CN117771841A - Dust collector intelligent control method and system based on dust concentration monitoring - Google Patents
Dust collector intelligent control method and system based on dust concentration monitoring Download PDFInfo
- Publication number
- CN117771841A CN117771841A CN202410203558.3A CN202410203558A CN117771841A CN 117771841 A CN117771841 A CN 117771841A CN 202410203558 A CN202410203558 A CN 202410203558A CN 117771841 A CN117771841 A CN 117771841A
- Authority
- CN
- China
- Prior art keywords
- dust
- cloth bag
- particle size
- data
- preset time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000428 dust Substances 0.000 title claims abstract description 706
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 239000004744 fabric Substances 0.000 claims abstract description 159
- 238000009825 accumulation Methods 0.000 claims abstract description 137
- 239000002245 particle Substances 0.000 claims abstract description 136
- 230000004913 activation Effects 0.000 claims abstract description 75
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims abstract description 27
- 239000003546 flue gas Substances 0.000 claims abstract description 27
- 238000011010 flushing procedure Methods 0.000 claims abstract description 17
- 239000000463 material Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000000779 smoke Substances 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 230000001186 cumulative effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 26
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 238000003672 processing method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 239000013618 particulate matter Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003921 particle size analysis Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Filtering Of Dispersed Particles In Gases (AREA)
- Sampling And Sample Adjustment (AREA)
Abstract
The disclosure provides a dust remover intelligent control method and system based on dust concentration monitoring, and relates to a bag-type dust remover control technology, wherein the method comprises the following steps: acquiring dust concentration data and dust image data; determining an effective dust removal particle size threshold and a maximum dust accumulation bearing capacity threshold; carrying out dust particle size ratio analysis according to dust image data, and determining the effective dust particle size ratio; correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data; carrying out cloth bag dust accumulation prediction based on standard dust concentration data and inlet flue gas flow speed to generate cloth bag predicted dust accumulation; when the predicted accumulated dust amount of the cloth bag meets the threshold value of the maximum accumulated dust bearing amount, a pulse valve is started to perform air flow flushing treatment under the command activation time node. The method can solve the technical problem of lower dust removal control accuracy of the existing bag-type dust remover control method, and can improve the dust removal control accuracy of the bag-type dust remover.
Description
Technical Field
The disclosure relates to bag-type dust collector control technology, and more particularly, to a dust collector intelligent control method and system based on dust concentration monitoring.
Background
The bag-type dust collector is a dry high-efficiency dust collector, also called a filter-type dust collector, and utilizes a bag-type filter element made of fiber braid to trap solid particles in dust-containing gas.
The existing bag-type dust collector control method is used for opening and closing a pulse valve according to the changes of parameters such as air pressure, temperature and the like in the dust collector, the method has higher requirements on the acquisition accuracy of sensors such as air pressure, temperature and the like, and when the service time is too long or the external environment interference is serious, the condition that the accuracy of acquired data is lower often exists, so that the control accuracy of the pulse valve of the bag-type dust collector is lower.
The existing cloth bag dust collector control method has the following defects: the lower accuracy of dust removal control leads to larger equipment quality damage and larger electric energy resource waste.
Disclosure of Invention
Therefore, in order to solve the above technical problems, the technical solution adopted in the embodiments of the present disclosure is as follows:
the intelligent control method of the dust remover based on dust concentration monitoring is applied to an intelligent control system of the dust remover based on dust concentration monitoring, and the system is in communication connection with a dust concentration detector, an industrial camera and a pulse valve control unit, and comprises the following steps: acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet flue gas of a target bag-type dust collector through a dust concentration detector, and the dust image data is obtained by acquiring images of the inlet flue gas through an industrial camera; acquiring basic data information of a dust collection cloth bag of the target cloth bag dust collector, and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data; performing dust particle size ratio analysis according to the dust image data, and determining an effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold; correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data; carrying out cloth bag dust collection amount prediction in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed, and generating cloth bag prediction dust collection amount, wherein the cloth bag prediction dust collection amount is the sum of cloth bag dust collection amount prediction results in a plurality of preset time windows, and the preset time windows are the time intervals of adjacent preset time nodes; when the cloth bag predicted accumulated dust accumulation amount meets the maximum accumulated dust bearing amount threshold, generating a pulse valve activation instruction, wherein the pulse valve activation instruction comprises an instruction activation time node; transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform reverse airflow flushing treatment on the dust collection cloth bag under the instruction activation time node.
Dust remover intelligent control system based on dust concentration monitoring, system and dust concentration detector, industry camera, pulse valve control unit communication connection include: the dust data acquisition module is used for acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet smoke of a target bag-type dust collector through the dust concentration detector, and the dust image data is obtained by acquiring images of the inlet smoke through the industrial camera; the threshold determining module is used for acquiring basic data information of a dust collection bag of the target bag-type dust collector and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data; the effective dust particle size ratio determining module is used for carrying out dust particle size ratio analysis according to the dust image data and determining the effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold; the standard dust concentration data generation module is used for correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data; the cloth bag prediction accumulated dust amount generation module is used for predicting cloth bag accumulated dust amount in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed to generate cloth bag prediction accumulated dust amount, and the cloth bag prediction accumulated dust amount is the sum of cloth bag accumulated dust amount prediction results in a plurality of preset time windows, wherein the preset time windows are the time intervals of adjacent preset time nodes; the pulse valve activation instruction generation module is used for generating a pulse valve activation instruction when the cloth bag predicted accumulated dust amount meets the maximum accumulated dust bearing amount threshold value, wherein the pulse valve activation instruction comprises an instruction activation time node; and the back air flow flushing processing module is used for transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform back air flow flushing processing on the dust collection cloth bag under the instruction activation time node.
By adopting the technical method, compared with the prior art, the technical progress of the present disclosure has the following points:
the technical problem of lower dust removal control accuracy in the existing bag-type dust remover control method can be solved, and firstly, dust concentration data and dust image data under a preset time node are obtained through a dust concentration detector and an industrial camera; the basic data information of the dust collection cloth bag of the target cloth bag dust collector is analyzed, and then an effective dust collection particle size threshold value and a maximum dust collection bearing capacity threshold value are determined, wherein the basic data information comprises quantity information, specification parameters, material properties and density data; then carrying out dust particle size ratio analysis according to the dust image data, and determining the effective dust particle size ratio based on the dust particle size ratio analysis result and the effective dust removal particle size threshold; correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data, so that the accuracy of obtaining the standard dust concentration data can be improved; building a dust accumulation amount prediction model based on a BP neural network, and predicting the dust accumulation amount of a cloth bag in a preset time window according to the standard dust concentration data and the inlet flue gas flow speed by using the dust accumulation amount prediction model to generate a cloth bag predicted dust accumulation amount, wherein the cloth bag predicted dust accumulation amount is the sum of cloth bag dust accumulation amount prediction results in a plurality of preset time windows, and the preset time windows are the time intervals of adjacent preset time nodes; judging the predicted accumulated dust amount of the cloth bag according to the maximum accumulated dust bearing amount threshold, and generating a pulse valve activation instruction when the predicted accumulated dust amount of the cloth bag meets the maximum accumulated dust bearing amount threshold, wherein the pulse valve activation instruction comprises an instruction activation time node; and finally, transmitting the pulse valve activation instruction to the pulse valve control unit, and starting a pulse valve to perform reverse airflow flushing treatment on the dust collection cloth bag under the instruction activation time node. The method can improve the accuracy of dust removal control of the bag-type dust remover, thereby reducing the damage to the equipment quality of the dust remover and prolonging the service life of the dust remover when the dust concentration is higher; when the dust concentration is low, unnecessary energy loss is reduced, and electric energy resources are saved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are used in the description of the embodiments will be briefly described below.
Fig. 1 is a schematic flow chart of a dust collector intelligent control method based on dust concentration monitoring.
Fig. 2 is a schematic flow chart of a method for intelligently controlling a dust collector based on dust concentration monitoring to generate a prediction accumulated dust accumulation of a cloth bag.
Fig. 3 is a schematic structural diagram of an intelligent control system of a dust collector based on dust concentration monitoring.
Reference numerals illustrate: the device comprises a dust data acquisition module 01, a threshold value determination module 02, an effective dust particle size ratio determination module 03, a standard dust concentration data generation module 04, a cloth bag prediction accumulated dust accumulation generation module 05, a pulse valve activation instruction generation module 06 and a back air flow flushing processing module 07.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
Based on the above description, as shown in fig. 1, the disclosure provides a dust collector intelligent control method based on dust concentration monitoring, where the method is applied to a dust collector intelligent control system based on dust concentration monitoring, and the system is in communication connection with a dust concentration detector, an industrial camera, and a pulse valve control unit, and includes:
the method is used for accurately controlling the pulse valve of the bag-type dust collector according to the dust real-time concentration monitoring data so as to achieve the aim of improving the dust collection control accuracy of the pulse valve, and is specifically implemented in an intelligent dust collector control system based on dust concentration monitoring, wherein the system is in communication connection with a dust concentration detector, an industrial camera and a pulse valve control unit, the dust concentration detector and the industrial camera input collected real-time monitoring data into the intelligent dust collection control system in a signal transmission mode, and the intelligent dust collection control system transmits a generated pulse valve activation instruction to the pulse valve control unit so as to realize pneumatic control of the pulse valve. The dust concentration detector and the industrial camera are arranged at the smoke inlet position of the bag-type dust collector, and the industrial camera is equipment with a high-precision image acquisition function.
Acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet flue gas of a target bag-type dust collector through a dust concentration detector, and the dust image data is obtained by acquiring images of the inlet flue gas through an industrial camera;
in this embodiment of the present application, first, a preset time node is obtained, where the preset time node can be set by a person skilled in the art according to an actual requirement, where the higher the actual control accuracy requirement is, the shorter the preset time node is, for example: the preset time node is set to be 2 minutes, namely data acquisition is carried out every 2 minutes. Then, detecting the dust concentration of inlet smoke of a target bag-type dust remover through the dust concentration detector in the preset time, wherein the target bag-type dust remover is the bag-type dust remover to be subjected to intelligent control optimization, and generating dust concentration data; and carrying out image acquisition on the inlet flue gas by the industrial camera to obtain dust image data. By obtaining the dust concentration data and the dust image data, raw data support is provided for generating standard dust concentration data for the next step.
Acquiring basic data information of a dust collection cloth bag of the target cloth bag dust collector, and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data;
in the embodiment of the application, firstly, basic data information of a dust collection cloth bag of the target cloth bag dust collector is collected, wherein the basic data information comprises quantity information, specification parameters, material properties and density data, and the specification parameters are data such as the size, the shape and the like of the dust collection cloth bag; the target cloth bag dust remover filters particles such as dust through a dust removing cloth bag, wherein the larger the density of the dust removing cloth bag is, the lower the passing probability of the particles such as dust is, and the better the dust removing effect is. And then carrying out dust removal performance analysis on the basic data information, and determining an effective dust removal particle size threshold and a maximum dust accumulation bearing capacity threshold according to a dust removal performance analysis result.
In one embodiment, the method further comprises:
analyzing the effective dust removal performance of the dust removal cloth bag based on the material attribute and the density data to generate an effective dust removal particle size threshold;
Calculating the maximum dust accumulation bearing capacity of the single dust collection cloth bag based on the specification parameters, the material properties and the density data, and generating the maximum dust accumulation bearing capacity of the single dust collection cloth bag;
and adding and summing the maximum dust accumulation bearing capacity according to the quantity information to obtain a maximum dust accumulation bearing capacity threshold.
In the embodiment of the application, firstly, data retrieval is carried out based on big data to obtain historical basic data information of a plurality of dust collection cloth bags, a plurality of effective dust collection particle size thresholds and a plurality of maximum dust collection bearing amounts, wherein the historical basic data information, the effective dust collection particle size thresholds and the maximum dust collection bearing amounts have corresponding relations, the effective dust collection particle size thresholds refer to the maximum particle size capable of carrying out particle filtering through the dust collection cloth bags, and when particles in flue gas enter a bag type dust collector, the particles with big particle size and big specific gravity are settled under the action of gravity and fall into a dust hopper, so that when the particle size of the particles is larger than the effective dust collection particle size thresholds, the particle filtering can be completed without passing through the dust collection cloth bags; the maximum dust accumulation bearing amount is the maximum particulate matter accumulation amount which can be borne by a single dust collection cloth bag, and when the particulate matter accumulation amount of the dust collection cloth bag is larger than the maximum particulate matter accumulation amount, the dust collection effect is reduced and the quality of the dust collection cloth bag is damaged. And then taking the historical basic data information of the dust removing cloth bags, the effective dust removing particle size thresholds and the maximum dust accumulation bearing capacity as sample data.
An effective dust removal performance analysis channel and a maximum dust accumulation bearing capacity calculation channel are constructed based on the BP neural network, wherein the input data of the effective dust removal performance analysis channel are material property and density data, and the output data are effective dust removal particle size thresholds; the input data of the maximum dust accumulation bearing amount calculation channel is specification parameters, material properties and density data, and the output data is the maximum dust accumulation bearing amount. And then performing supervised training on the effective dust removal performance analysis channel and the maximum dust accumulation bearing capacity calculation channel through the sample data to obtain the effective dust removal performance analysis channel and the maximum dust accumulation bearing capacity calculation channel, wherein the supervised training process of the effective dust removal performance analysis channel and the maximum dust accumulation bearing capacity calculation channel is the same as the training method of the lower dust accumulation capacity prediction model, and in order to embody the simplicity of the specification, the supervised training process of the lower dust accumulation capacity prediction model can be referred to by a person skilled in the art without unfolding the description.
Inputting the material properties and the density data into a trained effective dust removal performance analysis channel for effective dust removal performance analysis, and outputting an effective dust removal particle size threshold; inputting the specification parameters, the material properties and the density data into a training-completed maximum dust accumulation bearing amount calculation channel, and outputting a maximum dust accumulation bearing amount, wherein the maximum dust accumulation bearing amount is the maximum dust accumulation bearing amount of a single cloth bag; and then adding and summing the maximum dust accumulation bearing capacity according to the quantity information, and taking the summation result of the maximum dust accumulation bearing capacity as a maximum dust accumulation bearing capacity threshold, wherein the maximum dust accumulation bearing capacity threshold is the maximum dust accumulation bearing capacity of the whole target bag-type dust remover.
By constructing an effective dust removal performance analysis channel and a maximum accumulated dust bearing amount calculation channel based on the BP neural network, the efficiency and accuracy obtained by the effective dust removal particle size threshold and the maximum accumulated dust bearing amount can be improved, and the accuracy of dust removal control of the bag-type dust remover is improved.
Performing dust particle size ratio analysis according to the dust image data, and determining an effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold;
in the embodiment of the application, the dust image data is subjected to dust contour extraction, dust particle size ratio analysis is performed according to a dust contour extraction result, a dust particle size ratio analysis result is generated, and dust with the particle size smaller than an effective dust removal particle size threshold in the dust particle size ratio analysis result is marked as effective dust, so that an effective dust particle size ratio is obtained.
In one embodiment, the method further comprises:
carrying out graying treatment on the dust image data to generate a gray dust image;
carrying out dust contour feature extraction and edge fitting on the basis of the gray dust image to generate a plurality of dust contour data;
performing dust particle size calculation based on the plurality of dust profile data to obtain a plurality of dust particle size data;
And marking the dust particle sizes smaller than the effective dust removal particle size threshold value in the dust particle size data as effective dust particle sizes, and taking the ratio of the effective dust particle size quantity to the dust particle size data quantity as the effective dust particle size ratio.
In this embodiment of the present application, first, the gray-scale processing is performed on the dust image data, where the gray-scale processing refers to a process of converting a dust image into a gray-scale image, and the gray-scale processing may improve the image processing speed, and at the same time, may perform image enhancement on the dust image, and improve the image contrast, so as to improve the accuracy of dust particle size analysis in the image, and the common image gray-scale processing methods include a maximum value processing method, an average value processing method, and a weighted average processing method, so that a person skilled in the art may select an adapted image gray-scale processing method according to the actual situation, to generate a gray-scale dust image.
The gray scale dust image is then subjected to dust contour feature extraction and edge fitting by existing image processing techniques, such as: the dust contour feature extraction can be performed by a contour extraction method or a boundary tracking method, wherein the edge fitting refers to fitting connection of the blocked dust contour according to the existing dust contour feature, so that the accuracy of dust contour data acquisition is improved, and a plurality of dust contour data are generated. And then carrying out dust particle size calculation on the dust profile data to obtain dust particle size data.
Judging the dust particle sizes of the dust particle size data according to the effective dust particle size threshold, marking the dust particle sizes smaller than the effective dust particle size threshold in the dust particle size data as effective dust particle sizes, and then taking the ratio of the effective dust particle size number to the dust particle size data number as the effective dust particle size ratio to obtain the effective dust particle size ratio. By obtaining the effective dust particle size ratio, the dust concentration correction method provides support for the dust concentration data in the next step.
Correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data;
in the embodiment of the application, the dust concentration data is multiplied by the effective dust particle diameter ratio, and the product of the two is taken as standard dust concentration data, so that standard dust concentration data is obtained. The dust particle size identification is carried out on the flue gas image, the effective dust particle size ratio is determined, and the dust concentration data is corrected according to the effective dust particle size ratio, so that the accuracy of dust concentration data acquisition can be improved, and the accuracy of prediction of the dust accumulation of the cloth bag can be improved.
Carrying out cloth bag dust collection amount prediction in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed, and generating cloth bag prediction dust collection amount, wherein the cloth bag prediction dust collection amount is the sum of cloth bag dust collection amount prediction results in a plurality of preset time windows, and the preset time windows are the time intervals of adjacent preset time nodes;
In this embodiment, a preset time window is obtained, where the preset time window is a time interval between adjacent preset time nodes, for example: assuming that the preset time node is a primary time node of 2 minutes, the preset time window is a 2-minute time period; and predicting the bag dust collection amount of the dust collection bag in a preset time window according to the standard dust concentration data and the inlet flue gas flow speed, wherein the inlet flue gas flow speed can be obtained by collecting the flue gas speed through a sensor, generating a plurality of bag dust collection amount prediction results in the preset time window, adding and summing the plurality of bag dust collection amount prediction results, and taking the added and summed result as the bag dust collection amount prediction.
As shown in fig. 2, in one embodiment, the method further comprises:
acquiring a first preset time window, wherein the first preset time window is a time interval between a first preset time node and a second preset time node;
obtaining first standard dust concentration data of the first preset time node and second standard dust concentration data of the second preset time node;
inputting the first standard dust concentration data, the second standard dust concentration data and the inlet flue gas flow speed into a dust accumulation amount prediction model to obtain a first cloth bag dust accumulation amount prediction result;
And generating the cloth bag predicted dust accumulation amount based on the first cloth bag dust accumulation amount prediction result.
In this embodiment of the present application, first, a first preset time window is obtained, where the first preset time window is a time interval between a first preset time node and a second preset time node, the first preset time node is a time node for first performing flue gas data collection, and the second preset time node is a next time node adjacent to the first preset time node. And then obtaining first standard dust concentration data of the first preset time node and second standard dust concentration data of the second preset time node.
And constructing a dust accumulation amount prediction model based on the BP neural network, wherein the dust accumulation amount prediction model is a neural network model which can be subjected to iterative optimization in machine learning, and is obtained by performing supervision training through a training data set. Firstly, based on an industrial big data technology, carrying out data query by taking a target bag-type dust collector as an index condition to obtain a plurality of historical dust collection data, wherein the historical dust collection data are the same type of the target bag-type dust collector, the historical dust collection data comprise historical dust concentration data, historical smoke flow speed and historical accumulated dust accumulation of two adjacent time nodes, and the historical accumulated dust accumulation is the sum of the historical dust accumulation of a plurality of dust collection bags in the bag-type dust collector. The historical dust concentration data, the historical smoke flow speed and the historical dust accumulation amount of the two adjacent time nodes have a corresponding relation, and the time interval of the two adjacent time nodes and the time period of the preset time window can be the same or different. Constructing a sample data set according to the plurality of historical dust removal data, and dividing the sample data set into a sample training set and a sample verification set according to a preset data dividing rule, wherein the preset data dividing rule can be set by a person skilled in the art according to actual conditions, for example: the sample training set data is 85% and the sample validation set data is 15%.
Performing supervised training and supervised verification on the dust accumulation amount prediction model according to the sample training set and the sample verification set, firstly, randomly selecting sample training data from the sample training set as first sample training data, and performing supervised training on the dust accumulation amount prediction model according to the first sample training data to obtain a first dust accumulation amount prediction result output by the model; then comparing the first dust accumulation prediction result with the historical dust accumulation in the first sample training data; when the results are consistent, continuing to supervise and train the model according to the next sample training data; when the results are inconsistent, calculating the result deviation between the first dust accumulation prediction result and the historical dust accumulation in the first sample training data, optimizing and adjusting the weight parameters of the model according to the result deviation, then performing the supervision training of the next training data, and continuously performing iterative training until the model tends to be in a converged state, verifying the output result of the model through the sample verification set until the accuracy of the output result of the model is greater than or equal to a preset accuracy index, wherein the preset accuracy index can be set by a person skilled in the art according to actual conditions, for example: the preset accuracy index is set as the output result accuracy of 96%.
And then inputting the first standard dust concentration data, the second standard dust concentration data and the inlet flue gas flow speed into a dust accumulation amount prediction model after training is completed, and outputting a dust accumulation amount prediction result of the first cloth bag. And sequentially predicting the dust accumulation of the cloth bags in a plurality of preset time windows by using the same method for obtaining the first dust accumulation prediction result of the cloth bags to obtain the dust accumulation prediction results of the cloth bags in the plurality of preset time windows, and adding and summing the plurality of dust accumulation prediction results of the cloth bags to obtain the dust accumulation of the cloth bags.
The accuracy and efficiency of the bag dust accumulation prediction can be improved by constructing the dust accumulation prediction model based on the BP neural network and performing supervision training and verification on the dust accumulation prediction model based on model training sample data obtained by an industrial big data technology.
In one embodiment, the method further comprises:
the dust removing operation log of the target bag-type dust remover is called, and the maximum historical dust concentration data is obtained based on the dust removing operation log;
generating a prediction result of the maximum cloth bag dust accumulation amount in a preset time window based on the maximum historical dust concentration data;
and generating the cloth bag predicted dust accumulation amount based on the first cloth bag dust accumulation amount prediction result and the maximum cloth bag dust accumulation amount prediction result.
In the embodiment of the application, before the cloth bag prediction accumulated dust accumulation is generated, firstly, a dust removal operation log of the target cloth bag dust remover is called, and the maximum historical dust concentration data in the dust removal operation log is extracted. And carrying out cloth bag dust accumulation prediction on the maximum historical dust concentration data in a preset time window through the dust accumulation prediction model, wherein the concentration data of two adjacent time nodes input in the dust accumulation prediction model are the maximum historical dust concentration data, and obtaining a maximum cloth bag dust accumulation prediction result in the preset time window.
The purpose of calculating the maximum cloth bag dust collection amount prediction result is to prevent the damage to the dust collection effect and the quality of the dust collector caused by the exceeding of the cloth bag dust collection amount in the next preset time window, so that the cloth bag dust collection amount prediction result in the next preset time window is maximized. And then, when the accumulated dust accumulation of the cloth bag prediction is calculated each time, the maximum cloth bag accumulated dust amount prediction result is required to be added, and the sum of the cloth bag accumulated dust amount prediction results in a plurality of preset time windows is added to obtain the accumulated dust accumulation of the cloth bag prediction. The method has the advantages that the prediction result of the maximum cloth bag dust accumulation amount is generated to optimize the cloth bag predicted dust accumulation amount, so that the rationality of the cloth bag predicted dust accumulation amount can be improved, and the accuracy of dust removal control is further improved.
When the cloth bag predicted accumulated dust accumulation amount meets the maximum accumulated dust bearing amount threshold, generating a pulse valve activation instruction, wherein the pulse valve activation instruction comprises an instruction activation time node;
in this embodiment of the present application, the predicted accumulated dust amount of the cloth bag is determined according to the maximum accumulated dust bearing amount threshold, and when the predicted accumulated dust amount of the cloth bag is greater than or equal to the maximum accumulated dust bearing amount threshold, a pulse valve activation instruction is generated, where the pulse valve activation instruction includes an instruction activation time node.
In one embodiment, the method further comprises:
judging the predicted accumulated dust accumulation amount of the cloth bag according to the maximum accumulated dust bearing amount threshold;
when the cloth bag predicted accumulated dust amount is smaller than the maximum accumulated dust bearing amount threshold value, judging the cloth bag predicted accumulated dust amount in sequence according to a preset time node;
when the accumulated dust accumulation predicted by the cloth bag is larger than or equal to the threshold value of the maximum accumulated dust bearing capacity, recording the current preset time node as a first preset time node, and generating a pulse valve activation instruction based on the first preset time node.
In the embodiment of the application, firstly, judging the cloth bag prediction accumulated dust accumulation amount according to the maximum accumulated dust bearing amount threshold, and when the cloth bag prediction accumulated dust accumulation amount is smaller than the maximum accumulated dust bearing amount threshold, judging the cloth bag prediction accumulated dust accumulation amount of the next preset adjacent time node according to the preset time node sequence; when the accumulated dust accumulation predicted by the cloth bag is larger than or equal to the threshold value of the maximum accumulated dust bearing capacity, recording a current preset time node, taking the current preset time node as a first preset time node, and generating a pulse valve activation instruction according to the first preset time node, wherein the pulse valve activation instruction is used for opening a pulse valve to perform flushing work.
In one embodiment, the method further comprises:
and taking the next time node adjacent to the first preset time node as an instruction activation time node, embedding the instruction activation time node into the pulse valve activation instruction, and generating a pulse valve activation instruction.
In this embodiment of the present application, the next-time node adjacent to the first preset time node is used as an instruction activation time node, and because when the accumulated dust accumulation of the cloth bag prediction is calculated, the maximum cloth bag dust accumulation prediction result of the next-time node adjacent to the first preset time node is already added, the next-time node adjacent to the first preset time node is accurate and reasonable as the instruction activation time node, and the instruction activation time node is embedded into the pulse valve activation instruction, so as to generate the pulse valve activation instruction. By generating the pulse valve activation command, support is provided for the next step pulse valve actuation control.
Transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform reverse airflow flushing treatment on the dust collection cloth bag under the instruction activation time node.
In the embodiment of the application, the pulse valve activation instruction is transmitted to the pulse valve control unit, and the pulse valve control unit is controlled to start the pulse valve to perform reverse airflow flushing treatment on the dust collection cloth bag under the instruction activation time node. The back air flow flushing time and the back air flow speed of the pulse valve are dust removal standard flushing parameters which meet the setting of the threshold value of the maximum dust accumulation bearing capacity. The method can solve the technical problem of lower dust removal control accuracy of the existing bag-type dust remover control method, and improves the dust removal control accuracy of the bag-type dust remover, so that the equipment quality damage to the dust remover is reduced and the service life of the dust remover is prolonged when the dust concentration is higher; when the dust concentration is low, unnecessary energy loss is reduced, and electric energy resources are saved.
In one embodiment, as shown in fig. 3, there is provided an intelligent control system for a dust collector based on dust concentration monitoring, the system being in communication connection with a dust concentration detector, an industrial camera, a pulse valve control unit, comprising: the dust data acquisition module 01, the threshold value determination module 02, the effective dust particle size ratio determination module 03, the standard dust concentration data generation module 04, the cloth bag prediction dust accumulation generation module 05, the pulse valve activation instruction generation module 06, the back air flow flushing processing module 07, wherein:
the dust data acquisition module 01 is used for acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet smoke of a target bag-type dust collector through the dust concentration detector, and the dust image data is obtained by acquiring images of the inlet smoke through the industrial camera;
the threshold determining module 02 is used for acquiring basic data information of a dust collection cloth bag of the target cloth bag dust collector, and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data;
The effective dust particle size ratio determining module 03 is used for performing dust particle size ratio analysis according to the dust image data and determining the effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold;
the standard dust concentration data generation module 04 is used for correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data;
the cloth bag prediction accumulated dust amount generating module 05 is used for predicting the cloth bag accumulated dust amount in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed, and generating a cloth bag prediction accumulated dust amount which is the sum of cloth bag accumulated dust amount prediction results in a plurality of preset time windows, wherein the preset time windows are the time intervals of adjacent preset time nodes;
the pulse valve activation instruction generation module 06 is configured to generate a pulse valve activation instruction when the predicted accumulated dust accumulation amount of the cloth bag meets the threshold value of the maximum accumulated dust bearing amount, where the pulse valve activation instruction includes an instruction activation time node;
The back air flow flushing processing module 07 is used for transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform back air flow flushing processing on the dust collection cloth bag under the instruction activation time node.
In one embodiment, the system further comprises:
the effective dust removal particle size threshold generation module is used for carrying out effective dust removal performance analysis on the dust removal cloth bag based on the material attribute and the density data to generate an effective dust removal particle size threshold;
the maximum accumulated dust bearing amount calculation module is used for calculating the maximum accumulated dust bearing amount of the single dust removal cloth bag based on the specification parameters, the material properties and the density data, and generating the maximum accumulated dust bearing amount of the single dust removal cloth bag;
the maximum dust accumulation bearing capacity threshold obtaining module is used for carrying out addition summation on the maximum dust accumulation bearing capacity according to the quantity information to obtain a maximum dust accumulation bearing capacity threshold.
In one embodiment, the system further comprises:
The gray dust image generation module is used for carrying out gray processing on the dust image data to generate a gray dust image;
the dust contour data generation module is used for carrying out dust contour feature extraction and edge fitting based on the gray dust image to generate a plurality of dust contour data;
the dust particle size data obtaining module is used for carrying out dust particle size calculation based on the dust profile data to obtain dust particle size data;
the effective dust particle size ratio obtaining module is used for marking the dust particle sizes smaller than the effective dust removal particle size threshold value in the dust particle size data as effective dust particle sizes, and taking the ratio of the effective dust particle size number to the dust particle size data number as the effective dust particle size ratio.
In one embodiment, the system further comprises:
the first preset time window acquisition module is used for acquiring a first preset time window, and the first preset time window is the time interval between a first preset time node and a second preset time node;
The standard dust concentration data acquisition module is used for acquiring first standard dust concentration data of the first preset time node and second standard dust concentration data of the second preset time node;
the first cloth bag dust accumulation amount prediction result obtaining module is used for inputting the first standard dust concentration data, the second standard dust concentration data and the inlet flue gas flow speed into a dust accumulation amount prediction model to obtain a first cloth bag dust accumulation amount prediction result;
and the cloth bag prediction accumulated dust accumulation generating module is used for generating the cloth bag prediction accumulated dust accumulation based on the first cloth bag accumulated dust accumulation prediction result.
In one embodiment, the system further comprises:
the maximum historical dust concentration data obtaining module is used for calling a dust removal operation log of the target bag-type dust remover and obtaining the maximum historical dust concentration data based on the dust removal operation log;
the maximum cloth bag dust collection amount prediction result generation module is used for generating a maximum cloth bag dust collection amount prediction result in a preset time window based on the maximum historical dust concentration data;
And the cloth bag prediction accumulated dust accumulation generating module is used for generating the cloth bag prediction accumulated dust accumulation based on the first cloth bag accumulated dust accumulation prediction result and the maximum cloth bag accumulated dust accumulation prediction result.
In one embodiment, the system further comprises:
the cloth bag prediction accumulated dust accumulation judging module is used for judging the cloth bag prediction accumulated dust accumulation according to the maximum accumulated dust bearing threshold;
the cloth bag prediction accumulated dust accumulation amount sequential judging module is used for sequentially judging the cloth bag prediction accumulated dust accumulation amount according to a preset time node when the cloth bag prediction accumulated dust accumulation amount is smaller than the maximum accumulated dust bearing amount threshold;
the pulse valve activation instruction generation module is used for recording a current preset time node as a first preset time node when the accumulated dust accumulation predicted by the cloth bag is larger than or equal to the threshold value of the maximum dust bearing amount, and generating a pulse valve activation instruction based on the first preset time node.
In one embodiment, the system further comprises:
the instruction activation time node obtaining module is used for taking the next adjacent time node of the first preset time node as an instruction activation time node, embedding the instruction activation time node into the pulse valve activation instruction and generating the pulse valve activation instruction.
In summary, compared with the prior art, the embodiments of the present disclosure have the following technical effects:
(1) The accuracy of dust removal control of the bag-type dust remover can be improved by generating a pulse valve activation instruction, so that the damage to the equipment quality of the dust remover is reduced and the service life of the dust remover is prolonged when the dust concentration is high; when the dust concentration is low, unnecessary energy loss is reduced, and electric energy resources are saved.
(2) The dust particle size identification is carried out on the flue gas image, the effective dust particle size ratio is determined, and the dust concentration data is corrected according to the effective dust particle size ratio, so that the accuracy of dust concentration data acquisition can be improved, and the accuracy of prediction of the dust accumulation of the cloth bag can be improved.
(3) The accuracy and efficiency of the bag dust accumulation prediction can be improved by constructing the dust accumulation prediction model based on the BP neural network and performing supervision training and verification on the dust accumulation prediction model based on model training sample data obtained by an industrial big data technology.
(4) The method has the advantages that the prediction result of the maximum cloth bag dust accumulation amount is generated to optimize the cloth bag predicted dust accumulation amount, so that the rationality of the cloth bag predicted dust accumulation amount can be improved, and the accuracy of dust removal control is further improved.
The above examples merely represent a few embodiments of the present disclosure and are not to be construed as limiting the scope of the invention. Accordingly, various alterations, modifications and variations may be made by those having ordinary skill in the art without departing from the scope of the disclosed concept as defined by the following claims and all such alterations, modifications and variations are intended to be included within the scope of the present disclosure.
Claims (8)
1. The intelligent control method of the dust remover based on the dust concentration monitoring is characterized in that the method is applied to an intelligent control system of the dust remover based on the dust concentration monitoring, and the system is in communication connection with a dust concentration detector, an industrial camera and a pulse valve control unit, and the method comprises the following steps:
acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet flue gas of a target bag-type dust collector through a dust concentration detector, and the dust image data is obtained by acquiring images of the inlet flue gas through an industrial camera;
Acquiring basic data information of a dust collection cloth bag of the target cloth bag dust collector, and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data;
performing dust particle size ratio analysis according to the dust image data, and determining an effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold;
correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data;
carrying out cloth bag dust collection amount prediction in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed, and generating cloth bag prediction dust collection amount, wherein the cloth bag prediction dust collection amount is the sum of cloth bag dust collection amount prediction results in a plurality of preset time windows, and the preset time windows are the time intervals of adjacent preset time nodes;
when the cloth bag predicted accumulated dust accumulation amount meets the maximum accumulated dust bearing amount threshold, generating a pulse valve activation instruction, wherein the pulse valve activation instruction comprises an instruction activation time node;
Transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform reverse airflow flushing treatment on the dust collection cloth bag under the instruction activation time node.
2. The method of claim 1, wherein the determining, based on the primary data information, an effective dust removal particle size threshold and a maximum dust loading threshold further comprises:
analyzing the effective dust removal performance of the dust removal cloth bag based on the material attribute and the density data to generate an effective dust removal particle size threshold;
calculating the maximum dust accumulation bearing capacity of the single dust collection cloth bag based on the specification parameters, the material properties and the density data, and generating the maximum dust accumulation bearing capacity of the single dust collection cloth bag;
and adding and summing the maximum dust accumulation bearing capacity according to the quantity information to obtain a maximum dust accumulation bearing capacity threshold.
3. The method of claim 1, wherein the performing a dust particle size ratio analysis from the dust image data and determining an effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold value further comprises:
carrying out graying treatment on the dust image data to generate a gray dust image;
Carrying out dust contour feature extraction and edge fitting on the basis of the gray dust image to generate a plurality of dust contour data;
performing dust particle size calculation based on the plurality of dust profile data to obtain a plurality of dust particle size data;
and marking the dust particle sizes smaller than the effective dust removal particle size threshold value in the dust particle size data as effective dust particle sizes, and taking the ratio of the effective dust particle size quantity to the dust particle size data quantity as the effective dust particle size ratio.
4. The method of claim 1, wherein predicting the amount of dust accumulation in the bag within a preset time window based on the standard dust concentration data and the inlet flue gas flow rate, generating the predicted amount of dust accumulation in the bag, further comprises:
acquiring a first preset time window, wherein the first preset time window is a time interval between a first preset time node and a second preset time node;
obtaining first standard dust concentration data of the first preset time node and second standard dust concentration data of the second preset time node;
inputting the first standard dust concentration data, the second standard dust concentration data and the inlet flue gas flow speed into a dust accumulation amount prediction model to obtain a first cloth bag dust accumulation amount prediction result;
And generating the cloth bag predicted dust accumulation amount based on the first cloth bag dust accumulation amount prediction result.
5. The method of claim 4, wherein the generating the bag-on-a-bag predicted dust accumulation based on the first bag-on-dust prediction result further comprises:
the dust removing operation log of the target bag-type dust remover is called, and the maximum historical dust concentration data is obtained based on the dust removing operation log;
generating a prediction result of the maximum cloth bag dust accumulation amount in a preset time window based on the maximum historical dust concentration data;
and generating the cloth bag predicted dust accumulation amount based on the first cloth bag dust accumulation amount prediction result and the maximum cloth bag dust accumulation amount prediction result.
6. The method of claim 1, wherein the generating a pulse valve activation instruction when the predicted cumulative amount of dust in the cloth bag meets the maximum dust bearing amount threshold value further comprises:
judging the predicted accumulated dust accumulation amount of the cloth bag according to the maximum accumulated dust bearing amount threshold;
when the cloth bag predicted accumulated dust amount is smaller than the maximum accumulated dust bearing amount threshold value, judging the cloth bag predicted accumulated dust amount in sequence according to a preset time node;
When the accumulated dust accumulation predicted by the cloth bag is larger than or equal to the threshold value of the maximum accumulated dust bearing capacity, recording the current preset time node as a first preset time node, and generating a pulse valve activation instruction based on the first preset time node.
7. The method of claim 6, wherein generating a pulse valve activation command based on the first preset time node further comprises:
and taking the next time node adjacent to the first preset time node as an instruction activation time node, embedding the instruction activation time node into the pulse valve activation instruction, and generating a pulse valve activation instruction.
8. Dust concentration monitoring-based intelligent control system for a dust remover, which is used for executing the steps in the dust concentration monitoring-based intelligent control method for a dust remover according to any one of claims 1 to 7, wherein the system is in communication connection with a dust concentration detector, an industrial camera and a pulse valve control unit, and comprises the following components:
the dust data acquisition module is used for acquiring dust concentration data and dust image data under a preset time node, wherein the dust concentration data is obtained by detecting the dust concentration of inlet smoke of a target bag-type dust collector through the dust concentration detector, and the dust image data is obtained by acquiring images of the inlet smoke through the industrial camera;
The threshold determining module is used for acquiring basic data information of a dust collection bag of the target bag-type dust collector and determining an effective dust collection particle size threshold and a maximum dust collection bearing capacity threshold based on the basic data information, wherein the basic data information comprises quantity information, specification parameters, material properties and density data;
the effective dust particle size ratio determining module is used for carrying out dust particle size ratio analysis according to the dust image data and determining the effective dust particle size ratio based on a dust particle size ratio analysis result and the effective dust removal particle size threshold;
the standard dust concentration data generation module is used for correcting the dust concentration data according to the effective dust particle size ratio to generate standard dust concentration data;
the cloth bag prediction accumulated dust amount generation module is used for predicting cloth bag accumulated dust amount in a preset time window based on the standard dust concentration data and the inlet flue gas flow speed to generate cloth bag prediction accumulated dust amount, and the cloth bag prediction accumulated dust amount is the sum of cloth bag accumulated dust amount prediction results in a plurality of preset time windows, wherein the preset time windows are the time intervals of adjacent preset time nodes;
The pulse valve activation instruction generation module is used for generating a pulse valve activation instruction when the cloth bag predicted accumulated dust amount meets the maximum accumulated dust bearing amount threshold value, wherein the pulse valve activation instruction comprises an instruction activation time node;
and the back air flow flushing processing module is used for transmitting the pulse valve activation instruction to the pulse valve control unit, and starting the pulse valve to perform back air flow flushing processing on the dust collection cloth bag under the instruction activation time node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410203558.3A CN117771841B (en) | 2024-02-23 | 2024-02-23 | Dust collector intelligent control method and system based on dust concentration monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410203558.3A CN117771841B (en) | 2024-02-23 | 2024-02-23 | Dust collector intelligent control method and system based on dust concentration monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117771841A true CN117771841A (en) | 2024-03-29 |
| CN117771841B CN117771841B (en) | 2024-05-28 |
Family
ID=90394758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410203558.3A Active CN117771841B (en) | 2024-02-23 | 2024-02-23 | Dust collector intelligent control method and system based on dust concentration monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117771841B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118749852A (en) * | 2024-09-06 | 2024-10-11 | 南京特沃斯清洁设备有限公司 | Floor washing data processing method and device for industrial dust polluted floor |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5711785A (en) * | 1995-10-26 | 1998-01-27 | Ormet Corporation | Method and apparatus for controlling the cleaning cycle of air filter elements and for predicting the useful life thereof |
| KR20100107762A (en) * | 2009-03-26 | 2010-10-06 | 현대제철 주식회사 | Apparatus for detecting damage of bag filter for dust collecting and method thereof |
| CN107907458A (en) * | 2017-12-21 | 2018-04-13 | 秦皇岛首钢华盛有限公司 | Deduster detection system |
-
2024
- 2024-02-23 CN CN202410203558.3A patent/CN117771841B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5711785A (en) * | 1995-10-26 | 1998-01-27 | Ormet Corporation | Method and apparatus for controlling the cleaning cycle of air filter elements and for predicting the useful life thereof |
| KR20100107762A (en) * | 2009-03-26 | 2010-10-06 | 현대제철 주식회사 | Apparatus for detecting damage of bag filter for dust collecting and method thereof |
| CN107907458A (en) * | 2017-12-21 | 2018-04-13 | 秦皇岛首钢华盛有限公司 | Deduster detection system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118749852A (en) * | 2024-09-06 | 2024-10-11 | 南京特沃斯清洁设备有限公司 | Floor washing data processing method and device for industrial dust polluted floor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117771841B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117771841B (en) | Dust collector intelligent control method and system based on dust concentration monitoring | |
| CN110861987B (en) | Elevator fault judgment logic verification method, system and storage medium | |
| CN115511398B (en) | Welding quality intelligent detection method and system based on time sensitive network | |
| KR20180080010A (en) | Filtration and Dust Collection System and Apparatus for controlling Dust Collection System | |
| CN113574480B (en) | Device for predicting equipment damage | |
| CN109603340A (en) | A kind of intelligent electric automation dedusting control system and method | |
| CN110738357A (en) | Method, device and system for predicting dust collection amount of coal yard and storage medium | |
| CN110727669A (en) | Device and method for cleaning sensor data of power system | |
| CN116381490A (en) | Push rod motor performance detection system and method based on data analysis | |
| CN117650790B (en) | Welding shielding gas measurement data compression storage method based on intelligent recognition of working conditions | |
| CN117679868B (en) | Leakage accurate positioning system and method for bag-type dust collector | |
| CN114723187A (en) | Intelligent tower crane, fault prediction method of intelligent tower crane and storage medium | |
| CN113535697B (en) | Climbing frame data cleaning method, climbing frame control device and storage medium | |
| CN108804796B (en) | Annular cooler air leakage rate detection method based on frequency spectrum characteristics | |
| CN110138812A (en) | Network Safety Analysis system | |
| CN118050591A (en) | Distribution network 10KV overhead line fault early warning and positioning system based on AI | |
| RU121944U1 (en) | AUTOMATED SYSTEM FOR IDENTIFYING FAULT SENSORS AMONG SENSORS INTENDED FOR CONTROL OF TECHNOLOGICAL PROCESSES | |
| CN116976531A (en) | Integrated management method and system for underground electric control equipment | |
| CN116329197A (en) | Production cleaning control method of filter antenna | |
| CN115508732A (en) | Battery pack service life prediction method and device | |
| CN116603322A (en) | Dust removal control method and device, dust removal equipment, computing equipment and storage medium | |
| CN118242337B (en) | Oil product monitoring method and system for hydraulic oil filtration | |
| CN117190370B (en) | Rolled copper foil processing device, method and storage medium | |
| CN118066647B (en) | Fan abnormality judgment method of digital fresh air purifier | |
| CN116150636B (en) | Fault monitoring method and system for transmission module |
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 |