CN-120410813-B - Mine safety training detection method and system based on mixed reality

CN120410813BCN 120410813 BCN120410813 BCN 120410813BCN-120410813-B

Abstract

The application belongs to the technical field of mine safety mixed reality interactive training, and particularly provides a mine safety training detection method and system based on mixed reality, wherein the method mainly comprises the steps of acquiring a mine basic data set and generating reinforced safety constraint boundary data according to the mine basic data set; generating environment risk features according to the reinforced safety constraint boundary data, generating safety behavior features according to the reinforced safety constraint boundary data and the environment risk features, generating risk evolution features according to the environment risk features and the safety behavior features, generating emergency response features according to the safety behavior features and the risk evolution features, and generating dynamic risk visualization pictures according to the risk evolution features and the emergency response features. The application realizes the visualization of training scene dynamics, operation behavior compliance detection automation and risk evolution process, and improves the safety training effectiveness and emergency processing capability.

Inventors

LI HONGYE
SONG ZHENHUA
CHEN RUI
YAO FAN
ZHAO XIAOXI
Xi Mengbo
XU HAOYU
GUO JIAHAO
XIE FANGMING
LI YUDIAN

Assignees

诺文科风机(北京)有限公司

Dates

Publication Date: 20260512
Application Date: 20250630

Claims (7)

1. The mine safety training detection method based on mixed reality is characterized by comprising the following steps of: Acquiring a mine basic data set, and performing dynamic scene construction processing according to the mine basic data set to generate reinforced safety constraint boundary data; Performing environment coupling acquisition processing according to the reinforced safety constraint boundary data to generate environment risk characteristics comprising human-computer interaction space coordinate data and collaborative risk field data; Comprising the following steps: Acquiring miner operation video stream data and environmental gas concentration real-time monitoring data; analyzing the personnel and equipment space relation of the miner operation video stream data to obtain man-machine interaction space coordinate data; Generating dynamic dangerous source distribution data based on the real-time monitoring data of the concentration of the environmental gas; fusing dynamic dangerous source distribution data and reinforced safety constraint boundary data to construct cooperative risk field data; Generating environmental risk characteristics comprising human-computer interaction space coordinate data and collaborative risk field data; Performing closed-loop action verification according to the reinforced safety constraint boundary data and the environment risk characteristics, and generating safety behavior characteristics including equipment operation deviation data and anti-interference disaster avoidance path data; performing collaborative risk deduction according to the environmental risk characteristics and the safety behavior characteristics to generate risk evolution characteristics, wherein the method comprises the steps of reconstructing collaborative risk field data to generate dynamic three-dimensional risk field data, combining equipment operation deviation data to generate risk collaborative evolution prediction data, combining anti-interference disaster avoidance path data to verify an escape scheme, and obtaining emergency escape effectiveness index data; performing multistage response processing according to the safety behavior characteristic and the risk evolution characteristic to generate an emergency response characteristic, wherein the method comprises the following steps: Performing collaborative evacuation path planning on the collaborative operation group position data according to the risk evolution characteristics to generate multi-unit collaborative evacuation scheme data; carrying out path safety fusion evaluation on the multi-unit cooperative evacuation scheme data and the anti-interference disaster avoidance path data according to the risk evolution characteristics to obtain final evacuation safety coefficient data; and carrying out holographic decision feedback processing according to the risk evolution characteristics and the emergency response characteristics to generate a dynamic risk visualization picture.
2. The mixed reality-based mine safety training detection method of claim 1, wherein the mine basic data set comprises mine roadway three-dimensional point cloud basic data and preset standard operation flow node data; Carrying out dynamic scene construction processing according to a mine basic data set to generate risk propagation path data and reinforced safety constraint boundary data, wherein the method comprises the following steps: Carrying out mobile equipment safety gap calculation based on mine roadway three-dimensional point cloud basic data to obtain dynamic equipment safety boundary data; carrying out space track superposition on the risk propagation path data and the dynamic equipment safety boundary data to obtain composite safety constraint boundary data; and acquiring historical accident scene reproduction data, and carrying out space risk reinforcement by combining the historical accident scene reproduction data and the composite safety constraint boundary data to obtain reinforced safety constraint boundary data.
3. The mixed reality based mine safety training detection method of claim 1, wherein the closed loop action verification is performed according to the reinforced safety constraint boundary data and the environment risk characteristics to generate safety behavior characteristics, comprising: Performing operation space compliance detection according to the human-computer interaction space coordinate data and the reinforced safety constraint boundary data to obtain equipment operation deviation data; security behavior features including device operational deviation data and anti-interference disaster avoidance path data are generated.
4. The mine safety training detection method based on mixed reality according to claim 1, wherein the collaborative evacuation path planning is performed on collaborative operation group position data according to risk evolution characteristics, and multi-unit collaborative evacuation scheme data is generated, comprising: performing team risk coupling analysis on the collaborative operation group position data and the risk collaborative evolution prediction data to obtain team risk coupling coefficient data; And planning an evacuation channel according to the team risk coupling coefficient data and the emergency escape effectiveness index data to obtain multi-unit cooperative evacuation scheme data.
5. The mine safety training detection method based on mixed reality according to claim 1, wherein the method for carrying out path safety fusion evaluation on the multi-unit cooperative evacuation scheme data and the anti-interference disaster avoidance path data according to the risk evolution characteristics to obtain final evacuation safety coefficient data comprises the following steps: Generating an optimized path by fusing the multi-unit cooperative evacuation scheme data and the anti-interference disaster avoidance path data to obtain optimized disaster avoidance path data; And cooperatively evaluating path risks of the optimized disaster avoidance path data and the risk cooperative evolution prediction data to obtain final evacuation safety coefficient data.
6. The mine safety training detection method based on mixed reality according to claim 1, wherein the method for generating a dynamic risk visualization picture by performing holographic decision feedback processing according to risk evolution characteristics and emergency response characteristics comprises the steps of: carrying out holographic space mapping on the dynamic three-dimensional risk field data to generate virtual-real fusion risk field data; Generating collaborative escape guiding animation data based on virtual-real fusion risk field data and multi-unit collaborative evacuation scheme data; and driving the collaborative escape guiding animation data and the early warning signal to generate a dynamic risk visualization picture.
7. Mine safety training detecting system based on mixed reality, characterized by, it includes: the dynamic safety constraint modeling module is used for acquiring a mine basic data set, carrying out dynamic scene construction processing according to the mine basic data set and generating reinforced safety constraint boundary data; The environment risk field coupling module is used for carrying out environment coupling acquisition processing according to the reinforced safety constraint boundary data to generate environment risk characteristics comprising human-computer interaction space coordinate data and collaborative risk field data; Comprising the following steps: Acquiring miner operation video stream data and environmental gas concentration real-time monitoring data; analyzing the personnel and equipment space relation of the miner operation video stream data to obtain man-machine interaction space coordinate data; Generating dynamic dangerous source distribution data based on the real-time monitoring data of the concentration of the environmental gas; fusing dynamic dangerous source distribution data and reinforced safety constraint boundary data to construct cooperative risk field data; Generating environmental risk characteristics comprising human-computer interaction space coordinate data and collaborative risk field data; The safety behavior closed-loop verification module performs closed-loop action verification according to the reinforced safety constraint boundary data and the environment risk characteristics to generate safety behavior characteristics comprising equipment operation deviation data and anti-interference disaster avoidance path data; The risk evolution collaborative deduction module performs collaborative risk deduction according to the environmental risk characteristics and the safety behavior characteristics to generate risk evolution characteristics, and comprises the steps of reconstructing collaborative risk field data to generate dynamic three-dimensional risk field data, generating risk collaborative evolution prediction data by combining equipment operation deviation data, verifying an escape scheme by combining anti-interference disaster avoidance path data to obtain emergency escape effectiveness index data; The team emergency cooperative response module is used for carrying out multistage response processing according to the safety behavior characteristics and the risk evolution characteristics to generate emergency response characteristics; and the mixed reality decision feedback module is used for carrying out multistage response processing according to the safety behavior characteristics and the risk evolution characteristics to generate emergency response characteristics, and comprises the following steps: Performing collaborative evacuation path planning on the collaborative operation group position data according to the risk evolution characteristics to generate multi-unit collaborative evacuation scheme data; carrying out path safety fusion evaluation on the multi-unit cooperative evacuation scheme data and the anti-interference disaster avoidance path data according to the risk evolution characteristics to obtain final evacuation safety coefficient data; and carrying out holographic decision feedback processing according to the risk evolution characteristics and the emergency response characteristics to generate a dynamic risk visualization picture.

Description

Mine safety training detection method and system based on mixed reality Technical Field The application belongs to the technical field of mine safety mixed reality interactive training, and particularly relates to a mine safety training detection method and system based on mixed reality. Background In traditional mine safety training, knowledge infusion and static scene simulation are mainly focused, real-time detection and dynamic evaluation mechanisms for operation behaviors of students are lacking, for example, theoretical teaching and animation demonstration are difficult to track specific actions of the students in virtual or actual scenes, and simulation exercise involves operation experience, but quantitative detection means for action compliance and risk response effectiveness are lacking. The operation deviation of a student is difficult to find in time in the traditional mine safety training process, the mastering degree of the student on the safety standard is difficult to evaluate, personalized feedback is difficult to provide for individual behavior characteristics, and due to the lack of closed loop verification of a detection link on a training effect, whether the student's behavior accords with the safety standard or not is difficult to prejudge when facing the real underground risk, so that the conversion efficiency of training to the actual safety capability is affected. Disclosure of Invention According to the mine safety training detection method and system based on mixed reality, the problem of insufficient training effect caused by fixed scene, lack of real-time behavior detection and closed-loop risk assessment in the mine safety training process in the prior art is effectively solved, the training scene is dynamic, the operation behavior compliance detection is automatic, the risk evolution process is visualized, and the safety training effectiveness and the emergency processing capability are improved. In order to achieve the above purpose, the present application adopts the following technical scheme: In a first aspect, the application provides a mine safety training detection method based on mixed reality, comprising the following steps: and acquiring a mine basic data set, and performing dynamic scene construction processing according to the mine basic data set to generate reinforced safety constraint boundary data. And performing environment coupling acquisition processing according to the reinforced safety constraint boundary data to generate environment risk characteristics. And performing closed-loop action verification according to the reinforced safety constraint boundary data and the environment risk characteristics to generate safety behavior characteristics. And carrying out collaborative risk deduction according to the environmental risk characteristics and the safety behavior characteristics to generate risk evolution characteristics. And carrying out multistage response processing according to the safety behavior characteristics and the risk evolution characteristics to generate emergency response characteristics. And carrying out holographic decision feedback processing according to the risk evolution characteristics and the emergency response characteristics to generate a dynamic risk visualization picture. Further, the mine basic data set comprises mine roadway three-dimensional point cloud basic data and preset standard operation flow node data. Carrying out dynamic scene construction processing according to a mine basic data set to generate risk propagation path data and reinforced safety constraint boundary data, wherein the method comprises the following steps: And carrying out risk line marking on the node data of the preset standard operation flow to obtain risk propagation path data. And carrying out space track superposition on the risk propagation path data and the dynamic equipment safety boundary data to obtain composite safety constraint boundary data. And acquiring historical accident scene reproduction data, and carrying out space risk reinforcement by combining the historical accident scene reproduction data and the composite safety constraint boundary data to obtain reinforced safety constraint boundary data. Further, performing environment coupling acquisition processing according to the reinforced security constraint boundary data to generate environment risk characteristics, including: and acquiring miner operation video stream data and ambient gas concentration real-time monitoring data. And analyzing the personnel and equipment spatial relationship of the miner operation video stream data to obtain the human-computer interaction spatial coordinate data. Dynamic hazard source distribution data is generated based on the ambient gas concentration real-time monitoring data. And fusing dynamic dangerous source distribution data and reinforced safety constraint boundary data to construct collaborative risk field data. And generating environment risk