Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Active Publication Date: 2020-07-28
CHINA OILFIELD SERVICES
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, due to the arrangement of a large number of different types and different types of sensors, there are many collected state characteristic parameters of the top drive, which greatly increases the difficulty of subsequent data processing; if the number of sensors is reduced in a large range, it is difficult to ensure that the collected state characteristic parameters It can best describe the real-time operation of the top drive
Secondly, under different working conditions (different speed, load, etc.), the state characteristic parameters collected by the sensor will change greatly, thus affecting the accuracy of the fault diagnosis results. In the research of the prior art, it is usually assumed that The equipment operates under constant working conditions, and the conclusions obtained from this have great limitations, which cannot reflect the real situation well and are difficult to apply to the actual top drive monitoring fault detection

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fault diagnosis model training method and device
  • Fault diagnosis model training method and device
  • Fault diagnosis model training method and device

Examples

Experimental program
Comparison scheme
Effect test

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...

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

No PUM Login to View More

Abstract

The invention discloses a fault diagnosis model training method. The method comprises the steps of acquiring state characteristic parameters, collected by sensors in multiple top drive systems, of thetop drive systems, wherein the position of the sensor in the top drive system is determined according to a random weight genetic algorithm; respectively eliminating variable working condition characteristic parameters in each acquired state characteristic parameter by utilizing a redundant attribute projection algorithm; respectively fusing the plurality of state characteristic parameters withoutthe variable working condition characteristic parameters to obtain a plurality of fused state characteristic parameters; respectively marking fault types for the plurality of fused state characteristic parameters to obtain training data; and training a pre-established fault diagnosis model by adopting the training data. Through the scheme of the invention, the accuracy of fault diagnosis is improved.

Description

technical field [0001] This article relates to oil drilling technology, especially a fault diagnosis model training method and device. Background technique [0002] Top Drive Drilling System (Top Drive) is a new type of drilling equipment that appeared in the 1980s. This equipment can directly drive the drill string from the upper part of the derrick space and send it down along the special guide rail. It can complete various drilling operations such as rotary drilling, circulating drilling fluid, root connection, make-up and breakout, and reaming. The application of the top drive not only improves the drilling speed, but its most fundamental advantage is that the power is always connected with the drilling tool during the tripping process, and the drilling tool can be quickly rotated when encountering resistance or jamming, and the mud can be connected to scratch eye operations, increasing the safety of drilling operations. Therefore, the emergence of the top drive drilli...

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
no application Login to View More
IPC IPC(8): G06F30/23G06K9/62G06N3/12G06N3/08
CPCG06N3/126G06N3/08G06F18/24G06F18/253
Inventor 蒋爱国王金江谷明李文锦秦建安于昊天冼敏元张来斌陈冲刘拴忠
Owner CHINA OILFIELD SERVICES