A Method for Eliminating Gross Errors in Slope Monitoring Data
A technology for monitoring data and gross error removal, applied in special data processing applications, instruments, artificial life, etc., can solve the problem that the accuracy of the single-layer ELM model cannot meet the industrial requirements, and achieves high accuracy of gross error elimination and parameterization. Optimize and improve the effect of stability
Active Publication Date: 2020-12-25
NORTHEASTERN UNIV LIAONING
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, through the cross-validation of multiple sets of data, it is found that the accuracy of the single-layer ELM model cannot meet the standards required by the industry.
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
[0066] In order to better explain the present invention and facilitate understanding, the present invention will be described in detail below through specific embodiments in conjunction with the accompanying drawings.
[0067] (1) Method
[0068] Such as Figure 14 As shown: this embodiment discloses a method for removing gross errors in slope monitoring data, including the following steps:
[0069] S1. Data preprocessing: Preprocessing the slope detection data that needs gross error removal to obtain characteristic data;
[0070] In this step, the monitoring data obtained from the slope monitoring equipment will be preliminarily processed, and the characteristic data in the data will be extracted for further data gross error elimination.
[0071] S2. Establish a prediction matrix: input the characteristic data obtained in S1 into m PSO-TELM models respectively, and obtain a prediction matrix T according to the output results of the m PSO-TELM models; the prediction matrix T...
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 belongs to the technical field of slope monitoring, and in particular relates to a method for eliminating gross errors in slope monitoring data, which includes the following steps: S1. Data preprocessing: preprocess the slope detection data that needs to be eliminated, and obtain Feature data; S2. Establish a prediction matrix: Input the feature data obtained in S1 into m PSO-TELM models respectively, and obtain the prediction matrix T based on the output results of the m PSO-TELM models; S3. Eliminate gross error data: Calculate the column-wise average of the prediction matrix T to obtain a new matrix T′ = (a 1 ,a 2 ,…,a n ) 1×n , and then calculate the mean s and variance d of the matrix T′; if the elements in T′ satisfy: a i ‑s>d,(i=1,2,…n), then a should be eliminated i corresponding feature data, otherwise, retain a i Corresponding characteristic data can be used to obtain accurate slope monitoring data. The method for eliminating gross errors in slope monitoring data provided by the present invention has the beneficial effect of high accuracy in eliminating gross errors.
Description
technical field [0001] The invention belongs to the technical field of slope monitoring, in particular to a method for eliminating gross errors in slope monitoring data. Background technique [0002] In order to ensure the quality and level of slope safety monitoring work, monitoring data analysis is an indispensable and inseparable part of slope engineering safety monitoring work, and it is an important and key link for safety monitoring, construction guidance and improvement of design methods. , will play an important role in different stages of construction and operation of various slope projects. This subject first analyzes the traditional gross error elimination methods, such as Raida's rule, cluster analysis, etc., and finds that the traditional processing methods have obvious defects. At the same time, based on the elimination idea of traditional methods, an ELM classification algorithm is proposed to eliminate gross errors. Firstly, by analyzing the mean square e...
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 Patents(China)
IPC IPC(8): G06N3/00G06F30/20
CPCG06N3/006G06F30/20
Inventor 肖冬张盛永毛亚纯柳小波
Owner NORTHEASTERN UNIV LIAONING