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

Coal face hydraulic support working resistance prediction method based on LSTM neural network

A technology of coal mining face and hydraulic support, which is applied in the field of coal mine pressure, can solve the problems of large errors and inability to achieve real-time calculations, etc.

Pending Publication Date: 2020-12-29
中煤能源研究院有限责任公司
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the working resistance of hydraulic supports is generally calculated by empirical formula or approximate theoretical formula, but most of them calculate the maximum working resistance, which cannot be calculated in real time, and the current calculation method has large errors

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
  • Coal face hydraulic support working resistance prediction method based on LSTM neural network
  • Coal face hydraulic support working resistance prediction method based on LSTM neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0019] In the case of no conflict, the embodiments and the features in the embodiments of the present invention can be combined with each other.

Embodiment

[0021] This embodiment discloses a method for predicting the working resistance of a hydraulic support in a coal mining face based on an LSTM neural network, which specifically includes the following steps:

[0022] Step 1: Collect the historical data of the working resistance of the hydraulic support in the coal mining face since mining, including the P (x, y, z) coordinate value at the center of the coal seam floor where the hydraulic support is located, the recording time t of the working resistance, and the working resistance value of the hydraulic support F.

[0023] Step 2: Use the collected coordinates of P (x, y, z) at the center of the coal seam floor where the hydraulic support is located and the recording time t of the working resistance as the input parameters of the LSTM neural network, and use the working resistance value F of the hydraulic support as the LSTM neural network output parameters.

[0024] Step 3: Initialize the LSTM neural network model, set the nu...

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 coal face hydraulic support working resistance prediction method based on an LSTM neural network. According to the method, a P (x, y, z) coordinate value, working resistancerecording time t and a hydraulic support working resistance value F at the center of a coal seam floor where a hydraulic support is located, which are collected by a coal face of a coal mine since mining, in the LSTM neural network are trained, the trained LSTM neural network can predict the working resistance of the hydraulic support at any position and at any time point of the working face according to requirements. Compared with traditional theoretical calculation, the method has the advantages of being high in prediction accuracy, capable of guiding production and the like, and meanwhile anew thought is provided for working face hydraulic support working resistance prediction.

Description

technical field [0001] The invention belongs to the field of coal mine rock pressure, and in particular relates to a method for predicting the working resistance of a hydraulic support in a coal mining face based on an LSTM neural network. Background technique [0002] At present, the working resistance of hydraulic supports is generally calculated using empirical formulas or approximate theoretical formulas, but most of them calculate the maximum working resistance, which cannot be calculated in real time, and the current calculation methods have large errors. In recent years, as the research and development of artificial intelligence technology has become more and more mature, it can be applied to coal mine pressure prediction. LSTM (Long-Short Term Memory) neural network, that is, long-term short-term memory neural network, can predict the value at a certain time point based on historical data, which is very suitable for the prediction of hydraulic support working resista...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/17G06F30/27G06N3/04G06N3/08G06Q10/04G06Q50/02G06F119/12G06F119/14
CPCG06F30/27G06F30/17G06Q10/04G06Q50/02G06N3/049G06N3/08G06F2119/12G06F2119/14G06N3/045
Inventor 程海星朱磊吴玉意徐凯刘文涛张新福
Owner 中煤能源研究院有限责任公司