Fault diagnosis model training method and device
A technology of fault diagnosis model and training method, applied in the direction of genetic model, neural learning method, biological neural network model, etc., can solve problems such as increasing the difficulty of data processing, changing, affecting the accuracy of fault diagnosis results, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0087] figure 1 It is a flow chart of the fault diagnosis model training method of the embodiment of the present invention.
[0088] Step 100. Acquire the state characteristic parameters of the top drive system collected by the sensors in the multiple top drive systems.
[0089] In this embodiment, the position of the sensor in the top drive system is determined according to a random weight genetic algorithm (Random Weight Genetic Algorithm, RWGA).
[0090] The collected state characteristic parameters of the top drive system include online collection of characteristic parameters reflecting the real-time operating state of the top drive, including vibration, temperature, oil parameters, etc., specifically including time domain characteristic parameters and frequency domain characteristic parameters. Among them, the characteristic parameters of the time domain include: maximum value, minimum value, range, mean value, and root mean square; and the dimensionless time domain char...
Embodiment 2
[0147] In order to solve the above problems, such as Figure 4 As shown, the present invention also provides a fault detection method, and the specific implementation process is as follows:
[0148] Step 400. When the top drive system fails, obtain the state characteristic parameters of the top drive system collected by the sensors in the top drive system; wherein, the position of the sensor in the top drive system is determined according to a random weight genetic algorithm .
[0149] In this embodiment, according to the position of the sensor determined by the method in Embodiment 1, when the top drive system fails, the state characteristic parameters of the top drive system collected by the sensors in the top drive system are obtained. The collected state characteristic parameters of the top drive system include time domain characteristic parameters and frequency domain characteristic parameters. Among them, the characteristic parameters of the time domain include: maximu...
Embodiment 3
[0178] In order to solve the above problems, such as Figure 5 As shown, the present invention also provides a fault diagnosis model training device, which includes: a memory and a processor; the memory is used to save a program for fault diagnosis model training;
[0179] The processor is configured to read and execute the program for fault diagnosis model training, and perform the following operations:
[0180] Obtaining the state characteristic parameters of the top drive system collected by the sensors in the multiple top drive systems; wherein, the position of the sensor in the top drive system is determined according to a random weight genetic algorithm;
[0181]Use the redundant attribute projection algorithm to eliminate the variable working condition characteristic parameters in each collected state characteristic parameter;
[0182] The multiple state characteristic parameters after the variable working condition characteristic parameters have been eliminated are re...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


