CN115081156B - Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine - Google Patents
Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine Download PDFInfo
- Publication number
- CN115081156B CN115081156B CN202210857036.6A CN202210857036A CN115081156B CN 115081156 B CN115081156 B CN 115081156B CN 202210857036 A CN202210857036 A CN 202210857036A CN 115081156 B CN115081156 B CN 115081156B
- Authority
- CN
- China
- Prior art keywords
- ventilation
- self
- decision
- mine
- particle
- 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.)
- Active
Links
- 238000009423 ventilation Methods 0.000 title claims abstract description 324
- 238000000034 method Methods 0.000 title claims abstract description 80
- 239000002245 particle Substances 0.000 claims description 106
- 230000008569 process Effects 0.000 claims description 44
- 238000005457 optimization Methods 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 37
- 210000004556 brain Anatomy 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000012544 monitoring process Methods 0.000 claims description 22
- 150000001875 compounds Chemical class 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000003909 pattern recognition Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 230000033228 biological regulation Effects 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 11
- 239000000428 dust Substances 0.000 claims description 9
- 230000001276 controlling effect Effects 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 238000013178 mathematical model Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 230000009123 feedback regulation Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 6
- 230000008447 perception Effects 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 239000003245 coal Substances 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000006378 damage Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 231100000614 poison Toxicity 0.000 description 3
- 230000007096 poisonous effect Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 231100000331 toxic Toxicity 0.000 description 2
- 230000002588 toxic effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 101100049748 Archaeoglobus fulgidus (strain ATCC 49558 / DSM 4304 / JCM 9628 / NBRC 100126 / VC-16) wtpA gene Proteins 0.000 description 1
- 101100514057 Azotobacter vinelandii modE gene Proteins 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 101150103307 modA gene Proteins 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F1/00—Ventilation of mines or tunnels; Distribution of ventilating currents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Ventilation (AREA)
- Computing Systems (AREA)
- Mining & Mineral Resources (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Fluid Mechanics (AREA)
Abstract
The invention belongs to the technical field of intelligent ventilation control of mines, and particularly relates to an intelligent ventilation control platform and a control method for a mine, which realize intelligent control of automatic sensing acquisition of ventilation parameters, automatic analysis and decision of ventilation states and automatic feedback execution of ventilation facilities.
Description
Technical Field
The invention belongs to the technical field of intelligent ventilation control of mines, and particularly relates to a self-sensing, self-decision and self-executing intelligent ventilation control platform and a control method for a mine, which realize intelligent control of automatic sensing acquisition of ventilation parameters, automatic analysis and decision of ventilation states and automatic feedback execution of ventilation facilities.
Background
The intellectualization of energy industry is a necessary trend of current energy development, and the intellectualization development of coal serving as main energy in China is already scheduled. However, compared with other industries, most coal mine enterprises in China are still in a state of manual and semi-manual mining, and the intelligent level is not high. The method is characterized in that the method comprises the following steps of detecting the occurrence of a large number of major accidents in the mine, and carrying out real-time reliable and stable adjustment according to requirements and disaster emergency intelligent control on a ventilation system in a disaster period.
In view of the development trend of coal intelligence, ventilation intelligence is important content of coal intelligence, and the technical core of ventilation intelligence is to realize unmanned autonomous execution of intelligent ventilation processes of a mine, such as accurate data perception, intelligent scheme decision and remote regulation control. The pattern recognition and intelligent decision algorithm is the core for realizing the technical contents. Mine ventilation pattern recognition is an important algorithm for ventilation intelligence, and the research is less. In 2014, the Luxin Mingzhi teaches a state identification method and a polymorphic automatic identification method for a mine ventilation system. According to the method, the roadway is classified, and the change of the wind resistance of the roadway is identified through the wind speed and temperature and humidity sensors of key places. The method mainly aims at identifying the wind resistance change of the mine ventilation system, and cannot identify other types of ventilation state changes. In 2018, a mine ventilation multi-stage mode identification method is provided by the aid of beam-start exceeding and the like. The multistage pattern recognition adopts hierarchical indexes such as disaster resistance, wind flow stability, fan operation efficiency, ton mine ventilation cost, ventilation engineering cost and the like, and then the pattern recognition judgment is realized through cluster analysis, weighted distance, fuzzy algorithm and the like. The method cannot effectively utilize sensor data of the intelligent mine, can only be applied to optimization of a manual regulation scheme, and cannot identify various early warnings, faults and catastrophes of the mine. The mine ventilation intelligent decision algorithm is one of mine ventilation intelligent core algorithms. The main methods for traditional mine ventilation scheme decision making fall into three categories: (1) a method for constructing a topological relation based on graph theory, such as a loop method, a path method and the like; (2) solving methods based on nonlinear mathematical programming, such as Lagrange multiplier method and the like; (3) and (3) a solving method based on evolutionary computation. The method has advantages and disadvantages, the adjusting process of the graph theory topological relation solution method depends on the participation of technicians, and the actual adjusting effect cannot reach an ideal value due to the change of the total wind resistance of the mine caused by one-time rheostatic resistance, and the method needs to be continuously adjusted until the requirement is met. The solving method of the mathematical programming is slow, and the problem of local optimization also exists. In recent years, with the development of evolutionary computation, intelligent algorithms such as Genetic Algorithm (GA), simulated annealing algorithm (SA) and particle swarm algorithm (PSO) are also applied to mine ventilation, but the decision speed and precision for large networks are low, and real-time application in actual sites is difficult. The prior art has the defects that the key algorithm nodes of mine intelligent ventilation cannot be communicated, and self-perception, self-decision and self-execution cannot be realized.
Disclosure of Invention
The invention provides a self-sensing and self-decision self-executing intelligent ventilation management and control platform and a management and control method for a mine, aiming at solving the problem that an intelligent ventilation management and control platform capable of automatically sensing and acquiring parameters, analyzing decisions and remotely feeding back and adjusting does not exist in the existing intelligent ventilation field of the mine.
The invention is realized by adopting the following technical scheme:
a self-perception, self-decision and self-execution intelligent mine ventilation management and control platform comprises:
the accurate sensing module is used for acquiring various ventilation parameters of a ventilation pipe network in real time, cleaning the acquired parameters to form basic data and uploading the basic data to a mine ventilation brain system;
the mine ventilation brain system is used for analyzing the basic data provided by the accurate sensing module in real time, identifying the operation mode of the ventilation system, generating a decision scheme and transmitting the decision scheme to the feedback adjusting module,
the mine ventilation brain system comprises a ventilation pattern recognition module and a decision-making module,
and the feedback adjusting module is used for receiving the decision-making scheme and controlling the ventilation facility to adjust the ventilation system.
Further, the accurate sensing module comprises:
the ventilation parameter monitoring module is used for monitoring the wind speed, wind pressure, gas type and gas temperature and humidity in a ventilation pipe network;
the ventilation power monitoring module is used for monitoring the operation parameters and the control parameters of the ventilation facility, and comprises operation air quantity, operation negative pressure, operation power, motor power, revolution and start-stop information;
the ventilation structure monitoring module is used for monitoring the opening and closing state, the opening area, the air leakage quantity and the pressure difference of the air door;
and the dust monitoring module is used for monitoring the dust concentration of an operation site and an air return roadway.
Furthermore, the ventilation parameter monitoring module comprises a wind speed sensor, a wind pressure sensor, a gas sensor and a gas temperature and humidity sensor which are arranged in a mine ventilation pipe network; the ventilation power monitoring module comprises an air speed sensor, an air pressure sensor, a motor parameter sensor, a rotating speed sensor and a start-stop sensor which are arranged on the ventilator accessory device.
Further, the mine ventilation brain system further comprises:
a ventilation system three-dimensional stereogram dynamic visualization module used for realizing the front-end display of a true three-dimensional ventilation system, realizing the fine modeling and rendering of three-dimensional primitives and the dynamic real-time display of ventilation sensor data,
and the network resolving simulation module is used for realizing the simulation calculation of the wind direction and the wind volume of the whole mine tunnel and the operation condition of the ventilator according to the wind resistance of the tunnel or the data of the sensor and providing another basic data for the ventilation mode identification.
Furthermore, the ventilation mode identification module is composed of a multi-channel parallel fuzzy detector, and the multi-channel parallel fuzzy detector comprises a ventilation power detector, a ventilation resistance detector, a ventilation structure detector, an air volume supply-demand ratio detector, a roadway deformation detector, a fire detector, a dust hazard detector and a gas detector.
Further, the decision module comprises a scheme optimization decision module and an emergency plan decision module,
the scheme optimization decision module is used for controlling abnormal ventilation by taking the controlled air volume as a solution, and realizing the search of an optimal solution between ventilation power consumption and air volume demand of the ventilation system by initializing a target function and calculating the regulation scheme of the ventilation system through a parallel-computing backbone particle swarm algorithm;
the emergency plan decision module is used for regulating and controlling the air volume as a solution to regulate and control abnormal ventilation or disaster change.
Further, the mathematical model (1) of the ventilation pattern recognition module is represented as follows:
in the formula (I), the compound is shown in the specification,χ det is a detectordetThe output ventilation modes comprise normal, early warning, catastrophe and failure modes; taking a maximum membership degree mode;σ det mod[] is a detectordetMode(s) formodA membership function of;Xfor the input feature, different detectors read different sensor data as input values.
Further, the solution optimization decision module comprises the following calculation process,
in the formula (I), the compound is shown in the specification,
the expression of the objective function for the solution optimization decision consists of weighted economic terms and safety terms by solving for min
Obtaining an optimal scheme;ωas a weight of the ventilation power consumption term, 0<ω<1；ζAn economic term expression of the objective function;ψis the expression of the safety item of the objective function;kthe number of ventilators;lthe number of wind utilization places;q af for ventilatorsaAir volume of (m) 3 /s；
For ventilatorsaA wind pressure characteristic function of;
for ventilatorsaA power characteristic function of;εa minimum value that avoids the denominator being 0;q bs to place using windbAir supply amount of (m) 3 /s；q bl To place using windbLower limit of air volume, m 3 /s；q bu For using wind placebUpper limit of air volume of (m) 3 /s；q br For using wind placebRequired air volume of (m) 3 /s。
Constantly updating particlesiAnd calculating an objective function of the corresponding position
All the particles are gathered to the optimal position continuously to realize optimization, and the number of the roadways is set tomThe number of the air doors to be adjusted is set tosNumber of particles set asz，
ParticlesiIs located bysThe equivalent wind resistance of each air door to be adjusted is as follows:
in the formula (I), the compound is shown in the specification,R i (t) Are particlesiFirst, thetThe location at the time of the secondary update;r 1 , r 2 ,…,r s for the equivalent wind resistance of all the air doors to be adjusted,
single particle oftThe +1 update equation is as follows:
in the formula (I), the compound is shown in the specification,R i (t+ 1) is thetParticles at +1 updateiThe sampling position of (a);Nis normally distributed;μ i (t) Is as followstMean of normal distribution after the secondary update;σ i (t) Is as followstThe variance of the normal distribution after the secondary update;
wherein, the mean and variance of the normal distribution are obtained by the following formula:
in the formula (I), the compound is shown in the specification,R i * (t) Is as followstParticles at time of secondary updateiThe optimal position of (a);R g * (t) Is as followstThe optimal position of the population during the secondary update,
solving for the second using a ventilation network solution algorithmtParticles at +1 updateiAir volume of all roadways:
in the formula (I), the compound is shown in the specification,Q i (t+1) Are particlesiFirst, thet+1 calculation of all tunnel air volumeq 1 , q 2 , … , q m Composition m 3 /s；
Calculating an algorithm for the ventilation network;
calculate the firstt+1 update times of population global optimal position and particleiOptimal position:
R g * (t+1) Is as followstThe global optimal position of the population after +1 update,R i * (t+1) Is as followst+1 particles after updateiIs located at a position which is optimal for the position of the sensor,Ris the position of the particles and is,
when the calculation reaches the maximum iteration step maxtOr value of an objective function
Stopping calculation after certain precision is reached, and enabling the equivalent wind resistance corresponding to the optimal position of the population at the momentR g * And converting the opening degree into the opening degree of the air door to form an optimization scheme.
Further, parallelizing the computational process of the solution optimization decisions using a parallel computing architecture comprising a particle layer, a computation layer, and a sharing layer,
the particle layer is composed of different processes, each process comprises a plurality of particles as basic units, all particle group processes do not directly communicate with each other, and the layer stores the second particle group processtCurrent positions of all particles after the second update
And optimum position
，i=1, 2, …, z；
The computing layer is connected with the particle layer and the sharing layer, information is collected from the sharing layer and the particle layer respectively, data exchange and high-speed parallel computing between the two layers are achieved, and a better computing result is fed back to the particle layer and the sharing layer; first, thetThe specific process of +1 update is as follows: (1) Information gathering, where processes in a compute layer gather globally optimal locations from a share layer
And global optimum
Reading the optimum position of each particle from the particle layer
Sum particle optimum
(ii) a (2) Particle position and objective function value calculation using the optimal position of the particle
And global optimal position
ComputingtPosition of particle at time +1
And further calculates the objective function value of the position
(ii) a (3) Updating the optimal position and the optimal value if the value of the objective function
Less than global optimum
Then will bet+1 times global optimum position
Is arranged as
Global optimum value set to
(ii) a If the value of the objective function
Less than optimum for the particle
Then will bet+1 order particle optimum position
Is arranged as
Optimum value of particle
Is arranged as
；
The sharing layer is responsible for storing the global optimal position and the global optimal value, is a shared memory among a plurality of processes, ensures the communication safety among the processes by a process lock, and only one process can operate the shared memory at the same time.
Furthermore, the parallel computing architecture is deployed on the cloud server, and high-speed decision computing is achieved according to server load balancing.
Further, mine intelligence management and control platform still include:
and the knowledge database module is used for storing the structured and unstructured data of the ventilation system, receiving and storing the real-time data acquired by the accurate sensing module and the decision scheme data of the decision module in real time.
Furthermore, the intelligent mine management and control platform further comprises a ventilation pipe network model, wherein the ventilation pipe network model is a physical model built according to real mine scaling and is used for intelligent ventilation teaching and scientific research.
A self-perception, self-decision and self-execution intelligent mine ventilation management and control method is completed based on a self-perception, self-decision and self-execution intelligent mine ventilation management and control platform and comprises the following steps:
s1, a precise sensing module collects various ventilation parameters of a ventilation pipe network in real time, and the collected parameters are subjected to data cleaning and uploaded to a mine ventilation brain system;
s2, analyzing and recognizing a ventilation mode in real time by a mine ventilation brain system, generating a decision scheme, and transmitting the decision scheme to a feedback regulation module;
and S3, the feedback adjusting module receives the decision scheme and controls the ventilation facility to adjust the ventilation system.
Further, in the step S2, the ventilation mode output by each detector is obtained through the mathematical model (1) in the ventilation mode recognition, which includes normal, early warning, failure, catastrophe, and the like.
Further, when the operation mode of the ventilation system in the step S2 is identified as abnormal ventilation which can use the air volume regulation and control as a solution, a decision scheme for scheme optimization is generated; and the operation mode of the ventilation system is identified as a decision scheme for generating an emergency plan when the ventilation abnormity or catastrophe which is difficult to solve by regulating and controlling the air volume is taken as a solution.
The mine ventilation brain system integrates an intelligent ventilation algorithm and visual software, the accurate sensing module collects parameters of a ventilation system in real time and uploads the parameters to the mine ventilation brain system for decision analysis, and the feedback adjusting module executes an adjusting instruction of the mine ventilation brain system, so that the basic requirements of real-time intelligent ventilation data sensing, analysis decision, remote execution and knowledge storage are met. Real-time parameters are obtained through the accurate sensing module, states of ventilation systems are analyzed and recognized through a mine ventilation brain system, a decision scheme is given, ventilation processes such as various mine ventilation modes, working face ventilation modes, normal ventilation of mines, full mines and local headwind are simulated through the opening and closing states of air adjusting doors, and disaster relief decisions of fault and catastrophe processes can be restored.
The intelligent ventilation sensing decision-making implementation method can realize the intelligent ventilation sensing decision-making implementation process of the mine, the platform has the advantages of practical fit, wide application range, strong applicability, strong expandability and the like, and ideas and products are provided for related research and application of intelligent ventilation of the mine.
The following describes in detail the change of ventilation mode and the implementation of local wind reversal of the intelligent ventilation management and control platform through the accompanying drawings and related embodiments.
Drawings
Fig. 1 is a diagram of the logical relationship of each part of the intelligent ventilation control platform.
Fig. 2 is a flow chart of ventilation pattern recognition.
Fig. 3 is a diagram of an intelligent decision-making parallel computation architecture for ventilation.
Fig. 4 is a flow chart of ventilation scheme optimization decision.
Fig. 5 shows the sensing, decision and execution scenario logic of the intelligent ventilation control platform.
Fig. 6 shows the central parallel ventilation mode and the main ventilation route of the intelligent ventilation management and control platform.
Fig. 7 shows the diagonal ventilation mode of the two wings of the intelligent ventilation control platform and the main ventilation route thereof.
FIG. 8 is a partial headwind forward ventilation path for a work surface.
Fig. 9 is a ventilation route after local headwind of the working face.
In the figure:
1-wind cave, ventilator and accessory device; 2-remote control of the air door;
3-closable air shaft (open); 4-closable air shaft (closed).
Detailed Description
The present invention will now be described more fully hereinafter with reference to the accompanying drawings and examples, in which it is to be understood that the examples described are only a few, but not all, of the specific embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
A self-perception, self-decision and self-execution intelligent ventilation control platform for a mine comprises a mine ventilation brain system, an accurate perception module, a feedback regulation module and a knowledge database.
The mine ventilation brain system is the core of the whole ventilation control platform, and provides an intelligent ventilation algorithm and visual software support for the platform. The accurate sensing module collects various ventilation parameters of a ventilation pipe network in real time, and the collected parameters are subjected to data cleaning and uploaded to a mine ventilation brain system and a knowledge database. The mine ventilation brain system analyzes and identifies the operation mode of the ventilation system in real time and generates a decision-making scheme, the mode and the scheme obtained through analysis are transmitted to the feedback adjusting module, the feedback adjusting module controls ventilation facilities or a ventilation machine to adjust the ventilation system, the knowledge database stores the structured and unstructured data of the ventilation system, and receives and stores the sensor multi-source heterogeneous real-time data collected by the accurate sensing module and the decision-making scheme data of the decision-making control module in real time.
The mine ventilation brain system integrates functions of ventilation system three-dimensional stereogram dynamic visualization, network resolving simulation, ventilation mode identification, scheme optimization decision, emergency plan decision and the like. Wherein the ventilation pattern recognition and scheme optimization decision is the core function of the system.
1. Ventilation pattern recognition
Ventilation mode identification is an algorithm that detects the operating mode of the ventilation system in real time based on sensor data.
Fig. 2 shows a flow chart of ventilation pattern recognition. The mode identification is formed by a multi-channel parallel fuzzy detector, and comprises a ventilation power detector, a ventilation resistance detector, a ventilation structure detector, an air volume supply-demand ratio detector, a roadway deformation detector, a fire detector, a dust hazard detector and a gas detector, wherein each detector is formed by different nonlinear membership functions and is used for detecting different modes such as normal, early warning, fault, catastrophe and the like, and a mathematical model is expressed as follows:
in the formula (I), the compound is shown in the specification,χ det is a detectordetThe output ventilation mode comprises a normal mode, an early warning mode, a fault mode and a catastrophe mode corresponding to each detector; the V-shaped is a mode for taking the maximum membership degree;σ det mod[] is a detectordetMode(s)modA membership function of;Xfor the input feature, different detectors read different sensor data as input values.
DetectordetThe output ventilation mode comprisesχ Ventilation power = normal "," early warning "," catastrophe "or" failure "),χ Resistance to ventilation = normal "," early warning "," catastrophe "or" failure "),χ Ventilation structure = 'normal', 'early warning', 'catastrophe' or 'failure'、χ Air quantity supply-demand ratio = "normal", "early warning", "catastrophic" or "failure"、χ Deformation of tunnel = 'normal', 'early warning', 'catastrophe' or 'failure'、χ Fire hazard = normal "," early warning "," catastrophe "or" failure "),χ Dust damage = normal "," early warning "," catastrophe "or" failure "),χ Gas (es) = normal "," early warning "," catastrophic "or" failure ".
After the ventilation mode identification is completed, a scheme optimization decision or an emergency plan decision method is selected in a knowledge database in a rule retrieval, matching or reasoning mode. Scheme optimization decision is used for regulation and control of ventilation abnormal mode with regulation and control of air volume as solution, including ventilation power detector abnormalityχ Ventilation power Abnormality of the = fault and ventilation supply-demand detectorχ Air quantity supply-demand ratio = 'fault' and other solutions for regulating air volumeVentilation anomaly of solutionχ Gas (es) = faultχ Dust = failure. Example 3 is an abnormality of the ventilation power detector and an abnormality of the ventilation demand-supply ratio detector. The emergency plan decision is expert experience recorded in a knowledge base, aims at ventilation regulation and control of abnormal ventilation or catastrophe modes which are difficult to solve by a scheme optimization decision algorithm, and comprisesχ Resistance to ventilation = faultχ Ventilation structure = faultχ Deformation of roadway = faultχ Fire hazard In the case of a failure of the device,χ ventilation power (ii) = "catastropheχ Resistance to ventilation (ii) = "catastropheχ Ventilation structure (ii) = "catastropheχ Air quantity supply-demand ratio =' catastropheχ Deformation of tunnel =' catastropheχ Fire hazard (ii) = "catastropheχ Gas (es) =' catastropheχ Dust (I) and (II) = "catastrophic"; the ventilation resistance detector is abnormal in example 1, and the fire detector is abnormal in example 2.
The rest of normal and early warning can not trigger action, but the early warning can display early warning information on a three-dimensional interface.
Scheme optimization decision
With the advancement and succession of face excavation, it is difficult to ensure that the original ventilation scheme is still suitable for the changed ventilation system. The scheme of the mine ventilation system is difficult to make into consideration of the ventilation power consumption or the air quantity needed by an air utilization place, and the unreasonable mine ventilation scheme can cause huge resource waste and even bring potential safety hazards. And in the scheme optimization decision, when the air volume is adjusted daily, the ventilation power consumption and the air volume demand of a ventilation system are ensured to find an optimal solution, so that the system is in an optimal state all the time. And when the ventilation power detector detects that the power consumption of the main ventilator is abnormal or the ventilation supply-demand ratio detector detects that the air supply quantity of the wind using place is abnormal, calling a scheme optimization decision algorithm to optimize the ventilation scheme. The algorithm content is as follows:
constructing an objective function based on economy (ventilation power consumption) and safety (air demand):
in the formula (I), the compound is shown in the specification,
the expression of the objective function for scheme optimization decision-making is composed of weighted economic terms and safety terms, and is obtained by solving min
Obtaining an optimal scheme;ωas a weight of the ventilation power consumption term, 0<ω<1；ζAn economic term expression of the objective function;ψis the expression of the safety item of the objective function;kthe number of ventilators;lthe number of wind sites;q af for ventilatorsaAir volume of (c), m 3 /s；
For ventilatorsaA wind pressure characteristic function of;
for ventilatorsaA power characteristic function of (a);εa minimum value to avoid the denominator being 0;q bs to place using windbAir supply amount of (m) 3 /s；q bl For using wind placebLower limit of air volume, m 3 /s；q bu To place using windbUpper limit of air volume of (c), m 3 /s；q br For using wind placebRequired air volume of (m) 3 /s。
And solving by using an improved backbone particle swarm optimization (BBPSO) to obtain an optimal decision scheme. Continuously updating particles by algorithmiAnd calculating an objective function of the corresponding position
All particles are optimized by continuously converging towards the optimal position. The number of the lanes is set asmTo be adjustedThe number of the air doors is set assThe number of particles is set toz。
ParticlesiIs located bysThe equivalent wind resistance of each air door to be adjusted is as follows:
in the formula (I), the compound is shown in the specification,R i (t) Are particlesiFirst, thetThe location at the time of the secondary update;r 1 , r 2 ,…,r s the equivalent wind resistance of all the air doors to be adjusted.
Single particle oftThe +1 update equation is as follows:
in the formula (I), the compound is shown in the specification,R i (t+ 1) is thetParticles at +1 updateiThe sampling position of (a);Nis normally distributed;μ i (t) Is as followstMean of normal distribution after the secondary update;σ i (t) Is as followstThe variance of the normal distribution after the secondary update;
wherein, the mean and variance of the normal distribution are obtained by the following formula:
in the formula (I), the compound is shown in the specification,R i * (t) Is as followstParticles at time of secondary updateiThe optimal position of (a);R g * (t) Is as followstAnd (4) the optimal position of the population during secondary updating.
Solving using a ventilation network solution algorithmtParticles at +1 updateiAir volume of all tunnels:
in the formula (I), the compound is shown in the specification,Q i (t+1) Are particlesiFirst, thetThe air volume of all the roadways in +1 calculation is determined byq 1 , q 2 , … , q m Composition m 3 /s；
Calculating an algorithm for the ventilation network;
calculate the firstt+1 update population global optimal position and particleiOptimal position:
in the formula:R g * (t+ 1) is thetThe global optimal position of the population after +1 update,R i * (t+ 1) is thet+1 particles after updateiIs located at a position which is optimal for the position of the sensor,Ris the position of the particles and is,
when the calculation reaches the maximum iteration step maxtOr the value of an objective function
And stopping calculation after certain precision is achieved. Equivalent wind resistance corresponding to the optimal position of the population at the momentR g * And converting the opening degree into the opening degree of the air door to form an optimization scheme.
By using a process pool and a shared memory technology, a parallel computing architecture of a backbone particle swarm optimization decision algorithm is designed, the computing process is parallelized, the solving speed is greatly improved, and the real-time computation of ventilation decision is realized. As shown in fig. 3, the architecture includes a particle layer, a computation layer, and a shared layer in common.
The particle layer is composed of different processes, each process comprises a plurality of particles as basic units, the particle swarm processes do not directly communicate with each other, and the layer stores the first particletCurrent positions of all particles after the second update
And an optimum position
，i=1, 2, …, z；
The computing layer is connected with the particle layer and the sharing layer, information is collected from the sharing layer and the particle layer respectively, data exchange and high-speed parallel computing between the two layers are achieved, and a better computing result is fed back to the particle layer and the sharing layer; first, thetThe specific process of +1 updates is as follows: and (1) collecting information. Collecting globally optimal locations from a shared layer by processes in a compute layer
And global optimum
Reading the optimum position of each particle from the particle layer
And particle optimum
. And (2) calculating the position of the particle and the objective function value. Using optimal position of particles
And global optimal position
ComputingtPosition of particle at time +1
And further calculates the objective function value of the position
. And (3) updating the optimal position and the optimal value. If the value of the objective function
Less than global optimum
Then will be the firstt+1 Global optimal position
Is arranged as
Global optimum value set to
(ii) a If the value of the objective function
Less than optimum for the particle
Then will bet+1 order particle optimum position
Is arranged as
Optimum value of particle
Is arranged as
。
The sharing layer is responsible for storing the global optimal position and the global optimal value, is a shared memory among a plurality of processes, ensures the communication safety among the processes by a process lock, and only one process can operate the shared memory at the same time.
Fig. 4 is a flow chart of ventilation scheme optimization decision. The air quantity of the wind utilization place or the ventilation power consumption is unreasonable through the ventilation mode identification of the data acquired by the sensor. And starting scheme optimization decision calculation, initializing a target function, calculating a ventilation system adjusting scheme through a backbone particle swarm algorithm of parallel calculation, and distributing an instruction to the remote control equipment.
The feedback regulation module takes a PLC control system as a core, comprises an upper computer, a controller, a sensor and the like, is used for remotely executing commands of a mine ventilation brain system, also supports manual control through a control box, and comprises a variable-frequency main ventilator, a variable-frequency local ventilator, a remote control air door and a closable air inlet shaft. The mine ventilation brain system analysis accurate sensing module is used for collecting cleaned ventilation parameters, the mine ventilation brain system analyzes and makes a decision to provide a ventilation system adjusting scheme, and an instruction is distributed to the feedback adjusting module. The system can realize real-time regulation and distribution as required of the air quantity of the ventilation system by changing the working condition of the ventilator, the opening and closing quantity of the air door and the opening and closing state of the air shaft.
The ventilation parameter monitoring module is arranged in a mine ventilation pipe network, and the ventilation pipe network is a carrier of ventilation airflow and comprises various types of roadways such as a mining working face, a transportation main roadway, an air inlet and return roadway and the like. Hardware equipment such as accurate perception module, feedback adjustment module, calamity simulation module, industry looped netowrk and transmission substation have been arranged in the ventilation pipe network. The disaster simulation module can control the processes of mine dust damage, mine heat damage, gas explosion, coal and gas outburst, mine fire and the like at a specific position in a pipe network. The industrial ring network and the transmission substation are used for equipment communication and provide a reliable channel for data transmission. When the intelligent mine ventilation management and control platform is used for intelligent ventilation teaching and scientific research, the intelligent mine ventilation management and control platform further comprises a ventilation pipe network model, wherein the ventilation pipe network model is built according to the real mine scale, and the ventilation pipe network model is generally 1.
The ventilator and the air door are remotely controlled by the mine ventilation brain system, different combination changes of the fan blade angle and the air door opening and closing modes are completed, and various mine ventilation modes, working face ventilation modes, simulation of mine wind-back and the like can be realized.
1. Various mine ventilation modes can be realized by changing the states of the corresponding air doors: (1) diagonal (2) regional (3) central parallel (4) hybrid.
2. Various working face ventilation modes can be simulated by changing the corresponding damper states, such as: u-shaped, Z-shaped and Y-shaped.
3. The full mine counter-wind and the local counter-wind can be realized by changing the angle of the fan blades and the corresponding air door state.
The above instructions are realized by depending on the designed air door arrangement scheme of the ventilation pipe network.
The knowledge database accesses real-time sensor data, knowledge data and the like generated by various information systems of the mine according to a uniform format, provides the real-time sensor data, the knowledge data and the like for various application systems through a uniform data access interface in a service mode, and completes the rapid exchange of real-time knowledge data and historical knowledge data.
Example 1: ventilation mode change-central parallel → diagonal two wings
The technical route of example 1 is: precise data perception and acquisition → ventilation mode identification → ventilation resistance detector abnormity → knowledge database matching → emergency plan decision making
A central parallel ventilation mode is adopted in a newly built mine, and air inlet and return shafts are all positioned in an industrial square. However, as mining progresses, the working face is further away from the industrial square, so that the ventilation route becomes longer, the ventilation resistance is increased, and at the moment, the ventilation mode needs to be changed into a two-wing diagonal mode, and the ventilation resistance is reduced. The intelligent ventilation management and control platform can simulate the scene.
As shown in fig. 6, the ventilation mode of the intelligent ventilation control platform is a central parallel type. The central parallel ventilation mode is a mine ventilation mode in which the air inlet shaft and the air return shaft are positioned in the center of the system. Two air inlet shafts are opened, one air inlet shaft is closed, a central parallel ventilation mode that the two air inlet shafts in the center of the system are formed through a specific air door regulation scheme, and the right wing ventilator is communicated with the air return shaft in the center of the system is formed. The major ventilation paths in the figure show that the ventilation circuit is long and the resistance is high.
The method comprises the following steps: the accurate sensing module obtains time sequence data of wind speed and wind pressure through the wind speed and wind pressure sensors arranged on the main ventilator and the main ventilation route, and performs data cleaning on the wind speed and wind pressure sensor data. The cleaning process mainly comprises data abnormal value detection and filtering smoothing processing.
Step two: and uploading the cleaned data to a mine ventilation brain system, and calling a ventilation mode recognition algorithm to recognize the state of the ventilation system. After the monitoring values of the wind speed and the wind pressure sensor are input into the ventilation resistance detector, whether the resistance of the whole ventilation pipe network meets a reasonable resistance distribution range can be judged through the following formula:
in the formula (I), the compound is shown in the specification,χ 1 is a ventilation resistance detector;Vthe monitoring value is m/s of the wind speed sensor;Pis the monitoring value Pa of the wind pressure sensor.
When in useχ 1 And the condition of the air conditioner is that the air conditioner is about to or exceeds a reasonable resistance range when the condition of the air conditioner is not satisfied.
Step three: and inputting the state recognition result into a knowledge database, and triggering an emergency plan event that the ventilation mode of the whole mine is changed from a central parallel mode to a two-wing diagonal mode through retrieval, matching or reasoning rules.
Step four: and the action instructions are distributed to related ventilation facilities in the ventilation pipe network through the feedback adjusting module, and the executed result and the executed ventilation system data are fed back to the mine ventilation brain system after the execution is finished and are stored in the knowledge database.
As shown in fig. 7, the ventilation mode of the intelligent ventilation control platform is a two-wing diagonal mode. Two air inlet shafts are opened, one air inlet shaft is closed, and a specific air door regulating scheme (the air door on a ventilation route in the figure is opened) forms a two-wing diagonal ventilation mode that the air inlet shaft is positioned in the center of the system, and the air return shafts are respectively positioned on the left wing and the right wing. It can be seen from the main ventilation route in the figure that the ventilation route is greatly shortened and the resistance is reduced.
Example 2: local headwind of working face in fire period
The technical route of the second embodiment is as follows: data accurate perception acquisition → ventilation pattern recognition → fire detector abnormality → knowledge database matching → emergency plan decision
Local headwind generally occurs in a fire scene, toxic and harmful gas can be prevented from flowing to an operation place or a place where people are located, and the method is an effective means for mine disaster emergency rescue.
Taking the working surface of the left wing ventilation system as an example, as shown in fig. 8. The fire hazard takes place in flame sign department, observes the wind current direction, and the poisonous and harmful gas that the fire hazard formed will move to the working face, and the workman of working face will receive poisonous and harmful gas's harm. At the moment, the air door near the working face must be regulated and controlled, the air flow direction is changed from upwind to downwind, the fresh air flow can be effectively ensured to flow into a working place, the poisonous and harmful gas is prevented from being poured into the working face, casualties are avoided, and precious time is provided for mine emergency rescue. The intelligent ventilation control platform for the mine can simulate the process of fire disaster and ventilation emergency rescue.
The method comprises the following steps: the accurate sensing module acquires real-time wind speed, temperature, humidity and each gas concentration time sequence data by deploying wind speed, temperature and humidity and gas sensors near the working face and the working face crossheading, and monitors the working state of the working face in real time.
Step two: and uploading the cleaned data to a mine ventilation brain system, and calling a ventilation mode recognition algorithm to recognize the state of the ventilation system. When the wind speed, the temperature and the humidity and the monitoring values of the gas sensors are input into a fire detector, whether a fire disaster occurs or not and the position and the grade of the disaster can be judged according to the following formula.
In the formula (I), the compound is shown in the specification,χ 2 a fire detector;Vis the monitoring value of the wind speed sensor, m 3 /s；TThe temperature is the monitoring value of a temperature sensor, DEG C;Cis the monitoring value of the gas sensor.
Step three: when the temperature is higher than the set temperatureχ 2 If the condition is not critical, the state recognition result is input to the knowledge databaseAnd triggering an emergency plan event of local headwind of the working face through retrieval, matching or reasoning rules.
Step four: and the feedback adjusting module is used for distributing the action instruction to related air doors near the working face, confirming whether the place where the working face personnel is located is safe or not after the execution is finished, and generating a next-step emergency strategy, such as calculating a disaster avoiding route and the like. And feeding back the execution result and the executed ventilation system data to the mine ventilation brain system, and storing the ventilation system data into a knowledge database.
As shown in fig. 9, the working face can be ventilated from local headwind of upward ventilation to downward ventilation only by changing the opening and closing conditions of the four air doors. At the moment, toxic and harmful gas generated by fire disaster can not be transported to the operation site, and the safety of operation personnel can be ensured.
Example 3: normal ventilation period scheme optimization decision
The technical route of the third embodiment is as follows: precise perception and collection of data → ventilation pattern recognition → ventilation power or ventilation supply-demand ratio detector abnormity → knowledge database matching → scheme optimization decision
And the normal ventilation period scheme optimization decision is to perform optimization regulation and control on the ventilation system daily, so that the ventilation system is in the state of optimal economy and highest safety all the time. The scheme optimization decision process is illustrated by way of example.
The method comprises the following steps: the accurate sensing module monitors the working condition, the running power consumption and the efficiency of the main ventilator in real time through the wind speed, the wind pressure and the motor parameter sensors arranged at the main ventilator, and monitors the wind speed, the gas, the temperature and the humidity of the working surface and the actual wind supply quantity of the working surface in real time through the sensors arranged at wind using places of each working surface.
Step two: and uploading data such as working condition, power consumption and efficiency of the main ventilator and wind demand and wind supply data of each working face to a mine ventilation brain system, and calling a ventilation power detector and a supply-demand ratio detector to perform ventilation mode identification.
In the formula (I), the compound is shown in the specification,χ 3 is a ventilation power detector;χ 4 a supply-demand ratio detector for ventilation;Wis the main ventilator power, kW;ηefficiency of the main ventilator,%;Lthe number of working people on the working face;
step three: when the temperature is higher than the set temperatureχ 3 Orχ 4 And when the signals are out of order, calling an intelligent decision algorithm of the scheme. Initializing an objective function, a global optimum and an optimum location, andzparticles of each particlesThe wind resistance of each adjustable air door. The particle set is as follows:
step four: will be provided withzDistributing the particles to multi-core CPU, and generatingpParallel computing pool of processes, each process being assignedz/pThe individual particles were counted.
Step five: respectively calculatezIndividual optimum value of each particle
Individual optimum positionR i * Global optimum of particle swarm
And global optimal positionR g * . And updating the current position of the individual according to the updating rule, and updating the optimal value and the optimal position of the individual and the population. First, thetThe +1 parameter update calculation procedure is as follows:
step six: repeat without interruptionStep five, when the global optimum value
Reaching a predetermined requirement or exceeding a certain number of iteration steps maxtAnd then stopping calculation, and recording the global optimal position at the moment:
step seven: will be provided withR g * The wind resistance of each air door to be adjusted is converted into a specific air door adjusting opening, and each air door adjusting instruction is distributed through the feedback adjusting module. And after the execution is finished, the execution result and the executed ventilation system data are fed back to the mine ventilation brain system and are stored in a knowledge database.
Claims (10)
1. A self-perception self-decision self-execution intelligent mine ventilation and control system is characterized by comprising:
the accurate sensing module is used for acquiring various ventilation parameters of a ventilation pipe network in real time, cleaning the acquired parameters to form basic data and uploading the basic data to a mine ventilation brain system;
the mine ventilation brain system is used for analyzing the basic data provided by the accurate sensing module in real time, identifying the operation mode of the ventilation system and generating a decision scheme, transmitting the decision scheme to the feedback adjusting module,
the mine ventilation brain system comprises a ventilation pattern recognition module and a decision-making module,
the ventilation pattern recognition module is composed of a multi-channel parallel fuzzy detector, and a mathematical model (1) of the ventilation pattern recognition module is expressed as follows:
in the formula (I), the compound is shown in the specification,χ det is a detectordetThe ventilation mode of the output is set as,including normal, early warning, catastrophe and failure modes; taking a maximum membership degree mode;σ det mod[] is a detectordetMode(s) formodA membership function of (c);Xfor input features, different detectors read different sensor data as input values;
a feedback adjusting module for receiving the decision-making scheme and controlling the ventilation facility to adjust the ventilation system,
and the knowledge database module is used for storing the structured and unstructured data of the ventilation system, receiving and storing the real-time data acquired by the accurate sensing module and the decision scheme data of the decision module in real time.
2. The intelligent ventilation and control system for the mine, which is self-sensing, self-decision making and self-execution according to claim 1, is characterized in that the accurate sensing module comprises a ventilation parameter monitoring module and a ventilation power monitoring module, wherein the ventilation parameter monitoring module comprises a wind speed sensor, a wind pressure sensor, a gas sensor and a gas temperature and humidity sensor which are arranged in a mine ventilation pipe network; the ventilation power monitoring module comprises an air speed sensor, an air pressure sensor, a motor parameter sensor, a rotating speed sensor and a start-stop sensor which are arranged on the ventilator accessory device.
3. The intelligent self-sensing, self-decision and self-execution mine ventilation and control system according to claim 1 or 2, wherein the multichannel parallel fuzzy detector comprises a ventilation dynamic detector, a ventilation resistance detector, a ventilation structure detector, an air volume supply-demand ratio detector, a roadway deformation detector, a fire detector, a dust detector and a gas detector.
4. The mine intelligent ventilation and control system with self-perception, self-decision and self-execution as claimed in claim 3, wherein the decision module comprises a plan optimization decision module and an emergency plan decision module,
the scheme optimization decision module is used for adjusting and controlling a ventilation mode when ventilation is abnormal by taking the adjustment and control of air volume as a solution, and realizing the search of an optimal solution between ventilation power consumption and air volume demand of a ventilation system by initializing a target function and calculating a ventilation system adjustment scheme through a parallel-computing backbone particle swarm algorithm;
the emergency plan decision module is used for regulating and controlling the air volume as a solution to regulate and control the ventilation mode during abnormal ventilation or catastrophe which is difficult to solve.
5. The intelligent mine ventilation and control system with self-perception, self-decision and self-execution functions as claimed in claim 4, wherein the solution optimization and decision module comprises the following calculation processes:
in the formula (I), the compound is shown in the specification,
the expression of the objective function for the solution optimization decision consists of weighted economic terms and safety terms by solving for min
Obtaining an optimal scheme;ωas a weight of the ventilation power consumption term, 0<ω<1；ζAn economic term expression of the objective function;ψa security term expression that is an objective function;kthe number of ventilators;lthe number of wind utilization places;q af for ventilatorsaAir volume of (c), m 3 /s；
For ventilatorsaA wind pressure characteristic function of;
for ventilatorsaA power characteristic function of;εa minimum value to avoid the denominator being 0;q bs to place using windbAir supply amount of (m) 3 /s；q bl To place using windbLower limit of air volume, m 3 /s；q bu To place using windbUpper limit of air volume of (m) 3 /s；q br To place using windbAir volume required of (m) 3 /s;
Constantly updating particlesiAnd calculating an objective function of the corresponding position
All particles are gathered to the optimal position continuously to realize optimization, and the number of the roadways is set tomThe number of the air doors to be adjusted is set tosThe number of particles is set toz，
ParticlesiIs located bysThe equivalent wind resistance of each air door to be adjusted is as follows:
in the formula (I), the compound is shown in the specification,R i (t) Are particlesiFirst, thetThe location at the time of the secondary update;r 1 , r 2 ,…,r s for the equivalent wind resistance of all the air doors to be adjusted,
single particle oftThe +1 update equation is as follows:
in the formula (I), the compound is shown in the specification,R i (t+ 1) is thetParticles at +1 updateiThe sampling position of (a);Nis normally distributed;μ i (t) Is a firsttMean of normal distribution after the secondary update;σ i (t) Is as followstThe variance of the normal distribution after the secondary update;
wherein, the mean and variance of the normal distribution are obtained by the following formula:
in the formula (I), the compound is shown in the specification,R i * (t) Is as followstParticles at time of secondary updateiThe optimal position of (a);R g * (t) Is a firsttThe optimal position of the population during the secondary update,
solving using a ventilation network solution algorithmtParticles at +1 updateiAir volume of all tunnels:
in the formula (I), the compound is shown in the specification,Q i (t+1) Are particlesiFirst, thet+1 calculation of all tunnel air volumeq 1 , q 2 , … , q m Composition m 3 /s；
calculate the firstt+1 update times of population global optimal position and particleiOptimal position:
in the formula:R g * (t+ 1) is thetThe global optimal position of the population after +1 update,R i * (t+ 1) is thet+1 particles after updateiIs located in the optimum position of the beam path,Ris the position of the particles and is,
when the calculation reaches the maximum iteration step maxtOr value of an objective function
Stopping calculation after certain precision is reached, and enabling the equivalent wind resistance corresponding to the optimal position of the population at the momentR g * And converting the opening degree into the opening degree of the air door to form an optimization scheme.
6. The mine intelligent ventilation control system of self-perception self-decision self-execution according to claim 5, wherein the computational process of solution optimization decisions is parallelized using a parallel computing architecture comprising a particle layer, a computation layer and a sharing layer,
the particle layer is composed of different processes, each process comprises a plurality of particles as basic units, the particle swarm processes do not directly communicate with each other, and the layer stores the first particletCurrent positions of all particles after the second update
And an optimum position
，i=1, 2, …, z；
The computing layer is connected with the particle layer and the sharing layer, information is collected from the sharing layer and the particle layer respectively, data exchange and high-speed parallel computing between the two layers are achieved, and a better computing result is fed back to the particle layer and the sharing layer; first, thetThe specific process of +1 updates is as follows: (1) Information gathering, where processes in a compute layer gather globally optimal locations from a share layer
And global optimum
Reading the optimum position of each particle from the particle layer
Sum particle optimum
(ii) a (2) Calculating the position of the particle and the value of the objective function, using the optimal position of the particle
And global optimal position
Calculating outtPosition of particle at time +1
And then calculating the objective function value of the position
(ii) a (3) Updating the optimal position and the optimal value if the value of the objective function
Less than global optimum
Then will bet+1 Global optimal position
Is arranged as
Global optimum value set to
(ii) a If the value of the objective function
Less than optimum for the particle
Then will bet+1 order particle optimum position
Is arranged as
Optimum value of particle
Is arranged as
；
The sharing layer is responsible for storing the global optimal position and the global optimal value, is a shared memory among a plurality of processes, ensures the communication safety among the processes by a process lock, and only one process can operate the shared memory at the same time.
7. The intelligent ventilation and control system for mines with self-perception, self-decision and self-execution functions as claimed in claim 6, wherein the intelligent ventilation and control system for mines further comprises a ventilation pipe network model, and the ventilation pipe network model is a physical model built according to real mine scaling.
8. A self-perception self-decision self-execution intelligent ventilation control method for a mine, which is completed based on the self-perception self-decision self-execution intelligent ventilation control system for the mine according to one of claims 1 to 7, and is characterized by comprising the following steps:
s1, a precise sensing module collects various ventilation parameters of a ventilation pipe network in real time, and the collected parameters are subjected to data cleaning and uploaded to a mine ventilation brain system;
s2, analyzing and recognizing a ventilation mode in real time by a mine ventilation brain system, generating a decision scheme, and transmitting the decision scheme to a feedback regulation module;
and S3, the feedback adjusting module receives the decision scheme and controls the ventilation facility to adjust the ventilation system.
9. The intelligent ventilation control method for mines with self-perception, self-decision and self-execution according to claim 8 is characterized in that in the step S2, the ventilation mode recognition obtains the ventilation mode output by each detector through the mathematical model (1), wherein the ventilation mode includes normal, early warning, failure and catastrophe.
10. The intelligent ventilation control method for the mine, which is self-perception, self-decision and self-execution according to claim 9, is characterized in that when the operation mode of the ventilation system in the step S2 is identified as abnormal ventilation which can take the air volume regulation and control as a solution, a decision scheme for scheme optimization is generated; and the operation mode of the ventilation system is identified as a decision scheme for generating an emergency plan when the ventilation abnormity or catastrophe which is difficult to solve by regulating and controlling the air volume as a solution is solved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210857036.6A CN115081156B (en) | 2022-07-21 | 2022-07-21 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210857036.6A CN115081156B (en) | 2022-07-21 | 2022-07-21 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115081156A CN115081156A (en) | 2022-09-20 |
| CN115081156B true CN115081156B (en) | 2022-11-25 |
Family
ID=83260463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210857036.6A Active CN115081156B (en) | 2022-07-21 | 2022-07-21 | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115081156B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126658A (en) * | 2019-11-15 | 2020-05-08 | 太原理工大学 | Coal mine gas prediction method based on deep learning |
| CN112731889A (en) * | 2021-01-18 | 2021-04-30 | 太原理工大学 | Intelligent air regulation management system and regulation and control method thereof |
| CN112989533A (en) * | 2021-02-22 | 2021-06-18 | 中煤科工集团重庆研究院有限公司 | Mine series ventilation identification method based on component proton method |
| CN114627140A (en) * | 2022-05-16 | 2022-06-14 | 新风光电子科技股份有限公司 | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109958474A (en) * | 2019-03-18 | 2019-07-02 | 天地（常州）自动化股份有限公司 | Driving face in coal mine local ventilation intelligent control method and ventilated control system |
-
2022
- 2022-07-21 CN CN202210857036.6A patent/CN115081156B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126658A (en) * | 2019-11-15 | 2020-05-08 | 太原理工大学 | Coal mine gas prediction method based on deep learning |
| CN112731889A (en) * | 2021-01-18 | 2021-04-30 | 太原理工大学 | Intelligent air regulation management system and regulation and control method thereof |
| CN112989533A (en) * | 2021-02-22 | 2021-06-18 | 中煤科工集团重庆研究院有限公司 | Mine series ventilation identification method based on component proton method |
| CN114627140A (en) * | 2022-05-16 | 2022-06-14 | 新风光电子科技股份有限公司 | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter |
Non-Patent Citations (4)
| Title |
|---|
| Optimization of energy use for mine ventilation fan with variable speed drive;Vanguri Ranjith Babu .etc;《2016 International Conference on Intelligent Control Power and Instrumentation》;20170223;148-151 * |
| 煤矿通风系统现状及智能通风系统设计;杨杰等;《工矿自动化》;20151130(第11期);74-77 * |
| 矿井智能通风原理、关键技术及其初步实现;周福宝等;《煤炭学报》;20200630;第45卷(第6期);2225-2235 * |
| 面向通风智能化的风速传感器结构化数据降噪方法对比;张巍等;《中国安全生产科学技术》;20210831;第17卷(第8期);70-76 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115081156A (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102566576B (en) | Multiple inspection robot cooperative operation method for substation sequence control system | |
| CN110531029B (en) | Device for predicting air quality trend based on environmental protection Internet of things big data | |
| CN109028481A (en) | Unattended machine room control system and method of air conditioning system | |
| CN115963763A (en) | Mine intelligent ventilation regulation and control system based on digital twin and data driving | |
| CN103953393A (en) | Mine ventilation system partitioning stabilized dynamic monitoring and pre-warning system | |
| Ambroziak et al. | The PID controller optimisation module using Fuzzy Self-Tuning PSO for Air Handling Unit in continuous operation | |
| CN115081156B (en) | Self-perception, self-decision and self-execution intelligent ventilation control platform and control method for mine | |
| CN114581046A (en) | Data processing method based on big data and cloud computing and big data service platform | |
| CN115387836A (en) | System and method for intelligent decision and remote linkage based on mine ventilation system | |
| CN114647216A (en) | System and method for cooperatively controlling air cut-off of coal mine air shaft fan and regulating and controlling air quantity of roadway network | |
| CN115964503A (en) | Safety risk prediction method and system based on community equipment facilities | |
| KR20160091942A (en) | Method, system, and computer program product for analyzing production and/or process-engineering processes and/or process steps in a plant | |
| CN117151701A (en) | Industrial waste heat recycling system for cogeneration | |
| CN105116851B (en) | Hidden troubles removing information physical emerging system | |
| CN112821456B (en) | Distributed source-storage-load matching method and device based on transfer learning | |
| CN114118678B (en) | Iron works management system based on edge Internet of things and construction method thereof | |
| Taheri et al. | Real-world implementation of a cloud-based MPC for HVAC control in educational buildings | |
| CN113689064A (en) | Transparent transformer substation management system architecture | |
| Zhong et al. | Airflow optimizing control research based on genetic algorithm during mine fire period | |
| Wan | Design and optimization of intelligent ventilation system in coal mine | |
| CN117111540B (en) | Environment monitoring and early warning method and system for IO remote control bus module | |
| CN117557929B (en) | Unit collaborative optimization method based on multiple application scenes | |
| Coffey | Using building simulation and optimisation to calculate control lookup tables offline | |
| CN114756026B (en) | Inspection control system for experimental environment safety inspection | |
| AU2021103181A4 (en) | Air Conditioning Load Forecasting Method Based on Artificial Intelligence |
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 |