.(3)An elevator abnormal warning method based on a time series forecasting model is proposed.This thesis proposes a novel time series forecasting model based on the combination of recurrent neural network and dilated causal convolution network.The model can analyze and predict the time series data of elevators and predict whether the elevator components will be abnormal in the future.Finally,an elevator safety monitoring platform prototype system based on big data is developed.The functions of the system include elevator data management,visualization of elevator geographical location,elevator data visualization,elevator fault detection and elevator abnormality warning,etc.The experimental results show that the platform can effectively detect the fault of elevator and effectively predict the elevator abnormality.