Mine air flow sensing system and method based on image recognition

Abstract

The application provides a mine air flow sensing system and method based on image recognition, and relates to the field of mine ventilation. The system comprises a sensing module, an industrial control module, a dustproof module, a data generation module and a data acquisition module. The technical scheme provided by the application generates a two-dimensional non-steady temperature field through the data generation module, and uses the data acquisition module to collect video image data. The sensing module is used to pre-process, store and extract mine air flow information in the video image data. The industrial control module is used to accurately control the cooperative work among the data generation module, the data acquisition module and the dustproof module. The dustproof module is used to prevent dust from accumulating on the data generation module and the data acquisition module. The application solves the problem of insufficient explosion resistance of the sensor itself in the existing mine air flow monitoring technology using sensors, and can use data directly or indirectly related to mine air flow information to perform secondary correction of parameters, reproduction and inversion of mine air flow information.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mine ventilation, in particular to a mine air flow perception system and method based on image recognition. BACKGROUND

[0002] In underground mines of underground mining, a good ventilation system is an important guarantee for the safety of workers and the safety of mine production. A good ventilation system is not only to provide fresh air to the underground space, but more importantly, to monitor the underground air flow and monitor the state of the underground air flow in real time, so as to timely discover abnormalities and make adjustments. Thus, the risks caused by poor mine ventilation can be avoided, and the production environment can be further improved.

[0003] The mine air flow is colorless and intangible and cannot form video image data, so the current monitoring of mine air flow mostly relies on various sensors; although it has the advantage of high precision, the sensor is usually precise and fragile. However, the current underground mining of mineral resources still cannot do without blasting operations, especially in non-coal mines. The shock wave generated by blasting operation contains a lot of energy, so the mine air flow monitoring sensor is easily affected by the shock wave generated by blasting operation, resulting in its failure or even damage. The sensor arranged close to the stope is even more so. Due to the precision of its manufacture and the fragility of the material, once damaged, it will be difficult to repair, and usually only a new sensor can be used to replace it, which is high in cost.

[0004] In addition, when relying on various sensors to monitor the mine air flow, only the direct readings of the corrected mine air flow information such as air flow speed and temperature can be obtained. The most original data directly or indirectly related to the mine air flow information cannot be obtained, it is difficult to make secondary correction of the mine air flow information, and it is impossible to reproduce and invert the mine air flow information. Therefore, it is necessary to develop a mine air flow perception system and method that can not only resist the impact wave energy generated by underground blasting operation without being damaged, but also form video image data of colorless and intangible mine air flow, and obtain the most original data directly or indirectly related to the mine air flow information. SUMMARY

[0005] In view of the difficulty of forming video image data of mine air flow which is colorless and invisible, the characteristics that various sensors for monitoring mine air flow are easily damaged by underground blasting operation, and the deficiency that sensors are difficult to obtain data directly or indirectly related to mine air flow information, the application discloses a mine air flow perception system and method based on image recognition, which can not only collect colorless and invisible mine air flow information in the form of video image data, but also improve the ability of mine air flow monitoring equipment to resist damage, and can obtain the most original data directly or indirectly related to mine air flow information, thereby solving the problems of colorless and invisible mine air flow which is difficult to form video image data, and the insufficient anti-blast property of sensors in the existing mine air flow monitoring technology using sensors, and can use the obtained data directly or indirectly related to mine air flow information to perform secondary correction of parameters, reproduction and inversion of mine air flow information.

[0006] The technical scheme of the application is:

[0007] The application provides a mine air flow perception system based on image recognition, which comprises a perception module, an industrial control module, a dustproof module, a data generation module and a data acquisition module.

[0008] The data generation module is used to generate a two-dimensional non-steady temperature field containing mine air flow information under the control of the industrial control module; the mine air flow information includes air flow direction, air speed, air flow temperature and air humidity.

[0009] The data acquisition module is used to collect the two-dimensional non-steady temperature field containing mine air flow information generated by the data generation module in the form of video image data under the control of the industrial control module, and simultaneously obtain real-time temperature information of the data generation module.

[0010] The perception module is used to preprocess, store and extract mine air flow information in the video image data collected by the data acquisition module.

[0011] The industrial control module is used to control the cooperative work among the data generation module, the data acquisition module and the dustproof module, supervise the running state of the data generation module, the data acquisition module and the dustproof module, control the power supply of the data generation module, the data acquisition module and the dustproof module, and transmit the video image data collected by the data acquisition module to the perception module.

[0012] The dustproof module is arranged above the data generation module and the data acquisition module, and is used to generate a jet airflow under the control of the industrial control module to prevent dust from accumulating on the data generation module and the data acquisition module.

[0013] Further, the perception module and the industrial control module are connected by a transmission bus.

[0014] The data generation module and the industrial control module are connected through a control bus and a data generation module control branch;

[0015] The data acquisition module and the industrial control module are connected through a control bus and a data acquisition module control branch;

[0016] The dustproof module and the industrial control module are connected through a control bus and a dustproof module control branch;

[0017] Further, the perception module includes an image preprocessing module, an image database and a deep learning neural network model;

[0018] The image preprocessing module is used to simplify the video image data collected by the data acquisition module, eliminate the information irrelevant to the mine air flow information in the video image data, and obtain the preprocessed video image data;

[0019] The image database is used to store the original video image data collected by the data acquisition module and the video image data preprocessed by the image preprocessing module;

[0020] The deep learning neural network model is used to extract features from the processed video image data, identify and output the mine air flow information contained in the video image data;

[0021] Further, the industrial control module includes a data generation module controller, a dustproof module controller, a data transmission controller and a data acquisition module controller;

[0022] The dustproof module controller is used to control the power supply of the dustproof module, the opening or closing of the jet airflow, and the size of the generated jet airflow;

[0023] The data generation module controller is used to control the power supply of the data generation module and set the constant temperature value of the data generation module;

[0024] The data acquisition module controller is used to control the power supply of the data acquisition module and the collection of video image data;

[0025] The data transmission controller is used to receive real-time video image data collected by the data acquisition module and transmit it to the perception module;

[0026] Further, the data generation module includes a constant temperature heating panel, the power supply and constant temperature value of which are controlled by the data generation module controller in the industrial control module. After being powered on, the constant temperature heating panel uniformly heats up to the set constant temperature value and keeps constant, and then the power supply of the constant temperature heating panel is cut off. The constant temperature heating panel naturally cools down under the action of the mine air flow to generate a two-dimensional non-steady temperature field;

[0027] Further, the data acquisition module comprises a thermal imager for acquiring real-time temperature information of the constant temperature heating panel in the data generation module, and collecting video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel in the data generation module;

[0028] Further, the dust prevention module comprises an air curtain generator, an air door switch, a blocking air door, a panel air duct, a lens air duct, a lens air outlet and a panel air outlet.

[0029] The lens air outlet is aligned with the front lens of the thermal imager in the data acquisition module, the panel air outlet is aligned with the constant temperature heating panel, the panel air duct is arranged above the lens air duct, the panel air duct and the lens air duct are communicated with the air curtain generator, and the air inlets of the panel air duct and the lens air duct are arranged inside the air curtain generator; the air door switch is arranged at the air inlet of the panel air duct inside the air curtain generator, and the blocking air door is arranged on the air door switch.

[0030] The air curtain generator generates a jet airflow, the jet airflow enters the panel air duct and the lens air duct through the air inlets of the panel air duct and the lens air duct, and flows out from the panel air outlet and the lens air outlet to form a lens dust prevention air curtain and a panel dust prevention air curtain; when the air door switch is opened and the blocking air door is opened, the airflow generated by the air curtain generator flows into the panel air duct; when the air door switch is closed and the blocking air door is closed, the airflow is blocked from flowing into the panel air duct; the power supply and working state of the air curtain generator and the air door switch are controlled by the dust prevention module controller in the industrial control module.

[0031] In another aspect, the application provides a mine air flow sensing method based on image recognition, comprising the following steps:

[0032] Step 1: acquire video image data under different mine air flow information conditions, construct a video image data set and divide the video image data set into a training set, a validation set and a test set according to a set proportion;

[0033] Step 1.1: deploy the industrial control module, the data generation module and the data acquisition module in the laboratory, under different mine air flow information conditions, the constant temperature heating panel in the data generation module reaches a set constant temperature value and stops power supply, naturally cools down under the action of air flow, and the thermal imager in the data acquisition module is used to collect video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel during the natural cooling process under the action of air flow, to obtain a plurality of laboratory original video image data;

[0034] Step 1.2: Deploy the industrial control module, data generation module and data acquisition module in different mine tunnels, measure the mine air flow information in the mine tunnel, the constant temperature heating panel in the data generation module reaches the set constant temperature value and stops power supply, naturally cools down under the action of the air flow, and uses the thermal imager in the data acquisition module to collect the video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel during the natural cooling process under the action of the air flow, to obtain a plurality of measured original video image data;

[0035] Step 1.3: The image preprocessing module in the perception module is used to preprocess the laboratory original video image data and the measured original video image data respectively, the preprocessed laboratory original video image data and the measured original video image data are used as sample feature data, and the corresponding mine air flow information is set as the label of the sample feature data, and stored in the image database in the perception module, to obtain the laboratory original data set and the measured original data set respectively;

[0036] Step 1.4: The laboratory original data set is divided into training set and validation set according to the set proportion, and the measured original data set is used as test set;

[0037] Step 2: The training set is used to train the deep learning neural network model in the perception module, to obtain the trained deep learning neural network model, the performance of the trained deep learning neural network model is evaluated and the parameters are adjusted by using the validation set, and finally the perception accuracy of the trained deep learning neural network model in the measured data is evaluated by using the test set, to obtain the final deep learning neural network model;

[0038] Step 3: Deploy the mine air flow perception system in the mine tunnel to be measured;

[0039] Specifically, the perception module is deployed on the ground, the industrial control module, the data generation module, the data acquisition module and the dustproof module are all deployed in the mine tunnel, and the perception module is connected with the industrial control module through the transmission bus; the data generation module is connected with the industrial control module through the data generation module control branch, the data acquisition module is connected with the industrial control module through the data acquisition module control branch, and the dustproof module is connected with the industrial control module through the dustproof module control branch;

[0040] Step 4: Collect real-time video image data in the mine tunnel;

[0041] Step 4.1: The dustproof module controller in the industrial control module supplies power to the dustproof module and controls the wind curtain generator in the dustproof module to generate jet airflow, controls the opening of the air door switch, and blocks the opening of the air door and the panel air duct, the jet airflow flows out from the panel air outlet and the lens air outlet through the panel air duct and the lens air duct, forming a lens dustproof wind curtain and a panel dustproof wind curtain;

[0042] Step 4.2: The data generation module controller in the industrial control module sets a constant temperature value for the constant temperature heating panel in the data generation module and supplies power. If the data generation module starts normally, it transmits normal start state information to the dustproof module controller in the industrial control module, and executes step 4.3. If the data generation module cannot operate normally, it transmits abnormal operation information to the dustproof module controller in the industrial control module, determines that the data generation module is abnormal, and controls the dustproof module controller and the data generation module controller to cut off the power supply of the dustproof module and the data generation module. After the exception is eliminated, step 4.1 is executed again.

[0043] Step 4.3: After receiving the normal start state information feedback from the data generation module controller, the dustproof module controller in the industrial control module controls the air door switch to close, blocks the closure of the air door and the panel air duct, blocks the jet airflow through the panel air duct, and closes the panel dustproof air curtain. The dustproof module controller sends the air door closing information to the data acquisition module controller.

[0044] Step 4.4: After receiving the air door closing information, the data acquisition module controller in the industrial control module supplies power to the thermal imager in the data acquisition module. After the thermal imager starts running, the data acquisition module controller controls the thermal imager in the data acquisition module to obtain real-time temperature information of the constant temperature heating panel in the data generation module.

[0045] Step 4.5: The constant temperature heating panel uniformly heats up to the set constant temperature value and keeps the temperature constant. After the thermal imager in the data acquisition module obtains the real-time temperature information of the constant temperature heating panel and reaches the set constant temperature value, the data acquisition module controller sends a power-off signal to the data generation module controller.

[0046] Step 4.6: After receiving the power-off signal transmitted by the data acquisition module controller, the data generation module controller cuts off the power supply of the data generation module and feeds back the normal stop information of the data generation module to the data acquisition module controller. The constant temperature heating panel in the data generation module naturally cools down under the action of mine roadway airflow.

[0047] Step 4.7: After receiving the normal stop information feedback from the data generation module controller, the data acquisition module controller controls the thermal imager in the data acquisition module to collect video image data, and transmits the video image data to the data transmission controller in the industrial control module.

[0048] Step 4.8: After the data transmission controller receives the video image data, if the video image data has been successfully received, the data transmission controller sends a data reception success signal to the dustproof module controller, and transmits the video image data to the sensing module through the transmission bus, and then executes step 4.9; if the video image data fails to be received, the data transmission controller sends a data reception failure signal to the data acquisition module controller, and the data acquisition module transmits the video image data to the data transmission controller in the industrial control module again; if the video image data fails to be received for more than a set number of times, it is determined that the data transmission controller is abnormal, and the power supply of the dustproof module, the data generation module and the data acquisition module is cut off by the industrial control module, and step 4.1 is re-executed after the abnormality is eliminated;

[0049] Step 4.9: After the dustproof module controller receives the data reception success signal fed back by the data transmission controller, the dustproof module controller controls the opening of the air door switch to open the blocking air door, allowing the jet airflow to pass through the panel air duct and flow out of the panel air outlet, and forming the panel dustproof air curtain again.

[0050] Step 5: The sensing module is used to realize the mine air flow information sensing of the mine, and the mine air flow information is obtained.

[0051] Specifically, the sensing module receives the real-time video image data transmitted by the data transmission controller in the industrial control module, and stores the preprocessed image in the image database after the image preprocessing module, and the final deep learning neural network model in the sensing module extracts the mine air flow information in the video image data after obtaining the real-time video image data, and realizes the mine air flow information sensing.

[0052] Compared with the prior art, the beneficial effects of the present application are:

[0053] 1. Compared with the sensor technology, the anti-explosion performance of the constant temperature heating panel in the data generation module and the thermal imager in the data acquisition module in the technical solution provided by the present application is stronger, which can effectively resist the influence of the shock wave generated by the underground blasting operation.

[0054] 2. The mine air flow is colorless and intangible, and it is difficult to form video image data. The technical solution provided by the present application generates a two-dimensional non-steady temperature field through the data generation module, and collects video image data through the data acquisition module, which is the most original data directly or indirectly related to the mine air flow information; not only can the colorless and intangible mine air flow information be collected in the form of video image data, but also can be used for reproduction and inversion of the mine air flow information.

[0055] 3. The mine air flow information sensing technology based on image recognition provided by the present application is realized through the deep learning neural network model in the sensing module, which can improve the accuracy of mine air flow information sensing by adjusting the model or increasing the amount of video image data, and can also perform secondary correction of the mine air flow information sensing result.

[0056] 4. The dust prevention module is arranged in the mine air flow sensing system based on image recognition, dust accumulation on the data generation module and the data acquisition module can be prevented, influence of dust accumulation on data acquisition is reduced, and quality of collected video image data is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 FIG. 1 is a system structure schematic diagram of the mine air flow sensing system based on image recognition in the embodiment of the present application;

[0058] Figure 2 FIG. 2 is a device composition schematic diagram of the mine air flow sensing system based on image recognition in the embodiment of the present application;

[0059] Figure 3 FIG. 3 is a structure schematic diagram of the blocking damper in the embodiment of the present application;

[0060] Figure 4 FIG. 4 is an embodiment schematic diagram of the mine air flow sensing system based on image recognition in the embodiment of the present application deployed in a mine;

[0061] Figure 5 FIG. 5 is a partial enlarged view of the mine air flow sensing system based on image recognition deployed in the embodiment of the present application;

[0062] Wherein, I-sensing module; II-industrial control module; III-dust prevention module; IV-data generation module; V-data acquisition module; 3-transmission bus; 4-control bus; 5-dust prevention module control branch; 6-data acquisition module control branch; 7-data generation module control branch; 8-constant temperature heating panel; 9-thermal imager; 10-air curtain generator; 11-damper switch; 12-panel air duct; 13-lens air duct; 14-lens air outlet; 15-panel air outlet; 16-blocking damper; 17-mine tunnel. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. It should be declared that the following described embodiments and drawings are only used to help understand the method of the present application and its core idea, and are only some embodiments of the present application; for other skilled in the art, according to the idea provided by the present application, the specific implementation and application range will be changed; therefore, the content of the specification should not be understood as a limitation of the present application; all other embodiments obtained by the ordinary skilled in the art without making creative efforts are within the scope of protection of the present application.

[0064] Reference to an "embodiment" in this disclosure means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. As will be apparent to those of ordinary skill in the art, embodiments of the application described can be combined with one another.

[0065] The basic idea of the application is:

[0066] 1) The application proposes to use a device with strong anti-explosion performance as a data generation and acquisition device. Compared with various sensors with precise structure but relatively fragile, the constant temperature heating panel has better anti-explosion performance; even if it is deployed in the mine roadway close to the stope, it can also operate normally and maintain a good working state during the underground blasting operation.

[0067] 2) The application proposes to use a thermal imager to collect video image data of the natural cooling of the constant temperature heating panel under the action of mine air flow within a period of time. In the case of relatively stable ambient temperature and no air flow, if the temperature of an object is higher than the ambient temperature, its natural cooling process must have certain rules; if a certain air flow rate is applied in a single direction, the cooling speed of the object will be accelerated, and the cooling process must also have certain rules. Therefore, the constant temperature heating panel after reaching a constant temperature can be cut off its power supply and placed under the mine air flow, so that the constant temperature heating panel cools down due to the heat on the surface being taken away by the mine air flow flowing; and a thermal imager is used to collect video image data of the natural cooling of the constant temperature heating panel under the action of mine air flow; these video image data contain information related to mine air flow, and image recognition technology is used to extract these information.

[0068] As shown in Figure 1 , Figure 2 The mine air flow perception system based on image recognition includes a perception module I, an industrial control module II, a dustproof module III, a data generation module IV, and a data acquisition module V;

[0069] The data generation module IV is used to generate a two-dimensional non-steady temperature field containing mine air flow information under the control of the industrial control module II; the mine air flow information includes but is not limited to air flow direction, air speed, air flow temperature, and air humidity;

[0070] The data acquisition module V is used to collect the two-dimensional non-steady temperature field containing mine air flow information generated by the data generation module IV in the form of video image data under the control of the industrial control module II, and simultaneously obtain real-time temperature information of the data generation module IV;

[0071] The perception module I is used for pre-processing, storing and extracting mine air flow information in the video image data collected by the data acquisition module V.

[0072] The industrial control module II is used for accurately controlling the cooperative work among the data generation module IV, the data acquisition module V and the dustproof module III, monitoring the running state of the data generation module IV, the data acquisition module V and the dustproof module III, controlling the power supply of the data generation module IV, the data acquisition module V and the dustproof module III, and transmitting the video image data collected by the data acquisition module V to the perception module I.

[0073] The dustproof module III is arranged above the data generation module IV and the data acquisition module V, and is used for generating a jet airflow under the control of the industrial control module II to prevent dust from accumulating on the data generation module IV and the data acquisition module V.

[0074] One perception module I can be provided with a plurality of sets of industrial control modules II, data generation modules IV, data acquisition modules V and dustproof modules III.

[0075] The perception module I and the industrial control module II are connected by using a transmission bus 3.

[0076] The data generation module IV and the industrial control module II are connected by using a control bus 4 and a data generation module control branch 7.

[0077] The data acquisition module V and the industrial control module II are connected by using a control bus 4 and a data acquisition module control branch 6.

[0078] The dustproof module III and the industrial control module II are connected by using a control bus 4 and a dustproof module control branch 5.

[0079] The perception module I comprises an image preprocessing module, an image database and a deep learning neural network model.

[0080] The image preprocessing module is used for simplifying the video image data collected by the data acquisition module V, eliminating information irrelevant to the mine air flow information in the video image data, enhancing the detectability of the mine air flow information in the image, and obtaining pre-processed video image data.

[0081] The image database is used for storing the original video image data collected by the data acquisition module V and the video image data pre-processed by the image preprocessing module.

[0082] The deep learning neural network model includes but is not limited to a convolutional neural network, and is used for extracting features from the processed video image data, identifying and outputting the mine air flow information contained in the video image data.

[0083] The industrial control module II includes a data generation module controller, a dust prevention module controller, a data transmission controller and a data acquisition module controller;

[0084] The dust prevention module controller is used for controlling power supply of the dust prevention module III, opening or closing of the jet airflow and the size of the generated jet airflow;

[0085] The data generation module controller is used for controlling power supply of the data generation module IV and setting a constant temperature value of the data generation module IV;

[0086] The data acquisition module controller is used for controlling power supply of the data acquisition module V and acquisition of video image data;

[0087] The data transmission controller is used for receiving real-time video image data collected by the data acquisition module V and transmitting the real-time video image data to the perception module I;

[0088] The data generation module IV includes a constant temperature heating panel 8, power supply and a constant temperature value of which are controlled by the data generation module controller in the industrial control module II, the constant temperature heating panel 8 is uniformly heated to a set constant temperature value and kept constant after being powered on, then power supply of the constant temperature heating panel 8 is cut off, and the constant temperature heating panel 8 is naturally cooled to generate a two-dimensional non-steady temperature field under the action of mine airflow;

[0089] The data acquisition module V includes a thermal imager 9, which is used for acquiring real-time temperature information of the constant temperature heating panel 8 in the data generation module IV and collecting video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel 8 in the data generation module IV; power supply and working state of the thermal imager 9 are controlled by the data generation module controller in the industrial control module II;

[0090] The dust prevention module III includes an air curtain generator 10, an air door switch 11, a blocking air door 16, a panel air duct 12, a lens air duct 13, a lens air outlet 14 and a panel air outlet 15;

[0091] The lens air outlet 14 is aligned with a front lens of the thermal imager 9 in the data acquisition module V, the panel air outlet 15 is aligned with the constant temperature heating panel 8, the panel air duct 12 is arranged above the lens air duct 13, the panel air duct 12 and the lens air duct 13 are communicated with the air curtain generator 10, and air inlets of the panel air duct 12 and the lens air duct 13 are arranged inside the air curtain generator 10; the air door switch 11 is arranged at the air inlet of the panel air duct 12 inside the air curtain generator 10, and the blocking air door 16 is arranged on the air door switch 11;

[0092] The air curtain generator 10 generates a jet airflow, which enters the panel air duct 12 and the lens air duct 13 through the air inlet of the panel air duct 12 and the lens air duct 13, and flows out through the panel air outlet 15 and the lens air outlet 14, forming a lens dustproof air curtain and a panel dustproof air curtain, which can prevent dust accumulation on the data generation module IV and the data acquisition module V and reduce the influence of dust accumulation on data acquisition. Figure 3 As shown in the figure, the air door switch 11 is opened, the air door 16 is opened, and the airflow generated by the air curtain generator 10 flows into the panel air duct 12. When the air door switch 11 is closed, the air door 16 is closed with the panel air duct 12, and the airflow is blocked from flowing into the panel air duct 12. The power supply and working state of the air curtain generator 10 and the air door switch 11 are controlled by the dustproof module controller in the industrial control module II.

[0093] Figure 5 As shown in the figure, the air door switch 11 is opened, the air door 16 is opened, and the airflow generated by the air curtain generator 10 flows into the panel air duct 12. When the air door switch 11 is closed, the air door 16 is closed with the panel air duct 12, and the airflow is blocked from flowing into the panel air duct 12. The power supply and working state of the air curtain generator 10 and the air door switch 11 are controlled by the dustproof module controller in the industrial control module II. Figure 4 As shown in the figure, the air door switch 11 is opened, the air door 16 is opened, and the airflow generated by the air curtain generator 10 flows into the panel air duct 12. When the air door switch 11 is closed, the air door 16 is closed with the panel air duct 12, and the airflow is blocked from flowing into the panel air duct 12. The power supply and working state of the air curtain generator 10 and the air door switch 11 are controlled by the dustproof module controller in the industrial control module II. Figure 4 、 Figure 5 As shown in the figure, the air door switch 11 is opened, the air door 16 is opened, and the airflow generated by the air curtain generator 10 flows into the panel air duct 12. When the air door switch 11 is closed, the air door 16 is closed with the panel air duct 12, and the airflow is blocked from flowing into the panel air duct 12. The power supply and working state of the air curtain generator 10 and the air door switch 11 are controlled by the dustproof module controller in the industrial control module II.

[0094] Step 1: Obtain video image data under different mine air flow information conditions, construct a video image data set, and divide the video image data set into a training set, a validation set, and a test set according to a set proportion;

[0095] Step 1.1: Deploy the industrial control module II, the data generation module IV, and the data acquisition module V in the laboratory, and under different mine air flow information conditions, the constant temperature heating panel 8 in the data generation module IV reaches a set constant temperature value and stops power supply, naturally cools down under the action of air flow, and the thermal imager 9 in the data acquisition module V is used to collect video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel 8 during the natural cooling process under the action of air flow, to obtain a plurality of laboratory original video image data;

[0096] In this embodiment, the industrial control module II, the data generation module IV, and the data acquisition module V are deployed in the laboratory, the working state of the fan (such as the running direction, the blade installation angle, and the power) and the air temperature control measures (such as resistance heating and ice block cooling) are changed to set different mine air flow information conditions (including but not limited to air flow direction, air flow speed, and air flow temperature and humidity) for the air flow, so that the constant temperature heating panel 8 in the data generation module IV reaches a constant temperature value and stops power supply, and then naturally cools down under the action of air flow, and the thermal imager 9 in the data acquisition module V is used to collect video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel 8 during the natural cooling process under the action of air flow;

[0097] Step 1.2: The industrial control module II, the data generation module IV and the data acquisition module V are deployed in different mine roadways 17 to measure the mine air flow information in the mine roadway. The constant temperature heating panel 8 in the data generation module IV reaches the set constant temperature value and stops power supply, and naturally cools down under the action of the air flow. The thermal imager 9 in the data acquisition module V is used to collect the video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel 8 during the natural cooling process under the action of the air flow, and a plurality of measured original video image data are obtained.

[0098] In this embodiment, the industrial control module II, the data generation module IV and the data acquisition module V are temporarily deployed in different mine roadways 17 to measure the ventilation parameters (including but not limited to air flow direction, air flow speed and air flow temperature and humidity, etc.). The constant temperature heating panel 8 in the data generation module IV reaches the set constant temperature value and stops power supply, and naturally cools down under the action of the air flow. The thermal imager 9 in the data acquisition module V is used to collect the video image data of the two-dimensional non-steady temperature field generated by the constant temperature heating panel 8 during the natural cooling process under the action of the air flow.

[0099] Step 1.3: The image preprocessing module in the perception module I is used to preprocess the laboratory original video image data and the measured original video image data respectively. The preprocessed laboratory original video image data and the measured original video image data are used as sample feature data, and the corresponding mine air flow information is set as the label of the sample feature data, which is stored in the image database in the perception module I, and the laboratory original data set and the measured original data set are obtained respectively.

[0100] Step 1.4: The laboratory original data set is divided into training set and validation set according to the set proportion, and the measured original data set is used as test set.

[0101] In this embodiment, the training set is used for training the deep learning neural network model in the perception module I, the validation set is used for verifying the performance of the deep learning neural network model and the perception accuracy of the mine air flow information, and the test set is used for testing the perception accuracy of the mine air flow information of the deep learning neural network model in the measured data.

[0102] Step 2: The training set is used to train the deep learning neural network model in the perception module I to obtain the trained deep learning neural network model. The performance of the trained deep learning neural network model is evaluated and the parameters are adjusted by using the validation set. Finally, the perception accuracy of the mine air flow information of the trained deep learning neural network model in the measured data is evaluated by using the test set, and the final deep learning neural network model is obtained.

[0103] Step 3: The mine air flow perception system is deployed in the mine roadway to be measured.

[0104] Specifically: the perception module I is arranged on the ground, as shown in Figure 4 、 Figure 5 The industrial control module II, the data generation module IV, the data acquisition module V and the dustproof module III are arranged in the mine tunnel 17, the perception module I is connected with the industrial control module II through the transmission bus 3, the data generation module IV is connected with the industrial control module II through the data generation module control branch 7, the data acquisition module V is connected with the industrial control module II through the data acquisition module control branch 6, and the dustproof module III is connected with the industrial control module II through the dustproof module control branch 5 and the control bus 4.

[0105] Step 4: collecting real-time video image data in the mine tunnel 17;

[0106] Step 4.1: the dustproof module controller in the industrial control module II supplies power for the dustproof module III and controls the air curtain generator 10 in the dustproof module III to generate a jet airflow, controls the opening of the air door switch 11, and blocks the opening of the air door 16 and the panel air duct, the jet airflow passes through the panel air duct 12 and the lens air duct 13, and flows out from the panel air outlet 15 and the lens air outlet 24, to form a lens dustproof air curtain and a panel dustproof air curtain.

[0107] Step 4.2: the data generation module controller in the industrial control module II sets a constant temperature value for the constant temperature heating panel 8 in the data generation module IV and supplies power, if the data generation module IV starts normally, the normal start state information is transmitted to the dustproof module controller in the industrial control module II, and step 4.3 is performed, if the data generation module IV cannot normally run, the abnormal running information is transmitted to the dustproof module controller in the industrial control module II, it is judged that the data generation module IV is abnormal, the power supply of the dustproof module III and the data generation module IV is cut off by the industrial control module II, and after the exception is excluded, step 4.1 is re-executed.

[0108] Step 4.3: after the dustproof module controller in the industrial control module II receives the normal start state information of the data generation module IV fed back by the data generation module controller, the dustproof module controller controls the closing of the air door switch 11, blocks the closing of the air door 16 and the panel air duct 12, blocks the jet airflow passing through the panel air duct 12, the panel dustproof air curtain is closed, and the dustproof module controller sends the air door closing information to the data acquisition module controller.

[0109] Step 4.4: after the data acquisition module controller in the industrial control module II receives the air door closing information, the data acquisition module controller supplies power for the thermal imager 9 in the data acquisition module V, and after the thermal imager 9 starts to run, the data acquisition module controller controls the thermal imager 9 to acquire the real-time temperature information of the constant temperature heating panel 8 in the data generation module IV;

[0110] Step 4.5: The constant temperature heating panel 8 uniformly heats up to the set constant temperature value and keeps the temperature constant. When the thermal imager 9 in the data acquisition module V acquires the real-time temperature information of the constant temperature heating panel 8 and finds that the temperature has reached the set constant temperature value, the data acquisition module controller sends a power-off signal to the data generation module controller;

[0111] Step 4.6: After receiving the power-off signal transmitted by the data acquisition module controller, the data generation module controller cuts off the power supply of the data generation module IV and feeds back the normal stop information of the data generation module IV to the data acquisition module controller. The constant temperature heating panel 8 naturally cools down under the action of the mine air flow.

[0112] Step 4.7: After receiving the normal stop information fed back by the data generation module controller, the data acquisition module controller controls the thermal imager 9 to collect video image data and transmits the video image data to the data transmission controller in the industrial control module II.

[0113] Step 4.8: After receiving the video image data, if the video image data has been successfully received, the data transmission controller sends a data reception success signal to the dustproof module controller and transmits the video image data to the perception module I through the transmission bus 3, and then executes step 4.9; if the video image data reception fails, the data transmission controller sends a data reception failure signal to the data acquisition module controller, and the data acquisition module transmits the video image data to the data transmission controller in the industrial control module again; if the video image data reception fails for multiple times, it is determined that the data transmission controller is abnormal, and the power supply of the dustproof module III, the data generation module IV and the data acquisition module V is cut off by the industrial control module II to exclude the abnormality, and then step 4.1 is executed again.

[0114] Step 4.9: The dustproof module controller receives the data reception success signal fed back by the data transmission controller, controls the opening of the air door switch 11, opens the blocking air door 16, allows the jet air flow to pass through the panel air duct 12, flows out from the panel air outlet 15, and forms the panel dustproof air curtain again.

[0115] Step 5: The perception module I realizes the mine air flow information perception of the mine, and obtains the mine air flow information.

[0116] Specifically, the perception module I receives the real-time video image data transmitted by the data transmission controller in the industrial control module II, and stores it in the image database after image preprocessing. The final deep learning neural network model in the perception module I extracts the feature information related to the mine air flow in the real-time video image data, and finally outputs the mine air flow information (including but not limited to air flow direction, air flow speed, air flow temperature and humidity, etc.), realizing the mine air flow information perception.

Claims

1. A mine ventilation sensing system based on image recognition, characterized in that, It includes sensing modules, industrial control modules, dustproof modules, data generation modules, and data acquisition modules; The data generation module is used to generate a two-dimensional unsteady temperature field containing mine airflow information under the control of the industrial control module; the mine airflow information includes airflow direction, wind speed, airflow temperature and air humidity; The data generation module includes a constant temperature heating panel. Its power supply and constant temperature value are controlled by the data generation module controller in the industrial control module. After being powered on, the constant temperature heating panel heats up evenly to the set constant temperature value and remains constant. Then, the power supply of the constant temperature heating panel is cut off. Under the action of the mine airflow, the constant temperature heating panel naturally cools down and generates a two-dimensional unsteady temperature field. The data acquisition module is used to acquire, under the control of the industrial control module, a two-dimensional unsteady temperature field containing mine airflow information generated by the data generation module in the form of video image data, and at the same time acquire the real-time temperature information of the data generation module. The sensing module is used to preprocess, store, and extract mine airflow information from the video image data acquired by the data acquisition module. The perception module includes an image preprocessing module, an image database, and a deep learning neural network model; The image preprocessing module is used to simplify the video image data acquired by the data acquisition module, eliminate information in the video image data that is not related to the mine ventilation information, and obtain preprocessed video image data. The image database is used to store the original video image data acquired by the data acquisition module and the video image data preprocessed by the image preprocessing module; The deep learning neural network model is used to extract features from the processed video image data, identify and output the mine ventilation information contained in the video image data; The industrial control module is used to control the collaborative operation between the data generation module, the data acquisition module, and the dustproof module; Monitor the operational status of the data generation module, data acquisition module, and dust prevention module, and control the power supply of the data generation module, data acquisition module, and dust prevention module; The video image data acquired by the data acquisition module is transmitted to the sensing module; The dustproof module is installed above the data generation module and the data acquisition module, and is used to generate jet airflow under the control of the industrial control module to prevent dust from accumulating on the data generation module and the data acquisition module. The dustproof module includes an air curtain generator, an air damper switch, a blocking air damper, a panel air duct, a lens air duct, a lens air outlet, and a panel air outlet; The lens air outlet is aligned with the front lens of the thermal imager in the data acquisition module, the panel air outlet is aligned with the constant temperature heating panel, the panel air duct is located above the lens air duct, the panel air duct and the lens air duct are connected to the air curtain generator, and the air inlets of the panel air duct and the lens air duct are located inside the air curtain generator; the air damper switch is located at the air inlet of the panel air duct inside the air curtain generator, and the air damper switch is equipped with a blocking air damper. The air curtain generator produces jet airflow, which enters the panel air duct and lens air duct through the air inlets and exits through the panel air outlet and lens air outlet, forming a lens dustproof air curtain and a panel dustproof air curtain. When the damper switch is opened, the damper is opened, and the airflow generated by the air curtain generator flows into the panel air duct. When the damper switch is closed, the damper and panel air duct are closed, blocking the airflow from flowing into the panel air duct. The power supply and operating status of the air curtain generator and damper switch are controlled by the dustproof module controller in the industrial control module.

2. The mine ventilation sensing system based on image recognition according to claim 1, characterized in that, The sensing module and the industrial control module are connected via a transmission bus; The data generation module and the industrial control module are connected via a control bus and a control branch line of the data generation module. The data acquisition module and the industrial control module are connected via a control bus and a control branch line of the data acquisition module. The dustproof module and the industrial control module are connected via a control bus and a dustproof module control branch line.

3. The mine ventilation sensing system based on image recognition according to claim 1, characterized in that, The industrial control module includes a data generation module controller, a dustproof module controller, a data transmission controller, and a data acquisition module controller; The dustproof module controller is used to control the power supply of the dustproof module, the opening or closing of the jet airflow, and the magnitude of the generated jet airflow; The data generation module controller is used to control the power supply of the data generation module and set a constant temperature value for the data generation module. The data acquisition module controller is used to control the power supply of the data acquisition module and the acquisition of video image data; The data transmission controller is used to receive real-time video image data collected by the data acquisition module and transmit it to the sensing module.

4. The mine ventilation sensing system based on image recognition according to claim 1, characterized in that, The data acquisition module includes a thermal imager, used to acquire real-time temperature information of the constant-temperature heating panel in the data generation module, and to acquire video image data of the two-dimensional unsteady temperature field generated by the constant-temperature heating panel in the data generation module.

5. A mine ventilation sensing method based on image recognition, implemented based on the mine ventilation sensing system based on image recognition as described in claim 1, characterized in that, Includes the following steps: Step 1: Obtain video image data under different mine ventilation conditions, construct a video image dataset, and divide the video image dataset into training set, validation set, and test set according to a set ratio; Step 2: Train the deep learning neural network model in the perception module using the training set to obtain the trained deep learning neural network model. Use the validation set to evaluate the performance and adjust the parameters of the trained deep learning neural network model. Finally, use the test set to evaluate the accuracy of the trained deep learning neural network model in perceiving mine airflow information in the measured data to obtain the final deep learning neural network model. Step 3: Deploy a mine airflow sensing system in the mine roadway to be tested; Specifically, the sensing module is deployed on the ground, while the industrial control module, data generation module, data acquisition module, and dust prevention module are all deployed in the mine roadway. The sensing module is connected to the industrial control module through a transmission bus. The data generation module connects to the industrial control module via the data generation module control branch, the data acquisition module connects to the data acquisition module control branch, and the dustproof module connects to the industrial control module via the control bus through the dustproof module control branch. Step 4: Collect real-time video image data in the mine roadways; Step 5: Use the sensing module to sense the mine airflow information and obtain the mine airflow information; Specifically, the sensing module receives real-time video image data transmitted by the data transmission controller in the industrial control module. After preprocessing by the image pre-module, the data is stored in the image database. The final deep learning neural network model in the sensing module obtains the real-time video image data and extracts the mine airflow information from the video image data to realize the perception of mine airflow information.

6. The mine ventilation sensing method based on image recognition according to claim 5, characterized in that, Step 1 specifically includes: Step 1.1: Deploy the industrial control module, data generation module, and data acquisition module in the laboratory. Under different mine airflow conditions, the constant temperature heating panel in the data generation module reaches the set constant temperature value and stops power supply. It cools down naturally under the action of airflow. The thermal imager in the data acquisition module collects video image data of the two-dimensional unsteady temperature field generated during the natural cooling process of the constant temperature heating panel under the action of airflow, and obtains several original video image data of the laboratory. Step 1.2: Deploy the industrial control module, data generation module, and data acquisition module in different mine roadways to measure the mine airflow information in the mine roadways. The constant temperature heating panel in the data generation module reaches the set constant temperature value and stops power supply, allowing it to cool down naturally under the action of airflow. The thermal imager in the data acquisition module is used to collect video image data of the two-dimensional unsteady temperature field generated by the constant temperature heating panel during the natural cooling process under the action of airflow, resulting in several measured original video image data. Step 1.3: Use the image preprocessing module in the sensing module to preprocess the laboratory raw video image data and the measured raw video image data respectively. Use the preprocessed laboratory raw video image data and the measured raw video image data as sample feature data, and set the corresponding mine airflow information as the label of the sample feature data. Store them in the image database in the sensing module to obtain the laboratory raw dataset and the measured raw dataset respectively. Step 1.4: Divide the original laboratory dataset into a training set and a validation set according to a set ratio, and use the actual test dataset as the test set.

7. The mine ventilation sensing method based on image recognition according to claim 5, characterized in that, Step 4 specifically includes: Step 4.1: The dustproof module controller in the industrial control module supplies power to the dustproof module and controls the air curtain generator in the dustproof module to generate jet airflow. It controls the opening of the air damper switch, blocking the air damper from opening the panel air duct. The jet airflow flows out through the panel air duct and lens air duct, forming a lens dustproof air curtain and a panel dustproof air curtain. Step 4.2: The data generation module controller in the industrial control module sets a constant temperature value for the constant temperature heating panel in the data generation module and supplies power. If the data generation module starts normally, it transmits normal start status information to the dustproof module controller in the industrial control module and executes step 4.

3. If the data generation module cannot operate normally, it transmits abnormal operation information to the dustproof module controller in the industrial control module, determines that the data generation module is in an abnormal state, and controls the dustproof module controller and the data generation module controller in the industrial control module to cut off the power supply to the dustproof module and the data generation module. After the abnormality is eliminated, step 4.1 is executed again. Step 4.3: After receiving the normal start-up status information from the data generation module controller, the dustproof module controller in the industrial control module controls the damper switch to close, blocking the damper from closing with the panel air duct, blocking the jet airflow from passing through the panel air duct, closing the panel dustproof air curtain, and sending the damper switch closure information to the data acquisition module controller. Step 4.4: After receiving the damper switch closing information, the data acquisition module controller in the industrial control module supplies power to the thermal imager in the data acquisition module. After the thermal imager starts running, the data acquisition module controller controls the thermal imager in the data acquisition module to acquire the real-time temperature information of the constant temperature heating panel in the data generation module. Step 4.5: The constant temperature heating panel heats up evenly to the set constant temperature value and maintains the temperature constant. After the thermal imager in the data acquisition module obtains the real-time temperature information of the constant temperature heating panel and finds that the set constant temperature value has been reached, the data acquisition module controller sends a power-off signal to the data generation module controller. Step 4.6: After receiving the power failure signal transmitted by the data acquisition module controller, the data generation module controller cuts off the power supply to the data generation module and feeds back the normal shutdown information of the data generation module to the data acquisition module controller. The constant temperature heating panel in the data generation module cools down naturally under the action of the airflow in the mine roadway. Step 4.7: After receiving the normal stop information from the data generation module controller, the data acquisition module controller controls the thermal imager in the data acquisition module to acquire video image data and transmits the video image data to the data transmission controller in the industrial control module. Step 4.8: After receiving the video image data, if the video image data has been successfully received, the data transmission controller sends a data reception success signal to the dustproof module controller and transmits the video image data to the sensing module via the transmission bus before proceeding to step 4.9; if the video image data reception fails, the data transmission controller sends a data reception failure signal to the data acquisition module controller, and the data acquisition module transmits the video image data to the data transmission controller in the industrial control module again; if the video image data reception still fails after exceeding the set number of times, it is determined that the data transmission controller is in an abnormal state, and the industrial control module controls the power supply of the dustproof module, data generation module and data acquisition module to be cut off. After the abnormality is eliminated, step 4.1 is executed again. Step 4.9: After receiving the data reception success signal from the data transmission controller, the dustproof module controller controls the opening of the damper switch, opens the blocking damper, and allows the jet airflow to pass through the panel air duct and flow out from the panel air outlet, forming a panel dustproof air curtain again.

Images