CN109876569B - Online detection device, system and method for purified gas index of bag-type dust remover - Google Patents
Online detection device, system and method for purified gas index of bag-type dust remover Download PDFInfo
- Publication number
- CN109876569B CN109876569B CN201910322046.8A CN201910322046A CN109876569B CN 109876569 B CN109876569 B CN 109876569B CN 201910322046 A CN201910322046 A CN 201910322046A CN 109876569 B CN109876569 B CN 109876569B
- Authority
- CN
- China
- Prior art keywords
- image
- particle
- bag
- type dust
- module
- 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.)
- Expired - Fee Related
Links
- 239000000428 dust Substances 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 239000002245 particle Substances 0.000 claims abstract description 182
- 238000012544 monitoring process Methods 0.000 claims abstract description 85
- 230000008569 process Effects 0.000 claims abstract description 32
- 230000001678 irradiating effect Effects 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 61
- 238000012545 processing Methods 0.000 claims description 39
- 238000001914 filtration Methods 0.000 claims description 28
- 238000009826 distribution Methods 0.000 claims description 24
- 238000000926 separation method Methods 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 239000002184 metal Substances 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012804 iterative process Methods 0.000 claims description 3
- 239000007789 gas Substances 0.000 description 70
- 230000006870 function Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 11
- 238000010926 purge Methods 0.000 description 8
- 235000013339 cereals Nutrition 0.000 description 6
- 238000013461 design Methods 0.000 description 6
- 230000003111 delayed effect Effects 0.000 description 5
- 239000004744 fabric Substances 0.000 description 5
- 238000004134 energy conservation Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 241000566145 Otus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000011362 coarse particle Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003517 fume Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000002440 industrial waste Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010297 mechanical methods and process Methods 0.000 description 1
- 230000005226 mechanical processes and functions Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Abstract
The invention discloses a device, a system and a method for online detection of gas indexes in a bag-type dust remover, wherein the device comprises a laser emitting device and a camera module, the camera module comprises a camera and a main control module, and the laser emitting device is used for irradiating a laser beam on a gas outlet of the bag-type dust remover; the camera collects images of purified gas in the gas outlet irradiated by the laser beam; the main control module sends the collected purified gas image to the upper computer so that the upper computer can process the image to obtain the characteristic parameters of the purified gas. The laser beam irradiates and the camera module acquires the particle image of the air outlet of the bag-type dust collector, so that the real-time monitoring of the purified gas at the air outlet of the bag-type dust collector is realized, the characteristic parameters of the purified gas can be timely obtained so as to optimize and save energy of the bag-type dust collector in time, and the characteristic of no lag in real-time monitoring can be suitable for great popularization in the market.
Description
Technical Field
The invention relates to a device, a system and a method for online detection of gas indexes in a bag-type dust remover, and belongs to the technical field of dust removers.
Background
The dust-containing industrial waste gas is generated from mechanical processes such as crushing, screening, conveying and blasting of solid substances, or from processes such as combustion, high-temperature melting and chemical reaction. Dust collectors are widely used to control dust and fumes that have been generated.
The existing dust remover is mainly a pulse bag type dust remover, and the dust removing principle is as follows: when the dust-containing gas enters the dust remover from the air inlet, the dust-containing gas firstly touches the inclined plate and the baffle plate between the air inlet and the air outlet, the airflow turns to flow into the dust hopper, and simultaneously the airflow speed is slowed down, so that coarse particle dust in the gas can directly flow into the dust hopper under the action of inertia, and the effect of pre-collecting dust is achieved. The airflow entering the dust hopper is then folded upwards to pass through a filter bag internally provided with a metal framework, dust is trapped on the outer surface of the filter bag, and the purified gas enters a cleaning chamber at the upper part of the filter bag and is collected to an air outlet to be discharged. However, in the process of purifying dust-containing gas by passing through the filter bag, the dust accumulated on the filter bag is more and more along with the increase of time, the resistance of the filter bag is increased, so that the air volume for treatment is gradually reduced, and in order to work normally, the resistance needs to be controlled within a certain range (140-170 mm water column), so the filter bag needs to be cleaned. Therefore, the index of purified gas emission has great relation with the cloth bag ash removal time, the rotating speed of the induced draft fan, the quality of the cloth bag, the service life of the cloth bag and the like. If the dust removal process is optimally controlled, the particle size of the purified gas needs to be detected on line, but instruments capable of detecting the particle size of the purified gas on line are expensive and mostly have hysteresis.
The existing bag-type dust collector basically adopts a pulse controller to clean and control a bag, and most of the bag-type dust collector does not realize the online detection optimization control of discharge indexes. The large-scale bag-type dust collector utilizes a PLC (programmable logic controller) and is additionally provided with an upper computer, a pressure sensor and a purified gas detector to construct a distributed control system, and adopts a closed-loop control mode, however, the software and hardware of the bag-type dust collector are not unified, the algorithm has respective independence, and the control index cannot be standardized; the system is large and needs various technicians to cooperate; the cost of software and hardware is high, and the bag-type dust collector is not suitable for medium and small-sized bag-type dust collectors, so the bag-type dust collector cannot be popularized and used.
Disclosure of Invention
Aiming at the defects of the methods, the invention provides a device, a system and a method for online detection of gas indexes in a bag-type dust remover, which can integrate bag-type dust removal and particle characteristic real-time monitoring and can be suitable for great popularization in the market.
The technical scheme adopted for solving the technical problems is as follows:
in a first aspect, the online detection device for the gas index of the bag-type dust remover provided by the embodiment of the invention comprises a laser emission device and a camera module, wherein the camera module comprises a camera and a main control module, and the laser emission device is used for irradiating a laser beam on a gas outlet of the bag-type dust remover; the camera collects images of purified gas in the gas outlet irradiated by the laser beam; the main control module sends the collected purified gas image to the upper computer so that the upper computer can process the image to obtain the characteristic parameters of the purified gas.
As a possible implementation manner of this embodiment, the laser emitting device is provided with a light source focus, a convex lens and a filter in sequence from back to front.
As a possible implementation manner of this embodiment, the online detection device further includes a lens protection plate, a light shielding plate and a driving motor, the lens protection plate is disposed in front of the camera, the light shielding plate is disposed at a laser beam irradiation through hole of the laser emission device, a control end of the driving motor is electrically connected to the main control module, and an output shaft of the driving motor is used for respectively driving the lens protection plate and the light shielding plate to move.
As a possible implementation manner of this embodiment, the main control module includes a core control chip STM32F407, and an input circuit, an RS485 module, a camera chip, an output circuit, and an SD card that are connected to the core control chip STM 407, respectively, where the RS485 module is connected to an upper computer.
As a possible implementation manner of this embodiment, the main control module further includes an expansion input circuit and an expansion output circuit that are respectively connected to the core control chip STM32F 407.
In a second aspect, the system for online detection of gas indexes in bag-type dust remover provided by the embodiment of the invention comprises a process chamber, a computer optimization energy-saving control system, a bag-type dust remover, an air compressor, an induced draft fan, a compressed air pressure monitoring module, an outdoor air humidity monitoring module, a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtration outlet pressure monitoring module, a production process parameter monitoring module, an outdoor rainfall monitoring module, a remote GPRS module and an RS485 communication module, and further comprises the device for online detection of gas indexes in bag-type dust remover, wherein air to be dedusted is stored in the process chamber, and is dedusted under the action of the air compressor and the induced draft fan after reaching the bag-type dust remover through a pipeline, and is dedusted through the compressed air pressure monitoring module, The system comprises an outdoor air humidity monitoring module, a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtering outlet pressure monitoring module, a production process parameter monitoring module, an outdoor rainfall monitoring module, a pressure point and a rotating speed point, wherein the outdoor rainfall monitoring module detects all temperature and humidity, the pressure point and the rotating speed point, obtained data are returned to a computer optimization control system, particle images which are irradiated by laser beams through a laser emitting device and collected to the gas purified by a bag-type dust collector through a camera module are transmitted to the computer optimization energy-saving control system, and characteristic parameters of particle size distribution and particle concentration are monitored in real time through an image processing algorithm.
In a third aspect, the online detection method for the gas index in the bag-type dust remover provided by the embodiment of the invention comprises the following steps:
collecting a particle image of purified gas of a bag-type dust collector;
image restoration: processing the particle image by adopting a Lucy _ Richardson iterative nonlinear restoration algorithm, and converting the particle image from a dynamic state to a static state;
image filtering: filtering the particle image by adopting a non-local mean filtering algorithm to remove noise;
image segmentation: carrying out binarization segmentation on the particle image by adopting a K mean value clustering algorithm;
image overlapping processing: separating the overlapped particles from the particle image by adopting an overlapped particle automatic separation algorithm which combines template detection and curvature and constructs a separation line;
image reflection point processing: judging the range of the metal reflecting points by utilizing the function relation of the front end and the rear end of the particle image, and performing dust removal treatment by using a hole filling algorithm;
measurement and statistics of particle characteristic parameters: and (4) counting the equivalent diameter of the measured particles in the particle image, and obtaining the particle size distribution and the particle concentration of the particle image.
As a possible implementation manner of this embodiment, the process of image segmentation includes the following steps:
calculating the distance between the sample and each mean vector;
determining cluster marks according to the nearest mean vector;
dividing the samples into corresponding clusters;
a new mean vector is calculated.
As a possible implementation manner of this embodiment, the process of the image overlapping processing includes the following steps:
acquiring an overlapping area: converting a binary image into a gray image by adopting an urban distance conversion method, calculating the distance between each target pixel and the nearest background pixel, extracting an edge curve by calculating a distance conversion value and adopting a canny operator, smoothing the image by using a one-dimensional Gaussian function, calculating the amplitude and direction of a gradient, detecting and connecting the edge by a dual-threshold method, and performing tracking, conversion and stripping layer by layer from outside to inside in the iterative process of forming a final edge curve until the area is empty so as to obtain an overlapped area;
and (3) extracting a segmentation point: moving a circular template with a proper radius along the boundary line of the overlapped particle area to obtain the perimeter C of the intersection area of the circle and the particles; fitting the perimeter value C of the intersection region at each position of the boundary into a curve y; taking y as an objective function to solve the curvature of each point;
constructing a separation line: and drawing a separation line by adopting a bresenham algorithm, obtaining a virtual network by establishing a group of pixel centers passing through each row and each column, calculating the intersection points of the straight line and each vertical grid line according to the sequence of the straight line from the starting point to the end point, and calculating the distance difference between the candidate point and the real point for discrimination so as to determine the position of the next pixel point.
As a possible implementation manner of this embodiment, the process of processing the image reflection points includes the following steps:
dividing the image into 10 x 10 cells;
setting a threshold value, and judging and marking the front end and the rear end of the light reflection point according to the threshold value;
the connected region, i.e. the retro-reflective dot area, is filled with background pixels.
As a possible implementation manner of this embodiment, the process of measuring and counting the particle characteristic parameters includes the following steps:
calculating equivalent particle size: selecting an area diameter as an equivalent particle diameter;
counting the particle size distribution: selecting a plurality of representative particle sizes from small to large to form three particle size intervals of large, medium and small, counting all particles from small to a certain representative particle size, and representing frequency distribution by using accumulated number;
calculating the particle concentration: the equivalent circle volume is selected to characterize the particle volume, and the mass and concentration are calculated from the volume.
The technical scheme of the embodiment of the invention has the following beneficial effects:
the device for online detection of the gas index of the bag-type dust remover comprises a laser emitting device and a camera module, wherein the camera module comprises a camera and a main control module, and the laser emitting device is used for irradiating a laser beam on a gas outlet of the bag-type dust remover; the camera collects images of purified gas in the gas outlet irradiated by the laser beam; the main control module sends the collected purified gas image to the upper computer so that the upper computer can process the image to obtain the characteristic parameters of the purified gas. The laser beam irradiates and the camera module acquires the particle image of the air outlet of the bag-type dust collector, so that the real-time monitoring of the purified gas at the air outlet of the bag-type dust collector is realized, the characteristic parameters of the purified gas can be timely obtained so as to optimize and save energy of the bag-type dust collector in time, and the characteristic of no lag in real-time monitoring can be suitable for great popularization in the market.
The invention provides a bag-type dust remover purified gas index on-line detection system which comprises a process chamber, a computer optimization energy-saving control system, a bag-type dust remover, an air compressor, an induced draft fan, a compressed air pressure monitoring module, an outdoor air humidity monitoring module, a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtration outlet pressure monitoring module, a production process parameter monitoring module, an outdoor rainfall monitoring module, a remote GPRS (general packet radio service) module and an RS485 communication module and also comprises the bag-type dust remover purified gas index on-line detection device provided by the embodiment of the invention on the first aspect The system comprises a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtration outlet pressure monitoring module, a production process parameter monitoring module and an outdoor rainfall monitoring module, wherein the temperature and humidity, the pressure points and the rotating speed points at all positions are detected by the dust temperature monitoring module, the outdoor rainfall monitoring module to obtain data, the data are returned to a computer optimization control system, particle images which are irradiated by laser beams through a laser emitting device and collected to be purified gas through a camera module are transmitted to the computer optimization energy-saving control system, and characteristic parameters of particle size distribution and particle concentration are monitored in real time through an image processing algorithm. The process chamber stores air to be dedusted, the upper computer transmits signals after the air to be dedusted is electrified, dust gas reaches the bag-type dust remover through a pipeline, dedusting is carried out under the action of an air compressor and a draught fan, the laser device and the protective baffle are opened, the camera receives the signals to carry out image acquisition, the gas image after dust filtration is transmitted to the upper computer, and characteristic parameters such as particle size distribution, particle concentration and the like at the moment are obtained through algorithm processing. The invention can carry out closed-loop control and realize the integration of bag-type dust removal and particle characteristic real-time monitoring by combining with a peripheral analog electronic circuit. Compared with the existing purifier on the market, the cost of the system is reduced to the greatest extent; the whole process design is suitable for various devices such as large, medium and small devices; the real-time monitoring characteristic is not delayed, so that the method can be suitable for great popularization in the market; the advantages of optimizing energy conservation play an important role in environmental protection.
The invention utilizes laser to emit parallel light, and generates emitted light and refracted light through a purified gas outlet pipeline of a bag-type dust remover so as to form a visible light image, and a shooting device is invented based on the principle; and finally, acquiring characteristic parameters of purified gas, such as particle size distribution, particle concentration and the like, as a dust removal control index basis by adopting a series of image processing algorithms, and realizing dust removal optimization control. The system has the following characteristics: the cost is extremely low, the installation and the use in large, medium and small bag-type dust collectors can be realized, the dust collector is widely used in the market, and the dust collector plays an important role in the haze treatment of the nature.
The method for detecting the gas index on line by the bag-type dust remover in the technical scheme of the embodiment of the invention comprises the following steps: collecting a particle image of purified gas of a bag-type dust collector; image restoration: processing the particle image by adopting a Lucy _ Richardson iterative nonlinear restoration algorithm, and converting the particle image from a dynamic state to a static state; image filtering: filtering the particle image by adopting a non-local mean filtering algorithm to remove noise; image segmentation: carrying out binarization segmentation on the particle image by adopting a K mean value clustering algorithm; image overlapping processing: separating the overlapped particles from the particle image by adopting an overlapped particle automatic separation algorithm which combines template detection and curvature and constructs a separation line; image reflection point processing: judging the range of the metal reflecting points by utilizing the function relation of the front end and the rear end of the particle image, and performing dust removal treatment by using a hole filling algorithm; measurement and statistics of particle characteristic parameters: and (4) counting the equivalent diameter of the measured particles in the particle image, and obtaining the particle size distribution and the particle concentration of the particle image. The invention utilizes laser to emit parallel light, and generates emitted light and refracted light through a purified gas outlet pipeline of a bag-type dust remover so as to form a visible light image, and a shooting device is invented based on the principle; by adopting a series of image processing algorithms, finally acquiring characteristic parameters such as particle size distribution, particle concentration and the like of purified gas as a dust removal control index basis, not only realizing dust removal optimization control, but also integrating cloth bag dust removal and particle characteristic real-time monitoring; the whole process design is suitable for various devices such as large, medium and small devices; the real-time monitoring characteristic is not delayed, so that the method can be suitable for great popularization in the market; the advantages of optimizing energy conservation play an important role in environmental protection.
Description of the drawings:
FIG. 1 is a schematic diagram illustrating an in-line detection apparatus for a purge gas indicator of a bag-type dust collector according to an exemplary embodiment;
FIG. 2 is a functional block diagram illustrating a master control module in accordance with an exemplary embodiment;
fig. 3 is an electrical schematic diagram illustrating a host module according to an exemplary embodiment.
FIG. 4 is a schematic diagram illustrating a bag-type dust collector purge gas indicator on-line detection system according to an exemplary embodiment;
FIG. 5 is a flow diagram illustrating a method for online detection of a bag-type dust collector purge gas indicator according to an exemplary embodiment;
FIG. 6 is a schematic diagram of Lucy _ Richardson image restoration for a grain image according to the present invention;
FIG. 7 is a schematic diagram of one embodiment of the present invention for performing non-local mean filtering on a grain image;
FIG. 8 is a schematic diagram of one embodiment of the present invention for performing K-means clustering image segmentation on a grain image;
FIG. 9 is a schematic diagram of one embodiment of the present invention for performing image overlay processing on a grain image;
FIG. 10 is a schematic illustration of one type of image reflection point processing performed on a particle image according to the present invention;
FIG. 11 is a flow chart of a specific detection algorithm of the present invention.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
in order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
Fig. 1 is a schematic diagram illustrating a device for online detection of a purge gas indicator of a bag-type dust collector according to an exemplary embodiment. As shown in fig. 1, the gas index online detection device for a bag-type dust collector provided by the embodiment of the invention comprises a laser emission device 1 and a camera module 2, wherein the camera module 2 comprises a camera 201 and a main control module 202, and the laser emission device 1 is used for irradiating a laser beam on an air outlet of the bag-type dust collector; the camera 201 collects images of purified gas in the laser beam irradiated air outlet; the main control module 202 sends the acquired purge gas image to the upper computer so that the upper computer can perform image processing to obtain the characteristic parameters of the purge gas.
As a possible implementation manner of this embodiment, the laser emitting device 1 is provided with a light source focus 101, a convex lens 102 and a filter 103 in sequence from back to front.
As a possible implementation manner of this embodiment, the online detection device further includes a lens protection plate 203, a light shielding plate 104, and a driving motor 204, where the lens protection plate 203 is disposed in front of the camera 201, the light shielding plate 104 is disposed at a laser beam irradiation through hole of the laser emission device 1, a control end of the driving motor 204 is electrically connected to the main control module 202, and output shafts of the driving motor are used for respectively driving the lens protection plate 203 and the light shielding plate 104 to move.
The light source at the focus can change the scattered light into parallel light through the convex lens, partial reflecting points and scattering points can be removed through the filter, and the light shading plate can protect the lens and prevent pollution. The working principle is as follows: the device receives the command of an upper computer, the lens protection plate is opened under the action of the stepping motor, and the camera shoots to obtain a purified gas image which is discharged and transmits the purified gas image to the upper computer (a computer optimization energy-saving control system).
As a possible implementation manner of this embodiment, as shown in fig. 2, the main control module includes a core control chip STM32F407, and an input circuit, an RS485 module, a camera chip, an output circuit, and an SD card respectively connected thereto, where the RS485 module is connected to an upper computer.
As a possible implementation manner of this embodiment, the main control module further includes an expansion input circuit and an expansion output circuit that are respectively connected to the core control chip STM32F 407.
The core control chip adopts STM32F407, and the power supply adopts 5V and 12V; the 2-path motor controls 2 baffles (a lens protection plate and a light screen) to respectively protect the laser emitting device and the camera; in order to prevent the memory of the processor from being insufficient, the data storage SD card is expanded; the I/O circuit is used for receiving other auxiliary signals and simultaneously expanding 2 paths of input and 4 paths of output; the module adopts RS485 to communicate with an upper computer (a computer optimization energy-saving control system).
As shown in fig. 3, the circuit design of the main control module combines the advantages of the analog circuit and the high-performance digital signal controller on the basis of fully considering the bag dust removal and the real-time particle monitoring, and designs a low-cost, intelligent and easily-popularized circuit.
The embodiment is irradiated by the laser beam and collects the particle image of the gas outlet of the bag-type dust collector through the camera module, so that the real-time monitoring of the purified gas at the gas outlet of the bag-type dust collector is realized, the characteristic parameters of the purified gas can be timely obtained, the bag-type dust collector is optimized and energy-saving in time, and the characteristic that the real-time monitoring is not delayed can be suitable for the great popularization in the market.
FIG. 4 is a schematic diagram illustrating a bag-type dust collector purge gas indicator on-line detection system according to an exemplary embodiment. As shown in fig. 4, the system for online detection of gas index in bag-type dust remover provided by this embodiment includes a process chamber 3, a computer-optimized energy-saving control system 4, a bag-type dust remover 5, an air compressor 6, an induced draft fan 7, a compressed air pressure monitoring module 8, an outdoor air humidity monitoring module 9, a dust temperature monitoring module 10, a dust inlet pressure monitoring point module 11, an induced draft fan rotation speed monitoring module 12, a dust filtration outlet pressure monitoring module 13, a production process parameter monitoring module 14, an outdoor rainfall monitoring module 15, a remote GPRS module 16 and an RS485 communication module 17, and further includes an online detection device for gas index in bag-type dust remover, which is composed of a laser emitting device 1 and a camera module 2. Air to be dedusted is stored in the process chamber 3, reaches the bag-type dust remover 5 through a pipeline, is dedusted under the action of an air compressor 6 and an induced draft fan 7, the temperature, humidity, pressure and rotating speed points at each position are detected by a compressed air pressure monitoring module 8, an outdoor air humidity monitoring module 9, a dust temperature monitoring module 10, a dust inlet pressure monitoring point module 11, a draught fan rotating speed monitoring module 12, a dust filtering outlet pressure monitoring module 13, a production process parameter monitoring module 14 and an outdoor rainfall monitoring module 15, and the obtained data are returned to a computer optimization control system 4, and the laser emission device 1 irradiates laser beams, particle images of gas purified by the bag-type dust remover are collected by the camera module 2 and transmitted to the computer optimization energy-saving control system 4, and characteristic parameters of particle size distribution and particle concentration are monitored in real time through an image processing algorithm.
The process chamber stores air to be dedusted, the upper computer transmits signals after the air to be dedusted is electrified, dust gas reaches the bag-type dust remover through a pipeline, dedusting is carried out under the action of an air compressor and a draught fan, the laser device and the protective baffle are opened, the camera receives the signals to carry out image acquisition, the gas image after dust filtration is transmitted to the upper computer, and characteristic parameters such as particle size distribution, particle concentration and the like at the moment are obtained through algorithm processing. The embodiment can carry out closed-loop control, and realizes the integration of bag-type dust removal and particle characteristic real-time monitoring by combining a peripheral analog electronic circuit. Compared with the existing purifier on the market, the cost of the system is reduced to the greatest extent; the whole process design is suitable for various devices such as large, medium and small devices; the real-time monitoring characteristic is not delayed, so that the method can be suitable for great popularization in the market; the advantages of optimizing energy conservation play an important role in environmental protection.
The embodiment utilizes laser to emit parallel light, and emitted light and refracted light are generated through a purified gas outlet pipeline of a bag-type dust collector to form a visible light image, so that the shooting device is invented based on the principle; and finally, acquiring characteristic parameters of purified gas, such as particle size distribution, particle concentration and the like, as a dust removal control index basis by adopting a series of image processing algorithms, and realizing dust removal optimization control. The system has the following characteristics: the cost is extremely low, the installation and the use in large, medium and small bag-type dust collectors can be realized, the dust collector is widely used in the market, and the dust collector plays an important role in the haze treatment of the nature.
Fig. 5 is a flowchart illustrating an on-line detection method for a purge gas indicator of a bag-type dust collector according to an exemplary embodiment. As shown in fig. 5, the method for online detection of gas indexes in a bag-type dust collector provided by this embodiment includes the following steps:
collecting a particle image of purified gas of a bag-type dust collector;
image restoration: processing the particle image by adopting a Lucy _ Richardson iterative nonlinear restoration algorithm, and converting the particle image from a dynamic state to a static state;
image filtering: filtering the particle image by adopting a non-local mean filtering algorithm to remove noise;
image segmentation: carrying out binarization segmentation on the particle image by adopting a K mean value clustering algorithm;
image overlapping processing: separating the overlapped particles from the particle image by adopting an overlapped particle automatic separation algorithm which combines template detection and curvature and constructs a separation line;
image reflection point processing: judging the range of the metal reflecting points by utilizing the function relation of the front end and the rear end of the particle image, and performing dust removal treatment by using a hole filling algorithm;
measurement and statistics of particle characteristic parameters: and (4) counting the equivalent diameter of the measured particles in the particle image, and obtaining the particle size distribution and the particle concentration of the particle image.
As a possible implementation manner of this embodiment, the process of image segmentation includes the following steps:
calculating the distance between the sample and each mean vector;
determining cluster marks according to the nearest mean vector;
dividing the samples into corresponding clusters;
a new mean vector is calculated.
As a possible implementation manner of this embodiment, the process of the image overlapping processing includes the following steps:
acquiring an overlapping area: converting a binary image into a gray image by adopting an urban distance conversion method, calculating the distance between each target pixel and the nearest background pixel, extracting an edge curve by calculating a distance conversion value and adopting a canny operator, smoothing the image by using a one-dimensional Gaussian function, calculating the amplitude and direction of a gradient, detecting and connecting the edge by a dual-threshold method, and performing tracking, conversion and stripping layer by layer from outside to inside in the iterative process of forming a final edge curve until the area is empty so as to obtain an overlapped area;
and (3) extracting a segmentation point: moving a circular template with a proper radius along the boundary line of the overlapped particle area to obtain the perimeter C of the intersection area of the circle and the particles; fitting the perimeter value C of the intersection region at each position of the boundary into a curve y; taking y as an objective function to solve the curvature of each point;
constructing a separation line: and drawing a separation line by adopting a bresenham algorithm, obtaining a virtual network by establishing a group of pixel centers passing through each row and each column, calculating the intersection points of the straight line and each vertical grid line according to the sequence of the straight line from the starting point to the end point, and calculating the distance difference between the candidate point and the real point for discrimination so as to determine the position of the next pixel point.
As a possible implementation manner of this embodiment, the process of processing the image reflection points includes the following steps:
dividing the image into 10 x 10 cells;
setting a threshold value, and judging and marking the front end and the rear end of the light reflection point according to the threshold value;
the connected region, i.e. the retro-reflective dot area, is filled with background pixels.
As a possible implementation manner of this embodiment, the process of measuring and counting the particle characteristic parameters includes the following steps:
calculating equivalent particle size: selecting an area diameter as an equivalent particle diameter;
counting the particle size distribution: selecting a plurality of representative particle sizes from small to large to form three particle size intervals of large, medium and small, counting all particles from small to a certain representative particle size, and representing frequency distribution by using accumulated number;
calculating the particle concentration: the equivalent circle volume is selected to characterize the particle volume, and the mass and concentration are calculated from the volume.
The invention utilizes laser to emit parallel light, and generates emitted light and refracted light through a purified gas outlet pipeline of a bag-type dust remover so as to form a visible light image, and a shooting device is invented based on the principle; by adopting a series of image processing algorithms, finally acquiring characteristic parameters such as particle size distribution, particle concentration and the like of purified gas as a dust removal control index basis, not only realizing dust removal optimization control, but also integrating cloth bag dust removal and particle characteristic real-time monitoring; the whole process design is suitable for various devices such as large, medium and small devices; the real-time monitoring characteristic is not delayed, so that the method can be suitable for great popularization in the market; the advantages of optimizing energy conservation play an important role in environmental protection.
The image processing algorithm of the present invention is described in detail below with reference to fig. 6-11.
1. Image restoration-Lucy _ Richardson iteration nonlinear restoration algorithm
When the laser emitting device irradiates under the state of dust flying, relative motion is easily formed between particles and camera equipment in the whole imaging process, and the resolution and the contrast of an image are reduced under the condition, so that the image quality needs to be improved.
Aiming at the characteristics of the content transmitted by the system, the obtained dust image needs to be converted from a dynamic state into a static state, so a Lucy _ Richardson iterative nonlinear restoration algorithm is adopted, and the optimal estimation criterion is a maximum likelihood criterion, namely, a probability density function needs to be maximized.
The degradation model of the image is:
wherein f is the original image, g is the image with noise, h is the point spread function of the system, and n is the corruption noise.
The iteration L _ R expression is:
wherein
Is the estimate of f after k iterations, is the correlation operator, ψ (…) is the L _ R function.
2. Image filtering-non-local mean:
in the process that the dust image is restored through the image and is transmitted to the upper computer, although the laser irradiation technology can avoid the influence of uneven illumination, through a series of steps such as compression, transmission, decompression and the like, the SNR of the image is low, and the image quality needs to be improved through filtering.
Aiming at the content transmitted by the system, the contained noise is basically white Gaussian noise and the grain edge is rough, so that the NLM non-local mean filtering is adopted to realize noise filtering and simultaneously protect the target edge information. The basic idea is as follows: the value of the current pixel is obtained by weighted average of all pixel values in the image, and the weight is used for measuring the similarity between pixels and is characterized by Gaussian weighted Euclidean distance.
Let u ═ u (x) | x ∈ I } for the noisy image, I denotes the image domain, and NL [ u ] is the denoised image, where the gray value of each pixel is estimated using the weighted average of all other pixels in the whole image, i.e.:
NL[u](x)＝∑y∈Iω(x,y)u(y) (2.1)
3. image segmentation-K mean value clustering algorithm
After the dust image is filtered, binaryzation segmentation is needed for the steps of segmentation of overlapped particles, reflection point processing, boundary filling and the like. The classical threshold segmentation generally comprises a maximum inter-class variance, an iterative algorithm, a two-dimensional maximum entropy method and the like, however, the particle size difference in the particle image of the system is not obvious, and the optimal threshold selected by the Otus algorithm and the iterative algorithm is easy to have errors; the two-dimensional maximum entropy algorithm adopts an exhaustive algorithm to search a global optimal solution, and has complex calculation and influence on actual popularization.
Aiming at the characteristics of a dust removal system, a clustering algorithm is selected for binarization processing, and the basic idea is as follows: the clustering does not need training samples and belongs to an unsupervised statistical method. The K-means algorithm firstly averages each current class, then reclassifies the pixels according to the newly generated average, and iterates the newly generated class to execute the previous steps, if binarization is to be performed, the cluster is 2. The algorithm flow is as follows:
step 1: calculating the distance between the sample and each mean vector
dji＝||xj-μi||2 (3.1)
Step 2: determining x from the nearest mean vectorjCluster mark of
ρj＝argmini∈{1,2,…,k}dji (3.2)
Step 3: sample xjInto a corresponding cluster
Step 4: calculating a new mean vector
4. Image overlapping processing-automatic overlapped particle separation algorithm combining template detection and curvature and constructing separation line
The shape of the dust particles is not similar to that of cells, the rice grains have clear and regular outlines, the edges of the dust particles are uneven, the connected areas even have no gray level difference, and the overlapping phenomenon is easy to generate.
Common methods for separating overlapping particles are: mathematical morphological operations, watershed algorithms, and the like. However, the erosion-expansion operation in morphology tends to change the original shape of the particles excessively, and the particle size measurement has a large error. The watershed algorithm is easy to form a plurality of false minimum value points, so that the image is excessively segmented, and the particle count value is inaccurate. Therefore, in order to ensure the correctness of subsequent particle analysis, an automatic overlapped particle separation algorithm combining template detection and curvature and constructing a separation line is provided. The algorithm flow is as follows:
step 1: acquiring an overlapping area: and (5) adopting an urban distance transformation method. And converting the binary image into a gray image, calculating the distance between each target pixel and the nearest background pixel, and performing tracking, transformation and stripping layer by layer from outside to inside until the region is empty, thereby obtaining an overlapping region.
a. Calculating a distance transform value
wi,j(t+1)＝wi,j(0)+minBwx,y(t) (4.1)
Wherein d ((x, y), (i, j)) ═ x-i | + | y-j |, B { (x, y): d ((x, y), (i, j)) ≦ 1}
b. Extracting edge curve by canny operator, and smoothing image by one-dimensional Gaussian function
c. Calculating the magnitude and direction of the gradient
d. The dual threshold method detects and connects edges to form the final edge curve.
Step 2: and (3) extracting a segmentation point:
a. moving a circular template with a proper radius along the boundary line of the overlapped particle area to obtain the perimeter C of the intersection area of the circle and the particles;
b. fitting the perimeter value C of the intersection region at each position of the boundary into a curve y;
c. calculating curvature of each point by taking y as objective function
The lifting turning point is a dividing point;
step 3: constructing a separation line: the method adopts a bresenham algorithm to draw a separation line, and has the basic idea that a group of virtual networks passing through the centers of pixels in each row and each column is established, the intersection points of straight lines and each vertical grid line are calculated according to the sequence from a starting point to an end point of the straight lines, and the distance difference between a candidate point and a real point is calculated for discrimination, so that the position of the next pixel point is determined.
The error is used as the discrimination variable when the delta t is 2 delta y-delta x
When Δ t ≧ 0
When Δ t is reached<At 0 time
5. Image reflection point processing, namely judging metal reflection point range by utilizing front-end and back-end function relation and performing hole filling algorithm
When dust removal treatment is carried out, metal small chips may be contained in dust particle groups, the phenomenon of light reflection is easily caused during laser shooting, the problem of light reflection of metal is not solved, and an algorithm for judging the range of metal light reflection points and filling holes by utilizing a front-end function relation and a rear-end function relation is provided, wherein the algorithm flow is as follows:
step 1: dividing the image into 10 x 10 cells;
step 2: calculating the average value of the gray levels of all the areas, and taking the maximum value as the upper limit H of the brightness threshold; if the gray value of a certain pixel point is larger than or equal to H, the pixel point is marked as the front end F of the reflection point;
step 3: calculating the average value of the gray levels of all the areas, and taking the minimum value as the lower limit L of the brightness threshold; carrying out 8-neighborhood communication detection on the front end F of the reflecting point, and if the gray value of the front end F of the reflecting point is in a linear decreasing state on a certain path and is less than or equal to L at a certain position, marking the position as the rear end E of the reflecting point;
step 4: filling the connected region of E → F, namely filling the range of the reflecting points, with background pixels;
6. measurement and statistics of particle characteristic parameters
The particle size of a particle is defined as the dimension of the space occupied by the particle, and the characterization forms are generally three types: geometric equivalent diameter, physical equivalent diameter, and statistical diameter. For particle populations, statistical diameters are used in order to allow the measurement data to reflect the size and distribution of the particle projections.
Since the particles of the system are irregular, the equivalent particle size is needed, that is, when a certain physical property or physical behavior of the measured particle is most similar to a homogeneous sphere with a certain diameter, the diameter of the sphere is taken as the equivalent diameter of the measured particle. The specific calculation flow is as follows:
step 1: calculating equivalent particle size:
the area diameter is selected as the equivalent particle diameter, i.e.
Wherein S is the particle area and is characterized by the contained pixel number;
step 2: particle size distribution:
selecting a plurality of representative particle sizes in the order from small to large to form three particle size intervals of large, medium and small, counting all particles between small and certain representative particle size, and representing frequency distribution f by accumulated number1，f2，f3，
Wherein
Step 3: calculating the particle concentration: the equivalent circle volume is selected to characterize the particle volume, and the mass and concentration are calculated from the volume.
a. Calculating equivalent circle volume:
wherein r is the area diameter determined in (1)
b. Calculating the mass:
m＝ρv (6.4)
rho is the density of the particles and is determined according to actual conditions;
c. and (3) calculating the concentration:
the foregoing is only a preferred embodiment of the present invention, and it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements are also considered to be within the scope of the present invention.
Claims (9)
1. An online detection device for gas indexes in a bag-type dust remover is characterized by comprising a laser emitting device and a camera module, wherein the camera module comprises a camera and a main control module, and the laser emitting device is used for irradiating a laser beam on a gas outlet of the bag-type dust remover; the camera collects images of purified gas in the gas outlet irradiated by the laser beam; the main control module sends the acquired purified gas image to an upper computer so that the upper computer can perform image processing to obtain characteristic parameters of the purified gas;
the process of the upper computer for carrying out image processing to obtain the characteristic parameters of the purified gas comprises the following steps: processing the particle image of the purified gas by adopting a Lucy _ Richardson iterative nonlinear restoration algorithm, and converting the particle image from a dynamic state to a static state; filtering the particle image by adopting a non-local mean filtering algorithm to remove noise; carrying out binarization segmentation on the particle image by adopting a K mean value clustering algorithm; separating the overlapped particles from the particle image by adopting an overlapped particle automatic separation algorithm which combines template detection and curvature and constructs a separation line; judging the range of the metal reflecting points by utilizing the function relation of the front end and the rear end of the particle image, and performing dust removal treatment by using a hole filling algorithm; and (4) counting the equivalent diameter of the measured particles in the particle image, and obtaining the particle size distribution and the particle concentration of the particle image.
2. The on-line detection device for the gas index of the bag-type dust collector as claimed in claim 1, wherein a light source focus, a convex lens and a filter are sequentially arranged in the laser emission device from back to front.
3. The on-line detection device for the purified gas index of the bag-type dust collector as claimed in claim 2, further comprising a lens protection plate, a light shielding plate and a driving motor, wherein the lens protection plate is arranged in front of the camera, the light shielding plate is arranged at a laser beam irradiation through hole of the laser emission device, a control end of the driving motor is electrically connected with the main control module, and an output shaft of the driving motor is used for respectively driving the lens protection plate and the light shielding plate to move.
4. The online detection device for the gas index of the bag-type dust collector as claimed in any one of claims 1 to 3, wherein the main control module comprises a core control chip STM32F407, and an input circuit, an RS485 module, a camera chip, an output circuit and an SD card which are respectively connected with the core control chip STM 407, and the RS485 module is connected with an upper computer.
5. An on-line detection system for the purified gas index of a bag-type dust remover comprises a process chamber, a computer optimization energy-saving control system, the bag-type dust remover, an air compressor, an induced draft fan, a compressed air pressure monitoring module, an outdoor air humidity monitoring module, a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtration outlet pressure monitoring module, a production process parameter monitoring module, an outdoor rainfall monitoring module, a remote GPRS (general packet radio service) module and an RS485 communication module, and is characterized by further comprising the on-line detection device for the purified gas index of the bag-type dust remover, wherein air to be removed is stored in the process chamber, the air to be removed is removed under the action of the air compressor and the induced draft fan after reaching the bag-type dust remover through a pipeline, and the on-line detection system is used for removing dust under the action of the air compressor and the induced draft fan through the compressed air pressure monitoring module, the outdoor air humidity monitoring module, the induced draft fan rotating speed monitoring module and the compressed air humidity monitoring module, The system comprises a dust temperature monitoring module, a dust inlet pressure monitoring point module, an induced draft fan rotating speed monitoring module, a dust filtration outlet pressure monitoring module, a production process parameter monitoring module and an outdoor rainfall monitoring module, wherein the temperature and humidity, the pressure points and the rotating speed points at all positions are detected by the dust temperature monitoring module, the outdoor rainfall monitoring module to obtain data, the data are returned to a computer optimization control system, particle images which are irradiated by laser beams through a laser emitting device and collected to be purified gas through a camera module are transmitted to the computer optimization energy-saving control system, and characteristic parameters of particle size distribution and particle concentration are monitored in real time through an image processing algorithm.
6. The method for online detection by using the system for online detection of the gas index of the bag-type dust collector in claim 5 is characterized by comprising the following steps:
collecting a particle image of purified gas of a bag-type dust collector;
image restoration: processing the particle image by adopting a Lucy _ Richardson iterative nonlinear restoration algorithm, and converting the particle image from a dynamic state to a static state;
image filtering: filtering the particle image by adopting a non-local mean filtering algorithm to remove noise;
image segmentation: carrying out binarization segmentation on the particle image by adopting a K mean value clustering algorithm;
image overlapping processing: separating the overlapped particles from the particle image by adopting an overlapped particle automatic separation algorithm which combines template detection and curvature and constructs a separation line;
image reflection point processing: judging the range of the metal reflecting points by utilizing the function relation of the front end and the rear end of the particle image, and performing dust removal treatment by using a hole filling algorithm;
measurement and statistics of particle characteristic parameters: counting the equivalent diameter of the measured particles in the particle image to obtain the particle size distribution and the particle concentration of the particle image;
the image overlapping processing process comprises the following steps:
acquiring an overlapping area: converting a binary image into a gray image by adopting an urban distance conversion method, calculating the distance between each target pixel and the nearest background pixel, extracting an edge curve by calculating a distance conversion value and adopting a canny operator, smoothing the image by using a one-dimensional Gaussian function, calculating the amplitude and direction of a gradient, detecting and connecting the edge by a dual-threshold method, and performing tracking, conversion and stripping layer by layer from outside to inside in the iterative process of forming a final edge curve until the area is empty so as to obtain an overlapped area;
and (3) extracting a segmentation point: moving a circular template with a proper radius along the boundary line of the overlapped particle area to obtain the perimeter C of the intersection area of the circle and the particles; fitting the perimeter value C of the intersection region at each position of the boundary into a curve y; taking y as an objective function to solve the curvature of each point;
constructing a separation line: and drawing a separation line by adopting a bresenham algorithm, obtaining a virtual network by establishing a group of pixel centers passing through each row and each column, calculating the intersection points of the straight line and each vertical grid line according to the sequence of the straight line from the starting point to the end point, and calculating the distance difference between the candidate point and the real point for discrimination so as to determine the position of the next pixel point.
7. The method of claim 6, wherein the image segmentation process comprises the steps of:
calculating the distance between the sample and each mean vector;
determining cluster marks according to the nearest mean vector;
dividing the samples into corresponding clusters;
a new mean vector is calculated.
8. The method of claim 6, wherein the image reflection point processing comprises the steps of:
dividing the image into 10 x 10 cells;
setting a threshold value, and judging and marking the front end and the rear end of the light reflection point according to the threshold value;
the connected region, i.e. the retro-reflective dot area, is filled with background pixels.
9. The method of claim 6, wherein the measuring and counting of the particle characteristic parameters comprises the steps of:
calculating equivalent particle size: selecting an area diameter as an equivalent particle diameter;
counting the particle size distribution: selecting a plurality of representative particle sizes from small to large to form three particle size intervals of large, medium and small, counting all particles from small to a certain representative particle size, and representing frequency distribution by using accumulated number;
calculating the particle concentration: and calculating equivalent circle volume, selecting the equivalent circle volume to represent the particle volume, and calculating mass and concentration according to the volume.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322046.8A CN109876569B (en) | 2019-04-19 | 2019-04-19 | Online detection device, system and method for purified gas index of bag-type dust remover |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322046.8A CN109876569B (en) | 2019-04-19 | 2019-04-19 | Online detection device, system and method for purified gas index of bag-type dust remover |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109876569A CN109876569A (en) | 2019-06-14 |
| CN109876569B true CN109876569B (en) | 2021-07-23 |
Family
ID=66938051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910322046.8A Expired - Fee Related CN109876569B (en) | 2019-04-19 | 2019-04-19 | Online detection device, system and method for purified gas index of bag-type dust remover |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109876569B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110812964B (en) * | 2019-10-22 | 2022-08-12 | 南京科赫科技有限公司 | Intelligent alarming bag type dust collector |
| CN112284988A (en) * | 2020-10-15 | 2021-01-29 | 东北大学 | Device and method for measuring equivalent diameter of particle group |
| CN112871940B (en) * | 2020-12-22 | 2022-07-26 | 柏美迪康环境科技（上海）股份有限公司 | Paroxysmal non-fixed point source dust control effect monitoring system and method |
| CN112807890A (en) * | 2020-12-30 | 2021-05-18 | 天津东盛源管理咨询有限公司 | Bag-type dust collector control system and method |
| CN117543360A (en) * | 2023-11-14 | 2024-02-09 | 湖北华亿电气集团有限公司 | Outdoor looped netowrk case with dehumidification heat dissipation function |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100424465C (en) * | 2006-06-23 | 2008-10-08 | 北京神网创新科技有限公司 | Laser detection apparatus and method for in-furnace information |
| CN101509931B (en) * | 2009-03-16 | 2011-04-27 | 浙江大学 | Method and apparatus for on-line measuring two-dimension speed and particle size distribution of granules in pipe |
| CN103521008A (en) * | 2013-11-06 | 2014-01-22 | 山东开泰工业科技有限公司 | Optimization energy-saving dedusting control method and system of cloth bag pulse dust collector |
| CN104156702B (en) * | 2014-07-31 | 2017-12-08 | 郑州航空工业管理学院 | Mix the automatic classifying identification method of beans |
| CN105891074B (en) * | 2016-04-12 | 2018-11-23 | 东南大学 | A kind of dust concentration image collecting device and acquisition method |
| CN106203456B (en) * | 2016-07-20 | 2018-01-02 | 西安科技大学 | Coal dust Algorithm for Overlapping Granule separation method based on improved differential evolution particle cluster algorithm |
| CN108954721A (en) * | 2018-08-16 | 2018-12-07 | 中山路得斯空调有限公司 | Air purification system and control method thereof |
-
2019
- 2019-04-19 CN CN201910322046.8A patent/CN109876569B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109876569A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109876569B (en) | Online detection device, system and method for purified gas index of bag-type dust remover | |
| Zhao et al. | Cloud shape classification system based on multi-channel cnn and improved fdm | |
| CN102998316B (en) | Transparent liquid impurity detection system and detection method thereof | |
| CN104424466A (en) | Object detection method, object detection device and image pickup device | |
| CN107480585A (en) | Object detection method based on DPM algorithms | |
| CN111080691A (en) | Infrared hot spot detection method and device for photovoltaic module | |
| CN109101976B (en) | Method for detecting surface defects of arc-extinguishing grid plate | |
| CN109886932A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on SVM | |
| CN109603340A (en) | A kind of intelligent electric automation dedusting control system and method | |
| CN115908354A (en) | Photovoltaic panel defect detection method based on double-scale strategy and improved YOLOV5 network | |
| CN116052105A (en) | Pavement crack identification classification and area calculation method, system, equipment and terminal | |
| CN115294377A (en) | System and method for identifying road cracks | |
| Wang et al. | Automated defect and contaminant inspection of HVAC duct | |
| CN114782442A (en) | Photovoltaic cell panel intelligent inspection method and system based on artificial intelligence | |
| CN112883969B (en) | Rainfall intensity detection method based on convolutional neural network | |
| Wang et al. | Effective segmentation approach for solar photovoltaic panels in uneven illuminated color infrared images | |
| CN114170487A (en) | Vision-based water surface oil stain detection method | |
| CN114120218A (en) | River course floater monitoring method based on edge calculation | |
| CN111754497B (en) | Industrial defect detection method and system based on geometric algebra | |
| CN113469097A (en) | SSD (solid State disk) network-based real-time detection method for water surface floating object multiple cameras | |
| CN112396580A (en) | Circular part defect detection method | |
| Gao et al. | Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection | |
| CN107992863B (en) | Multi-resolution grain insect variety visual identification method | |
| CN110765900A (en) | DSSD-based automatic illegal building detection method and system | |
| CN109919863A (en) | A kind of full-automatic bacterial colony counting instrument, system and its method for counting colonies |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210723 |