A method for early fault detection of gearboxes
A technology of early failure and detection method, applied in the direction of measuring device, testing of mechanical components, testing of machine/structural components, etc., can solve the problems of extraction, difficult fault features, weak early fault features of gearboxes, etc., to achieve high detection rate , Improve the detection ability, avoid the effect of economic loss
Active Publication Date: 2022-05-10
沈阳科网通信息技术有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to solve the technical problems raised by the above-mentioned background technology, the present invention aims to provide a gearbox early fault detection method to solve the problem that the early fault characteristics of the gearbox are weak and hidden in a set of time-varying sequence signals, which makes the fault characteristics difficult to detect The Problem of Efficient Extraction in Strong Noise Background
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
[0034] Early fault detection of gearboxes has become an important branch and research hotspot of intelligent maintenance. Some existing methods basically detect early faults based on models and signal processing, but these methods have complex modeling, low model accuracy, poor timeliness for early fault detection, and inaccurate detection results. Therefore, the present invention combines the idea of depth decomposition theorem to divide the collected data in detail, so as to extract the features of weak fault information under strong noise background. At the same time, using the sliding window algorithm, taking into account the time series correlation of the data, the early fault detection ability is improved.
[0035] This embodiment takes the gearbox commonly used in mechanical equipment as an example, such as figure 1 As shown, the present invention adopts an early fault detection method based on deep recursive dynamic principal component analysis, and the specific ste...
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 method for early fault detection of a gear box, comprising the following steps: S1, signal acquisition: collecting vibration signals of the gear box under normal and fault working conditions, and decomposing the vibration signals through empirical mode decomposition; S2, Space decomposition: Combining with depth decomposition theorem, the original space is decomposed into multiple subspaces, and the dynamic principal component model of each subspace is established; S3, model update: through the sliding window algorithm, considering the time series correlation of data, the model is real-time Update; S4. Calculation of control limits: judge whether the gear box is faulty through the statistics and control limits, and update the model to recalculate the control limits. The present invention establishes a dynamic principal component model based on deep recursive dynamic principal component analysis, and then realizes early fault intelligent detection of the gearbox. Compared with the traditional early fault detection method, the present invention has the advantages of self-adaptability, high detection rate, fast detection speed and the like.
Description
technical field [0001] The invention relates to the technical field of gearbox intelligent early fault detection, in particular to a gearbox early fault detection method. Background technique [0002] With the rapid development of science and technology and modern industry, machinery and equipment in transportation, aerospace, national defense and other industries are becoming increasingly automated, integrated, high-speed and large-scale, and gearboxes have played a vital role in the development of various industries . Because the gearbox has many advantages such as small size, small mass, fixed transmission ratio, large transmission torque, compact structure, large carrying capacity, high efficiency, stable operation, and strong adaptability, it has become the most common power transmission and transmission equipment in the machinery industry. Transmission equipment that changes the speed is widely used in various mechanical equipment. Therefore, the performance of the g...
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 & AuthorityPatents(China)
IPC IPC(8): G01M13/021G01M13/028
CPCG01M13/021G01M13/028
Inventor李献文石怀涛吴俊新郭瑾李思慧
Owner沈阳科网通信息技术有限公司