Real-time Monitoring Method of Elevator Energy Consumption Based on K-means Clustering and BP Neural Network
This paper proposes a real-time monitoring method of elevator energy consumption based on the combination of K-means clustering algorithm and BP neural network,which addresses the issues of low monitoring accuracy and long monitoring time when existing methods are used to monitor elevator en-ergy consumption.The characteristic values of the main factors that affect real-time monitoring of building energy consumption are extracted from the cleaned energy consumption data,and the similarity coefficient method is used to calculate the similarity and obtain the similarity coefficient.The way of wavelet decompo-sition on similar elevator energy consumption data is used to obtain high and low frequency sequences.The study uses LSSVM-GSA detection method and mean square weighted processing method to process the low and high frequency parts,and reconstructs the two results to obtain the final real-time monitoring results.The simulation experimental results show that the proposed method can obtain highprecision,low time consumption,and high stability monitoring results.
elevator energy consumptionK-means clustering algorithmBP neural networkdata cleaning
NETL
NSTL
万方数据
