CN109603340A - A kind of intelligent electric automation dedusting control system and method - Google Patents
A kind of intelligent electric automation dedusting control system and method Download PDFInfo
- Publication number
- CN109603340A CN109603340A CN201811509650.3A CN201811509650A CN109603340A CN 109603340 A CN109603340 A CN 109603340A CN 201811509650 A CN201811509650 A CN 201811509650A CN 109603340 A CN109603340 A CN 109603340A
- Authority
- CN
- China
- Prior art keywords
- module
- fault
- data
- circuit
- smoke
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000000428 dust Substances 0.000 claims abstract description 80
- 238000001514 detection method Methods 0.000 claims abstract description 49
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 239000000779 smoke Substances 0.000 claims description 80
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 15
- 238000013500 data storage Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 230000005284 excitation Effects 0.000 claims description 6
- 230000033228 biological regulation Effects 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 4
- 238000012887 quadratic function Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 239000012634 fragment Substances 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000003750 conditioning effect Effects 0.000 abstract description 2
- 239000003500 flue dust Substances 0.000 abstract 3
- 238000003384 imaging method Methods 0.000 abstract 1
- 239000002956 ash Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000006477 desulfuration reaction Methods 0.000 description 1
- 230000023556 desulfurization Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000010881 fly ash Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002120 nanofilm Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D46/00—Filters or filtering processes specially modified for separating dispersed particles from gases or vapours
- B01D46/10—Particle separators, e.g. dust precipitators, using filter plates, sheets or pads having plane surfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D46/00—Filters or filtering processes specially modified for separating dispersed particles from gases or vapours
- B01D46/42—Auxiliary equipment or operation thereof
- B01D46/44—Auxiliary equipment or operation thereof controlling filtration
- B01D46/442—Auxiliary equipment or operation thereof controlling filtration by measuring the concentration of particles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D46/00—Filters or filtering processes specially modified for separating dispersed particles from gases or vapours
- B01D46/42—Auxiliary equipment or operation thereof
- B01D46/44—Auxiliary equipment or operation thereof controlling filtration
- B01D46/46—Auxiliary equipment or operation thereof controlling filtration automatic
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
Landscapes
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention belongs to dedusting technology fields, a kind of intelligent electric automation dedusting control system and method are disclosed, the intelligent electric automation dedusting control system includes: power supply module, flue dust detection module, parameter input module, main control module, power conditioning module, exhausting module, filtering module, fault detection module, data memory module, display module.The present invention utilizes an imaging sensor by flue dust detection module, such as the face CCD or CMOS battle array or line scan digital camera and laser beam, the discharge dust concentration from very low concentrations 0.01mg/kg to high concentration 50mg/kg or more can be measured, the flue dust on-line monitoring of minimum discharge requirement is met；Simultaneously, by fault detection module by fault data fragment map be image data, the problem of by fault identification is changed into the problem of handling data, reduce the risk for directly being pre-processed to data and information being caused to lose, the fault recognition rate of fan yaw system is improved, while also very vivid being visualized.
Description
Technical Field
The invention belongs to the technical field of dust removal, and particularly relates to an intelligent electric automatic dust removal control system and method.
Background
The dust removing device is commonly called a dust remover and is a device for removing or reducing the content of fly ash in smoke. The dust removing device can be classified into a biological nano-film dust suppression device, a cloud and mist dust suppression device, a cloth bag dust removing device, a cyclone dust removing device, a wet dust removing device, an electrostatic dust removing device and a desulfurization dust removing device. The method is applied to the industries of chemical industry, petroleum, metallurgy, building, mining, machinery, light spinning and the like. The dust remover consists of an ash bucket, an upper box body, a middle box body, a lower box body and the like, wherein the upper box body, the middle box body and the lower box body are of a chamber-divided structure. When the dust-free dust collection box works, dust-containing gas enters the dust hopper from the air inlet duct, coarse dust particles directly fall into the bottom of the dust hopper, fine dust particles turn upwards along with air flow and enter the middle box body and the lower box body, dust is accumulated on the outer surface of the filter bag, and the filtered gas enters the upper box body to the clean gas collection pipe-air outlet duct and is exhausted to the atmosphere through the air exhaust fan. The ash cleaning process is to cut off the air duct at the clean air outlet of the chamber to make the cloth bag in the state of no air flow passing through (air stopping and ash cleaning in different chambers). Then the pulse valve is opened to carry out pulse injection ash removal by compressed air, the closing time of the stop valve is enough to ensure that dust stripped from the filter bag after injection is settled to the ash bucket, the phenomenon that the dust is attached to the surface of the adjacent filter bag along with airflow after being separated from the surface of the filter bag is avoided, the ash removal of the filter bag is thorough, and the programmable controller carries out full-automatic control on an exhaust valve, the pulse valve, an ash discharge valve and the like. However, in the existing smoke detection method, a smoke containing smoke must be pumped into a measuring device by a pumping sampling system, online measurement cannot be performed, the measuring time is long, a long time is required for obtaining a measuring result, and real-time measurement cannot be realized; meanwhile, the wind power equipment for dust removal is prone to failure, and many problems are encountered during failure analysis, such as large data volume, low algorithm operation efficiency, poor result interpretability and the like.
In summary, the problems of the prior art are as follows:
(1) the existing smoke detection method has the advantages that a smoke containing smoke is sucked into a measuring device by a suction sampling system, online measurement cannot be carried out, the measuring time is long, the time for obtaining a measuring result is long, and real-time measurement cannot be realized; meanwhile, the wind power equipment for dust removal is prone to failure, and many problems are encountered during failure analysis, such as large data volume, low algorithm operation efficiency, poor result interpretability and the like.
(2) In the prior art, during the production process of processing the dust removal parameters in the processing parameter input module by the main control module, the traditional algorithm is adopted for fusing the data of the parameters, so that the real dust removal condition cannot be reflected, the data processing precision is reduced, and the control error is increased.
(3) In the prior art, in the process that the power of the exhaust fan is correspondingly adjusted by the power adjusting module according to the smoke concentration through the power adjusting circuit, when a fault occurs, the positioning and parameter interval identification of a fault element cannot be realized.
(4) In the prior art, a data storage module stores collected smoke data and fault information through a storage, unbalanced data sets in the collected smoke data and fault information data need to be classified, the storage adopts the existing algorithm, overall change of distribution of the unbalanced data sets and fuzzy positive and negative boundaries are easily caused, the data classification result is reduced, better storage of the smoke data and the fault information data by the storage is not convenient, and errors are easily caused.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent electric automatic dust removal control system and method.
The invention is realized in such a way that an intelligent electric automatic dust removal control method comprises the following steps:
firstly, supplying power to an intelligent electric automatic dust removal device through a power supply module; detecting smoke concentration data by a smoke detection module through a laser detector; inputting a dedusting parameter configuration operation by using an operation key through a parameter input module;
secondly, the main control module dispatches a power adjusting module through a PLC singlechip, and correspondingly adjusts the power of the exhaust fan according to the smoke concentration by using a power adjusting circuit;
thirdly, performing suction operation on the smoke dust by using an exhaust fan through an exhaust module; the absorbed smoke dust is filtered by the filter module through the filter screen;
detecting a fault signal of the fan by using a circuit signal detector through a fault detection module;
step five, storing the collected smoke data and fault information by a data storage module through a memory; and the display module is used for displaying the collected smoke data information and the fault information by using the display.
Further, the main control module processes the dust removal parameters in the processing parameter input module, performs data fusion on the parameters, and adopts a self-adaptive weighted data fusion algorithm, specifically comprising: different sets of measurement data have different weights, and under the optimal condition of minimum total mean square error, the corresponding weights of the measurement data are searched in a self-adaptive mode according to the sets of measurement data, so that the fused values are optimal;
after the weighting factor is introduced, the data fusion value of the intelligent detection system is as follows:
wherein,
the total mean square error is:
wherein sigma2Is each weighting factor WiA multivariate quadratic function of (a);
according to the theory of extreme value solving by multivariate function, the weight factor is solvedIs when is σ2A minimum value of
After the weighting factors are introduced according to the self-adaptive weighting model, the system data fusion value is
Further, in the process that the power adjusting module correspondingly adjusts the power of the exhaust fan according to the smoke concentration through the power adjusting circuit, the power adjusting circuit adopts a method for diagnosing the fault of the analog circuit functional module, and the method comprises the following steps:
firstly, dividing a circuit to be tested into modules according to different functions according to basic information of the circuit before testing, and then establishing a first-stage fault dictionary of each functional module of the circuit;
the second step is that: before testing, applying normal excitation according to each divided functional module, dividing the element to be tested into 5 intervals through 6 points and 5 sections, obtaining discrete working point tracks of the corresponding intervals through iteration simulation before testing, storing the discrete working point tracks in one-to-one correspondence, and establishing a second-level fault dictionary;
thirdly, after the measurement, applying the same excitation to the circuit during the actual diagnosis to obtain the related functional indexes of the circuit and the actually measured node voltage working points;
fourthly, after the detection, firstly carrying out fault detection; comparing first-level fault dictionaries of all functional modules of the circuit, and detecting whether the circuit functional indexes are consistent with the functional dictionaries; if the circuit function index is consistent with the function dictionary, judging that the circuit is normal, otherwise, judging that the circuit has a fault;
fifthly, after the detection and the fault detection in the fourth step, according to the circuit node voltage obtained in the third step, calculating the minimum distance from the actually-measured voltage working point to a discrete working point track dictionary corresponding to each element in the second-stage fault dictionary of the functional module, and judging the fault element according to the minimum distance to realize fault positioning;
and sixthly, calculating the interval of the corresponding discrete working point with the minimum distance from the working point of the measured voltage according to the positioned fault element, and identifying the parameter interval of the fault element.
Another object of the present invention is to provide an intelligent electric automatic dust removal control system for implementing the intelligent electric automatic dust removal control method, the intelligent electric automatic dust removal control system comprising:
the power supply module is connected with the main control module and used for supplying power to the intelligent electric automatic dust removal device;
the smoke detection module is connected with the main control module and used for detecting smoke concentration data through a laser detector;
the parameter input module is connected with the main control module and used for inputting dust removal parameter configuration operation through an operation key;
the main control module is connected with the power supply module, the smoke detection module, the parameter input module, the power regulation module, the air draft module, the filtering module, the fault detection module, the data storage module and the display module and is used for controlling each module to normally work through the PLC single chip microcomputer;
the power adjusting module is connected with the main control module and is used for correspondingly adjusting the power of the exhaust fan according to the smoke concentration through the power adjusting circuit;
the air exhaust module is connected with the main control module and is used for performing suction operation on the smoke dust through an exhaust fan;
the filter module is connected with the main control module and is used for filtering the absorbed smoke dust through the filter screen;
the fault detection module is connected with the main control module and used for detecting a fault signal of the fan through the circuit signal detector;
the data storage module is connected with the main control module and used for storing the collected smoke data and the fault information through the memory;
and the display module is connected with the main control module and used for displaying the collected smoke data information and the fault information through the display.
The invention also aims to provide a dust remover applying the intelligent electric automatic dust removal control method.
The invention has the advantages and positive effects that: the invention can measure the concentration of the discharged smoke dust from very low concentration of 0.01mg/kg to high concentration of more than 50mg/kg by using an image sensor, such as a CCD or CMOS area array or linear array digital camera and a laser beam, through the smoke dust detection module, thereby meeting the on-line monitoring of the smoke dust with ultra-low emission requirement; meanwhile, the fault data are analyzed from the angle of image recognition through the fault detection module, the fault data fragments are mapped into the image data, the problem of data processing is changed into the problem of fault recognition, the risk that information is lost due to the fact that data are directly preprocessed is reduced, the fault recognition rate of the fan yaw system is improved, and meanwhile visual display is performed vividly and vividly.
In the invention, the main control module carries out data fusion on the parameters in the production process of processing the dust removal parameters in the processing parameter input module, and a self-adaptive weighted data fusion algorithm is adopted, so that the real dust removal situation is reflected, the data processing precision is improved, and the control error is reduced.
In the process that the power of the exhaust fan is correspondingly adjusted by the power adjusting module according to the smoke concentration by the power adjusting circuit, the power adjusting circuit adopts a method of fault diagnosis of the analog circuit functional module in order to realize the positioning of fault elements and the identification of parameter intervals.
In the invention, in the process that the data storage module stores the collected smoke data and fault information through the memory, the memory needs to classify unbalanced data sets in the collected smoke data and fault information data, so as to avoid integral change of distribution of the unbalanced data sets and fuzzy positive and negative class boundaries, improve the classification result of the data, facilitate the memory to better store the smoke data and the fault information data and avoid errors, and adopt a random forest algorithm based on a KM-SMOTE algorithm.
Drawings
Fig. 1 is a flow chart of an intelligent electric automatic dust removal control method provided by the implementation of the invention.
FIG. 2 is a schematic structural diagram of an intelligent electric automatic dust removal control system provided by the implementation of the present invention;
in fig. 2: 1. a power supply module; 2. a smoke detection module; 3. a parameter input module; 4. a main control module; 5. a power conditioning module; 6. an air draft module; 7. a filtration module; 8. a fault detection module; 9. a data storage module; 10. and a display module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of the invention is provided in connection with the accompanying drawings and the embodiments.
As shown in fig. 1, the intelligent electric automatic dust removing control method provided by the embodiment of the present invention includes the following steps:
step S101, supplying power to the intelligent electric automatic dust removal device through a power supply module; detecting smoke concentration data by a smoke detection module through a laser detector; inputting a dedusting parameter configuration operation by using an operation key through a parameter input module;
step S102, the main control module dispatches a power adjusting module through a PLC singlechip, and correspondingly adjusts the power of an exhaust fan according to the smoke concentration by using a power adjusting circuit;
step S103, performing suction operation on the smoke dust by using an exhaust fan through an exhaust module; the absorbed smoke dust is filtered by the filter module through the filter screen;
step S104, detecting a fault signal of the fan by using a circuit signal detector through a fault detection module;
step S105, storing the collected smoke data and fault information by a data storage module through a memory; and the display module is used for displaying the collected smoke data information and the fault information by using the display.
As shown in fig. 2, an intelligent electric automatic dust removing control system provided by the embodiment of the present invention includes: the device comprises a power supply module 1, a smoke detection module 2, a parameter input module 3, a main control module 4, a power regulation module 5, an air draft module 6, a filtering module 7, a fault detection module 8, a data storage module 9 and a display module 10.
The power supply module 1 is connected with the main control module 4 and used for supplying power to the intelligent electric automatic dust removal device;
the smoke detection module 2 is connected with the main control module 4 and used for detecting smoke concentration data through a laser detector;
the parameter input module 3 is connected with the main control module 4 and is used for inputting dust removal parameter configuration operation through an operation key;
the main control module 4 is connected with the power supply module 1, the smoke detection module 2, the parameter input module 3, the power regulation module 5, the air draft module 6, the filtering module 7, the fault detection module 8, the data storage module 9 and the display module 10 and is used for controlling each module to normally work through the PLC single chip microcomputer;
the power adjusting module 5 is connected with the main control module 4 and is used for correspondingly adjusting the power of the exhaust fan according to the smoke concentration through a power adjusting circuit;
the air exhaust module 6 is connected with the main control module 4 and is used for performing suction operation on the smoke dust through an exhaust fan;
the filtering module 7 is connected with the main control module 4 and is used for filtering the absorbed smoke dust through a filter screen;
the fault detection module 8 is connected with the main control module 4 and used for detecting a fault signal of the fan through the circuit signal detector;
the data storage module 9 is connected with the main control module 4 and used for storing the collected smoke data and the fault information through a memory;
and the display module 10 is connected with the main control module 4 and is used for displaying the collected smoke data information and the fault information through a display.
In the process of processing the dust removal parameters in the processing parameter input module 3 by the main control module 4, data fusion needs to be performed on the parameters, so that the real dust removal situation is reflected, the precision of data processing is improved, and the control error is reduced, and a self-adaptive weighted data fusion algorithm is adopted, specifically:
different sets of measurement data have different weights, and under the optimal condition of minimum total mean square error, the corresponding weights of the measurement data are searched in a self-adaptive mode according to the sets of measurement data, so that the fused values are optimal;
after the weighting factor is introduced, the data fusion value of the intelligent detection system is as follows:
wherein,
the total mean square error is therefore:
wherein sigma2Is each weighting factor WiA multivariate quadratic function of (a);
according to the theory of extreme value solving by multivariate function, the weight factor can be solvedIs when is σ2A minimum value of
After the weighting factors are introduced according to the adaptive weighting model, the system data fusion value should be:
after the self-adaptive weighted data processing, the subsequent dust removal plan and management can be carried out by taking the data as a reference, and the more the fused data is close to the actual data, the more reasonable the plan can be made, which brings great convenience for the adjustment and optimization of the production process.
In the process that the power adjusting module 5 correspondingly adjusts the power of the exhaust fan according to the smoke concentration by the power adjusting circuit, the power adjusting circuit adopts a method for diagnosing faults of the analog circuit functional module in order to realize the positioning of fault elements and the identification of parameter intervals, and the method comprises the following steps:
firstly, dividing a circuit to be tested into modules according to different functions according to basic information of the circuit before testing, and then establishing a first-stage fault dictionary (actually, a function module dictionary is not a 'fault dictionary', and indexes required to be met when the circuit realizes normal functions) of each function module of the circuit;
the second step is that: before testing, applying normal excitation according to each divided functional module, dividing the element to be tested into 5 intervals through 6 points and 5 sections, obtaining discrete working point tracks of the corresponding intervals through iterative simulation before testing, and storing the discrete working point tracks in one-to-one correspondence, thereby establishing a second-level fault dictionary;
thirdly, after the measurement, applying the same excitation to the circuit during the actual diagnosis to obtain the related functional indexes of the circuit and the actually measured node voltage working points;
fourthly, after the detection, firstly carrying out fault detection; comparing first-level fault dictionaries of all functional modules of the circuit, and detecting whether the circuit functional indexes are consistent with the functional dictionaries; if the circuit function index is consistent with the function dictionary, judging that the circuit is normal, otherwise, judging that the circuit has a fault;
fifthly, after the detection and the fault detection in the fourth step, according to the circuit node voltage obtained in the third step, calculating the minimum distance from the actually-measured voltage working point to a discrete working point track dictionary corresponding to each element in the second-stage fault dictionary of the functional module, and judging the fault element according to the minimum distance to realize fault positioning;
and sixthly, calculating the interval of the corresponding discrete working point with the minimum distance from the working point of the measured voltage according to the positioned fault element, and identifying the parameter interval of the fault element.
In the process that the data storage module 9 stores the collected smoke data and fault information through the memory, the memory needs to classify unbalanced data sets in the collected smoke data and fault information data, so as to avoid integral change of distribution of the unbalanced data sets and fuzzy positive and negative boundary, improve classification results of the data, facilitate the memory to better store the smoke data and the fault information data, and avoid errors, and adopt a random forest algorithm based on a KM-SMOTE algorithm, and the method comprises the following steps:
step one, determining an initial cluster K value, wherein the size of the K value is generally a certain value required to be specified by a program or a value is set by experience, and the K value is simple and effective;
clustering and calculating cluster centers by using a K-means algorithm, selecting a rare data sample, carrying out clustering operation by using the K-means algorithm and recording the cluster centers, wherein the rare data are divided into K clusters, and the cluster center of each cluster is { c1，c2，…，ck}；
Step three, sample interpolation is carried out, in order to effectively reduce the bias of data and change the balance of the data, interpolation is carried out by utilizing the original sample points in the cluster center instead of the rare data set, namely according to a new algorithm KM-SMOTE algorithm provided in the text, a new interpolation formula is set as follows:
Xnew＝ci+rand(0，1)*(X-ci)，i＝1，2，…，k，；
X∈ci；
wherein XnewIs the new interpolated sample; c. CiForming a cluster core; x is ciOriginal sample data in cluster center clusters are obtained; rand (0, 1) represents some random number between 0 and 1;
processing the interpolated data set, interpolating samples with equal probability of each cluster center, wherein the samples in the rare data set may be more than the samples in the non-rare data set, and performing sample deletion operation at the moment, wherein the data deletion method is to delete data which may generate overfitting in each cluster until the data set balance is achieved;
and step five, classifying by using a random forest, and after processing the balanced data set, training and classifying by using the balanced data set. And recording and analyzing the classification result to obtain the experimental effect of the latest algorithm.
The detection method of the smoke detection module 2 provided by the invention comprises the following steps:
(1) laser beams emitted by the laser light source are incident to the measuring area from one end of the measuring area, and the measured smoke containing smoke dust passes through the measuring area;
(2) an image sensor arranged on the lateral side of the laser shoots a scattered light image of the smoke particles to the laser;
(3) the image sensor sends the measured scattered light signals to a computer for data processing:
a. analyzing the shot smoke dust scattered light image to obtain a light intensity value of the scattered light image;
b. when the smoke concentration is lower than 0.01mg/kg, the scattered light intensity is very weak, and a light intensity signal obtained by the image sensor is smaller than or close to the measurement lower limit of the sensor, the exposure time tau of the image sensor is increased to improve the intensity of the measured image signal, and the exposure time tau of the image sensor is adjusted from microseconds to milliseconds according to the concentration of the measured smoke;
c. the light intensity value is compared with a relation curve of scattering light intensity and smoke concentration obtained by laboratory calibration in advance in a computer to calculate the smoke concentration.
The detection method of the fault detection module 8 provided by the invention is as follows:
(1) collecting operation data of fan equipment;
(2) extracting fault data segments in a moving window mode, mapping into image data according to rules, and analyzing characteristics;
(3) analyzing and extracting fault image characteristics, carrying out clustering and classifying algorithm analysis on the fault image characteristics through training on the fault image characteristics, marking fault label for each fault image characteristic respectively, giving a category, and establishing a fault image library;
(4) and after the inflow real-time data is processed by the fault image, matching the fault image with a fault image library, and outputting the fault category or the running state of the wind power equipment.
The operation data of the fan equipment provided by the invention comprises scada data and plc fault log data of fan operation.
The fault image provided by the invention intercepts fault data fragments in a moving window mode, when the data is recovered to be normal, the interception of the fault data fragments is stopped, a plurality of fields in each fault data fragment are converted into image data with color bands through a fault image rule, and a plurality of fault data fragments form a group of monitoring data;
the fault image features are extracted through a full convolution network, clustering and classification are carried out on the fault image features, and training is carried out on the fault image features through a full connection condition random field and a Markov random field.
The fault image rule provided by the invention comprises the steps of arranging a plurality of fields into a matrix, and carrying out color marking on each field to form image data with color bands;
the color depth of the color band is high in fault level, the color depth of the color band is low in fault level, and the continuous length of the color band is the continuous time of the fault.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (5)
1. An intelligent electric automatic dust removal control method is characterized by comprising the following steps:
firstly, supplying power to an intelligent electric automatic dust removal device through a power supply module; detecting smoke concentration data by a smoke detection module through a laser detector; inputting a dedusting parameter configuration operation by using an operation key through a parameter input module;
secondly, the main control module dispatches a power adjusting module through a PLC singlechip, and correspondingly adjusts the power of the exhaust fan according to the smoke concentration by using a power adjusting circuit;
thirdly, performing suction operation on the smoke dust by using an exhaust fan through an exhaust module; the absorbed smoke dust is filtered by the filter module through the filter screen;
detecting a fault signal of the fan by using a circuit signal detector through a fault detection module;
step five, storing the collected smoke data and fault information by a data storage module through a memory; and the display module is used for displaying the collected smoke data information and the fault information by using the display.
2. The intelligent electric automatic dust removal control method according to claim 1, wherein the main control module processes dust removal parameters in the processing parameter input module, performs data fusion on the parameters, and adopts a self-adaptive weighted data fusion algorithm, specifically: different sets of measurement data have different weights, and under the optimal condition of minimum total mean square error, the corresponding weights of the measurement data are searched in a self-adaptive mode according to the sets of measurement data, so that the fused values are optimal;
after the weighting factor is introduced, the data fusion value of the intelligent detection system is as follows:
wherein,
the total mean square error is:
wherein sigma2Is each weighting factor WiA multivariate quadratic function of (a);
according to the theory of extreme value solving by multivariate function, the weight factor is solvedIs when is σ2A minimum value of
After the weighting factors are introduced according to the self-adaptive weighting model, the system data fusion value is
3. The intelligent electric automatic dust removal control method according to claim 1, wherein in the process that the power adjusting module correspondingly adjusts the power of the exhaust fan according to the smoke concentration through the power adjusting circuit, the power adjusting circuit adopts a method for diagnosing the fault of the analog circuit functional module, and the method comprises the following steps:
firstly, dividing a circuit to be tested into modules according to different functions according to basic information of the circuit before testing, and then establishing a first-stage fault dictionary of each functional module of the circuit;
the second step is that: before testing, applying normal excitation according to each divided functional module, dividing the element to be tested into 5 intervals through 6 points and 5 sections, obtaining discrete working point tracks of the corresponding intervals through iteration simulation before testing, storing the discrete working point tracks in one-to-one correspondence, and establishing a second-level fault dictionary;
thirdly, after the measurement, applying the same excitation to the circuit during the actual diagnosis to obtain the related functional indexes of the circuit and the actually measured node voltage working points;
fourthly, after the detection, firstly carrying out fault detection; comparing first-level fault dictionaries of all functional modules of the circuit, and detecting whether the circuit functional indexes are consistent with the functional dictionaries; if the circuit function index is consistent with the function dictionary, judging that the circuit is normal, otherwise, judging that the circuit has a fault;
fifthly, after the detection and the fault detection in the fourth step, according to the circuit node voltage obtained in the third step, calculating the minimum distance from the actually-measured voltage working point to a discrete working point track dictionary corresponding to each element in the second-stage fault dictionary of the functional module, and judging the fault element according to the minimum distance to realize fault positioning;
and sixthly, calculating the interval of the corresponding discrete working point with the minimum distance from the working point of the measured voltage according to the positioned fault element, and identifying the parameter interval of the fault element.
4. An intelligent electric automatic dust removal control system for implementing the intelligent electric automatic dust removal control method of claim 1, wherein the intelligent electric automatic dust removal control system comprises:
the power supply module is connected with the main control module and used for supplying power to the intelligent electric automatic dust removal device;
the smoke detection module is connected with the main control module and used for detecting smoke concentration data through a laser detector;
the parameter input module is connected with the main control module and used for inputting dust removal parameter configuration operation through an operation key;
the main control module is connected with the power supply module, the smoke detection module, the parameter input module, the power regulation module, the air draft module, the filtering module, the fault detection module, the data storage module and the display module and is used for controlling each module to normally work through the PLC single chip microcomputer;
the power adjusting module is connected with the main control module and is used for correspondingly adjusting the power of the exhaust fan according to the smoke concentration through the power adjusting circuit;
the air exhaust module is connected with the main control module and is used for performing suction operation on the smoke dust through an exhaust fan;
the filter module is connected with the main control module and is used for filtering the absorbed smoke dust through the filter screen;
the fault detection module is connected with the main control module and used for detecting a fault signal of the fan through the circuit signal detector;
the data storage module is connected with the main control module and used for storing the collected smoke data and the fault information through the memory;
and the display module is connected with the main control module and used for displaying the collected smoke data information and the fault information through the display.
5. A dust remover applying the intelligent electric automatic dust removal control method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811509650.3A CN109603340A (en) | 2018-12-11 | 2018-12-11 | A kind of intelligent electric automation dedusting control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811509650.3A CN109603340A (en) | 2018-12-11 | 2018-12-11 | A kind of intelligent electric automation dedusting control system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109603340A true CN109603340A (en) | 2019-04-12 |
Family
ID=66008081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811509650.3A Pending CN109603340A (en) | 2018-12-11 | 2018-12-11 | A kind of intelligent electric automation dedusting control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109603340A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110274075A (en) * | 2019-04-26 | 2019-09-24 | 山东莱钢永锋钢铁有限公司 | A kind of large flue ash discharging system |
| CN110968010A (en) * | 2019-12-24 | 2020-04-07 | 中冶建筑研究总院有限公司 | Novel non-process dust removal centralized monitoring system |
| CN112657290A (en) * | 2020-12-04 | 2021-04-16 | 上海钧控机器人有限公司 | Intelligence chinese mugwort cigarette processing apparatus |
| CN113989218A (en) * | 2021-10-26 | 2022-01-28 | 东莞高绮印刷有限公司 | Double electrostatic dust collection method and device based on parameter prediction model |
| CN115291580A (en) * | 2022-10-08 | 2022-11-04 | 山东聊城华阳医药辅料有限公司 | Medicine auxiliary material production data monitoring and management system and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435910A (en) * | 2011-09-14 | 2012-05-02 | 南京航空航天大学 | Power electronic circuit health monitoring method based on support vector classification |
| CN102652891A (en) * | 2012-05-09 | 2012-09-05 | 中国三冶集团有限公司电气安装工程公司 | Energy-saving automatic control device of cloth-bag dust removal system and control method for blast furnace dust removal |
| CN103239955A (en) * | 2013-05-14 | 2013-08-14 | 山东开泰工业科技有限公司 | Integrated controller for optimizing pulse dust removal |
| CN104504237A (en) * | 2014-11-21 | 2015-04-08 | 国家电网公司 | Automatic diagnosis and discrimination model of data for denitrification system of coal-fired power plant |
| CN204672034U (en) * | 2015-04-16 | 2015-09-30 | 武汉钢铁(集团)公司 | A kind of fiber bag precipitator energy-saving monitoring apparatus |
| KR20160002480A (en) * | 2014-06-30 | 2016-01-08 | 코웨이 주식회사 | System and method for automatic test of air purifier |
| CN105352535A (en) * | 2015-09-29 | 2016-02-24 | 河海大学 | Measurement method on the basis of multi-sensor date fusion |
| US20180093215A1 (en) * | 2016-10-05 | 2018-04-05 | Gs De México S De Rl De Cv | Dust collector control system |
| CN108921208A (en) * | 2018-06-20 | 2018-11-30 | 天津大学 | The aligned sample and modeling method of unbalanced data based on deep learning |
-
2018
- 2018-12-11 CN CN201811509650.3A patent/CN109603340A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435910A (en) * | 2011-09-14 | 2012-05-02 | 南京航空航天大学 | Power electronic circuit health monitoring method based on support vector classification |
| CN102652891A (en) * | 2012-05-09 | 2012-09-05 | 中国三冶集团有限公司电气安装工程公司 | Energy-saving automatic control device of cloth-bag dust removal system and control method for blast furnace dust removal |
| CN103239955A (en) * | 2013-05-14 | 2013-08-14 | 山东开泰工业科技有限公司 | Integrated controller for optimizing pulse dust removal |
| KR20160002480A (en) * | 2014-06-30 | 2016-01-08 | 코웨이 주식회사 | System and method for automatic test of air purifier |
| CN104504237A (en) * | 2014-11-21 | 2015-04-08 | 国家电网公司 | Automatic diagnosis and discrimination model of data for denitrification system of coal-fired power plant |
| CN204672034U (en) * | 2015-04-16 | 2015-09-30 | 武汉钢铁(集团)公司 | A kind of fiber bag precipitator energy-saving monitoring apparatus |
| CN105352535A (en) * | 2015-09-29 | 2016-02-24 | 河海大学 | Measurement method on the basis of multi-sensor date fusion |
| US20180093215A1 (en) * | 2016-10-05 | 2018-04-05 | Gs De México S De Rl De Cv | Dust collector control system |
| CN108921208A (en) * | 2018-06-20 | 2018-11-30 | 天津大学 | The aligned sample and modeling method of unbalanced data based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 杨昆等: "矿井粉尘浓度在线监测技术", 《辽宁工程技术大学学报（自然科学版）》 * |
| 胡梅等: "一种模拟电路功能模块故障诊断的方法", 《电子测量与仪器学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110274075A (en) * | 2019-04-26 | 2019-09-24 | 山东莱钢永锋钢铁有限公司 | A kind of large flue ash discharging system |
| CN110968010A (en) * | 2019-12-24 | 2020-04-07 | 中冶建筑研究总院有限公司 | Novel non-process dust removal centralized monitoring system |
| CN112657290A (en) * | 2020-12-04 | 2021-04-16 | 上海钧控机器人有限公司 | Intelligence chinese mugwort cigarette processing apparatus |
| CN112657290B (en) * | 2020-12-04 | 2022-11-01 | 上海钧控机器人有限公司 | Intelligence chinese mugwort cigarette processing apparatus |
| CN113989218A (en) * | 2021-10-26 | 2022-01-28 | 东莞高绮印刷有限公司 | Double electrostatic dust collection method and device based on parameter prediction model |
| CN113989218B (en) * | 2021-10-26 | 2022-05-20 | 东莞高绮印刷有限公司 | Double electrostatic dust collection method and device based on parameter prediction model |
| CN115291580A (en) * | 2022-10-08 | 2022-11-04 | 山东聊城华阳医药辅料有限公司 | Medicine auxiliary material production data monitoring and management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109603340A (en) | A kind of intelligent electric automation dedusting control system and method | |
| CN102473660B (en) | Automatic fault detection and classification in a plasma processing system and methods thereof | |
| CN115187527B (en) | Separation and identification method for multi-source mixed ultrahigh frequency partial discharge spectrum | |
| US7224825B2 (en) | Detecting and identifying hazardous substances contained in mail articles | |
| CN101915767B (en) | Method for systematically recognizing egg cracks | |
| CN109876569B (en) | Online detection device, system and method for purified gas index of bag-type dust remover | |
| CN111103854A (en) | System and method for improving production stability of tobacco cut-tobacco drier | |
| CN108304567B (en) | Method and system for identifying working condition mode and classifying data of high-voltage transformer | |
| CN111852792B (en) | Fan blade defect self-diagnosis positioning method based on machine vision | |
| CN112487708A (en) | Resistance spot welding quality prediction method based on ensemble learning | |
| CN102933952A (en) | Method and device for detecting biological material | |
| Schiele et al. | Automated classification of airborne pollen using neural networks | |
| CN116499938B (en) | Intelligent monitoring method for aerosol suspended matters in professional workplace | |
| CN110889441A (en) | Distance and point density based substation equipment data anomaly identification method | |
| CN105203434A (en) | Particle size spectrometer measuring water content of aerosol | |
| CN107121436A (en) | The Intelligent detecting method and identification device of a kind of silicon material quality | |
| CN110135466A (en) | A kind of exceeded vehicle judgment method of pollutant emission and system | |
| CN113918642A (en) | Data filtering, monitoring and early warning method based on power Internet of things equipment | |
| CN113063897A (en) | Air pollutant tracing method and device | |
| CN107238475A (en) | A kind of bag-type duster filtering bag on-line real time monitoring system | |
| CN114970977A (en) | Abnormal data detection method and system for digital urban air quality monitoring data | |
| US5072626A (en) | Measurement of ultrafine particle size distributions | |
| CN102967557B (en) | Biological aerosol water-content determination based on near infrared spectroscopy and classification method thereof | |
| CN116831307A (en) | Tobacco material winnowing impurity-removing process control method and device and storage medium | |
| Yang et al. | An integrated system for automated measurement of airborne pollen based on electrostatic enrichment and image analysis with machine vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |