Big data mining and fault prediction method based on full life cycle of elevator

Abstract

The invention discloses a big data mining and fault prediction method based on the full life cycle of an elevator, and the method is characterized in that the method comprises the following steps: collecting multi-source heterogeneous data in the full life cycle of the elevator, wherein the multi-source heterogeneous data comprises structural data, unstructural data, static data types and dynamicdata of elevator design, installation, maintenance and inspection links; building an elevator multi-source heterogeneous database; preprocessing the acquired data; and modeling and analyzing the preprocessed data, evaluating the model, and evaluating the elevator equipment fault by using the evaluated model. According to the method, data preprocessing and mining analysis are carried out on mass data of full-life-cycle links such as elevator inspection, design, installation and maintenance, elevator faults are predicted, the problem that in the prior art, only data of a certain single link of an elevator can be analyzed is solved, meanwhile, and a supervised learning mode is adopted, the fault of the elevator can be effectively predicted.

Description

technical field [0001] The invention relates to a big data mining and fault prediction method based on the whole life cycle of an elevator. Background technique [0002] With the continuous advancement of the pace of the city, there are more and more high-rise buildings, and elevators are a vital part of high-rise buildings. Elevators have a century-old history of development and have brought great convenience to people's daily life. At present, elevators have become a basic means of transportation in daily life. Taking Shanghai as an example, as of 2019, the number of elevators in Shanghai has exceeded 270,000, ranking first in the world's cities. Among the elevators in use, the elevators with a service life of more than 15 years The number is about 20,000; after 5 years, elevators with an age of more than 15 years will account for about 1 / 5 of the total number of elevators. However, the potential safety hazards brought by elevators have also attracted much attention. Fau...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: in the face of the massive basic information data and fault data of the elevator, the existing technology cannot connect multiple links of the elevator from design, installation, inspection to maintenance for data mining and analysis. The disjointed data mining of links leads to the low accuracy of the unsupervised learning data mining algorithm currently used, which makes it impossible to effectively predict the fault of the elevator

Images