Urban bridge condition grade real-time division method and device based on deep neural network
A deep neural network and neural network technology, applied in the field of real-time division, can solve problems such as high labor cost, untimely maintenance, and delayed maintenance time, and achieve the effect of high degree of automation, accurate and timely division, and high degree of intelligence
Active Publication Date: 2020-09-15
冯星星
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the status of urban bridges depends on manual experience to determine the score as appropriate, resulting in high labor costs, inaccurate and untimely classification of bridge status, and lagging maintenance timing, etc.
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
[0061] Such as figure 1 Shown, the real-time division method of urban bridge condition level based on deep neural network of the present invention, comprises the following steps:
[0062] Step 1. The real-time urban bridge condition monitoring data group X' is used as the input of the trained highest score neural network, the trained most likely score neural network and the trained lowest score neural network respectively, and the trained highest score neural network outputs The highest score A' of the real-time bridge condition, the trained most likely score neural network outputs the most likely score B' of the real-time bridge condition, the trained lowest score neural network outputs the lowest score C' of the real-time bridge condition, and the trained highest score neural network The network, the trained most likely scoring neural network and the trained lowest scoring neural network all have optimal network parameters, said optimal network parameters including optimal b...
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 an urban bridge condition grade real-time division method and device based on a deep neural network. The method comprises the following steps: step 1, taking a real-time urbanbridge condition monitoring data set as input of a trained neural network, and respectively obtaining a real-time bridge condition highest score, a real-time bridge condition most probable score and areal-time bridge condition lowest score; 2, calculating a real-time bridge condition score according to the real-time bridge condition highest score, the real-time bridge condition most probable score and the real-time bridge condition lowest score; and 3, dividing urban bridge condition grades in real time according to the real-time bridge condition scores. The method provided by the invention has simple steps, the urban bridge condition monitoring data and the expert score are automatically learned through the deep neural network, the correlation between the urban bridge condition and the expert score is established, the real-time bridge condition is autonomously scored, the bridge condition is graded in real time, the maintenance countermeasure is given in time, safe operation is achieved, the effect is remarkable, and convenience is brought to popularization.
Description
technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and device for real-time division of urban bridge condition levels based on a deep neural network. Background technique [0002] The maintenance of urban bridges is mainly carried out according to the classification of the sound state of the bridge structure, and the state level of the urban bridge is used to represent the sound state of the bridge structure. According to the "Technical Specifications for Urban Bridge Maintenance", the status of urban bridges is divided into five grades: A, B, C, D, and E. Each grade corresponds to a type of maintenance strategy. For example, the maintenance strategy corresponding to grade A is "daily maintenance", etc. , and at the same time, each urban bridge condition level corresponds to a bridge condition score range, for example, the score range corresponding to level A is [90,100] and so on. Therefore,...
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): G06Q10/06G06Q10/00G06Q50/08G06N3/04G06N3/08
CPCG06Q10/06393G06Q10/20G06Q50/08G06N3/08G06N3/045Y02A30/60
Inventor 冯星星
Owner 冯星星