Pressure working condition identification method based on elastic BP random forest fusion
A random forest and pressure technology, applied in the field of working condition identification, can solve problems such as the inability to accurately describe the pressure working conditions of equipment, and achieve the effects of accurate description, strong robustness, and time reduction
Pending Publication Date: 2022-06-03
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In order to solve the shortcomings of the above-mentioned prior art, the present invention proposes a pressure working condition identification method based on the elastic BP random forest fusion algorithm, in order to accurately and quickly identify the working condition of the pressure equipment, and solve the pressure equipment in the traditional The working condition identification method cannot accurately describe the problem of equipment pressure working conditions, so as to meet the needs of actual industrial scenarios
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
[0055] In this embodiment, a pressure condition identification method based on elastic BP random forest fusion is performed according to the following steps:
[0056] Step 1. For the original dataset D i preprocessing;
[0057] Step 1.1. According to the sampling period f, the pressure equipment is collected in the i-th period of time T i The M types of features in the non-stressed feature dataset D′ i , and D' i ={d i，1 ,...,d i,m ,...,d i,M }, where d i,m Represents the i-th segment time T i The m-th feature within , and d i,m ={x i,1,m ,...,x i,t,m ,...,x i,T,m }, x i,t,m Represents the i-th segment time T i Inner mth class feature d i,m The eigenvalues at the t-th time in ;
[0058] According to the sampling period f, the pressure equipment is collected at the i-1th period of time T i-1 pressure features within and in, Represents the i-1th segment time T i-1 The pressure value at time t in the inner;
[0059] According to the sampling period f, the ...
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 pressure working condition identification method based on elastic BP random forest fusion. The method comprises the following steps: 1, preprocessing an original data set Di; 2, establishing a classification model through a random forest algorithm; 3, establishing a regression model based on the elastic BP neural network; and 4, based on the models in the step 2 and the step 3 and the pressure working condition evaluation rule, constructing a fusion algorithm pressure working condition identification model so as to obtain the pressure working condition. According to the method, the problem that the pressure working condition of the pressure equipment cannot be accurately described in a traditional working condition identification method can be solved, so that the working condition of the pressure equipment can be accurately and quickly identified, and the requirements of actual industrial scenes are met.
Description
technical field [0001] The invention belongs to the field of working condition identification, in particular to a pressure working condition identification method based on elastic BP random forest fusion. Background technique [0002] With the rapid development of industry, pressure equipment is an indispensable equipment in many industrial production. Therefore, in order to improve production efficiency, most industrial production scenarios take pressure equipment as a research object and optimize it. For example, boiler equipment can judge its combustion state by identifying the working conditions of the main steam pressure, and oil pump equipment can judge its operating state according to the changing trend of outlet pressure. Due to the common characteristics of non-linearity, strong coupling and large hysteresis in industrial scenarios, key parameters cannot be obtained by conventional methods, so it is impossible to make timely and accurate judgments on current indust...
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 IPC IPC(8): G06F30/27G06K9/62G06N3/08G06F111/08G06F119/14
CPCG06F30/27G06N3/084G06F2111/08G06F2119/14G06F18/24323G06F18/214
Inventor 杨恺陈薇郑涛刘双飞张建飞刘辉
Owner HEFEI UNIV OF TECH