CN114627140A - Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter - Google Patents
Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter Download PDFInfo
- Publication number
- CN114627140A CN114627140A CN202210525322.2A CN202210525322A CN114627140A CN 114627140 A CN114627140 A CN 114627140A CN 202210525322 A CN202210525322 A CN 202210525322A CN 114627140 A CN114627140 A CN 114627140A
- Authority
- CN
- China
- Prior art keywords
- point
- gray level
- occurrence matrix
- calculating
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 67
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 239000000126 substance Substances 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 4
- 239000000428 dust Substances 0.000 description 22
- 238000004364 calculation method Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000005641 tunneling Effects 0.000 description 2
- 241001632422 Radiola linoides Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a coal mine ventilator intelligent adjusting method based on a high-voltage frequency converter, which comprises the steps of obtaining image information corresponding to an underground environment, preprocessing the image information and obtaining a gray image; acquiring an ROI (region of interest) in a gray image, extracting edge information of a target in the ROI, and taking pixel points in the edge information as seed points; acquiring a boundary area of a target by using an area growing algorithm; calculating a gray level co-occurrence matrix of the boundary area; acquiring the width of the boundary region according to the growing times of the seed points; obtaining an internal region of a target; calculating a gray level co-occurrence matrix of the internal region to obtain a difference value between the internal region and the boundary region; acquiring a gray level co-occurrence matrix of the ROI; calculating the entropy of the gray level co-occurrence matrix of the ROI; calculating the fuzzy degree of the image information based on the width, the difference value and the entropy; and adjusting the coal mine ventilator according to the fuzzy degree. The invention can accurately adjust the coal mine ventilator.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an intelligent adjusting method for a coal mine ventilator based on a high-voltage frequency converter.
Background
The coal mine ventilator is an essential important device for underground coal mine tunneling ventilation and gas discharge, and plays an important role in providing fresh air flow for a tunneling working face, discharging harmful gas and dust, improving the environmental condition of the working face, diluting after gas accumulation and discharging underground gas. Before the coal mine ventilator is put into use, working parameters of the coal mine ventilator are generally set in advance by workers, and then the coal mine ventilator works according to the working parameters; in the whole working process of the coal mine ventilator, working parameters of the coal mine ventilator cannot be adjusted again by workers, and the coal mine ventilator cannot reasonably adjust air volume according to the requirements of an actual working environment; therefore, the working mode of the coal mine ventilator has the problems of low operating efficiency, high energy consumption and the like, and further causes the cost of coal mining to be increased.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent adjusting method of a coal mine ventilator based on a high-voltage frequency converter, and the adopted technical scheme is as follows:
acquiring image information corresponding to an underground environment, and preprocessing the image information to obtain a gray image;
carrying out image segmentation on the gray level image to obtain an ROI (region of interest); only one target is present in the ROI region; extracting edge information of the target in the ROI area to obtain the center of the target;
taking the pixel points in the edge information as seed points; taking the connecting line of the seed point and the center as the growth direction of the corresponding seed point, calculating the gray difference value of the seed point and the pixel point closest to the seed point in the growth direction, when the gray difference value is smaller than a threshold value, performing primary growth on the seed point, taking the pixel point in the growth direction as the seed point, and repeating the steps until the gray difference value is larger than the threshold value, and stopping the growth of the seed point; acquiring a boundary area of a target, and acquiring the width of the boundary area according to the growth times of the seed points;
calculating a gray level co-occurrence matrix corresponding to the boundary area;
taking other regions except the boundary region in the ROI region as an internal region of a target; calculating a gray level co-occurrence matrix corresponding to the internal region;
the gray level co-occurrence matrix corresponding to the boundary area is differed with the gray level co-occurrence matrix corresponding to the internal area to obtain a difference value between the internal area and the boundary area;
acquiring a gray level co-occurrence matrix corresponding to the ROI according to a gray level co-occurrence matrix corresponding to the boundary region and a gray level co-occurrence matrix corresponding to the inner region; calculating the entropy of the gray level co-occurrence matrix corresponding to the ROI;
calculating the fuzzy degree of the image information based on the width, the difference value and the entropy; and according to the fuzzy degree, realizing intelligent adjustment of the coal mine ventilator.
Further, the method for acquiring the center of the target comprises the following steps: randomly selecting one pixel point in the edge information as a point a, randomly selecting one pixel point in the edge information as a point b, crossing the straight line of the point a and the point b to form an edge at a point c, and calculating the distance between the point a and the point b
Calculating the distance between the point b and the point c
Comparison of
And
the size of (1) when
Is greater than
Then point b moves towards point a until point a
And
is equal, the point b stops moving; and randomly selecting pixel points except the pixel points at the positions of the point a and the point c on the edge to be recorded as a point d, intersecting the straight line passing through the point a and the point d with the edge at a point e, and calculating the distance between the point d and the point b
Calculating the distance between the point b and the point e
Comparison of
And
the size of (1) when
Is greater than
Then point b moves towards point d until
And
is equal, the point b stops moving; by analogy, all the pixel points on the edge are processed byAnd acquiring the center of the target.
Further, the width is:
wherein, in the step (A),
is the width of the border area and,
is the total number of the seed points,
the growth times of the t-th seed point.
Further, when the gray level co-occurrence matrix of the boundary region is calculated, two adjacent pixel points in the scanning angle need to be formed into a pixel point pair, where the scanning angle forming the pixel point pair is the growth direction.
Further, the difference value calculation method comprises the following steps: and (3) subtracting the gray level co-occurrence matrix corresponding to the boundary area from the gray level co-occurrence matrix corresponding to the internal area to obtain a difference gray level co-occurrence matrix, and calculating the sum of all elements in the difference gray level co-occurrence matrix to obtain a difference value.
Further, the blur degree is:
wherein the content of the first and second substances,
the normalized value for the width of the bounding region,
is composed of
The corresponding weight of the weight is set to be,
the difference value is used as the difference value,
is composed of
The corresponding weight of the weight is set to be,
the entropy of the corresponding gray level co-occurrence matrix for the ROI region,
is composed of
The corresponding weight.
The embodiment of the invention at least has the following beneficial effects:
the invention relates to the technical field of image processing, in particular to a coal mine ventilator intelligent adjusting method based on a high-voltage frequency converter, which comprises the steps of obtaining image information corresponding to an underground environment, preprocessing the image information and obtaining a gray image; acquiring an ROI (region of interest) in a gray image, extracting edge information of a target in the ROI, and taking pixel points in the edge information as seed points; acquiring a boundary area of a target by using an area growing algorithm; calculating a gray level co-occurrence matrix of the boundary area; acquiring the width of the boundary region according to the growing times of the seed points; obtaining an internal region of a target; calculating a gray level co-occurrence matrix of the internal region to obtain a difference value between the internal region and the boundary region; acquiring a gray level co-occurrence matrix of the ROI; calculating the entropy of the gray level co-occurrence matrix of the ROI; calculating the fuzzy degree of the image information based on the width, the difference value and the entropy; and adjusting the coal mine ventilator according to the fuzzy degree.
According to the invention, the image information is subjected to relevant processing to obtain the fuzzy degree of the image information, and the coal mine ventilator can be accurately adjusted by adjusting the fuzzy degree. Meanwhile, the dust concentration in the underground environment is represented by the fuzzy degree, compared with the traditional method for obtaining the data of the underground dust concentration, the data is generally obtained by workers through a dust detector, the collection is difficult, the human resources are wasted, the equipment cost is high, and the installation position of the equipment can influence the construction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart of steps of an intelligent adjusting method of a coal mine ventilator based on a high-voltage frequency converter.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the proposed solution, its specific implementation, structure, features and effects will be made with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Referring to fig. 1, a flow chart of steps of an intelligent adjustment method for a coal mine ventilator based on a high-voltage frequency converter according to an embodiment of the present invention is shown, where the method includes the following steps:
step 1, obtaining image information corresponding to an underground environment, preprocessing the image information to obtain a gray image, and performing image segmentation on the gray image to obtain an ROI (region of interest).
Specifically, utilize the high resolution camera to obtain the image information that the environment corresponds in the pit, because the operational environment of digging the coal is dim, the embodiment adopts fixed light source to shine the operational environment in the pit, makes image information can reflect the relevant information of operational environment more directly perceivedly.
The image information acquired by the high-resolution camera is an RGB image, and in order to reduce the calculated amount of image processing, the gray level image is obtained by performing graying operation on the image information by adopting a weighted average algorithm; as another embodiment, a maximum value method, a component method, or the like may be employed.
In this embodiment, the image segmentation is performed on the gray image by using the tsu method, which is the prior art and is not described herein again.
And 2, extracting the edge information of the target in the ROI area to obtain the center of the target.
The edge detection is performed on the ROI by using a canny operator, the edge of the target in the ROI is extracted, and the ROI of the embodiment only has one target. The canny operator is not easily interfered by noise, has strong anti-noise capability and can more accurately detect the edge of the target.
The method for acquiring the center of the target comprises the following steps: randomly selecting one pixel point in the edge information as a point a, randomly selecting one pixel point in the edge information as a point b, crossing the straight line of the point a and the point b to intersect with the edge at a point c, and calculating the distance between the point a and the point b
Calculating the distance between the point b and the point c
Comparison of
And
the size of (1) when
Is greater than
Then point b moves towards point a until point a
And
is equal, the point b stops moving; and randomly selecting pixel points except the pixel points at the positions of the point a and the point c on the edge to be recorded as a point d, crossing the straight line of the point a and the point d to intersect with the edge at a point e, and calculating the distance between the point d and the point b
Calculating the distance between the point b and the point e
Comparison of
And
the size of (2)
Is greater than
Then point b moves towards point d until
And
is equal, the point b stops moving; and repeating the process of traversing all the pixel points on the edge to obtain the center of the target.
It should be noted that the target includes workers and working equipment in the construction environment, and when the high-resolution camera is used to obtain image information corresponding to the downhole environment, the high-resolution camera cannot completely shoot each worker and each working equipment; therefore, in this embodiment, a complete target photographed by one high-resolution camera is arbitrarily selected, and the edge of the target is a closed edge, so that a straight line passing through a certain pixel point in the target internal region intersects with two pixel points in the edge information.
Step 3, taking pixel points in the edge information as seed points; taking a connecting line of the seed point and the center as a growth direction of the corresponding seed point, calculating a gray difference value of the seed point and a pixel point closest to the seed point in the growth direction, when the gray difference value is smaller than a threshold value, performing primary growth on the seed point, taking the pixel point in the growth direction as the seed point, and repeating the steps until the gray difference value is larger than the threshold value, and stopping the growth of the seed point; and acquiring the boundary area of the target, and acquiring the width of the boundary area according to the growing times of the seed points.
The method for acquiring the boundary region of the target is a region growing algorithm, and the basic idea of the region growing algorithm is to combine pixel points with similar properties together; for each region, firstly, a seed point is appointed as a starting point of growth, then pixel points of 8 neighborhoods around the seed point are compared with the seed point, and the pixel points with similar properties are combined to continue to grow outwards until the pixel points meeting the conditions are included. By this, the growth of such a region is completed.
Specifically, a pixel point closest to the seed point in the growth direction is recorded as a neighborhood pixel point of the seed point, a gray value difference value of the neighborhood pixel point and the seed point is calculated, and the neighborhood pixel point and the seed point corresponding to the gray value difference value smaller than a threshold value are combined together; at the moment, the seed points grow for one time, the neighborhood pixel points are used as the seed points, and the analogy is repeated until the gray difference value is smaller than the threshold value, and the seed points stop growing; the threshold value is set by the implementer according to the actual situation.
Of the above seed pointsThe method for acquiring the neighborhood pixel points comprises the following steps: the growth direction of the seed point is the connecting line of the seed point and the center, and the included angle formed by the connecting line and the horizontal straight line in the clockwise direction is recorded as
Will be at the seed point
And taking the pixel points in the direction as neighborhood pixel points of the seed points. For example, if the included angle formed by the connecting line of the seed point and the center and the horizontal straight line in the clockwise direction is 30 degrees, the pixel point corresponding to the direction with the angle of 30 degrees formed by the seed point is marked as the neighborhood pixel point of the seed point; the number of the neighborhood pixels is two, one neighborhood pixel is on the right side of the seed point, and the other neighborhood pixel is on the left side of the seed point.
In a traditional region growing algorithm, the seed points are selected randomly, the growing directions of the seed points are 8 neighborhood pixel points of the seed points, namely the growing directions of the seed points are 8; the angles formed by the 8 neighborhood pixel points and the seed points are respectively 0 degree, 45 degrees, 90 degrees and 135 degrees; in this embodiment, the pixel points in the target edge information are all seed points, the growth directions of the seed points are 2, and all the seed points grow simultaneously; in this embodiment, when the growth direction of the seed point is 30 °, the distance from the neighborhood pixel point of the seed point to the seed point is longer than the distance from the neighborhood pixel point of the seed point 8 to the seed point, and the pixel point between the seed point and the neighborhood pixel point is an irrelevant pixel point of the seed point. When the boundary area is obtained, a plurality of seed points grow in the corresponding growth direction, calculation of irrelevant pixel points is reduced, growth efficiency is improved, and a growth result can be accurately obtained.
Specifically, the width is:
wherein, in the step (A),
is the width of the border area and,
is the total number of the seed points,
the growth times of the t-th seed point.
The width of the boundary region characterizes the dust concentration in the working environment, and the wider the width of the boundary region, the higher the dust concentration in the working environment. When the dust concentration in the working environment is too high, the image information shot by the high-resolution camera can be blurred due to the blocking of dust; the larger the dust concentration is, the more blurred the image information is, and the more blurred the image information is, the wider the boundary area of the target in the image information is, so that the width of the boundary area can represent the dust concentration in the working environment.
When the gray level co-occurrence matrix corresponding to the boundary region is calculated, two adjacent pixel points in the scanning angle need to be formed into a pixel point pair, wherein the scanning angle forming the pixel point pair is the growth direction. Each seed point forms a corresponding angle with the center
And seeds are spotted on
Growth is carried out in the direction; therefore, the texture of the boundary region is mainly distributed in
In the direction; in this embodiment, the gray value of each pixel point in the boundary region is divided into 16 gray levels, and the corresponding gray levels in the boundary region are divided into 16 gray levels
Two adjacent pixels in the direction form a pixel point pair, and the times of the pixel point pair occurrence are counted, so that the pixel point pair is obtainedAnd normalizing the occurrence frequency of each pixel point pair to obtain the occurrence probability of each pixel point pair and obtain a gray level co-occurrence matrix corresponding to the boundary area.
It should be noted that, in the conventional acquisition of the gray level co-occurrence matrix, 4 directions of 0 °, 45 °, 90 °, and 135 ° need to be scanned, and the pixels in the 4 directions form pixel point pairs, so as to acquire the gray level co-occurrence matrix, which not only has an excessively large calculation amount, but also has an influence on the acquisition result of the gray level co-occurrence matrix caused by the gray level information at a useless angle, and cannot accurately represent texture information in the corresponding region. According to the embodiment, the gray level co-occurrence matrix is obtained by utilizing the growth direction, the detection effect is more accurate, and the calculated amount is smaller.
Step 4, taking other regions except the boundary region in the ROI region as target inner regions; calculating a gray level co-occurrence matrix corresponding to the internal region; and (4) making a difference between the gray level co-occurrence matrix corresponding to the boundary area and the gray level co-occurrence matrix corresponding to the internal area to obtain a difference value between the internal area and the boundary area.
The boundary region divides the ROI into two parts, one part is the boundary region of the target, and the other part is the internal region of the target; when the gray level co-occurrence matrix corresponding to the internal area is calculated, the gray level corresponding to the internal area is consistent with the gray level corresponding to the boundary area; the method for calculating the gray level co-occurrence matrix corresponding to the internal region is the same as the method for acquiring the gray level co-occurrence matrix in the prior art, and is not described again.
The difference value calculation method comprises the following steps: and (3) making a difference between the gray level co-occurrence matrix corresponding to the boundary area and the gray level co-occurrence matrix corresponding to the internal area to obtain a difference gray level co-occurrence matrix, and calculating the sum of each element in the difference gray level co-occurrence matrix to obtain a difference value.
The calculation formula of the difference value is as follows:
wherein the content of the first and second substances,
is the total number of gray levels of the pixel,
is a pixel point pair formed by pixel points corresponding to the ith gray level and the jth gray level,
as pairs of pixel points
The values in the gray co-occurrence matrix correspond in the boundary region,
as pairs of pixel points
The inner region corresponds to a value in the gray co-occurrence matrix.
The difference value in this embodiment represents the similarity between the inner region and the boundary region of the target, and the smaller the difference is, the higher the similarity between the inner region and the boundary region of the target is; conversely, the lower the similarity between the inner region and the boundary region of the target; when the dust concentration in the working environment is higher, the degree of blurring of the image information is larger, the similarity between the boundary region and the inner region is higher, and the difference value is smaller.
Step 5, acquiring a gray level co-occurrence matrix corresponding to the ROI according to the gray level co-occurrence matrix corresponding to the boundary region and the gray level co-occurrence matrix corresponding to the inner region; calculating the entropy of the gray level co-occurrence matrix corresponding to the ROI;
preferably, an average gray level co-occurrence matrix of the gray level co-occurrence matrix corresponding to the boundary region and the gray level co-occurrence matrix corresponding to the internal region is calculated, and the average gray level co-occurrence matrix is used as the gray level co-occurrence matrix corresponding to the ROI region, so that not only can texture information of the ROI region be accurately represented, but also the calculation amount is reduced.
The above manner of calculating the entropy of the gray level co-occurrence matrix corresponding to the ROI region is the same as the conventional manner of calculating the entropy of the gray level co-occurrence matrix, and the calculation manner of the entropy of the gray level co-occurrence matrix is a known technique and is not described again.
It should be noted that the entropy reflects the disorder of the gray value distribution in the ROI region, and represents the texture complexity in the ROI region, and the texture complexity can reflect the blurring degree of the image information; the more irregular the gray value change of each pixel point in the ROI area is, the larger the entropy value is, the higher the texture complexity in the ROI area is, the lower the dust concentration is, and the clearer the image information is; conversely, the smaller the entropy value, the lower the texture complexity in the ROI region, the higher the dust concentration, and the more blurred the image information.
Step 6, calculating the fuzzy degree of the image information based on the width, the difference value and the entropy; according to the fuzzy degree, the intelligent adjustment of the coal mine ventilator is realized.
The degree of blurring was:
wherein the content of the first and second substances,
the normalized value for the width of the bounding region,
is composed of
The corresponding weight of the weight is set to be,
the difference value is used as the difference value,
is composed of
The corresponding weight of the weight is set to be,
the entropy of the corresponding gray level co-occurrence matrix for the gray level image,
is composed of
The corresponding weight.
This embodiment normalizes the blur degree to obtain
By using
And representing the dust concentration in the current working environment, wherein the higher the fuzzy degree of the image information is, the higher the dust concentration in the current working environment is, and conversely, the lower the dust concentration in the current working environment is.
Further, in order to carry out intelligent regulation to the colliery ventilation blower more accurately, in this embodiment, still utilize gas detection appearance to acquire the gas concentration in the current operational environment to record the gas concentration as
The method comprises the following steps of calculating the air volume of the coal mine ventilator to be adjusted, specifically:
wherein the content of the first and second substances,
in order to adjust the air quantity of the coal mine ventilator,
is the dust concentration in the current working environment,
is the concentration of the dust in the standard,
is the gas concentration in the current working environment,
is the standard gas concentration, and the gas concentration,
the current air quantity of the coal mine ventilator.
Based on the determined air volume, the air volume of the coal mine ventilator is controlled by intelligently adjusting the rotating speed of the fan through the high-voltage frequency converter. When in use
When the air volume is positive, the air volume of the coal mine ventilator is increased, and when the air volume is positive
When the air volume is a negative value, the air volume of the coal mine ventilator is reduced; the standard dust concentration is the management limit judgment standard for the dust contact concentration of the coal mine operation places in the national standard, and the standard gas concentration is the standard gas concentration in the national standard. The embodiment utilizes the dust concentration in the image information real-time supervision operational environment, through the gas concentration in the gas detector real-time supervision operational environment, adjusts colliery ventilation blower's amount of wind in real time, makes the dust concentration in the pit and gas concentration keep in the within range that the safety in production required.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (6)
1. The intelligent coal mine ventilator adjusting method based on the high-voltage frequency converter is characterized by comprising the following steps of:
acquiring image information corresponding to an underground environment, and preprocessing the image information to obtain a gray image;
carrying out image segmentation on the gray level image to obtain an ROI (region of interest); only one target is present in the ROI region; extracting edge information of a target in the ROI area, and acquiring the center of the target;
taking the pixel points in the edge information as seed points; taking the connecting line of the seed point and the center as the growth direction of the corresponding seed point, calculating the gray difference value of the seed point and the pixel point closest to the seed point in the growth direction, when the gray difference value is smaller than a threshold value, performing primary growth on the seed point, taking the pixel point in the growth direction as the seed point, and repeating the steps until the gray difference value is larger than the threshold value, and stopping the growth of the seed point; acquiring a boundary area of a target, and acquiring the width of the boundary area according to the growth times of the seed points;
calculating a gray level co-occurrence matrix corresponding to the boundary area;
taking other regions except the boundary region in the ROI region as an internal region of a target; calculating a gray level co-occurrence matrix corresponding to the internal region;
the gray level co-occurrence matrix corresponding to the boundary area is differed with the gray level co-occurrence matrix corresponding to the internal area to obtain a difference value between the internal area and the boundary area;
acquiring a gray level co-occurrence matrix corresponding to the ROI according to a gray level co-occurrence matrix corresponding to the boundary region and a gray level co-occurrence matrix corresponding to the inner region; calculating the entropy of the gray level co-occurrence matrix corresponding to the ROI;
calculating the fuzzy degree of the image information based on the width, the difference value and the entropy; and according to the fuzzy degree, realizing intelligent adjustment of the coal mine ventilator.
2. The intelligent adjusting method for the coal mine ventilator based on the high-voltage frequency converter as claimed in claim 1,
the method for acquiring the center of the target comprises the following steps: randomly selecting one pixel point in the edge information as a point a, randomly selecting one pixel point in the edge information as a point b, crossing the straight line of the point a and the point b to form an edge at a point c, and calculating the distance between the point a and the point b
Calculating the distance between the point b and the point c
Comparison of
And with
The size of (1) when
Is greater than
Then point b moves towards point a until point a
And
is equal, the point b stops moving; and randomly selecting pixel points except the pixel points at the positions of the point a and the point c on the edge to be recorded as a point d, intersecting the straight line passing through the point a and the point d with the edge at a point e, and calculating the distance between the point d and the point b
Calculating the distance between the point b and the point e
Comparison of
And
the size of (2)
Is greater than
Then point b moves towards point d until
And
is equal, the point b stops moving; and repeating the steps to traverse all the pixel points on the edge to obtain the center of the target.
3. The intelligent adjusting method for the coal mine ventilator based on the high-voltage frequency converter as claimed in claim 1,
the width is:
wherein, in the step (A),
is the width of the border area and,
is the total number of the seed points,
the growth times of the t-th seed point.
4. The intelligent adjusting method for the coal mine ventilator based on the high-voltage frequency converter is characterized in that when the gray level co-occurrence matrix of the boundary area is calculated, two adjacent pixel points in a scanning angle need to be formed into a pixel point pair, wherein the scanning angle forming the pixel point pair is the growth direction.
5. The intelligent adjusting method for the coal mine ventilator based on the high-voltage frequency converter is characterized in that the difference value is calculated by the following steps: and (3) making a difference between the gray level co-occurrence matrix corresponding to the boundary area and the gray level co-occurrence matrix corresponding to the internal area to obtain a difference gray level co-occurrence matrix, and calculating the sum of each element in the difference gray level co-occurrence matrix to obtain a difference value.
6. The intelligent adjusting method for the coal mine ventilator based on the high-voltage frequency converter as claimed in claim 1,
the degree of blur is:
wherein the content of the first and second substances,
the normalized value for the width of the bounding region,
is composed of
The corresponding weight of the weight is set to be,
the difference value is used as the difference value,
is composed of
The corresponding weight of the weight is set to be,
the entropy of the corresponding gray level co-occurrence matrix for the ROI region,
is composed of
The corresponding weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210525322.2A CN114627140B (en) | 2022-05-16 | 2022-05-16 | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210525322.2A CN114627140B (en) | 2022-05-16 | 2022-05-16 | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114627140A true CN114627140A (en) | 2022-06-14 |
| CN114627140B CN114627140B (en) | 2022-08-16 |
Family
ID=81907164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210525322.2A Active CN114627140B (en) | 2022-05-16 | 2022-05-16 | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114627140B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081156A (en) * | 2022-07-21 | 2022-09-20 | 太原理工大学 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
| CN115272319A (en) * | 2022-09-27 | 2022-11-01 | 江苏亚振钻石有限公司 | Ore granularity detection method |
| CN115633259A (en) * | 2022-11-15 | 2023-01-20 | 深圳市泰迅数码有限公司 | Automatic regulation and control method and system for intelligent camera based on artificial intelligence |
| CN115809417A (en) * | 2023-02-09 | 2023-03-17 | 新风光电子科技股份有限公司 | Production line operation signal detection method for high-voltage frequency converter control cabinet |
| CN116721391A (en) * | 2023-08-11 | 2023-09-08 | 山东恒信科技发展有限公司 | Method for detecting separation effect of raw oil based on computer vision |
| CN117152132A (en) * | 2023-10-30 | 2023-12-01 | 山东济宁运河煤矿有限责任公司 | Intelligent detection system for coal sample grinding based on laser burning technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942812A (en) * | 2014-03-12 | 2014-07-23 | 华南理工大学 | Moving object detection method based on Gaussian mixture and edge detection |
| WO2014113786A1 (en) * | 2013-01-18 | 2014-07-24 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Quantitative predictors of tumor severity |
| CN110532511A (en) * | 2019-07-26 | 2019-12-03 | 四川师范大学 | It is a kind of based on gray scale-order co-occurrence matrix rotary inertia powder concentration measurement method |
| KR20200037909A (en) * | 2018-10-01 | 2020-04-10 | 삼성디스플레이 주식회사 | Laser irradiation apparatus, driving method thereof, and method for fabricating display device using the same |
| CN113530872A (en) * | 2021-08-24 | 2021-10-22 | 西安重装韩城煤矿机械有限公司 | Mining local ventilation system and method for self-adaptive gas discharge |
| CN113935992A (en) * | 2021-12-15 | 2022-01-14 | 武汉和众成设备工贸有限公司 | Image processing-based oil pollution interference resistant gear crack detection method and system |
| CN114387273A (en) * | 2022-03-24 | 2022-04-22 | 莱芜职业技术学院 | Environmental dust concentration detection method and system based on computer image recognition |
| CN114419025A (en) * | 2022-01-27 | 2022-04-29 | 江苏泰和木业有限公司 | Fiberboard quality evaluation method based on image processing |
-
2022
- 2022-05-16 CN CN202210525322.2A patent/CN114627140B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014113786A1 (en) * | 2013-01-18 | 2014-07-24 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Quantitative predictors of tumor severity |
| CN103942812A (en) * | 2014-03-12 | 2014-07-23 | 华南理工大学 | Moving object detection method based on Gaussian mixture and edge detection |
| KR20200037909A (en) * | 2018-10-01 | 2020-04-10 | 삼성디스플레이 주식회사 | Laser irradiation apparatus, driving method thereof, and method for fabricating display device using the same |
| CN110532511A (en) * | 2019-07-26 | 2019-12-03 | 四川师范大学 | It is a kind of based on gray scale-order co-occurrence matrix rotary inertia powder concentration measurement method |
| CN113530872A (en) * | 2021-08-24 | 2021-10-22 | 西安重装韩城煤矿机械有限公司 | Mining local ventilation system and method for self-adaptive gas discharge |
| CN113935992A (en) * | 2021-12-15 | 2022-01-14 | 武汉和众成设备工贸有限公司 | Image processing-based oil pollution interference resistant gear crack detection method and system |
| CN114419025A (en) * | 2022-01-27 | 2022-04-29 | 江苏泰和木业有限公司 | Fiberboard quality evaluation method based on image processing |
| CN114387273A (en) * | 2022-03-24 | 2022-04-22 | 莱芜职业技术学院 | Environmental dust concentration detection method and system based on computer image recognition |
Non-Patent Citations (3)
| Title |
|---|
| SONG YUHENG 等: "Image Segmentation Algorithms Overview", 《ARXIV:1707.02051V1》 * |
| 刘伟华: "基于机器视觉的煤尘在线检测***关键技术研究", 《知网博士电子期刊》 * |
| 杨柳: "复杂背景下基于视频图像的火灾识别技术研究", 《知网硕士电子期刊》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081156B (en) * | 2022-07-21 | 2022-11-25 | 太原理工大学 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
| CN115081156A (en) * | 2022-07-21 | 2022-09-20 | 太原理工大学 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
| CN115131387B (en) * | 2022-08-25 | 2023-01-24 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
| CN115131387A (en) * | 2022-08-25 | 2022-09-30 | 山东鼎泰新能源有限公司 | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing |
| CN115272319A (en) * | 2022-09-27 | 2022-11-01 | 江苏亚振钻石有限公司 | Ore granularity detection method |
| CN115272319B (en) * | 2022-09-27 | 2022-12-20 | 江苏亚振钻石有限公司 | Ore granularity detection method |
| CN115633259A (en) * | 2022-11-15 | 2023-01-20 | 深圳市泰迅数码有限公司 | Automatic regulation and control method and system for intelligent camera based on artificial intelligence |
| CN115633259B (en) * | 2022-11-15 | 2023-03-10 | 深圳市泰迅数码有限公司 | Automatic regulation and control method and system for intelligent camera based on artificial intelligence |
| CN115809417A (en) * | 2023-02-09 | 2023-03-17 | 新风光电子科技股份有限公司 | Production line operation signal detection method for high-voltage frequency converter control cabinet |
| CN116721391A (en) * | 2023-08-11 | 2023-09-08 | 山东恒信科技发展有限公司 | Method for detecting separation effect of raw oil based on computer vision |
| CN116721391B (en) * | 2023-08-11 | 2023-10-31 | 山东恒信科技发展有限公司 | Method for detecting separation effect of raw oil based on computer vision |
| CN117152132A (en) * | 2023-10-30 | 2023-12-01 | 山东济宁运河煤矿有限责任公司 | Intelligent detection system for coal sample grinding based on laser burning technology |
| CN117152132B (en) * | 2023-10-30 | 2024-02-02 | 山东济宁运河煤矿有限责任公司 | Intelligent detection system for coal sample grinding based on laser burning technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114627140B (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114627140B (en) | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter | |
| CN111814711A (en) | Image feature fast matching method and system applied to mine machine vision | |
| CN111047555A (en) | Ore image granularity detection algorithm based on image processing technology | |
| CN109325935B (en) | Power transmission line detection method based on unmanned aerial vehicle image | |
| CN104851086B (en) | A kind of image detecting method for cable surface defect | |
| CN106290388A (en) | A kind of insulator breakdown automatic testing method | |
| CN115631116B (en) | Aircraft power inspection system based on binocular vision | |
| CN113034397A (en) | Real-time multi-environment self-adaptive track automatic tracing high-altitude parabolic detection method | |
| CN116630321B (en) | Intelligent bridge health monitoring system based on artificial intelligence | |
| CN103945197A (en) | Electric power facility external damage prevention warming scheme based on video motion detecting technology | |
| CN115841633A (en) | Power tower and power line associated correction power tower and power line detection method | |
| CN115409742A (en) | Vegetation coverage density assessment method based on landscaping | |
| CN114332096A (en) | Pig farm pig example segmentation method based on deep learning | |
| CN112686120A (en) | Power transmission line anomaly detection method based on unmanned aerial vehicle aerial image | |
| CN115018872A (en) | Intelligent control method of dust collection equipment for municipal construction | |
| CN114742785A (en) | Hydraulic joint cleanliness control method based on image processing | |
| WO2024077979A1 (en) | Mushroom cluster contour segmentation and reconstruction method based on improved solov2 | |
| CN113019955A (en) | Intelligent ore sorting equipment and method based on dual-energy X-ray | |
| CN108009480A (en) | A kind of image human body behavioral value method of feature based identification | |
| CN115131387B (en) | Gasoline engine spray wall collision parameter automatic extraction method and system based on image processing | |
| CN115049606A (en) | High-altitude parabolic detection and tracing method integrating kinematics and machine vision | |
| CN111382674B (en) | Identification method of aggressive pig based on visual saliency | |
| CN113406625A (en) | SAR image superpixel sliding window CFAR detection method | |
| CN112132767A (en) | Solar cell panel shadow processing method based on computer vision | |
| CN117475157B (en) | Agricultural planting enhancement monitoring method based on unmanned aerial vehicle remote sensing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |