A ventilation and dust reduction method and device based on excavation working face

Abstract

The present application discloses a ventilation and dust reduction method and device based on an excavation working face, the method comprising: obtaining the dust concentration of a predetermined area in a mine collected by a dust sensor; inputting the dust concentration into a pre-trained first machine learning model, and obtaining a first wind speed corresponding to the dust concentration from the first machine learning model; obtaining an image of the predetermined area captured by a camera; inputting the image into a pre-trained second machine learning model, and obtaining a second wind speed corresponding to the image from the second machine learning model; selecting a fan speed with a larger wind speed value from the first wind speed and the second wind speed; and controlling the fan in the predetermined area according to the fan speed with a larger wind speed value. The present application solves the problem caused by manually starting and shutting down fans in mines, thereby realizing automatic control of fans and better ventilating and dust reduction in mines on the basis of energy saving.

Description

Technical Field

[0001] The present application relates to the field of mine ventilation, and more specifically, to a ventilation and dust reduction method and device based on an excavation working face. Background Art

[0002] Ventilators (or simply fans), known as the "lungs of mines", are fixed equipment in mines. They are responsible for delivering fresh air to the mines, exhausting dust and dirty airflow, ensuring safe production in mines and personal safety. Real-time and accurate monitoring of the operating status and operating environment of mine fans plays a vital role in safe production in mines.

[0003] The start-up of the fan is generally controlled manually. This control method is to start the fan after the worker reaches the work position and shut down the fan before the worker leaves work. This processing method is not intelligent enough and cannot meet the needs of intelligent control. Summary of the invention

[0004] The embodiments of the present application provide a ventilation and dust reduction method and device based on an excavation working face, so as to at least solve the problems caused by manually starting and shutting down fans in mines.

[0005] According to one aspect of the present application, a ventilation and dust reduction method based on an excavation working face is provided, including: obtaining the dust concentration in a predetermined area of ​​a mine collected by a dust sensor; inputting the dust concentration into a pre-trained first machine learning model, and obtaining a first wind speed corresponding to the dust concentration from the first machine learning model; obtaining an image of the predetermined area taken by a camera; inputting the image into a pre-trained second machine learning model, and obtaining a second wind speed corresponding to the image from the second machine learning model; selecting a fan speed with a larger wind speed value from the first wind speed and the second wind speed; and controlling the fan in the predetermined area according to the fan speed with a larger wind speed value.

[0006] Furthermore, the first machine learning model is trained using multiple groups of first training data, where the first training data includes dust concentration and wind speed of the fan corresponding to the dust concentration.

[0007] Furthermore, the second machine learning model is trained using multiple sets of second training data, and the second training data includes an image of the predetermined area and a wind speed of the fan corresponding to the dust concentration represented in the image.

[0008] Further, selecting a wind speed of a wind turbine with a larger wind speed value from the first wind speed and the second wind speed includes:

[0009] If the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range, the wind speed of the wind turbine with the larger wind speed value is selected from the first wind speed and the second wind speed;

[0010] If the absolute value of the difference between the first wind speed and the second wind speed is outside the predetermined range, the fan in the area is started using the larger wind speed between the first wind speed and the second wind speed, and the wind speed is maintained for a predetermined time of blowing. After the predetermined time of blowing, it is determined whether the dust concentration decreases by more than a threshold value within the predetermined time. If it exceeds the threshold, the fan speed is reduced by a predetermined value and blowing is performed for a second time, and so on, until the fan speed is reduced to the smaller wind speed between the first wind speed and the second wind speed.

[0011] Furthermore, the predetermined range is predetermined.

[0012] According to another aspect of the present application, a ventilation and dust reduction device based on an excavation working face is also provided, including: a first acquisition module, used to obtain the dust concentration of a predetermined area in a mine collected by a dust sensor; a second acquisition module, used to input the dust concentration into a pre-trained first machine learning model, and obtain a first wind speed corresponding to the dust concentration from the first machine learning model; a third acquisition module, used to obtain an image of the predetermined area taken by a camera; a fourth acquisition module, used to input the image into a pre-trained second machine learning model, and obtain a second wind speed corresponding to the image from the second machine learning model; a selection module, used to select a fan speed with a larger wind speed value from the first wind speed and the second wind speed; a control module, used to control the fan in the predetermined area according to the fan speed with a larger wind speed value.

[0013] Furthermore, the first machine learning model is trained using multiple groups of first training data, where the first training data includes dust concentration and wind speed of the fan corresponding to the dust concentration.

[0014] Furthermore, the second machine learning model is trained using multiple sets of second training data, and the second training data includes an image of the predetermined area and a wind speed of the fan corresponding to the dust concentration represented in the image.

[0015] Further, the selection module is used to select a wind turbine wind speed with a larger wind speed value from the first wind speed and the second wind speed when the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range.

[0016] Furthermore, the predetermined range is predetermined.

[0017] In the embodiment of the present application, the dust concentration in a predetermined area of ​​the mine collected by the dust sensor is adopted; the dust concentration is input into a pre-trained first machine learning model, and a first wind speed corresponding to the dust concentration is obtained from the first machine learning model; an image of the predetermined area captured by a camera is obtained; the image is input into a pre-trained second machine learning model, and a second wind speed corresponding to the image is obtained from the second machine learning model; a fan speed with a larger wind speed value is selected from the first wind speed and the second wind speed; and the fan in the predetermined area is controlled according to the fan speed with a larger wind speed value. The present application solves the problems caused by manually starting and shutting down fans in mines, thereby realizing automatic control of fans and better ventilating and dust reduction in mines on the basis of energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 It is a flow chart of ventilation and dust reduction based on the excavation working face according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0022] There is only one tunnel in the underground coal mine excavation working face in the mine, and air supply and return are completed in this tunnel. The fan outside the excavation tunnel sends air into the excavation head through the wind pipe to dilute the dust in the excavation head. Then a set of fans is installed near the excavation head to extract the air inside the excavation head to the outside of the excavation tunnel to achieve dust reduction. The start and stop of the above-mentioned fan and the size of the air volume need to be analyzed according to the monitored tunnel environment, and the execution instructions of the fan are given to achieve the best dust reduction effect in the excavation tunnel. In the above-mentioned tunnel environment, dust concentration is the core concern. The embodiment of the present application is mainly a method of controlling the fan based on dust concentration.

[0023] In this embodiment, a ventilation and dust reduction method based on an excavation working face is provided. Figure 1is a flow chart of ventilation and dust reduction based on the excavation working face according to an embodiment of the present application, such as Figure 1 As shown below, Figure 1 The steps involved are described in detail.

[0024] Step S102, obtaining dust concentration in a predetermined area of ​​the mine collected by a dust sensor.

[0025] Step S104: input the dust concentration into a pre-trained first machine learning model, and obtain the first wind speed corresponding to the dust concentration from the first machine learning model; for example, the first machine learning model is trained using multiple groups of first training data, and the first training data includes the dust concentration and the wind speed of the fan corresponding to the dust concentration.

[0026] As an optional implementation, the dust concentration and the wind speed of the fan corresponding to the dust concentration are obtained through experiments, and a time period (e.g., 5 minutes) is predetermined. When the dust concentration is a predetermined value, the wind speed that can reduce the dust concentration to a standard value by blowing within the predetermined time period is obtained, and the wind speed is the wind speed of the fan corresponding to the dust concentration of the predetermined value. The standard value is obtained in advance from the enterprise operating specifications.

[0027] Step S106, obtaining an image captured by a camera of the predetermined area.

[0028] Step S108: input the image into a pre-trained second machine learning model, and obtain the second wind speed corresponding to the image from the second machine learning model; for example, the second machine learning model is trained using multiple sets of second training data, and the second training data includes the image of the predetermined area and the wind speed of the fan corresponding to the dust concentration represented in the image.

[0029] As an optional implementation, in this step, the second machine learning model can be a machine learning model based on image recognition of dust concentration, and the second machine learning model is trained using multiple sets of training data, wherein the training data includes images and dust concentrations of the images marked with manual labels. The image captured of the predetermined area is input into the second machine learning model, and the output dust concentration is obtained from the second machine learning model; the dust concentration is input into the first machine learning model to obtain the second wind speed.

[0030] As an optional implementation, the image used to train the second machine learning model is obtained by processing the captured image as follows: a dust-free background image is captured, and both the image to be identified and the background image for dust concentration identification are binarized to obtain two black-and-white images, and the image obtained by subtracting each pixel value from the two black-and-white images is used as the image used to train the second machine learning model. The image captured in the predetermined area is also binarized, and the image obtained by subtracting each pixel value from the background image is input into the second machine learning model to obtain the output dust concentration.

[0031] Step S110, selecting a wind speed of a wind turbine with a larger wind speed value from the first wind speed and the second wind speed;

[0032] Optionally, in this step, if the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range, the wind speed of the wind turbine with the larger wind speed value is selected from the first wind speed and the second wind speed, wherein the predetermined range is predetermined.

[0033] Step S112: controlling the fans in the predetermined area according to the wind speed of the fan with the larger wind speed value.

[0034] The above steps solve the problems caused by manual starting and shutting down of fans in mines, thereby realizing automatic control of fans and better ventilating and reducing dust in mines on the basis of energy saving.

[0035] As another optional implementation, a preconfigured standard value may be obtained, and when the dust concentration is lower than the standard value, the fan is not started. However, when the dust concentration is lower than the standard value, a first dust concentration value of a first time period is obtained, and then a second dust concentration value of a second time period after the first time period is obtained. If the second dust concentration value is greater than the first dust concentration value, and the second dust concentration value is less than the standard value and the difference between the second dust concentration value and the first dust concentration value is greater than the preconfigured concentration value, the fan is started at the preconfigured wind speed.

[0036] In another optional embodiment, the operating status of the fan can also be monitored, and if the operating status of the fan is abnormal, an alarm message is issued, wherein the alarm message is sent to the management personnel, and the alarm message sent to the management personnel is used to indicate that the operating status of the fan is abnormal; staff working in the area where the fan is located are obtained, wherein the staff in the area where the fan is located are determined by smart devices carried by the staff; the alarm message is sent to the smart device of the staff in the area where the fan is located, and the alarm message sent to the smart device is used to instruct the staff to leave the area where the fan is located.

[0037] There are many ways to monitor the operating status of the fan. For example, the monitoring system may include a monitoring center, a transmission device and a monitoring device; the monitoring device includes a power sensor, a negative pressure and differential pressure detector, a winding temperature monitor, a vibration sensor and a wind speed monitoring sensor; the transmission device includes a switch and an optical terminal, the switch is connected to the optical terminal 22, the optical terminal is connected to the power sensor, the negative pressure and differential pressure detector, the winding temperature monitor, the vibration sensor and the wind speed monitoring sensor, and the switch is connected to the monitoring center.

[0038] The monitoring center realizes the functions of monitoring data collection, display, storage, analysis, report printing and remote control. The transmission device is equipped with a flame-retardant optical cable and a communication cable for mining. Through the switch and the optical terminal, the real-time transmission of monitoring data and the effective issuance of control signals can be realized. The monitoring equipment also includes a monitoring substation, a monitoring sensor, a transmitter, and a control actuator. The power sensor can understand the current operating status of the fan by monitoring some electrical parameters, which is conducive to discovering motor faults. The vibration sensor is a single-axis intelligent vibration sensor, which can directly convert the mechanical vibration signal into digital waveform data and transmit it to the computer for processing through the RS485 interface of the sensor. It has a stainless steel waterproof shell, which makes the sensor suitable for humid environments. The built-in DSP signal processor of the sensor performs FFT (Fourier transform) analysis on the vibration data and calculates the speed and displacement values. The sensor can directly output vibration waveform data in the time domain and frequency domain.

[0039] The solution in this embodiment can be applied to fans of various structures. For example, in this embodiment, such a fan system is provided. The mine fan system includes a closed wall, a fan, a wind duct and a sealed door. The sealed door and the wind duct are arranged on the sealed wall. The fan is arranged in the wind duct. An anti-backflow component is arranged in conjunction with the fan. The anti-backflow component is fixedly arranged in front of the wind duct. The anti-backflow component includes a frame and at least four baffles. The baffles are movably connected to the frame through a rotating shaft. The opening direction of the baffles is the same as the air outlet direction of the fan. Preferably, the baffles of the anti-backflow component are arranged in sequence from top to bottom. Preferably, the angle between the baffles of the anti-backflow component and the plumb bob plane when opened is 50° to 89°.

[0040] In this embodiment, a dust-proof filtering device for a mine ventilator can also be added to the fan, and the filtering device includes an air inlet pipe, and a first filter box, a second filter box and a third filter box which are connected to each other through a connecting pipe are arranged on one side of the air inlet pipe in sequence, and the air inlet pipe is connected to the first filter box, and a first motor is arranged in the first filter box, and a first fan is arranged on the first motor, and a first filter screen is also arranged in the first filter box. When the first fan is operated, the outside air is sucked into the first filter box, and the air is filtered for the first time on the first filter screen; a plurality of atomizing nozzles are arranged on the top of the second filter box, and a water tank connected to the atomizing nozzle is arranged on the outer surface of the top of the second filter box, and a plurality of layers of second filter screens are also arranged in the second filter box. The air is moistened by atomized water in the second filter box and is filtered for the second time by the second filter screen; a plurality of layers of third filter screens are arranged in the third filter box, and the air is filtered for the third time in the third filter box.

[0041] Optionally, a first bracket is provided in the first filter box, the first motor is provided on the first bracket, and the first filter is provided on the side of the first motor away from the air inlet pipe. The first motor is a double-output shaft motor, the output shaft of the first motor close to the air inlet pipe is provided with a first fan, the output shaft of the first motor away from the air inlet pipe is provided with a rotating shaft, the rotating shaft is provided with a brush, and the brush contacts the first filter. The rotating shaft is rotatably connected with the output shaft, the connecting end of the rotating shaft and the output shaft is provided with an internal meshing ratchet, and the connecting end of the output shaft and the rotating shaft is provided with a ratchet that cooperates with the internal meshing ratchet. Two layers of second filter are provided in the second filter box, and a plurality of atomizing nozzles are provided on the upper part of the second filter to contact with the second filter, and the atomizing nozzle can wet the second filter. A partition is provided at the lower part of the second filter box, and a slot for inserting the second filter is provided at a corresponding position on the partition, and a through hole is also provided on the partition, and the sewage in the second filter box can enter the bottom of the second filter box through the through hole. The partition is arranged obliquely, and the through hole is provided at the lower end of the partition. A sewage outlet is provided at one side of the bottom of the second filter box. The third filter box is provided with two layers of third filter screens. The third filter box is provided with a second bracket, the second bracket is provided with a second motor, the second motor is provided with a second fan, and the second motor assists the first motor to increase the inflow speed of air.

[0042] In this embodiment, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the method in the above embodiment.

[0043] The above program can be run in the processor, or it can be stored in the memory (or computer-readable medium), which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0044] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0045] Such a device or system is provided in this embodiment. The device is called a ventilation and dust reduction device for mines based on automatic control, and includes: a first acquisition module for acquiring the dust concentration of a predetermined area in a mine collected by a dust sensor; a second acquisition module for inputting the dust concentration into a pre-trained first machine learning model, and acquiring the first wind speed corresponding to the dust concentration from the first machine learning model; a third acquisition module for acquiring an image of the predetermined area taken by a camera; a fourth acquisition module for inputting the image into a pre-trained second machine learning model, and acquiring the second wind speed corresponding to the image from the second machine learning model; a selection module for selecting a fan speed with a larger wind speed value from the first wind speed and the second wind speed; and a control module for controlling the fan in the predetermined area according to the fan speed with a larger wind speed value.

[0046] The system or device is used to implement the functions of the method in the above-mentioned embodiment. Each module in the system or device corresponds to each step in the method, which has been explained in the method and will not be repeated here.

[0047] For example, the first machine learning model is trained using multiple sets of first training data, the first training data including dust concentration and wind speed of the fan corresponding to the dust concentration. Optionally, the second machine learning model is trained using multiple sets of second training data, the second training data including an image of the predetermined area and wind speed of the fan corresponding to the dust concentration represented in the image.

[0048] For another example, the selection module is used to select the wind turbine wind speed with a larger wind speed value from the first wind speed and the second wind speed when the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range. Optionally, the predetermined range is predetermined.

[0049] The above-mentioned embodiments solve the problems caused by manually starting and shutting down the fans in the mine, thereby realizing automatic control of the fans and better ventilating and reducing dust in the mine on the basis of energy saving.

[0050] The system or device is used to implement the functions of the method in the above-mentioned embodiment. Each module in the system or device corresponds to each step in the method, which has been explained in the method and will not be repeated here.

[0051] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A ventilation and dust reduction method based on an excavation working face, characterized in that: include: Obtain dust concentration in a predetermined area of ​​the mine collected by a dust sensor; Inputting the dust concentration into a pre-trained first machine learning model, and obtaining a first wind speed corresponding to the dust concentration from the first machine learning model; Acquire an image captured by a camera of the predetermined area; Inputting the image into a pre-trained second machine learning model, and obtaining a second wind speed corresponding to the image from the second machine learning model; Selecting a wind speed of the wind turbine with a larger wind speed value from the first wind speed and the second wind speed; The fans in the predetermined area are controlled according to the wind speed of the fan with the larger wind speed value.

2. The method according to claim 1, characterized in that: The first machine learning model is trained using multiple groups of first training data, where the first training data includes dust concentration and wind speed of the fan corresponding to the dust concentration.

3. The method according to claim 1, characterized in that The second machine learning model is trained using multiple sets of second training data, where the second training data includes an image of the predetermined area and a wind speed of the fan corresponding to the dust concentration represented in the image.

4. The method according to any one of claims 1 to 3, characterized in that Selecting the wind turbine wind speed with a larger wind speed value from the first wind speed and the second wind speed includes: If the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range, the wind speed of the wind turbine with the larger wind speed value is selected from the first wind speed and the second wind speed; If the absolute value of the difference between the first wind speed and the second wind speed is outside the predetermined range, the fan in the area is started using the larger wind speed between the first wind speed and the second wind speed, and the wind speed is maintained for a predetermined time of blowing. After the predetermined time of blowing, it is determined whether the dust concentration decreases by more than a threshold value within the predetermined time. If it exceeds the threshold, the fan speed is reduced by a predetermined value and blowing is performed for a second time, and so on, until the fan speed is reduced to the smaller wind speed between the first wind speed and the second wind speed.

5. The method according to claim 4, characterized in that The predetermined range is predetermined.

6. A ventilation and dust reduction device based on the excavation working face, characterized in that: include: The first acquisition module is used to obtain the dust concentration of a predetermined area in the mine collected by the dust sensor; A second acquisition module, used for inputting the dust concentration into a pre-trained first machine learning model, and acquiring a first wind speed corresponding to the dust concentration from the first machine learning model; A third acquisition module is used to acquire an image captured by a camera on the predetermined area; a fourth acquisition module, configured to input the image into a pre-trained second machine learning model, and acquire a second wind speed corresponding to the image from the second machine learning model; A selection module, configured to select a wind speed of the wind turbine having a larger wind speed value from the first wind speed and the second wind speed; The control module is used to control the fans in the predetermined area according to the wind speed of the fans with larger wind speed values.

7. The device according to claim 6, characterized in that The first machine learning model is trained using multiple groups of first training data, where the first training data includes dust concentration and wind speed of the fan corresponding to the dust concentration.

8. The device according to claim 6, characterized in that The second machine learning model is trained using multiple sets of second training data, where the second training data includes an image of the predetermined area and a wind speed of the fan corresponding to the dust concentration represented in the image.

9. The device according to any one of claims 6 to 8, characterized in that The selection module is used to: When the absolute value of the difference between the first wind speed and the second wind speed is within a predetermined range, a wind speed of a wind turbine with a larger wind speed value is selected from the first wind speed and the second wind speed.

10. The device according to claim 9, characterized in that The predetermined range is predetermined.

Images