Guangdong University of Petrochemical Technology

Foshan University

Chenglin Wen

Ye Ke

Shaolin Hu

Qinghua Zhang

Wei Yu

Yan Jiang

Gaowei Lei

Qiliang Guo

Henghui Liang

Zhipeng Wang

Wenzhuo Chen

Guo Xie

Xinchen Zhu

Rui Chen

Man Xie

Wenqiang Jiang

Disclosed is an autonomous mining method of industrial big data based on model sets, which comprises the following steps: S, building model sets and a mining engine based on domain knowledge and structural characteristics of multi-source heterogeneous data; S, carrying out data sampling on the multi-source heterogeneous data, and counting the fault-tolerant estimation of random error variance; S, mining data sets by using the mining engine, and determining the optimal fault-tolerant model of each sampled data sequence and the optimal fault-tolerant estimation of model parameters; S, performing goodness-of-fit statistics calculation and VV&A test by using the optimal fault-tolerant model; S, acquiring data model representation and connotation knowledge based on model clustering. The method can realize the automation of the mining process of big data, the integration of associated knowledge, the expansion of model sets, the integration of mining and modeling and the optimization of mining results.

Autonomous mining method of industrial big data based on model sets

A convenient swing monitoring method and device for skyscrapers is provided. The method firstly designs a building monitoring network based on multi-mode integrated navigation receivers by adopting a vertically distributed three-layer three-dimensional mesh layout, then determines a maximum deviation, maximum inclination angle and maximum inclination azimuth of a building structure, constructs a high-fidelity fault-tolerant filter with anti-outlier effects, draws curves changing with time of structural deformation variables of the building structure, and finally judges whether the building structure has abnormal changes in line with relevant international and domestic building safety standards. The perception and warning of the collapse risk of super-high building structures can be effectively realized, the risk perception ability of skyscraper disasters is improved, and the influence of various factors on the safety of super-high buildings can be accurately monitored, analyzed and evaluated, so as to prevent risks beforehand.

Convenient monitoring method and system for swing collapse risk of skyscrapers

Complicated system fault diagnosis method and system based on a multi-stage model are provided. The method includes: establishing an integer-order mathematical model, a 0.1-level fractional order mathematical model, and a 0.01-level fractional order mathematical model of a permanent magnet synchronous motor system; designing an integer-order status observer based on the integer-order mathematical model, designing a 0.1-level fractional order status observer based on the 0.1-level fractional order mathematical model, and designing a 0.01-level fractional order status observer based on the 0.01-level fractional mathematical model; corresponding residual values can be obtained by the observers and compared with corresponding threshold values to judge whether there is a fault. The system includes first through third modules. Observers with different accuracy degrees are set up and the permanent magnet synchronous motor system is diagnosed through the observers. The fault diagnosis method and system are mainly used in motor diagnosis.

Complicated system fault diagnosis method and system based on multi-stage model

Growing community of inventors

Maoming, China

Chenglin Wen