Detection device and dust concentration detection method

Abstract

The application provides a detection device and a dust concentration detection method. The detection device comprises a shell, a one-line laser, an image acquisition device, a particle counter and a detection device. The shell has a detection cavity and an air inlet hole which are in communication with each other, and the air inlet hole is used for conveying a to-be-detected gas into the detection cavity. The detection device is arranged in the detection cavity and is used for detecting the dust mass concentration of the to-be-detected gas. A processing module is connected with the image acquisition device, the particle counter and the detection device. The processing module has a first working mode and a second working mode. When the processing module is in the first working mode, the processing module establishes a support vector machine model according to a laser surface image, a counting value of the particle counter and a detection value of the detection device. When the processing module is in the second working mode, the processing module calculates the dust mass concentration of the to-be-detected gas according to the laser surface image and the counting value based on the support vector machine model. The application effectively solves the problem that the dust mass concentration detection device in the prior art cannot perform real-time detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dust concentration detection, in particular to a detection device and a dust concentration detection method. BACKGROUND

[0002] At present, fine dust particles suspended in the air not only cause respiratory diseases in human body, but also cause the visibility of cities and regions to decrease and buildings to corrode. Therefore, the measurement of dust mass concentration in workplaces and urban environments is crucial for people's health and travel.

[0003] In the prior art, dust mass concentration sensors are usually used for detecting dust mass concentration. The dust mass concentration sensor can only detect the average value of dust mass concentration within a certain time range, and the detection is not the real-time concentration value in the current area.

[0004] However, for some mine workplaces with large ventilation intensity, the dust mass concentration in the air changes greatly. The difference between the detection method of the dust mass concentration sensor and the actual dust mass concentration in the mine workplace is large, which seriously affects the personal health of the workers. SUMMARY

[0005] The main purpose of the present application is to provide a detection device and a dust concentration detection method to solve the problem that the dust mass concentration detection device in the prior art cannot perform real-time detection.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a detection device is provided for detecting the dust mass concentration of a to-be-detected gas. The detection device comprises: a shell having a detection cavity and an air inlet hole in communication with each other, the air inlet hole being used for conveying the to-be-detected gas into the detection cavity; a linear laser, which is arranged in the detection cavity and is used for emitting a linear laser; an image acquisition device, a central axis of a camera of the image acquisition device being arranged at a first included angle with a laser plane of the linear laser, so as to acquire a laser plane image of the linear laser; a particle counter, which is arranged in the detection cavity and is used for counting dust of different particle sizes in the to-be-detected gas; a detection device, which is arranged in the detection cavity and is used for detecting the dust mass concentration of the to-be-detected gas; and a processing module, which is connected with the image acquisition device, the particle counter and the detection device, and has a first working mode and a second working mode. When the processing module is in the first working mode, the processing module establishes a support vector machine model according to the laser plane image, a counting value of the particle counter and a detection value of the detection device. When the processing module is in the second working mode, the processing module calculates the dust mass concentration of the to-be-detected gas according to the laser plane image and the counting value based on the support vector machine model.

[0007] Further, the detection device further comprises a light-absorbing structure arranged on the cavity wall of the detection cavity, for absorbing the light beam in the detection cavity; wherein at least part of the light-absorbing structure is made of light-absorbing material.

[0008] Further, the shell further has a detection port in communication with the detection cavity, the image acquisition device is arranged outside the detection cavity, and the detection device further comprises a blocking structure arranged at the detection port, for blocking the detection port; wherein at least part of the blocking structure is made of transparent material, and the image acquisition device acquires the laser facet image of the one-dimensional line laser in the detection cavity through the part of the blocking structure.

[0009] Further, the blocking structure comprises: a blocking body made of transparent material; and a cylindrical connecting portion, a first end of the cylindrical connecting portion extending into the detection cavity, and the blocking body being arranged on the first end; and an annular stopper arranged on a second end of the cylindrical connecting portion, the annular stopper being used for limiting and stopping at least part of the outer surface of the shell; wherein at least part of the image acquisition device extends into the inner cavity of the cylindrical connecting portion via the second end.

[0010] Further, the shell further has a gas outlet in communication with the gas inlet through the detection cavity, and the detection device further comprises: a first tubular structure arranged at the gas outlet; and a suction device in communication with the detection cavity through the first tubular structure, the suction device being used for sucking out at least part of the gas in the detection cavity to the outside of the shell, so that the to-be-detected gas outside the shell flows into the detection cavity through the gas inlet; wherein a filter is arranged in the first tubular structure.

[0011] According to another aspect of the present application, a dust concentration detection method is provided for detecting the dust mass concentration of a to-be-detected gas, the dust concentration detection method being applicable to the detection device described above, and the dust concentration detection method comprising:

[0012] Step S1: operating the image acquisition device of the detection device to acquire the laser facet image of the one-dimensional line laser emitted by the one-dimensional line laser of the detection device;

[0013] Step S2: acquiring the average gray value, the peak signal-to-noise ratio of the laser facet image, and the counting value of the particle counter of the detection device, and inputting the average gray value, the peak signal-to-noise ratio, and the counting value into the support vector machine model to obtain the dust mass concentration.

[0014] Further, in step S2, the method for establishing the support vector machine model comprises:

[0015] Step S21: sucking out the gas of a preset volume in the detection cavity of the detection device to the outside of the shell by the suction device of the detection device;

[0016] Step S22: the operation image acquisition device acquires a plurality of sample laser plane images of a line laser emitted by a line laser emitter;

[0017] Step S23: the processing module obtains a sample average gray value and a sample peak signal-to-noise ratio of each sample laser plane image, the processing module obtains a sample count value of a particle counter corresponding to each sample laser plane image at the time of acquisition, and the processing module obtains a sample detection value of a detection device of a detection apparatus corresponding to each sample laser plane image at the time of acquisition; wherein the sample laser plane image and the sample average gray value, the sample peak signal-to-noise ratio, the sample count value and the sample detection value corresponding to the sample laser plane image form a group of sample data;

[0018] Step S24: the processing module selects at least one group of sample data, takes the sample average gray value, the sample peak signal-to-noise ratio and the sample count value in the sample data as input variables, takes the sample detection value in the sample data as an output variable, and uses a support vector machine to simulate a functional relationship between the input variables and the output variables to establish a support vector machine model.

[0019] Further, the method for establishing the support vector machine model further comprises:

[0020] Step S25: the processing module selects at least another group of sample data, and inputs the sample average gray value, the sample peak signal-to-noise ratio and the sample count value in the group of sample data into the support vector machine model to obtain a predicted dust mass concentration value A1; wherein if a sample detection value A2 in the group of sample data and the predicted dust mass concentration value A1 satisfy: 1.08A2≤A1≤0.95A2, it is judged that the support vector machine model is qualified.

[0021] Further, the method for obtaining the average gray value and the peak signal-to-noise ratio of the laser plane image comprises:

[0022] Step S26: the processing module converts the laser plane image into a gray scale image, and intercepts a center scattering region in the gray scale image;

[0023] Step S27: the center scattering region is filtered based on a median filter algorithm to obtain a filtered image matrix;

[0024] Step S28: coordinates of each pixel point in the filtered image matrix are obtained to calculate the peak signal-to-noise ratio according to the coordinates of each pixel point, and a formula for calculating the peak signal-to-noise ratio is:

[0025]

[0026] Wherein, M is the length value of the central scattering area, N is the width value of the central scattering area, R is the horizontal coordinate and vertical coordinate of the pixel point before the central scattering area is filtered, and F is the horizontal coordinate and vertical coordinate of the pixel point after the central scattering area is filtered.

[0027] Further, the method for obtaining the average gray value and the peak signal-to-noise ratio of the laser surface image further comprises:

[0028] Step S29: performing binaryzation processing on the central scattering area based on the Otsu binaryzation method;

[0029] Step S30: performing normalization processing on the binaryzated central scattering area based on the maximum-minimum normalization method to obtain a scattering image matrix;

[0030] Step S31: performing Hadamard product on the scattering image matrix and the filtered image matrix to obtain a finished gray scale image;

[0031] Step S32: obtaining the average gray value from the finished gray scale image by the processing module.

[0032] The technical scheme of the present application is used for detecting the dust mass concentration of the to-be-detected gas. The shell of the detection device has a detection cavity and a gas inlet hole that are in communication with each other. The gas inlet hole is used for conveying the to-be-detected gas into the detection cavity. A linear laser is arranged in the detection cavity to emit a linear laser. The central axis of the camera of the image acquisition device is arranged at a first included angle with the laser surface of the linear laser to acquire the laser surface image of the linear laser. A particle counter is arranged in the detection cavity to count the dust of different particle sizes in the to-be-detected gas. A detection device is arranged in the detection cavity to detect the dust mass concentration of the to-be-detected gas. A processing module is connected with the image acquisition device, the particle counter, and the detection device. The processing module has a first working mode and a second working mode. When the processing module is in the first working mode, the processing module establishes a support vector machine model according to the laser surface image, the counting value of the particle counter, and the detection value of the detection device. When the processing module is in the second working mode, the processing module calculates the dust mass concentration of the to-be-detected gas based on the support vector machine model according to the laser surface image and the counting value. In this way, the detection device can establish a support vector machine model according to the laser surface image, the counting value of the particle counter, and the detection value of the detection device. After the support vector machine model is established, the staff only needs to continuously convey the to-be-detected gas into the detection cavity through the gas inlet hole. The control module can calculate the real-time dust mass concentration of the to-be-detected gas based on the support vector machine model by using the laser surface image acquired by the image acquisition device in real time and the real-time counting value of the particle counter. Thus, the problem that the dust mass concentration detection device in the prior art cannot be detected in real time is solved, and the personal health of the staff is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0033] The accompanying drawings, which form a part of this specification, are included to provide a further understanding of the application, and are incorporated in and constitute a part of this specification. The embodiments of the application, and their

[0034] Figure 1 A schematic diagram showing the overall structure of an embodiment of the detection device according to the present application is shown;

[0035] Figure 2 A flow chart showing an embodiment of the dust concentration detection method according to the present application is shown.

[0036] In the above drawings, the following reference signs are used:

[0037] 10, housing; 11, detection cavity; 12, air inlet hole; 13, air outlet hole; 14, detection port; 20, linear laser; 30, image acquisition device; 40, particle counter; 50, detection device; 60, processing module; 70, light absorption structure; 80, plugging structure; 81, plugging body; 82, cylindrical connecting portion; 83, annular stop portion; 90, first tubular structure; 100, suction device; 110, filter; 120, second tubular structure; 121, first sub-tube segment; 122, second sub-tube segment. DETAILED DESCRIPTION

[0038] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0039] It should be noted that, unless otherwise specified, all technical and scientific terms used in the present application have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0040] In the present application, unless otherwise specified, the orientation words such as "up", "down" are generally directed to the directions shown in the drawings, or are directed to the vertical, perpendicular or gravity directions; similarly, for the convenience of understanding and description, "left", "right" are generally directed to the left and right shown in the drawings; "inner", "outer" refer to the inner and outer relative to the contour of each component, but the above orientation words are not used to limit the present application.

[0041] In order to solve the problem that the dust mass concentration detection device in the prior art cannot perform real-time detection, the present application provides a detection device and a dust concentration detection method.

[0042] As Figure 1As shown, the detection device is used for detecting the dust mass concentration of the to-be-detected gas, and comprises a shell 10, a one-line laser 20, an image acquisition device 30, a particle counter 40, a detection device 50 and a processing module 60. The shell 10 has a detection cavity 11 and a gas inlet hole 12 which are in communication with each other, and the gas inlet hole 12 is used for conveying the to-be-detected gas into the detection cavity 11. The one-line laser 20 is arranged in the detection cavity 11, and is used for emitting a one-line laser. The central axis of the camera of the image acquisition device 30 and the laser plane of the one-line laser are arranged at a first included angle, so as to acquire the laser plane image of the one-line laser. The particle counter 40 is arranged in the detection cavity 11, and is used for counting the dust of different particle sizes in the to-be-detected gas. The detection device 50 is arranged in the detection cavity 11, and is used for detecting the dust mass concentration of the to-be-detected gas. The processing module 60 is connected with the image acquisition device 30, the particle counter 40 and the detection device 50, and has a first working mode and a second working mode. When the processing module 60 is in the first working mode, the processing module 60 establishes a support vector machine model according to the laser plane image, the counting value of the particle counter 40 and the detection value of the detection device 50. When the processing module 60 is in the second working mode, the processing module 60 calculates the dust mass concentration of the to-be-detected gas according to the laser plane image and the counting value based on the support vector machine model.

[0043] The technical scheme is applied, the detection equipment is used for detecting the dust mass concentration of the to-be-detected gas, the shell 10 of the detection equipment has a detection cavity 11 and a gas inlet hole 12 that are in communication, the gas inlet hole 12 is used for conveying the to-be-detected gas into the detection cavity 11, a linear laser 20 is arranged in the detection cavity 11 and is used for emitting a linear laser, a center axis of a camera of an image acquisition device 30 and a laser plane of the linear laser are arranged at a first included angle, and the image acquisition device 30 is used for acquiring a laser plane image of the linear laser, a particle counter 40 is arranged in the detection cavity and is used for counting dust of different particle sizes in the to-be-detected gas, a detection device 50 is arranged in the detection cavity and is used for detecting the dust mass concentration of the to-be-detected gas, a processing module 60 is connected with the image acquisition device 30, the particle counter 40 and the detection device 50, the processing module 60 has a first working mode and a second working mode, when the processing module 60 is in the first working mode, the processing module 60 establishes a support vector machine model according to the laser plane image, a counting value of the particle counter 40 and a detection value of the detection device 50, when the processing module 60 is in the second working mode, the processing module 60 calculates the dust mass concentration of the to-be-detected gas according to the laser plane image and the counting value based on the support vector machine model. In this way, the detection equipment can establish a support vector machine model according to the laser plane image, the counting value of the particle counter 40 and the detection value of the detection device 50, after the support vector machine model is established, the staff only needs to continuously convey the to-be-detected gas into the detection cavity 11 through the gas inlet hole 12, and the control module can calculate the real-time dust mass concentration of the to-be-detected gas by using the laser plane image acquired by the image acquisition device 30 in real time and the real-time counting value of the particle counter 40 based on the support vector machine model, thereby solving the problem that the dust mass concentration detection device in the prior art cannot be detected in real time, and the personal health of the staff is ensured.

[0044] In the embodiment, the image acquisition device 30 is an industrial camera.

[0045] The industrial camera adopts a 4K high-definition USB industrial camera, is matched with a C interface and a manually adjusted aperture and focal length lens.

[0046] In the embodiment, the linear laser 20 can emit a linear laser, and the linear laser can form a laser plane.

[0047] Specifically, the linear laser 20 adopts a conductor laser, the output laser wavelength is 650 nm, the working power is 10 mW, and the structural components include a laser diode, a metal shell, a lens, a constant power circuit board and high-quality wires with a DC plug / red and black wires.

[0048] In the embodiment, the central axis of the camera of the industrial camera is arranged at 90° with the laser plane of the linear laser, so as to avoid the deflection and inclination of the collected image of the industrial camera, and to affect the calculation result of the subsequent step, and to improve the detection accuracy of the detection device.

[0049] In the embodiment, the particle counter 40 is an optical particle counter, which can measure the number of dusts with different particle sizes.

[0050] In the embodiment, the detection device 50 is a dust concentration sensor. As shown in Figure 1 The detection device 50 further comprises a light-absorbing structure 70 arranged on the cavity wall of the detection cavity 11, for absorbing the light beam in the detection cavity 11. At least part of the light-absorbing structure 70 is made of light-absorbing material. In this way, the above arrangement can sufficiently reduce the brightness in the detection cavity 11, so as to ensure that the linear laser emitted by the linear laser has a high contrast with other areas in the detection cavity 11, and to ensure that the image acquisition device 30 can clearly and completely photograph and collect the laser plane of the linear laser, so as to ensure the calculation accuracy of the subsequent step, and to improve the detection accuracy of the detection device.

[0051] In the embodiment, the light-absorbing structure 70 is a light-absorbing cloth.

[0052] Optionally, the light-absorbing cloth is bonded to the cavity wall of the detection cavity 11.

[0053] In the embodiment, the dust concentration sensor can detect the mass concentration of particles with different particle sizes, including 0.3 microns, 0.5 microns, 1.0 microns, 2.5 microns, 5.0 microns and 10 microns.

[0054] As shown in Figure 1 The shell 10 further has a detection port 14 communicating with the detection cavity 11, the image acquisition device 30 is arranged outside the detection cavity 11, and the detection device 50 further comprises a plugging structure 80 arranged at the detection port 14 for plugging the detection port 14. At least part of the plugging structure 80 is made of transparent material, and the image acquisition device 30 collects the image of the laser plane of the linear laser in the detection cavity 11 through the part of the plugging structure 80. In this way, the plugging structure 80 made of transparent material can separate the image acquisition device 30 and the detection cavity 11 while realizing the image acquisition function of the image acquisition device 30, so as to avoid the direct contact between the tiny dust in the gas to be detected and the image acquisition device 30, and to cause the image acquisition device 30 to be filled with dust and even damaged, and to prolong the service life of the image acquisition device 30.

[0055] As shown in Figure 1As shown, the plugging structure 80 includes a plugging body 81, a cylindrical connecting part 82 and an annular stop part 83, the plugging body 81 is made of transparent material. The first end of the cylindrical connecting part 82 extends into the detection cavity 11, and the plugging body 81 is arranged on the first end. The annular stop part 83 is arranged on the second end of the cylindrical connecting part 82, and the annular stop part 83 is used for limiting stop with at least part of the outer surface of the shell 10. At least part of the image acquisition device 30 extends into the inner cavity of the cylindrical connecting part 82 via the second end. In this way, the above arrangement reduces the disassembly difficulty of the worker through the limiting stop between the annular stop part 83 and the shell 10, that is, the worker only needs to extend the cylindrical connecting part 82 into the detection port 14 until the annular stop part 83 is limited and stopped with the shell 10, and then it can be judged that the plugging structure 80 is installed in place. At the same time, the cylindrical connecting part 82 can protect the image acquisition device 30 on the one hand to prolong the service life of the image acquisition device 30; on the other hand, it can reduce the distance between the acquisition end of the image acquisition device 30 and the laser surface of the linear laser, so that the image acquired by the image acquisition device 30 is clearer and more complete.

[0056] As shown in the figure, Figure 1 The shell 10 also has an air outlet hole 13, which communicates with the air inlet hole 12 through the detection cavity 11, and the detection equipment also includes a first tubular structure 90 and a suction device 100, and the first tubular structure 90 is arranged at the air outlet hole 13. The suction device 100 communicates with the detection cavity 11 through the first tubular structure 90, and the suction device 100 sucks at least part of the gas in the detection cavity 11 out of the shell 10, so that the to-be-detected gas outside the shell 10 flows into the detection cavity 11 through the air inlet hole 12. Wherein, the first tubular structure 90 is provided with a filter 110. In this way, the above arrangement makes the setting position of the suction device 100 more flexible and diverse through the first tubular structure 90, so as to adapt to different working conditions and use requirements, and also improves the processing flexibility of the worker; on the other hand, the filter 110 in the first tubular structure 90 can filter and adsorb dust in the gas, which not only can avoid the dust staying in the detection cavity 11 to cause the detection result of the detection equipment to be larger, thereby improving the detection result accuracy of the detection equipment, but also can avoid the dust entering the suction device 100 with the gas to cause the damage of the suction device 100, thereby prolonging the service life of the suction device 100. At the same time, since the detection equipment adopts passive air intake (that is, the gas is sucked by the suction device 100 to reduce the air pressure in the detection cavity 11, and then the to-be-detected gas outside is sucked), the distribution of the gas in the detection cavity 11 is more uniform, which further improves the detection accuracy of the detection equipment.

[0057] In this embodiment, the suction device 100 is a suction pump.

[0058] Optionally, the filter 110 is a filter membrane.

[0059] As shown in Figure 1 The detection device further includes a second tubular structure 120, the second tubular structure 120 is arranged at the air inlet hole 12, and the detection cavity 11 is in communication with the outside through the second tubular structure 120. Among them, the second tubular structure 120 includes a first sub-tube segment 121 and a second sub-tube segment 122 connected with each other, and the first sub-tube segment 121 and the second sub-tube segment 122 are arranged at a second included angle. In this way, the second tubular structure 120 composed of the first sub-tube segment 121 and the second sub-tube segment 122 connected with each other can not only realize the air inlet of the air inlet hole 12, but also shield the light beam from the outside, so as to avoid the light beam from the outside entering the detection cavity 11 through the air inlet hole 12 and affecting the quality of the image collected by the image acquisition device 30, thereby improving the detection accuracy of the detection device. At the same time, the above-mentioned arrangement makes the included angle between the first sub-tube segment 121 and the second sub-tube segment 122 more flexible and diverse, so as to adapt to different working conditions and use requirements, and also improves the processing flexibility of the workers.

[0060] In the embodiment, the first sub-tube segment 121 is arranged close to the air inlet hole 12, and the particle counter 40 is arranged on the inner wall of the first sub-tube segment 121 close to the air inlet hole 12, so as to detect the number of particles of different particle sizes in the gas passing through the air inlet hole 12.

[0061] In the embodiment, the particle counter 40 can detect particles of different particle sizes including 0.3 microns, 0.5 microns, 1.0 microns, 2.5 microns, 5.0 microns and 10 microns.

[0062] In the embodiment, the first sub-tube segment 121 and the second sub-tube segment 122 are arranged at an angle of 90°.

[0063] It should be noted that the value of the second included angle between the first sub-tube segment 121 and the second sub-tube segment 122 is not limited to this, and can be adjusted according to the working conditions and use requirements. Optionally, the value of the second included angle between the first sub-tube segment 121 and the second sub-tube segment 122 is 60°, or 70°, or 80°, or 100°, or 110°, or 120°.

[0064] The application also provides a dust concentration detection method, as shown in Figure 2 The dust concentration detection method is used for detecting the dust mass concentration of a to-be-detected gas, and is suitable for the above-mentioned detection device. The dust concentration detection method comprises the following steps:

[0065] Step S1: operating the image acquisition device 30 of the detection device to collect a laser plane image of a linear laser emitted by the linear laser emitter 20 of the detection device;

[0066] Step S2: obtaining the average gray value, the peak signal-to-noise ratio of the laser surface image, and the counting value of the particle counter 40 of the detection device, inputting the average gray value, the peak signal-to-noise ratio, and the counting value into the support vector machine model to obtain the dust mass concentration.

[0067] In the embodiment, since the image collected by the image acquisition device 30 and the counting value of the particle counter 40 are both instantaneous values, the average gray value and the peak signal-to-noise ratio obtained by the processing module 60 are also instantaneous values, and thus the detection device can perform real-time calculation on the dust mass concentration of the to-be-detected gas based on the support vector machine model, thereby solving the problem that the dust mass concentration detection device in the prior art cannot perform real-time detection.

[0068] Specifically, in step S2, the method for establishing the support vector machine model comprises:

[0069] Step S21: sucking the preset volume of gas in the detection cavity 11 of the detection device to outside the shell 10 through the suction device 100 of the detection device;

[0070] Specifically, the preset volume of gas also enters the shell 10 through the gas inlet hole 12 at the same time of suction.

[0071] Step S22: operating the image acquisition device 30 to collect a plurality of sample laser surface images of the linear laser emitted by the linear laser 20;

[0072] Step S23: the processing module 60 obtains sample average gray values and sample peak signal-to-noise ratios of the sample laser surface images, the processing module 60 obtains sample counting values of the particle counter 40 corresponding to the sample laser surface images at the time of collection, and the processing module 60 obtains sample detection values of the detection device 50 corresponding to the sample laser surface images at the time of collection; wherein the sample laser surface image and the sample average gray value, the sample peak signal-to-noise ratio, the sample counting value, and the sample detection value corresponding to the sample laser surface image form a group of sample data;

[0073] Step S24: the processing module 60 selects at least one group of sample data, takes the sample average gray value, the sample peak signal-to-noise ratio, and the sample counting value in the sample data as input variables, takes the sample detection value in the sample data as an output variable, and uses the support vector machine to simulate the functional relationship between the input variables and the output variables to establish the support vector machine model (actually a prediction model).

[0074] Specifically, the method for establishing the support vector machine model further comprises:

[0075] Step S25: The processing module 60 selects at least another set of sample data, and inputs the sample average gray value, sample peak signal-to-noise ratio and sample count value in the set of sample data into the support vector machine model to obtain a predicted dust mass concentration value A1; wherein, if the sample detection value A2 and the predicted dust mass concentration value A1 in the set of sample data satisfy: 1.08A2≤A1≤0.95A2, it is judged that the support vector machine model is qualified. In this way, the above setting provides a verification basis for whether the support vector machine model is accurate, so as to ensure the accuracy of the establishment of the support vector machine model, and further improve the detection accuracy of the detection equipment.

[0076] Specifically, if the support vector machine model does not satisfy the numerical relationship between the sample detection value A2 and the predicted dust mass concentration value A1, it is judged that the support vector machine model is unqualified, and the processing module repeats step S24 and re-establishes the support vector machine model.

[0077] Specifically, the method for obtaining the average gray value and the peak signal-to-noise ratio of the laser surface image comprises:

[0078] Step S26: The processing module 60 converts the laser surface image into a gray scale image, and intercepts the center scattering area in the gray scale image;

[0079] Step S27: The center scattering area is filtered based on a median filtering algorithm to obtain a filtered image matrix;

[0080] Step S28: The coordinates of each pixel point in the filtered image matrix are obtained to calculate the peak signal-to-noise ratio according to the coordinates of each pixel point, and the formula for calculating the peak signal-to-noise ratio is:

[0081]

[0082] Wherein, M is the length value of the center scattering area, N is the width value of the center scattering area, Ri,j is the horizontal coordinate and vertical coordinate of the pixel point before filtering processing of the center scattering area, and Fi,j is the horizontal coordinate and vertical coordinate of the pixel point after filtering processing of the center scattering area.

[0083] Specifically, the method for obtaining the average gray value and the peak signal-to-noise ratio of the laser surface image further comprises:

[0084] Step S29: The center scattering area is binarized based on the Otsu binarization method;

[0085] Step S30: The normalized center scattering area after binarization is normalized based on the maximum-minimum normalization method to obtain a scattering image matrix;

[0086] Step S31: The scattering image matrix and the filtered image matrix are multiplied by Hadamard to obtain a finished gray scale image;

[0087] Step S32: The processing module 60 obtains the average gray value according to the finished gray scale image.

[0088] Specifically, the center scattering area is binarized by the Otsu binarization method, so that the pixel points not containing scattering information can be removed, and the subsequent prediction accuracy is improved.

[0089] Specifically, before the operation image acquisition device 30 acquires the laser plane image of the linear laser emitted by the linear laser 20 in step S1, the dust concentration detection method further comprises:

[0090] The suction device 100 of the detection equipment sucks the gas in the detection cavity 11 in the detection cavity 11 to the outside of the shell 10. In this way, the above-mentioned setting makes the to-be-detected gas in the detection cavity 11 in a constant flow process, that is, the to-be-detected gas outside can flow into the detection cavity 11 constantly, and because the detection equipment can detect the instantaneous dust mass concentration of the to-be-detected gas, the detection value of the detection equipment can accurately reflect the dust mass concentration of the to-be-detected gas outside.

[0091] Specifically, in step S21, the size of the preset volume is consistent with the volume of the detection cavity 11. In this way, the above-mentioned setting can on the one hand ensure that the detection cavity 11 is filled with to-be-detected gas to ensure the detection accuracy of the detection equipment; on the other hand, after the to-be-detected gas of the preset volume is introduced, the suction device 100 immediately stops working to ensure that the gas in the detection cavity 11 is in a stopped flow state, thereby ensuring that the detection result of the detection device 50 is more accurate, thereby improving the detection accuracy of the detection equipment.

[0092] Specifically, the support vector machine model obtained by the above-mentioned method is actually a prediction model, that is, after obtaining the above-mentioned model, the detection device 50 is no longer used, and only the average gray value, the peak signal-to-noise ratio and the particle count value of different particle sizes are used as input variables, so that the corresponding dust mass concentration can be obtained. Although the conventional sensor (detection device 50) capable of measuring only the average value of the dust mass concentration in a certain time range is used in the training process of the prediction model, the worker can intentionally control the dust mass concentration of the gas introduced into the detection equipment not to change (that is, the average value of the dust mass concentration in a certain time range is equal to the instantaneous value), so that the prediction value of the prediction model is the corresponding instantaneous value (the average gray value, the peak signal-to-noise ratio and the particle count value of different particle sizes are all instantaneous values).

[0093] From the above description, it can be seen that the above-mentioned embodiments of the present application achieve the following technical effects:

[0094] The detection equipment is used for detecting the dust mass concentration of the to-be-detected gas, a shell of the detection equipment has a detection cavity and a gas inlet hole which are in communication, the gas inlet hole is used for conveying the to-be-detected gas into the detection cavity, a linear laser is arranged in the detection cavity and used for emitting a linear laser, a central axis of a camera of an image acquisition device is arranged at a first included angle with a laser plane of the linear laser and used for acquiring a laser plane image of the linear laser, a particle counter is arranged in the detection cavity and used for counting dusts of different particle sizes in the to-be-detected gas, a detection device is arranged in the detection cavity and used for detecting the dust mass concentration of the to-be-detected gas, a processing module is connected with the image acquisition device, the particle counter and the detection device, the processing module has a first working mode and a second working mode, when the processing module is in the first working mode, the processing module establishes a support vector machine model according to the laser plane image, a counting value of the particle counter and a detection value of the detection device, when the processing module is in the second working mode, the processing module calculates the dust mass concentration of the to-be-detected gas according to the laser plane image and the counting value based on the support vector machine model. In this way, the detection equipment can establish a support vector machine model according to the laser plane image, the counting value of the particle counter and the detection value of the detection device, after the support vector machine model is established, the staff only needs to continuously convey the to-be-detected gas into the detection cavity through the gas inlet hole, and the control module can calculate the real-time dust mass concentration of the to-be-detected gas by using the laser plane image acquired by the image acquisition device in real time and the real-time counting value of the particle counter based on the support vector machine model, thereby solving the problem that the dust mass concentration detection device in the prior art cannot be detected in real time, and the personal health of the staff is ensured.

[0095] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should belong to the protection scope of the present application.

[0096] It should be noted that the terms used herein are only intended to describe specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form, unless the context clearly indicates otherwise, and it should also be understood that, when the terms "comprise" and / or "include" are used in the specification, there is a feature, step, work, device, component and / or combination thereof.

[0097] It should be noted that the terms "first", "second", and the like, used in the description and in the claims of the present application as well as above-mentioned figures are used to distinguish between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of data so designated is not meant to limit a given item described by such data to the same category as other data designated by the same designations, but instead is so designated only for convenience as a means of discriminating between the two series of items that refer to a same data.

[0098] The preferred embodiments of the application described herein are examples of the present application and are not intended to limit the scope of the application. Various modifications and changes can be made thereto by those skilled in the art which freely adapt to the idea and principles of the application, without departing from the spirit and scope thereof, and it is to be understood that such modifications and changes are to be included within the scope of the application as defined by the appended claims.

Claims

1. A detection device for detecting a dust mass concentration of a gas to be detected, characterized by comprising: The detection device comprises: a shell (10) having a detection cavity (11) and an air inlet hole (12) in communication with each other, the air inlet hole (12) being used for conveying a gas to be detected into the detection cavity (11); a linear laser (20) arranged in the detection cavity (11), the linear laser (20) being used for emitting a linear laser beam; an image acquisition device (30), a central axis of a camera of the image acquisition device (30) and a laser plane of the linear laser beam forming a first included angle, the image acquisition device (30) being used for acquiring a laser plane image of the linear laser beam; a particle counter (40) arranged in the detection cavity (11), the particle counter (40) being used for counting dusts of different particle sizes in the gas to be detected; a detection device (50) arranged in the detection cavity (11), the detection device (50) being used for detecting a dust mass concentration of the gas to be detected; a processing module (60) connected with the image acquisition device (30), the particle counter (40) and the detection device (50), the processing module (60) having a first working mode and a second working mode, when the processing module (60) is in the first working mode, the processing module (60) establishes a support vector machine model according to the laser plane image, a counting value of the particle counter (40) and a detection value of the detection device (50), when the processing module (60) is in the second working mode, the processing module (60) calculates the dust mass concentration of the gas to be detected according to the laser plane image and the counting value based on the support vector machine model.

2. The detection device of claim 1, wherein, The detection device (50) further comprises light-absorbing structures (70) arranged on a cavity wall of the detection cavity (11) and used for absorbing light beams in the detection cavity (11), wherein at least part of the light-absorbing structures (70) are made of light-absorbing materials.

3. The detection device of claim 1, wherein, The shell (10) further has a detection opening (14) in communication with the detection cavity (11), the image acquisition device (30) is arranged outside the detection cavity (11), and the detection device (50) further comprises: a plugging structure (80) arranged at the detection opening (14) and used for plugging the detection opening (14), wherein at least part of the plugging structure (80) is made of transparent materials, and the image acquisition device (30) acquires the laser plane image of the linear laser beam in the detection cavity (11) through the part of the plugging structure (80).

4. The detection device of claim 3, wherein, The plugging structure (80) comprises: a plugging body (81) made of transparent materials; a cylindrical connecting part (82) having a first end extending into the detection cavity (11), the plugging body (81) being arranged on the first end; a ring-shaped stop part (83) arranged on a second end of the cylindrical connecting part (82) and used for limiting and stopping at least part of an outer surface of the shell (10). At least part of the image acquisition device (30) extends into the inner cavity of the cylindrical connecting portion (82) via the second end.

5. The detection device of claim 1, wherein, The shell (10) also has an air outlet hole (13) which communicates with the air inlet hole (12) through the detection cavity (11), and the detection device further comprises: A first tubular structure (90) is arranged at the air outlet hole (13); A suction device (100) which communicates with the detection cavity (11) through the first tubular structure (90), and the suction device (100) draws at least part of the gas in the detection cavity (11) out of the shell (10) to make the to-be-detected gas outside the shell (10) flow into the detection cavity (11) through the air inlet hole (12); wherein a filter (110) is arranged in the first tubular structure (90).

6. A dust concentration detection method for detecting a dust mass concentration of a gas to be detected, characterized by comprising: The dust concentration detection method is suitable for the detection device of any one of claims 1-5, and the dust concentration detection method comprises: Step S1: operating the image acquisition device (30) of the detection device to acquire a laser plane image of a linear laser emitted by a linear laser emitter (20) of the detection device; Step S2: obtaining an average gray value, a peak signal-to-noise ratio of the laser plane image, and a counting value of a particle counter (40) of the detection device, inputting the average gray value, the peak signal-to-noise ratio, and the counting value into a support vector machine model to obtain the dust mass concentration.

7. The dust concentration detection method according to claim 6, characterized by, In the step S2, the method for establishing the support vector machine model comprises: Step S21: drawing a preset volume of gas in a detection cavity (11) of the detection device out of a shell (10) by a suction device (100) of the detection device; Step S22: operating the image acquisition device (30) to acquire a plurality of sample laser plane images of a linear laser emitted by a linear laser emitter (20); Step S23: the processing module (60) obtains a sample average gray value and a sample peak signal-to-noise ratio of each of the sample laser plane images, the processing module (60) obtains a sample counting value of the particle counter (40) corresponding to each of the sample laser plane images when the sample laser plane image is acquired, and the processing module (60) obtains a sample detection value of a detection device (50) of the detection device corresponding to each of the sample laser plane images when the sample laser plane image is acquired; wherein the sample laser plane image and the sample average gray value, the sample peak signal-to-noise ratio, the sample counting value, and the sample detection value corresponding to the sample laser plane image form a group of sample data; Step S24: the processing module (60) selects at least one group of sample data, takes the sample average gray value, the sample peak signal-to-noise ratio, and the sample counting value in the sample data as input variables, takes the sample detection value in the sample data as an output variable, and simulates a functional relationship between the input variables and the output variables by using a support vector machine to establish the support vector machine model.

8. The dust concentration detection method according to claim 7, characterized by, The method for establishing the support vector machine model further comprises: Step S25: the processing module (60) selects at least another group of sample data, and inputs the sample average gray value, sample peak signal-to-noise ratio and sample count value in the group of sample data into the support vector machine model to obtain a predicted dust mass concentration value A1; wherein if a sample detection value A2 in the group of sample data and the predicted dust mass concentration value A1 satisfy: 1.08A2≤A1≤0.95A2, it is judged that the support vector machine model is qualified.

9. The dust concentration detection method according to claim 6, characterized by, The method for obtaining the average gray value and the peak signal-to-noise ratio of the laser surface image comprises: Step S26: the processing module (60) converts the laser surface image into a gray image, and intercepts a center scattering area in the gray image; Step S27: the center scattering area is filtered based on a median filtering algorithm to obtain a filtered image matrix; Step S28: coordinates of each pixel point in the filtered image matrix are obtained to calculate the peak signal-to-noise ratio according to the coordinates of each pixel point, and a formula for calculating the peak signal-to-noise ratio is: Wherein, M is a length value of the center scattering area, N is a width value of the center scattering area, R(i,j) is a horizontal coordinate and a vertical coordinate of a pixel point before filtering processing of the center scattering area, and F(i,j) is a horizontal coordinate and a vertical coordinate of a pixel point after filtering processing of the center scattering area.

10. The dust concentration detection method according to claim 9, characterized by, The method for obtaining the average gray value and the peak signal-to-noise ratio of the laser surface image further comprises: Step S29: the center scattering area is binarized based on the Otsu binarization method; Step S30: the binarized center scattering area is normalized based on a maximum-minimum normalization method to obtain a scattering image matrix; Step S31: the scattering image matrix and the filtered image matrix are subjected to Hadamard product to obtain a finished gray image; Step S32: the processing module (60) obtains the average gray value according to the finished gray image.

Images