An Improved Bayesian Optimal LightGBM Fault Diagnosis Method
A technology of fault diagnosis and fault diagnosis model, applied in the field of fault diagnosis, can solve problems such as the influence of fault diagnosis model accuracy and fault diagnosis accuracy, achieve high fault prediction efficiency and accuracy, improve fault diagnosis accuracy and model robustness. The effect of stickiness and low model computational complexity
Active Publication Date: 2022-05-13
ZHEJIANG UNIV OF TECH
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of the above-mentioned problems existing in the prior art, in order to solve the problem that hyperparameter uncertainty affects the accuracy of fault diagnosis, the purpose of the present invention is to provide an improved Bayesian optimized LightGBM fault diagnosis method for solving The problem that the uncertainty of hyperparameters affects the accuracy of the fault diagnosis model, so as to improve the accuracy of fault diagnosis and the robustness of the model
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
[0041] The present invention will be further described below in conjunction with accompanying drawing of description, but protection scope of the present invention is not limited thereto:
[0042] Improved Bayesian optimized LightGBM fault diagnosis method, including the following steps:
[0043] 1) Determine the hyperparameters and hyperparameter value ranges that the LightGBM model needs to optimize; step 1) determines the hyperparameters and hyperparameter value ranges that the LightGBM model needs to optimize, in the following manner:
[0044] The hyperparameter max_depth sets the value range to the interval [1,11];
[0045] The hyperparameter learning_rate sets the value range to the interval [0.1,0.9];
[0046] The hyperparameter colsample_bytree sets the value range to the interval [0.1,0.9];
[0047] The hyperparameter subsample sets the value range to the interval [0.1,0.9];
[0048]The hyperparameter max_bin sets the value range to the interval [25,150].
[0049]...
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 improved Bayesian optimized LightGBM fault diagnosis method, comprising the following steps: 1) determining the hyperparameters and hyperparameter value ranges that need to be optimized for the LightGBM model; 2) improving the Bayesian optimization algorithm to obtain Improved Bayesian optimization algorithm GP-ProbHedge; 3) Use the method of step 2) combined with the 5-fold cross-validation method to select the optimal hyperparameter combination of the fault diagnosis model; 4) Build an improved Bayesian optimized LightGBM fault diagnosis model, and give Model iteration process and optimization results. By adopting the above-mentioned technology, compared with the prior art, the present invention proposes an improved Bayesian optimization algorithm to optimize and select the parameters of the fault model. The variance function is improved, and an improved Bayesian optimization LightGBM fault diagnosis method is proposed to diagnose and predict equipment faults.
Description
technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to an improved Bayesian optimized LightGBM fault diagnosis method. Background technique [0002] At present, the research hotspot of fault diagnosis is mainly the data-driven fault diagnosis method based on machine learning algorithm, but the fault diagnosis model constructed based on this method still has a large number of uncertain parameters, which leads to the problem of large fluctuations in the accuracy of fault diagnosis of the model. The change of different hyperparameters has a great influence on the prediction accuracy of the fault diagnosis model. Selecting a better parameter combination can give full play to the superior performance of the fault diagnosis model and greatly improve the recognition rate of fault diagnosis, which will bring huge benefits to the enterprise. economic benefits. So how to choose the combination of hyperparameters that can make the mode...
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): G06Q10/04G06Q10/00G06N7/00G06N5/00
CPCG06F11/3447G06F11/3457G06F18/214
Inventor 姜少飞许青青邬天骥李吉泉李志高启龙
Owner ZHEJIANG UNIV OF TECH