Guangdong University of Petrochemical Technology

Ye Ke

Shaolin Hu

Qinghua Zhang

Chenglin Wen

Jinpeng Chen

Naiquan Su

Gaowei Lei

Guanhua Zhu

Qiliang Guo

Xinchen Zhu

Man Xie

Wenzhuo Chen

Wenqiang Jiang

Guo Xie

Shihua Wang

The present disclosure relates to a passive outlier-tolerant and active outlier-tolerant learning method with abnormal samples and a system thereof. The method includes the following steps: (1) judging the distribution of abnormal samples in a train set, and calling a corresponding outlier-tolerant algorithm based on the distribution to carry out feature learning on the sample feature quantity in the train set to obtain an outlier-tolerant learning result; (2) training an initial learning model by using the outlier-tolerant learning result to obtain an intermediate learning model; (3) processing the test set by a preset outlier-correction algorithm to obtain an outlier-corrected test set; (4) testing the intermediate learning model using the outlier-corrected test set to obtain a final learning model. The scheme of the present disclosure can improve the passive outlier tolerance and active outlier tolerance of a machine learning process to abnormal samples.

Passive outlier-tolerant and active outlier-tolerant learning method with abnormal samples and system thereof

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

A method and system for diagnosis of error coding faults from multiple instruments are provided. The method includes acquiring sampling data series of a combination of instruments in a petrochemical process, determining a type of the sampling data series, and performing error diagnosis according to the type. The present disclosure can solve the error coding problem in a multi-instrument cooperation mode and provide safe and reliable data guarantee for safe and efficient petrochemical production.

Method and system for diagnosis of error coding faults from multiple instruments

Growing community of inventors

Maoming, China

Ye Ke