CN113868952A - Online detection method for temperature field and ring thickness distribution in rotary kiln - Google Patents

Online detection method for temperature field and ring thickness distribution in rotary kiln Download PDF

Info

Publication number
CN113868952A
CN113868952A CN202111146465.4A CN202111146465A CN113868952A CN 113868952 A CN113868952 A CN 113868952A CN 202111146465 A CN202111146465 A CN 202111146465A CN 113868952 A CN113868952 A CN 113868952A
Authority
CN
China
Prior art keywords
kiln
flow
temperature
layer
temperature field
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111146465.4A
Other languages
Chinese (zh)
Inventor
付冬梅
许晋豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology Beijing USTB
Shunde Graduate School of USTB
Original Assignee
University of Science and Technology Beijing USTB
Shunde Graduate School of USTB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology Beijing USTB, Shunde Graduate School of USTB filed Critical University of Science and Technology Beijing USTB
Priority to CN202111146465.4A priority Critical patent/CN113868952A/en
Publication of CN113868952A publication Critical patent/CN113868952A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
    • G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
    • G01B21/08—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness for measuring thickness
    • G01B21/085—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness for measuring thickness using thermal means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00—Thermometers specially adapted for specific purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • 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
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06F2119/08—Thermal analysis or thermal optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Optimization (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Molecular Biology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Fluid Mechanics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Muffle Furnaces And Rotary Kilns (AREA)

Abstract

The invention provides an on-line detection method for temperature field and ring thickness distribution in a rotary kiln, belonging to the technical field of cement production. The method comprises the following steps: historical data acquisition and dimension conversion are carried out on the measurable process variables in the industrial field, and a measurable process variable working condition set is constructed according to the historical data; establishing a space rectangular coordinate system and a solid geometry by a computational fluid mechanics simulation technology, and calculating three-dimensional temperature field data in the kiln under the working condition set of measurable process variables according to a rotary kiln mechanism model; sampling three-dimensional temperature field data under various working conditions along an X, Y, Z axis, and training a deep neural network to establish a kiln temperature field soft measurement model based on the deep neural network by combining measurable process variable data under the same working conditions; and establishing a soft measurement model of the thickness of the ring formation in the kiln through a heat transfer equation based on the temperature in the kiln detected on line. By adopting the method and the device, the technical problem that the temperature field and the thickness distribution of the ring in the rotary kiln cannot be detected can be solved.

Description

Online detection method for temperature field and ring thickness distribution in rotary kiln
Technical Field
The invention relates to the technical field of cement production, in particular to an online detection method for temperature field and ring thickness distribution in a rotary kiln.
Background
The cement industry is an important basic industry for national economic development and plays an important role in improving the aspects of civil life, economic construction and national defense safety. The cement production has the characteristics of high pollution, high energy consumption and high emission, but is also an important means for treating municipal waste and hazardous waste. The cement production process can be summarized as "two mills and one burning", wherein clinker calcination is the most critical production link. The rotary kiln is used as the core thermal equipment of a clinker calcining system, and the running state of the rotary kiln has important significance for ensuring production safety, improving product quality and realizing energy conservation and emission reduction.
The temperature field and the thickness of the ring formation in the kiln are important indexes for reflecting the running state of the rotary kiln. The clinker quality is reduced due to the low temperature of the burning zone, and serious ring formation is easily generated in the kiln due to the high temperature of the burning zone, so that the kiln lining is damaged, and safety accidents are caused. However, because the internal environment of the rotary kiln is severe and relatively closed, the existing techniques cannot detect the temperature field and the ring thickness distribution in the kiln in real time, which causes great uncertainty in the operating state of the rotary kiln.
Disclosure of Invention
The embodiment of the invention provides an online detection method for temperature field and ring thickness distribution in a rotary kiln, which can solve the technical problem that the temperature field and ring thickness distribution in the rotary kiln cannot be detected. The technical scheme is as follows:
on one hand, the embodiment of the invention provides an online detection method for temperature field and ring thickness distribution in a rotary kiln, which is applied to electronic equipment and comprises the following steps:
historical data acquisition and dimension conversion are carried out on the measurable process variables in the industrial field, and a measurable process variable working condition set is constructed according to the historical data;
establishing a space rectangular coordinate system and a solid geometry by a computational fluid mechanics simulation technology, and calculating three-dimensional temperature field data in the kiln under the working condition set of measurable process variables according to a rotary kiln mechanism model;
sampling three-dimensional temperature field data under various working conditions along an X, Y, Z axis, and training a deep neural network to establish a kiln temperature field soft measurement model based on the deep neural network by combining measurable process variable data under the same working conditions, so as to realize online detection of temperature distribution in a kiln;
and establishing a soft measurement model of the thickness of the ring formation in the kiln through a heat transfer equation based on the temperature in the kiln detected on line, so as to realize the on-line detection of the thickness distribution of the ring formation in the kiln.
Further, the industrial field measurable process variables include: the axial flow air pressure of the burner, the rotational flow air pressure of the burner, the coal flow of the burner, the material flow and the secondary air temperature;
the method for acquiring historical data and converting dimensions of the measurable process variables on the industrial site and constructing the working condition set of the measurable process variables according to the historical data comprises the following steps:
historical data acquisition is carried out on 5 industrial field measurable process variables of axial flow air pressure of a combustor, cyclone air pressure of the combustor, coal flow of the combustor, material flow and secondary air temperature;
converting axial flow wind pressure and rotational flow wind pressure of the combustor into axial flow wind flow speed and rotational flow wind flow speed through a pressure-wind speed conversion formula;
according to the collected historical data, a measurable process variable working condition set comprising axial flow wind flow velocity, rotational flow wind flow velocity, burner coal flow, material flow and secondary air temperature is constructed:
Figure BDA0003285576030000021
wherein the subscripts min, med, and max are eachRespectively representing a minimum value, an average value and a maximum value; x1、X2、X3、X4And X5Respectively representing value sets of axial flow air flow velocity, rotational flow air flow velocity, burner coal flow, material flow and secondary air temperature; phi represents a set of measurable process variable operating conditions.
Further, the pressure-wind speed conversion formula is expressed as:
Figure BDA0003285576030000022
wherein, CpRepresenting a flow coefficient of the throttle valve; a. thetRepresenting the flow area of the throttle valve port; Δ p represents the pressure difference at the inlet and the outlet of the throttle valve; s represents the flow area of the air channel of the combustor; v represents the wind speed in the burner duct.
Further, the establishing the spatial rectangular coordinate system and the solid geometry by the computational fluid dynamics simulation technology comprises:
establishing a space rectangular coordinate system by taking the circle center of a plane of a secondary air inlet as a coordinate origin O, the horizontal direction as an X axis, the vertical direction as a Y axis and the axial direction of the rotary kiln as a Z axis;
according to the inner diameter r of the rotary kilncMaterial filling angle omega and material repose angle betarThe kiln body slope tan θ and the burner structural parameters create a solid geometry in 1:1 dimensions.
Further, the rotary kiln mechanism model meets the mass conservation law, the energy conservation law and the momentum conservation law equation;
the mechanism model of the rotary kiln comprises: the method comprises the following steps of controlling a Realizable k-epsilon turbulence model of a turbulence flow process of fluid in the kiln, controlling a P1 radiation model of a radiation heat transfer process in the kiln, controlling a non-premixed combustion probability density function model of a non-premixed combustion process of fuel and an oxidant in the kiln and controlling a discrete phase model of a diffusion process of pulverized coal particles.
Further, the built kiln temperature field soft measurement model based on the deep neural network is represented as follows:
Figure BDA0003285576030000031
wherein x is1、x2、x3、x4、x5、x6、x7And x8Respectively representing the normalized axial flow wind flow velocity, rotational flow wind flow velocity, coal flow, material flow, secondary wind temperature, X-axis coordinates, Y-axis coordinates and Z-axis coordinates;
Figure BDA0003285576030000032
represents the ith neuron output of layer 1,
Figure BDA0003285576030000033
indicating that the output of the jth neuron at level 2, …,
Figure BDA0003285576030000034
represents the kth neuron output of the l-1 layer; sigma1Denotes the activation function, σ, of layer 12Representing the activation function of layer 2, …, σl-1Represents the activation function of layer l-1;
Figure BDA0003285576030000035
represents the connection weight of the 1 st input of the 1 st layer and the ith neuron of the 2 nd layer,
Figure BDA0003285576030000036
representing the connection weight of the level 1, 2 nd input to the level 2, i-th neuron, …,
Figure BDA0003285576030000037
representing the connection weight of the jth input of the l-1 layer and the kth neuron of the l layer;
Figure BDA0003285576030000038
represents the connection bias of the ith neuron in the layer 1,
Figure BDA0003285576030000039
represents the connection of the jth neuron of layer 2The offset, …,
Figure BDA00032855760300000310
represents the connection paranoid of the kth neuron of the l-1 layer; y represents the temperature at a location within the kiln; i. j … … k represents the current neuron sequence numbers of layer 1 and layer 2 … … l-1 respectively; n is1、n1……nl-1Represent the total number of layer 1, 2 … … l-1 neurons, respectively.
Further, the soft measurement model of the thickness of the built ring in the kiln is represented as follows:
Figure BDA0003285576030000041
wherein λ represents air thermal conductivity; prRepresenting the prandtl number; d represents the diameter of the kiln shell; v represents the air viscosity; n represents the kiln rotational speed; v represents ambient wind speed; g represents the gravitational acceleration; beta represents the thermal expansion coefficient of air and is 2/(T)m+Ta) (ii) a a represents the convection heat transfer coefficient of the kiln shell;
Figure BDA0003285576030000042
represents the heat transfer capacity of the kiln shell on the length dl; σ represents a Boltzmann constant; epsiloneRepresenting the emissivity of the kiln shell; t isa、TmAnd TwRespectively representing the ambient temperature, the kiln shell temperature and the temperature in the kiln; lambda [ alpha ]m、λbAnd λcRespectively representing the heat conductivity coefficient of the kiln shell, the heat conductivity coefficient of the refractory brick and the heat conductivity coefficient of the ring formation; r ism、rb、rcRespectively showing the outer surface radius of the kiln shell, the outer surface radius of the refractory brick and the outer surface radius of the ring formation; d represents the thickness of the loop.
In one aspect, an electronic device is provided, and the electronic device includes a processor and a memory, where the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the above-mentioned online detection method for temperature field and ring thickness distribution in a rotary kiln.
In one aspect, a computer-readable storage medium is provided, where at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the above-mentioned method for online detection of temperature field and ring formation thickness distribution in a rotary kiln.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the embodiment of the invention, X, Y, Z axis coordinates are introduced into the input of the soft measurement model of the temperature field in the kiln, so that the temperature at any position in a three-dimensional space can be detected on line through a measurable process variable, and the ring formation thickness in the kiln can be detected on line by using the obtained soft measurement calculation result of the temperature in the kiln, so that the technical problem that the distribution of the temperature field and the ring formation thickness in the rotary kiln can not be detected is solved, and the running state of the rotary kiln can be evaluated more accurately.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for online detection of temperature field and ring formation thickness distribution in a rotary kiln according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a method for online detection of temperature field and ring thickness distribution in a rotary kiln according to an embodiment of the present invention;
FIG. 3 is a schematic perspective view of a rotary kiln according to an embodiment of the present invention;
FIG. 4 is a schematic view of media in an axial cross-section of a rotary kiln according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1 and fig. 2, an embodiment of the present invention provides an online detection method for a temperature field and a ring thickness distribution in a rotary kiln, which may be implemented by electronic equipment, and the method includes:
s101, historical data acquisition and dimension conversion are carried out on the measurable process variables in the industrial field, and a measurable process variable working condition set is constructed according to the historical data;
in this embodiment, the measurable process variables in the industrial field include: the axial flow air pressure of the burner, the rotational flow air pressure of the burner, the coal flow of the burner, the material flow and the secondary air temperature;
in this embodiment, the acquiring historical data and the converting dimensions of the measurable process variable in the industrial field, and constructing the working condition set of the measurable process variable according to the historical data may specifically include the following steps:
a1, collecting historical data of 5 measurable process variables of axial flow air pressure of a combustor, cyclone air pressure of the combustor, coal flow of the combustor, material flow and secondary air temperature of the combustor in an industrial field;
a2, converting axial flow wind pressure and rotational flow wind pressure of a combustor into axial flow wind flow speed and rotational flow wind flow speed through a pressure-wind speed conversion formula; wherein the pressure-wind speed conversion formula is expressed as:
Figure BDA0003285576030000051
wherein, CpRepresenting a flow coefficient of the throttle valve; a. thetRepresenting the flow area of the throttle valve port; Δ p represents the pressure difference at the inlet and the outlet of the throttle valve; s represents the flow area of the air channel of the combustor; v represents the wind speed in the burner duct;
a3, constructing a measurable process variable working condition set comprising axial flow wind flow velocity, rotational flow wind flow velocity, burner coal flow, material flow and secondary air temperature according to collected historical data:
Figure BDA0003285576030000061
wherein subscripts min, med, and max represent the minimum, average, and maximum values, respectively; x1、X2、X3、X4And X5Respectively representing value sets of axial flow air flow velocity, rotational flow air flow velocity, burner coal flow, material flow and secondary air temperature; phi represents a set of measurable process variable operating conditions.
S102, establishing a space rectangular coordinate system and a solid geometry through a computational fluid dynamics simulation technology, and calculating three-dimensional temperature field data in the kiln under a measurable process variable working condition set according to a rotary kiln mechanism model, wherein the three-dimensional temperature field data comprises: x, Y, Z axis coordinate and temperature value corresponding to the coordinate (specifically: temperature in kiln);
in this embodiment, as shown in fig. 3, the method for establishing the spatial rectangular coordinate system and the solid geometry includes: establishing a space rectangular coordinate system by taking the circle center of a plane of a secondary air inlet as a coordinate origin O, the horizontal direction as an X axis, the vertical direction as a Y axis and the axial direction of the rotary kiln as a Z axis; according to the inner diameter r of the rotary kilncThe solid geometry is created according to the 1:1 dimension by parameters such as the material filling angle omega, the material repose angle beta, the kiln body inclination tan alpha, the burner structure and the like.
In this embodiment, the mechanism model of the rotary kiln includes: a readable k-epsilon turbulence Model (i.e., a Realizable k-epsilon turbulence Model) for controlling the turbulent flow process of the fluid in the kiln, a P1 radiation Model for controlling the radiation heat transfer process in the kiln, a non-premixed combustion Probability Density Function (PDF) Model for controlling the non-premixed combustion process of the fuel and oxidant in the kiln, and a Discrete Phase Model (DPM) Model for controlling the diffusion process of the pulverized coal particles. In addition, the rotary kiln mechanism model also can satisfy mass conservation law, energy conservation law and momentum conservation law equations.
S103, sampling three-dimensional temperature field data under various working conditions along an X, Y, Z axis, and training a deep neural network to establish a kiln temperature field soft measurement model based on the deep neural network by combining measurable process variable data under the same working conditions, so as to realize online detection of temperature distribution in a kiln;
in this embodiment, normalization preprocessing is performed on input data by equation (3):
Figure BDA0003285576030000062
wherein x isi-inputRepresenting input data (including axial flow wind flow velocity, rotational flow wind flow velocity, coal flow, material flow, secondary air temperature, X-axis coordinate, Y-axis coordinate and Z-axis coordinate); x is the number ofi-minAnd xi-maxRepresenting input data xi-inputMaximum and minimum values of; x is the number ofiThe normalized data is represented.
In this embodiment, the forward propagation process of the deep neural network is realized by equation (4):
Figure BDA0003285576030000071
wherein the content of the first and second substances,
Figure BDA0003285576030000072
a kth neuron output representing a l-th layer of the deep neural network; sigmalRepresents the activation function of the l-th layer; m represents the number of layer l-1 neurons;
Figure BDA0003285576030000073
representing the connection weight of the jth neuron of the l-1 layer and the kth neuron of the l layer;
Figure BDA0003285576030000074
represents the jth neuron output of the l-1 layer;
Figure BDA0003285576030000075
representing the connection paranoid of the kth neuron of the l layer;
in the present embodiment, the loss function is calculated by equation (5):
Figure BDA0003285576030000076
wherein θ represents an updated weight parameter; j (θ) represents a loss function with parameter θ; h represents the number of samples per batch; y isiRepresenting an output predicted value; oiIndicating the output target value.
In this embodiment, the weight parameter of the neural network is updated by equation (6):
Figure BDA0003285576030000077
wherein s represents the number of steps of the update; θ represents an updated weight parameter; j (θ) represents a loss function with parameter θ; gsRepresents the loss function Js(θs-1) Deriving the gradient from θ; beta is a1Representing a first moment attenuation coefficient; beta is a2Representing a second moment attenuation coefficient; m issRepresents the gradient gsThe first moment of (d); v. ofsRepresents the gradient gsSecond order moment of (d);
Figure BDA0003285576030000078
bias correction values representing first order moments;
Figure BDA0003285576030000079
bias correction values representing second order moments; α represents a learning rate; epsilon0Is a stability factor;
in this embodiment, whether the training process is stopped is determined by equation (7):
|J(θs+1)-J(θs)|＜ξ (7)
where ξ is a user-defined value.
The soft measurement model of the in-kiln temperature field based on the deep neural network after the training is finished can be expressed as follows:
Figure BDA0003285576030000081
wherein x is1、x2、x3、x4、x5、x6、x7And x8Respectively representing the normalized axial flow wind flow velocity, rotational flow wind flow velocity, coal flow, material flow, secondary wind temperature, X-axis coordinates, Y-axis coordinates and Z-axis coordinates;
Figure BDA0003285576030000082
represents the ith neuron output of layer 1,
Figure BDA0003285576030000083
indicating that the output of the jth neuron at level 2, …,
Figure BDA0003285576030000084
represents the kth neuron output of the l-1 layer, and so on; sigma1Denotes the activation function, σ, of layer 12Representing the activation function of layer 2, …, σl-1Represents the activation function of layer l-1, and so on;
Figure BDA0003285576030000085
represents the connection weight of the 1 st input of the 1 st layer and the ith neuron of the 2 nd layer,
Figure BDA0003285576030000086
representing the connection weight of the level 1, 2 nd input to the level 2, i-th neuron, …,
Figure BDA0003285576030000087
represents the connection weight of the jth input of the l-1 th layer and the kth neuron of the l layer, and so on;
Figure BDA0003285576030000088
represents the connection bias of the ith neuron in the layer 1,
Figure BDA0003285576030000089
indicating the connectivity bias of the jth neuron at level 2, …,
Figure BDA00032855760300000810
represents the connection bias of the kth neuron of layer l-1, and so onPushing; y represents the temperature at a location within the kiln; i. j … … k represents the current neuron sequence numbers of layer 1 and layer 2 … … l-1 respectively; n is1、n1……nl-1Represent the total number of layer 1, 2 … … l-1 neurons, respectively.
And S104, establishing a soft measurement model of the thickness of the ring formation in the kiln through a heat transfer equation based on the temperature in the kiln, the temperature of the kiln shell, the ambient temperature and the ambient wind speed which are detected on line, and realizing the on-line detection of the thickness distribution of the ring formation in the kiln. The method specifically comprises the following steps:
in this embodiment, the convection heat transfer coefficient of the kiln shell is calculated by the following equation (9) to equation (12):
Figure BDA00032855760300000811
Figure BDA00032855760300000812
Figure BDA00032855760300000813
Figure BDA00032855760300000814
wherein D represents the kiln shell diameter; upsilon isaRepresents the air viscosity; n represents a kiln rotational speed (unit: rpm); rewRepresents the Reynolds number of rotation; v represents ambient wind speed; re represents the cross-flow reynolds number; t ismThe temperature of the outer surface of the kiln shell (the temperature of the kiln shell is abbreviated); t isaRepresents the ambient temperature; beta is aaRepresents a thermal expansion coefficient of air, and is 2/(T)m+Ta) (ii) a g represents the gravitational acceleration; gr denotes the Gravadaff number; λ represents the air thermal conductivity; prRepresenting the prandtl number; alpha is alphacRepresenting the convection heat transfer coefficient of the kiln shell;
in this embodiment, the heat dissipation amount of the kiln shell is calculated by the following equation (13) to equation (15):
Figure BDA0003285576030000091
Figure BDA0003285576030000092
Figure BDA0003285576030000093
wherein the content of the first and second substances,
Figure BDA0003285576030000094
and
Figure BDA0003285576030000095
respectively representing the radiant heat transfer quantity, the convection heat transfer quantity and the total heat transfer quantity of the kiln shell on the dl length; r ismRepresenting the radius of the kiln shell; alpha is alphacRepresenting the convection heat transfer coefficient of the kiln shell; σ represents a Boltzmann constant; epsiloneRepresenting the emissivity of the kiln shell; t isaAnd TmRespectively representing the ambient temperature and the kiln shell outer surface temperature.
In this embodiment, the heat transfer relationship through the different media layers of the kiln wall can be expressed as:
Figure BDA0003285576030000096
Figure BDA0003285576030000097
Figure BDA0003285576030000098
wherein the content of the first and second substances,
Figure BDA0003285576030000099
indicating kiln shell dlHeat transfer over length; t ism、Tb、TcAnd TwRespectively showing the temperature of the outer surface of the kiln shell, the temperature of the outer surface of a refractory brick, the temperature of the outer surface of a ring formation and the temperature of the inner surface of the ring formation (the temperature in the kiln); lambda [ alpha ]m、λbAnd λcRespectively representing the heat conductivity coefficient of the kiln shell, the heat conductivity coefficient of the refractory brick and the heat conductivity coefficient of the ring formation; r ism、rb、rcAnd rwRespectively showing the outer surface radius of the kiln shell, the outer surface radius of the refractory brick, the outer surface radius of the ring formation and the inner surface radius of the ring formation, as shown in FIG. 4;
in this embodiment, the soft measurement model of the ring thickness in the kiln after the sorting and simplification can be expressed as:
Figure BDA00032855760300000910
wherein λ represents air thermal conductivity; prRepresenting the prandtl number; d represents the diameter of the kiln shell; upsilon isaRepresents the air viscosity; n represents a kiln rotational speed (unit: rpm); v represents ambient wind speed; g represents the gravitational acceleration; beta is aaRepresents a thermal expansion coefficient of air, and is 2/(T)m+Ta)；αcRepresenting the convection heat transfer coefficient of the kiln shell;
Figure BDA00032855760300000911
represents the heat transfer capacity of the kiln shell on the length dl; σ represents a Boltzmann constant; epsiloneRepresenting the emissivity of the kiln shell; t isa、TmAnd TwRespectively representing the ambient temperature, the kiln shell temperature and the ring formation inner surface temperature (namely the temperature in the kiln); lambda [ alpha ]m、λbAnd λcRespectively representing the heat conductivity coefficient of the kiln shell, the heat conductivity coefficient of the refractory brick and the heat conductivity coefficient of the ring formation; r ism、rb、rcRespectively showing the outer surface radius of the kiln shell, the outer surface radius of the refractory brick and the outer surface radius of the ring formation; d represents the thickness of the loop.
In summary, the technical solutions provided by the present invention at least have the following beneficial effects:
1. x, Y, Z axis coordinates are introduced into the input of a soft measurement model of the temperature field in the kiln, so that the temperature at any position in a three-dimensional space can be detected on line through measurable process variables, the temperature field distribution can be visually displayed, and the method has good intuitiveness and interactivity;
2. the on-line detection of the ring thickness in the kiln can be realized by using the measurable process variables (comprising the kiln shell temperature, the ambient temperature and the ambient wind speed) and the soft measurement calculation result of the temperature in the kiln output by the soft measurement model of the temperature field in the kiln through the soft measurement model of the ring thickness in the kiln, and the ring thickness distribution can be visually displayed, so that the method has good accuracy and practicability;
3. the online detection method for the temperature field and the ring formation thickness distribution in the rotary kiln, provided by the embodiment of the invention, has universality, is suitable for the problem that variables cannot be detected in the industrial process, can be normally executed even under the condition that the obtained sensor data is very limited, solves the problem that the temperature field and the ring formation distribution in the rotary kiln cannot be detected, reduces the uncertainty of the industrial process according to the detection result, and can be used for judging the running state of the rotary kiln, optimizing process parameters and assisting in manual decision; the method can be applied to wider industrial scenes, so that the industrial process is more accurate and intelligent.
Fig. 5 is a schematic structural diagram of an electronic device 600 according to an embodiment of the present invention, where the electronic device 600 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where the memory 602 stores at least one instruction, and the at least one instruction is loaded and executed by the processor 601 to implement the above-mentioned online detection method for the temperature field and the ring thickness distribution in the rotary kiln.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, is also provided that includes instructions executable by a processor in a terminal to perform the above-described method for online detection of temperature field and ring thickness distribution in a rotary kiln. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (7)

1. An online detection method for temperature field and ring thickness distribution in a rotary kiln is characterized by comprising the following steps:
historical data acquisition and dimension conversion are carried out on the measurable process variables in the industrial field, and a measurable process variable working condition set is constructed according to the historical data;
establishing a space rectangular coordinate system and a solid geometry by a computational fluid mechanics simulation technology, and calculating three-dimensional temperature field data in the kiln under the working condition set of measurable process variables according to a rotary kiln mechanism model;
sampling three-dimensional temperature field data under various working conditions along an X, Y, Z axis, and training a deep neural network to establish a kiln temperature field soft measurement model based on the deep neural network by combining measurable process variable data under the same working conditions, so as to realize online detection of temperature distribution in a kiln;
and establishing a soft measurement model of the thickness of the ring formation in the kiln through a heat transfer equation based on the temperature in the kiln detected on line, so as to realize the on-line detection of the thickness distribution of the ring formation in the kiln.
2. The method of claim 1, wherein the industrial field measurable process variables include: the axial flow air pressure of the burner, the rotational flow air pressure of the burner, the coal flow of the burner, the material flow and the secondary air temperature;
the method for acquiring historical data and converting dimensions of the measurable process variables on the industrial site and constructing the working condition set of the measurable process variables according to the historical data comprises the following steps:
historical data acquisition is carried out on 5 industrial field measurable process variables of axial flow air pressure of a combustor, cyclone air pressure of the combustor, coal flow of the combustor, material flow and secondary air temperature;
converting axial flow wind pressure and rotational flow wind pressure of the combustor into axial flow wind flow speed and rotational flow wind flow speed through a pressure-wind speed conversion formula;
according to the collected historical data, a measurable process variable working condition set comprising axial flow wind flow velocity, rotational flow wind flow velocity, burner coal flow, material flow and secondary air temperature is constructed:
Figure FDA0003285576020000011
wherein subscripts min, med, and max represent the minimum, average, and maximum values, respectively; x1、X2、X3、X4And X5Respectively representing value sets of axial flow air flow velocity, rotational flow air flow velocity, burner coal flow, material flow and secondary air temperature; phi represents a set of measurable process variable operating conditions.
3. The method for on-line detection of the temperature field and the ring thickness distribution in the rotary kiln according to claim 2, wherein the pressure-wind speed conversion formula is represented as:
Figure FDA0003285576020000021
wherein, CpRepresenting a flow coefficient of the throttle valve; a. thetRepresenting the flow area of the throttle valve port; Δ p represents the pressure difference at the inlet and the outlet of the throttle valve; s represents the flow area of the air channel of the combustor; v represents the wind speed in the burner duct.
4. The method for on-line detection of temperature field and ring thickness distribution in a rotary kiln as claimed in claim 1, wherein said establishing a spatial rectangular coordinate system and a solid geometry by computational fluid dynamics simulation technique comprises:
establishing a space rectangular coordinate system by taking the circle center of a plane of a secondary air inlet as a coordinate origin O, the horizontal direction as an X axis, the vertical direction as a Y axis and the axial direction of the rotary kiln as a Z axis;
according to the inner diameter r of the rotary kilncMaterial filling angle omega and material repose angle betarThe kiln body slope tan θ and the burner structural parameters create a solid geometry in 1:1 dimensions.
5. The method for on-line detection of the temperature field and the thickness distribution of the formed ring in the rotary kiln according to claim 1, wherein the rotary kiln mechanism model meets mass conservation law, energy conservation law and momentum conservation law equations;
the mechanism model of the rotary kiln comprises: the method comprises the following steps of controlling a Realizable k-epsilon turbulence model of a turbulence flow process of fluid in the kiln, controlling a P1 radiation model of a radiation heat transfer process in the kiln, controlling a non-premixed combustion probability density function model of a non-premixed combustion process of fuel and an oxidant in the kiln and controlling a discrete phase model of a diffusion process of pulverized coal particles.
6. The method for on-line detection of the temperature field and the ring thickness distribution in the rotary kiln according to claim 1, wherein the built kiln temperature field soft measurement model based on the deep neural network is represented as follows:
Figure FDA0003285576020000031
wherein x is1、x2、x3、x4、x5、x6、x7And x8Respectively representing the normalized axial flow wind flow velocity, rotational flow wind flow velocity, coal flow, material flow, secondary air temperature, X-axis coordinate, Y-axis coordinate anda Z-axis coordinate;
Figure FDA0003285576020000032
represents the ith neuron output of layer 1,
Figure FDA0003285576020000033
indicating that the output of the jth neuron at level 2, …,
Figure FDA0003285576020000034
represents the kth neuron output of the l-1 layer; sigma1Denotes the activation function, σ, of layer 12Representing the activation function of layer 2, …, σl-1Represents the activation function of layer l-1;
Figure FDA0003285576020000035
represents the connection weight of the 1 st input of the 1 st layer and the ith neuron of the 2 nd layer,
Figure FDA0003285576020000036
representing the connection weight of the level 1, 2 nd input to the level 2, i-th neuron, …,
Figure FDA0003285576020000037
representing the connection weight of the jth input of the l-1 layer and the kth neuron of the l layer;
Figure FDA0003285576020000038
represents the connection bias of the ith neuron in the layer 1,
Figure FDA0003285576020000039
indicating the connectivity bias of the jth neuron at level 2, …,
Figure FDA00032855760200000310
represents the connection paranoid of the kth neuron of the l-1 layer; y represents the temperature at a location within the kiln; i. j … … k represents the current neuron sequence numbers of layer 1 and layer 2 … … l-1 respectively; n is1、n1……nl-1Represent the total number of layer 1, 2 … … l-1 neurons, respectively.
7. The method for on-line detection of the temperature field and the ring formation thickness distribution in the rotary kiln as claimed in claim 1, wherein the soft measurement model of the ring formation thickness in the kiln is represented as follows:
Figure FDA00032855760200000311
wherein λ represents air thermal conductivity; prRepresenting the prandtl number; d represents the diameter of the kiln shell; v represents the air viscosity; n represents the kiln rotational speed; v represents ambient wind speed; g represents the gravitational acceleration; beta represents the thermal expansion coefficient of air and is 2/(T)m+Ta) (ii) a Alpha represents the convection heat transfer coefficient of the kiln shell;
Figure FDA00032855760200000312
represents the heat transfer capacity of the kiln shell on the length dl; σ represents a Boltzmann constant; epsiloneRepresenting the emissivity of the kiln shell; t isa、TmAnd TwRespectively representing the ambient temperature, the kiln shell temperature and the temperature in the kiln; lambda [ alpha ]m、λbAnd λcRespectively representing the heat conductivity coefficient of the kiln shell, the heat conductivity coefficient of the refractory brick and the heat conductivity coefficient of the ring formation; r ism、rb、rcRespectively showing the outer surface radius of the kiln shell, the outer surface radius of the refractory brick and the outer surface radius of the ring formation; d represents the thickness of the loop.
CN202111146465.4A 2021-09-28 2021-09-28 Online detection method for temperature field and ring thickness distribution in rotary kiln Pending CN113868952A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111146465.4A CN113868952A (en) 2021-09-28 2021-09-28 Online detection method for temperature field and ring thickness distribution in rotary kiln

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111146465.4A CN113868952A (en) 2021-09-28 2021-09-28 Online detection method for temperature field and ring thickness distribution in rotary kiln

Publications (1)

Publication Number Publication Date
CN113868952A true CN113868952A (en) 2021-12-31

Family

ID=78992331

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111146465.4A Pending CN113868952A (en) 2021-09-28 2021-09-28 Online detection method for temperature field and ring thickness distribution in rotary kiln

Country Status (1)

Country Link
CN (1) CN113868952A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114854922A (en) * 2022-04-26 2022-08-05 酒泉钢铁(集团)有限责任公司 Method for determining ring formation position of iron-containing material of rotary kiln and continuously cleaning iron-containing material by direct reduction

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114854922A (en) * 2022-04-26 2022-08-05 酒泉钢铁(集团)有限责任公司 Method for determining ring formation position of iron-containing material of rotary kiln and continuously cleaning iron-containing material by direct reduction

Similar Documents

Publication Publication Date Title
CN111339716B (en) Boiler high-temperature flue gas flow field online agent model construction method
CN104750131B (en) A kind of fluidized-bed temperature control method based on parameter identification
CN106503380B (en) Coking nitrogen oxides in effluent concentration prediction method and forecasting system
CN105005632B (en) The blast furnace crucible corrosion Forecasting Methodology of multiple layer refractory tile stove wall construction
CN113868952A (en) Online detection method for temperature field and ring thickness distribution in rotary kiln
CN106649919A (en) Method and system for predicting carbon content of fly ash in coal-fired power plant boiler
WO2022198914A1 (en) Blast furnace throat temperature estimation method based on multilayer ore-coke ratio distribution model
CN114239430A (en) Method and system for predicting NOx at furnace outlet based on numerical simulation
Jiménez et al. Formation and emission of submicron particles in pulverized olive residue (orujillo) combustion
Xu et al. A soft sensor modeling of cement rotary kiln temperature field based on model-driven and data-driven methods
Liu et al. Thermocapillary flow transition in an evaporating liquid layer in a heated cylindrical cell
CN108197723A (en) Coal motor group net coal consumption rate and the Optimization of Energy Saving dispatching method of pollutant emission
JP5990811B2 (en) Method for predicting sulfide corrosion of boiler furnace wall pipes.
Carvalho et al. Prediction of the flow, reaction and heat transfer in an oxy‐fuel glass furnace
CN114675607A (en) Fired coal heat value prediction and correction control method combining flame temperature
CN113074459A (en) Boiler control optimization method and system
CN113239612A (en) Boiler combustion state diagnosis method and system and storage medium
CN116085823A (en) Boiler combustion control method and system
Shi et al. Online nondestructive evaluation of TBC crack using infrared thermography
Hu et al. Zone modelling coupled with dynamic flow pattern for the prediction of transient performance of metal reheating
Zheng et al. Prediction of NOx concentration from coal combustion using LS-SVR
Roy et al. CFD simulation of wind effects on industrial chimneys
CN111651872A (en) Nuclear explosion radioactive contamination prediction method based on gas-solid two-phase flow simulation
Chen Control method of mechanical smoke emission in high-rise building corridor
CN104832914B (en) A kind of ring wall protection combustion furnace and its heat and mass method for numerical simulation

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