Liquid hazardous chemical substance volatilization concentration abnormity discovery method based on outlier data mining
A technology for outlier data and abnormal discovery, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problem of long running time of sensor monitoring data, and improve the ability of production safety risk identification, high comprehensive performance, The effect of improving execution efficiency
Pending Publication Date: 2021-06-11
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to solve the problems of incompatibility and long running time of the existing outlier data mining algorithm in the case of gas concentration sensor arrays collecting batch data, and to invent a liquid state algorithm based on outlier data mining. The abnormal discovery method of the volatile concentration of hazardous chemicals uses the improved local anomaly factor algorithm to perform outlier analysis on sensor data, and accurately and efficiently excavates outlier sensor data points
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0057] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.
[0058] The present invention is for existing dislocated data mining algorithms that cannot effectively detect the problem of excessive operational time of the outgaming gas concentration sensor. First, use the decancing information entropy to determine the weight of each attribute, such as the sensor deployed location information, wind speed, temperature, concentration, etc. Then use the Optics clustering algorithm to screen the gas concentration sensor raw data set to obtain the initial extensive data set, and then replace the accessibility distance in the local abnormality factor algorithm with P Weight; finally use the newly defined P Weight-based localization The group factor LOFBP calculates the extensive extent to which the group's data set is the extent of the object, excavate the outlink data points.
[0059] figure 1 It is a flow chart of ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a liquid hazardous chemical substance volatilization concentration abnormity discovery method based on outlier data mining. The method is characterized by comprising the following steps: firstly, introducing a dedivision information entropy to determine the weight of an outlier attribute; an original data set collected by a sensor being screened by using a density-based clustering algorithm to obtain a preliminary outlier data set, so that the operation efficiency of the algorithm is improved; then, replacing a reachable distance in a local abnormal factor algorithm with a P weight; and finally, calculating the outlier degree of the object in the preliminary outlier data set by using a newly defined local outlier factor LOFBP based on a P weight. According to the invention, a large amount of gas concentration sensor data is processed by using a data mining technology, so that the data credibility of a single gas concentration sensor can be improved, and the data of a plurality of gas concentration sensor arrays form a whole to carry out space gas concentration estimation; therefore, dangerous chemical production and processing enterprises are effectively helped to improve the production safety risk identification capability and prevent production accidents.
Description
Technical field [0001] The present invention relates to an extension data mining method, in particular a liquid hazardous chemical volatile concentration abnormality discovery based on local abnormal factor, and applies to group data mining techniques to a data volatile gas concentration estimate. Treatment analysis, timely discovery of abnormal concentration indicators to improve production safety risk recognition capabilities, specifically a liquid hazardous chemical volatile concentration of liquid hazardous chemicals based on off-group data excavation. Background technique [0002] The storage of liquid hazardous chemicals has been related to the safety of life and property of our people. Different liquid hazardous chemicals exhibit different traits. Volatility is the commonality of most liquid hazardous chemicals, such as gasoline, LNG, liquid ammonia, alcohol, and benzenes are common volatile hazardous chemicals. In practice, petrochemical companies often need frequent moni...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/23G06F18/2433
Inventor 薛善良彭振峰韦青燕肖雪
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS