Vehicle Operating Condition Recognition Method Based on Vibration Signal Analysis
A vibration signal, working condition identification technology, applied in vehicle testing, machine/structural component testing, measuring devices, etc., can solve problems such as inconvenient installation and use, and achieve the effect of ensuring integrity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0012] Specific implementation mode one: the following combination figure 1 Describe this embodiment, the vehicle operating condition identification method based on vibration signal analysis described in this embodiment, the method includes the following steps:
[0013] Step 1. Collect the vibration signal of the vehicle and perform denoising processing on it;
[0014] Step 2, performing signal feature value extraction on the denoised vibration signal;
[0015] Step 3. Carry out intelligent identification of working conditions according to the feature values extracted in step 2; output the vehicle working condition type.
specific Embodiment approach 2
[0016] Embodiment 2: This embodiment will further explain Embodiment 1. In step 1, the vibration signal of the vehicle is denoised using the singular value decomposition noise reduction method, and the observed vehicle vibration signal sequence x i ={x 1 ,x 2 ,...x Q} Carry out singular value decomposition for noise reduction, Q is the sampling point, the specific process is:
[0017] Step 1-1. Select the subsequence {x in the observed signal sequence 1 ,x 2 ,...x q} as the first row vector y of the p×q-dimensional phase space matrix 1 ;
[0018] Step 1-2, move one step to the right to get the subsequence {x 2 ,x 3 ,...x q+1}, as the second row vector y of the p×q-dimensional phase space matrix 2 ;
[0019] Steps 1-3, and so on, get a column vector (y 1 ,y 2 ,...y p ) T ;
[0020] Steps 1-4, each vector corresponds to a point in the phase space, and all vectors constitute the p×q-dimensional reconstructed phase space orbit matrix H:
[0021]
[0022] In the...
specific Embodiment approach 3
[0026] Specific implementation mode three: this implementation mode further explains implementation mode two. In step two, the process of extracting the signal feature value of the vibration signal after denoising is as follows:
[0027] The denoised signal G is x i ={x 1 ,x 2 ,...x N}, its Fourier transform expression is:
[0028]
[0029] The amplitude spectrum expression of the signal is:
[0030]
[0031] The power spectrum expression of the signal is:
[0032]
[0033] Among them, X R (k) represents the real part, X I (k) represents the imaginary part:
[0034]
[0035]
[0036] Then draw the spectrum diagram of the vibration signal to present the frequency distribution of the vibration signal, and select the frequency components under different working conditions as the signal characteristic value.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


