Underground carry-scraper fault diagnosis method based on KPCA
A fault diagnosis and scraper technology, which is applied in earth movers/excavators, construction, etc., can solve the problem that it is difficult to meet the overall and rapid requirements of fault diagnosis algorithms, and it is difficult to obtain complete knowledge bases and samples accurately, faults bug detection etc.
Active Publication Date: 2021-06-18
UNIV OF SCI & TECH BEIJING
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] For the problem of fault diagnosis, traditional methods are divided into fault diagnosis methods based on analytical models and knowledge-based fault diagnosis methods according to different principles. However, it lacks the consideration of the strong coupling between the variables of the scraper and the strong nonlinear characteristics
At the same time, with the increasingly complex system structure, it is more difficult to obtain the complete knowledge base and samples required by such algorithms, and it is difficult to guarantee the accuracy of fault diagnosis.
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 1
[0071] In the modeling process of the fault model of underground scraper based on KPCA algorithm, it is necessary to collect multi-variable measurement data of underground scraper under stable operating conditions, such as engine oil temperature, engine oil pressure, engine coolant temperature, transmission oil Temperature, gearbox oil pressure, hydraulic oil temperature and other information obtained by corresponding sensors. These collected measurement data form a data matrix X(x 1 ,x 2 ,...,x n )∈R n x m , n represents the number of samples, and m represents the number of features.
[0072] Establishing the fault diagnosis model of underground LHD based on KPCA algorithm needs to go through the following three stages:
[0073] Step 1: Model training. Call the historical normal operation status data of the underground LHD to train the model and determine T 2 Confidence limits for the statistic and the SPE statistic. This embodiment selects 4000 data points when the u...
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 provides an underground carry-scraper fault diagnosis method based on KPCA, and belongs to the technical field of underground carry-scraper fault diagnosis. The underground carry-scraper fault diagnosis method comprises the steps that a KPCA model is established by utilizing historical data generated in the actual production process of an underground carry-scraper; through decomposing a feature value, T2 and SPE statistics of a principal component subspace and a residual subspace are established by further solving a feature vector; respective control limits are obtained by utilizing modeling data and distribution of the two statistics, the respective control limits are compared with the statistical magnitude of the current detection data to determine whether a system is abnormal or not so as to complete the fault detection; and the contribution value of each parameter to the statistical magnitude is calculated to obtain a contribution rate graph, and a fault variable is positioned. According to the method, the case verification is carried out by adopting actual production data of the underground carry-scraper of the Chambishi copper mine, and a test result shows that the method is very effective.
Description
technical field [0001] The invention relates to the technical field of fault diagnosis of an underground scraper, in particular to a KPCA-based fault diagnosis method for an underground scraper. Background technique [0002] Mining equipment underground scraper is used in mining operations in mines. The working environment is harsh and the working conditions are complicated. It is prone to failure due to bumps, dust, humidity, etc., resulting in long-term shutdown of the equipment for maintenance and even blockage of the roadway, often causing a lot of economic losses. . Therefore, the fault diagnosis of the underground scraper is very important. The timely detection and accurate positioning of the fault of the underground scraper can greatly reduce the maintenance time and improve the working efficiency of the equipment. [0003] For the problem of fault diagnosis, traditional methods are divided into fault diagnosis methods based on analytical models and knowledge-based f...
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): E02F9/26E02F9/20
CPCE02F9/268E02F9/20
Inventor 孟宇杨仕昆刘立顾青
Owner UNIV OF SCI & TECH BEIJING