CN110205427B - Intelligent hot blast stove optimization control system and method - Google Patents
Intelligent hot blast stove optimization control system and method Download PDFInfo
- Publication number
- CN110205427B CN110205427B CN201910537759.6A CN201910537759A CN110205427B CN 110205427 B CN110205427 B CN 110205427B CN 201910537759 A CN201910537759 A CN 201910537759A CN 110205427 B CN110205427 B CN 110205427B
- Authority
- CN
- China
- Prior art keywords
- time
- gas flow
- residual
- air supply
- lstm network
- 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
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21B—MANUFACTURE OF IRON OR STEEL
- C21B9/00—Stoves for heating the blast in blast furnaces
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Regulation And Control Of Combustion (AREA)
Abstract
The invention belongs to the technical field of hot blast stove combustion in the metallurgical industry, and particularly relates to an intelligent hot blast stove optimization control system and method. The system comprises: a remaining air supply time prediction module: the system is used for obtaining the residual air supply time of the hot blast stove based on the first LSTM network according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas; a remaining burn time prediction module: the device is used for obtaining the residual combustion time of the hot blast stove based on the second LSTM network according to the gas flow parameter and the waste gas temperature parameter; an optimization module: the gas flow rate is dynamically adjusted according to the obtained residual air supply time and the residual combustion time; historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training. The system is based on the LSTM network, so that the combustion time and the air supply time of the hot blast stove are matched, and the production efficiency of blast furnace ironmaking is improved.
Description
Technical Field
The invention belongs to the technical field of hot blast stove combustion in the metallurgical industry, and particularly relates to an intelligent hot blast stove optimization control system and method.
Background
The grain in the steel and iron product industry is a metal material which is most used by human beings, has high strength, good mechanical property, rich resources and low cost, is suitable for large-scale production, has wide application in various fields of social production and life, is an indispensable strategic basic industrial product, and plays an important role in national economic development.
The hot blast stove is a carrier of high blast temperature of the blast furnace, and works according to the principle of 'heat storage' to heat blast air to required temperature so as to improve the benefit and efficiency of the blast furnace. Hot blast stoves mainly have two problems: one is that sufficient heat is not available during combustion to meet the requirements of the air supply stage; secondly, the hot blast stove reaches the required heat but does not reach the stage of changing the stove, and the waste of coal gas is caused for maintaining the temperature. During operation, fluctuations in gas flow, pressure, and heat value, as well as air flow, pressure, and temperature, all affect the combustion process.
The operation of the hot blast stove is greatly interfered by external factors, the air supply time of each time is often different, and the combustion time of the hot blast stove of each time is also often different, so that an operator has to change the stove in advance when the operator does not reach an optimal combustion path, and the quality of hot blast is reduced; or the furnace changing requirement is met, and the air supply stage is not finished, so that additional coal gas is needed to maintain the temperature, and the coal gas is wasted.
Although basic automation of most domestic hot blast stoves is realized at present, except for individual large blast furnaces, the automatic control of the combustion process of the hot blast stove which is really reliable and practical is rare, and most of small and medium blast furnaces almost complete the combustion control of the hot blast stove by manual operation. Due to the factors of low automation level, insufficient manual experience and the like, the hot blast stove is good and bad in combustion, so that the temperature of hot air provided by the hot blast stove is low, and the state is unstable, thereby being not beneficial to the high-efficiency production of blast furnace ironmaking.
Disclosure of Invention
Technical problem to be solved
Aiming at the existing technical problems, the invention provides an intelligent hot blast stove optimization control system which is based on an LSTM network, so that the combustion time and the air supply time of the hot blast stove are matched, and the production efficiency of blast furnace ironmaking is improved.
(II) technical scheme
The invention provides an intelligent hot blast stove optimization control system, which comprises a rapid heating stage, a top temperature stabilization stage and a residual combustion time adjusting stage in the combustion process of a hot blast stove, wherein the system is applied to the residual combustion time adjusting stage and comprises the following steps:
a remaining air supply time prediction module: the system is used for obtaining the residual air supply time of the hot blast stove based on the first LSTM network according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas;
a remaining burn time prediction module: the device is used for obtaining the residual combustion time of the hot blast stove based on the second LSTM network according to the gas flow parameter and the waste gas temperature parameter;
an optimization module: the gas flow rate is dynamically adjusted according to the obtained residual air supply time and the residual combustion time;
historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training.
The invention also provides an intelligent hot blast stove optimization control method, which comprises the following steps:
a1, based on the first LSTM network, obtaining the residual air supply time of the hot blast stove according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas;
a2, based on the second LSTM network, obtaining the residual combustion time of the hot blast stove according to the gas flow parameter and the waste gas temperature parameter;
a3, dynamically adjusting the gas flow according to the obtained residual air supply time and residual combustion time;
historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training.
Further, in the step a1, acquiring an opening parameter of the air mixing valve and an exhaust gas temperature parameter at periodic intervals, wherein the interval time is 1-2 s;
in the step A2, the coal gas flow parameter and the waste gas temperature parameter are acquired at periodic intervals, and the time of the interval is 1-2 s.
Further, in the step a3, when the absolute value of the difference between the remaining combustion time and the remaining air supply time is less than 120s, the gas flow rate is not adjusted;
and when the absolute value of the difference value between the residual combustion time and the residual air supply time is more than or equal to 120s, adjusting the gas flow.
Further, when the absolute value of the difference between the remaining combustion time and the remaining air supply time is not less than 120s, adjusting the gas flow rate includes:
when the residual air supply time is longer than the residual combustion time, reducing the current gas flow by 5 percent;
and when the residual air supply time is less than the residual combustion time, increasing the current gas flow by 5%.
Further, in the step a3, the interval time of dynamically adjusting the gas flow is 20-40 s.
Further, the first and second LSTM networks each include an input layer and a fully connected layer;
inputting the acquired opening parameter and the exhaust gas temperature parameter of the air mixing valve into an input layer of a first LSTM network, and outputting the residual air supply time by a full connection layer of the first LSTM network;
inputting the obtained gas flow parameter and the obtained waste gas temperature parameter into an input layer of a second LSTM network, and outputting the remaining combustion time by a full connection layer of the second LSTM network;
further, a dropout optimization method is introduced to the full connection layers of the first and second LSTM networks, respectively.
(III) advantageous effects
In the intelligent hot blast stove optimization control system provided by the invention, the LSTM network is adopted to process sequence data, compared with the traditional RNN, the problem of gradient disappearance is avoided, the prediction effect is good, and the precision is high. According to the difference value between the residual combustion time and the residual air supply time, the combustion stage is dynamically adjusted in real time, and the combustion time is matched with the air supply time, so that the air temperature of the hot blast stove can meet the requirement, and the problems of coal gas waste and service life reduction of the hot blast stove caused by overlong combustion time are solved. Meanwhile, due to the optimization of the air-fuel ratio and the reduction of the fuel quantity, the emission of combustion products such as oxynitride and the like can be obviously reduced, and the environment protection is facilitated.
Drawings
FIG. 1 is a schematic diagram of the structure of an LSTM in the present invention;
FIG. 2 is a flow chart of the combustion process of the present invention.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.
In the intelligent hot blast stove optimization control system provided by the invention, a mode of alternately working 3-4 hot blast stoves is adopted, one hot blast stove supplies air, and the rest 2-3 hot blast stoves are in a combustion stage, namely the time of one combustion stage is 2-3 air supply times.
The working principle of the hot blast stove comprises a cycle period, and in one cycle period, the hot blast stove comprises two stages, namely a combustion stage and an air supply stage. In the combustion stage, coal gas and air are input into the combustion chamber to be combusted, so that the heat storage chamber is heated, heat is stored in the heat storage chamber through the heat stored in the checker bricks, the heat storage chamber is heated to a certain temperature, combustion is suspended, the next stage is started, and air supply is started. In the air supply stage, the air blower blows cold air through the cold air pipeline and then enters the heat storage chamber, the heat storage chamber keeps a higher heat storage level at the moment, the cold air enters the heat storage chamber and then heats the heat storage chamber through the checker bricks, and the cold air is sent into the blast furnace after heat exchange. The heat storage capacity of the regenerator is continuously reduced and the wind temperature is continuously increased. When the heat storage chamber can not heat cold air to the required target temperature, the heat storage chamber is switched to a combustion state, namely, the air supply period is switched to a combustion period, and the operation is circulated.
As shown in fig. 2, the hot blast stove includes a rapid heating stage, a top temperature stabilization stage and a remaining combustion time adjustment stage in the combustion process, and the intelligent hot blast stove optimization control system provided by the present invention is applied to the remaining combustion time adjustment stage, and the system includes:
a remaining air supply time prediction module: the system is used for obtaining the residual air supply time of the hot blast stove based on the first LSTM network according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas;
a remaining burn time prediction module: the device is used for obtaining the residual combustion time of the hot blast stove based on the second LSTM network according to the gas flow parameter and the waste gas temperature parameter;
an optimization module: the gas flow rate is dynamically adjusted according to the obtained residual air supply time and the residual combustion time;
historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training.
The invention also provides an intelligent hot blast stove optimization control method, which comprises the following steps:
and A1, obtaining the residual air supply time of the hot blast stove based on the first LSTM network according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas. Specifically, the OPC Server is connected through the configuration king, the opening degree and the exhaust gas temperature of the air mixing valve are acquired in real time, the opening degree and the exhaust gas temperature of the air mixing valve are input into an input layer of a first LSTM network trained in advance, wherein the sampling interval is 1-2s, preferably 1s, the sampling time step is 12-16s, preferably 15s, and the residual air supply time is output by a full connection layer of the first LSTM network. In order to prevent the phenomenon of overfitting, an optimization method of dropout is introduced into the full-connection layer.
And A2, based on the second LSTM network, obtaining the residual combustion time of the hot blast stove according to the gas flow parameter and the waste gas temperature parameter. Specifically, the method comprises the steps of acquiring gas flow and waste gas temperature in real time through a configuration Wang connection OPC Server, inputting the gas flow and the waste gas temperature to an input layer of a second LSTM network, wherein the sampling interval is 1-2s, preferably 1s, the sampling time step is 12-16s, preferably 15s, and the full connection layer of the second LSTM network outputs the residual combustion time. In order to prevent the phenomenon of overfitting, an optimization method of dropout is introduced into the full-connection layer.
Wherein the training process for the first and second LSTM networks comprises:
taking furnace one as an example, the required data such as waste gas temperature, gas flow, opening degree of a mixing valve, vault temperature and the like can be acquired in real time by connecting OPC Server through configuration king. The collected data are processed according to the following steps of 8: the 2 scale is divided into a training set and a test set. Establishing network structures of a first LSTM network and a second LSTM network by adopting Tensorflow, respectively inputting a training set into the first LSTM network and the second LSTM network, and calculating network parameters of the first LSTM network and the second LSTM network by adopting an Adam optimizer. And using the trained first LSTM network and the second LSTM network for testing the test set, calculating the error of the test set, adjusting the hyper-parameters of the first LSTM network and the second LSTM network, and training again until the result of the test set is within the error allowable range.
Further, as shown in fig. 1, the forward propagation calculation method inside the first LSTM network and the second LSTM network is as follows:
ft＝σ(Wf·[ht-1,Xt]+bf) (1)
it＝σ(Wi·[ht-1,Xt]+bi) (2)
ot＝σ(Wo·[ht-1,Xt]+bo) (5)
ht＝ot·tanh(ct) (6)
in the formula (f)tRepresenting a forgetting gate,. sigma.representing a sigmoid function, WfWeight matrix representing forgetting gate, ht-1Output data representing the last moment, XtInput data representing the current time, [ h ]t-1,Xt]Denotes a reaction oft-1、XtSplicing into a long vector in the horizontal direction, bfOffset value, i, representing a forgetting gatetDenotes an input gate, WiRepresenting the weight coefficient of the input gate, biWhich represents the offset value of the input gate,
indicating the currently input cell state, WcWeight matrix representing the state of the currently input cell, bcOffset value representing the state of the currently input cell, ctIndicating the state of the cell at the current time, otDenotes an output gate, WoWeight matrix representing output gates, boRepresents the offset value of the output gate, htRepresenting the final output.
And A3, dynamically adjusting the gas flow according to the obtained residual air supply time and residual combustion time.
When the absolute value of the difference value between the residual combustion time and the residual air supply time is less than 120s, the gas flow is not adjusted; when the absolute value of the difference value between the residual combustion time and the residual air supply time is more than or equal to 120s, adjusting the gas flow, wherein: when the residual air supply time is longer than the residual combustion time, reducing the current gas flow by 5 percent; and when the residual air supply time is less than the residual combustion time, increasing the current gas flow by 5%.
The working process is as follows:
each hot blast stove sequentially passes through a combustion stage and an air supply stage. The combustion phase comprises:
a rapid temperature rise stage: introducing coal gas into the hot blast stove, and setting the coal gas flow as the maximum value Qmax(Qmax＝160000m3And h), when the temperature of the vault reaches 90-97.5% of the preset temperature T, the gas flow is properly reduced, the temperature of the vault is ensured not to exceed the preset temperature T, and the stage of top temperature stabilization is started. Preferably, the temperature preset value T is set to 1400 ℃.
And (3) a top temperature stabilization stage: and detecting the vault temperature and the waste gas temperature once every 30s, properly adjusting the gas flow according to the vault temperature and the waste gas temperature, and not adjusting the gas flow when the vault temperature changes within the range of +/-2.5%. And entering a residual combustion time adjusting stage when the temperature difference between the exhaust gas temperature and the preset temperature value T is detected to be less than 30 ℃.
And (3) adjusting the residual combustion time: and obtaining data such as the waste gas temperature, the gas flow, the opening degree of the air mixing valve and the like in each sampling time period according to the sampling interval, obtaining the residual air supply time and the residual combustion time based on the first LSTM network and the second LSTM network, and dynamically adjusting the gas flow. Wherein, in order to prevent the influence on the hot blast stove caused by too frequent fluctuation, the gas flow is adjusted every 30 s. When the absolute value of the difference value between the residual combustion time and the residual air supply time is less than 120s, the gas flow is not adjusted; when the absolute value of the difference value between the residual combustion time and the residual air supply time is more than or equal to 120s, adjusting the gas flow, wherein: when the residual air supply time is longer than the residual combustion time, reducing the current gas flow by 5 percent; and when the residual air supply time is less than the residual combustion time, increasing the current gas flow by 5%.
When the detected exhaust gas temperature is set to 375 ℃, the furnace changing requirement is met, the combustion stage is ended, and the air supply stage is started.
Therefore, the air-fuel ratio of the hot blast stove is optimized, so that the coal gas waste caused by the condition that the combustion is in a state but the air supply stage is not finished is avoided; and the condition that the hot air quality does not reach the standard because the air supply stage is finished and the combustion process is still not finished is avoided.
Due to various external factors, the reaction of the combustion phase of each stove may be different, so in the adjustment phase of the remaining combustion time, the first LSTM network and the second LSTM network of each stove are trained respectively.
The technical principles of the present invention have been described above in connection with specific embodiments, which are intended to explain the principles of the present invention and should not be construed as limiting the scope of the present invention in any way. Based on the explanations herein, those skilled in the art will be able to conceive of other embodiments of the present invention without inventive efforts, which shall fall within the scope of the present invention.
Claims (7)
1. The utility model provides an intelligence hot-blast furnace optimal control system, hot-blast furnace include rapid heating up stage, top temperature stable stage and remaining burning time adjustment stage in the combustion process, are applied to remaining burning time adjustment stage with this system, its characterized in that, this system includes:
a remaining air supply time prediction module: the system is used for obtaining the residual air supply time of the hot blast stove based on the first LSTM network according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas;
a remaining burn time prediction module: the device is used for obtaining the residual combustion time of the hot blast stove based on the second LSTM network according to the gas flow parameter and the waste gas temperature parameter;
an optimization module: the method is used for dynamically adjusting the gas flow according to the obtained residual air supply time and residual combustion time, and specifically comprises the following steps:
when the absolute value of the difference value between the residual combustion time and the residual air supply time is more than or equal to 120s, the coal gas flow rate is adjusted, and the method comprises the following steps:
when the residual air supply time is longer than the residual combustion time, reducing the current gas flow by 5 percent;
when the residual air supply time is less than the residual combustion time, increasing the current gas flow by 5%;
historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training.
2. An intelligent hot blast stove optimization control method is characterized by comprising the following steps:
a1, based on the first LSTM network, obtaining the residual air supply time of the hot blast stove according to the opening parameter of the air mixing valve and the temperature parameter of the waste gas;
a2, based on the second LSTM network, obtaining the residual combustion time of the hot blast stove according to the gas flow parameter and the waste gas temperature parameter;
a3, dynamically adjusting the gas flow according to the obtained residual air supply time and residual combustion time, and specifically comprising the following steps:
when the absolute value of the difference value between the residual combustion time and the residual air supply time is more than or equal to 120s, the coal gas flow rate is adjusted, and the method comprises the following steps:
when the residual air supply time is longer than the residual combustion time, reducing the current gas flow by 5 percent;
when the residual air supply time is less than the residual combustion time, increasing the current gas flow by 5%;
historical data of the opening of the air mixing valve, the temperature of the waste gas and the gas flow are selected in advance, and structural parameters of the first LSTM network and the second LSTM network are obtained through BP algorithm training.
3. The intelligent hot blast stove optimization control method according to claim 2,
in the step A1, acquiring an opening parameter and an exhaust gas temperature parameter of the air mixing valve at periodic intervals, wherein the time of the interval is 1-2 s;
in the step A2, the coal gas flow parameter and the waste gas temperature parameter are acquired at periodic intervals, and the time of the interval is 1-2 s.
4. The intelligent hot blast stove optimization control method according to claim 2,
in step a3, when the absolute value of the difference between the remaining combustion time and the remaining air supply time is less than 120s, the gas flow rate is not adjusted.
5. The intelligent hot blast stove optimization control method according to claim 2, wherein in the step A3, the interval time for dynamically adjusting the gas flow is 20-40 s.
6. The intelligent hot blast stove optimization control method according to claim 2,
the first LSTM network and the second LSTM network both comprise an input layer and a full connection layer;
inputting the acquired opening parameter and the exhaust gas temperature parameter of the air mixing valve into an input layer of a first LSTM network, and outputting the residual air supply time by a full connection layer of the first LSTM network;
and inputting the obtained gas flow parameter and the obtained waste gas temperature parameter into an input layer of the second LSTM network, and outputting the remaining combustion time by a full-connection layer of the second LSTM network.
7. The intelligent hot blast stove optimization control method according to claim 6, characterized in that the optimization method of dropout is introduced to the full connection layers of the first and second LSTM networks, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537759.6A CN110205427B (en) | 2019-06-20 | 2019-06-20 | Intelligent hot blast stove optimization control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537759.6A CN110205427B (en) | 2019-06-20 | 2019-06-20 | Intelligent hot blast stove optimization control system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110205427A CN110205427A (en) | 2019-09-06 |
| CN110205427B true CN110205427B (en) | 2020-06-16 |
Family
ID=67793720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910537759.6A Active CN110205427B (en) | 2019-06-20 | 2019-06-20 | Intelligent hot blast stove optimization control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110205427B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717628B (en) * | 2019-10-09 | 2023-05-23 | 浪潮软件股份有限公司 | Goods source optimizing model construction method, optimizing model and optimizing method |
| CN111676365A (en) * | 2020-06-09 | 2020-09-18 | 邯郸钢铁集团有限责任公司 | LSTM-based method for predicting annealing temperature set value of transition steel coil |
| CN113420843B (en) * | 2021-08-23 | 2021-11-19 | 湖南省计量检测研究院 | Heat testing method, device, equipment and medium based on micro fluidized bed |
| CN114279494B (en) * | 2021-12-16 | 2023-05-26 | 金陵科技学院 | Fiber bragg grating blast furnace shell temperature compensation detection method based on improved LSTM |
| CN114610093B (en) * | 2022-03-09 | 2023-03-03 | 科大智能物联技术股份有限公司 | Burning furnace air supply control method based on variable period prediction of hot blast stove |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1766130A (en) * | 2005-12-09 | 2006-05-03 | 河北理工大学 | Harmonization control method for blast furnace hot blast stove system |
| CN101892338A (en) * | 2010-07-22 | 2010-11-24 | 首钢总公司 | Constant wind temperature control system for hot blast stove |
| CN108251591A (en) * | 2018-01-15 | 2018-07-06 | 上海大学 | Utilize the top bottom blowing converter producing process control method of LSTM systems |
-
2019
- 2019-06-20 CN CN201910537759.6A patent/CN110205427B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1766130A (en) * | 2005-12-09 | 2006-05-03 | 河北理工大学 | Harmonization control method for blast furnace hot blast stove system |
| CN101892338A (en) * | 2010-07-22 | 2010-11-24 | 首钢总公司 | Constant wind temperature control system for hot blast stove |
| CN108251591A (en) * | 2018-01-15 | 2018-07-06 | 上海大学 | Utilize the top bottom blowing converter producing process control method of LSTM systems |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110205427A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110205427B (en) | Intelligent hot blast stove optimization control system and method | |
| CN105423334B (en) | Combustion of Hot Air Furnace Intelligent Process Control system and method | |
| CN112359159B (en) | Hot blast stove automatic burning method and system based on deep reinforcement learning | |
| CN111562744B (en) | Boiler combustion implicit generalized predictive control method based on PSO algorithm | |
| CN110260356B (en) | Energy-saving control method of fluidized bed boiler | |
| CN108426266B (en) | Boiler combustion control system and method | |
| CN103243190A (en) | Method for predicting coal gas consumption of hot blast stove | |
| CN106829950B (en) | A kind of power-economizing method and device of cascade graphitizing furnaces | |
| CN114675543B (en) | Hot blast stove intelligent combustion control method based on optimized learning algorithm | |
| CN109710976B (en) | Method for predicting gas consumption of steel rolling heating furnace | |
| CN105700383B (en) | A kind of positive pressed baker optimal control method | |
| CN107976976B (en) | Time sequence optimization method for gas consumption equipment of iron and steel enterprise | |
| CN106362648A (en) | Heat accumulating type quick pyrolysis furnace temperature control method capable of controlling air-fuel ratio | |
| CN101892366B (en) | Low oxygen content and low nitrogen consumption control system and method for radiant tube-heated non-oxidation roller hearth furnace | |
| CN106127351A (en) | A kind of blast funnace hot blast stove initially burns producer gas flow optimization system | |
| CN114721253A (en) | Heating furnace temperature fractional order PID control system and method based on artificial bee colony algorithm | |
| CN114134017A (en) | Anaerobic fermentation temperature control system and method based on BP neural network prediction | |
| CN106753443A (en) | The system of nitrogen oxides in a kind of coke oven exhaust gas from Sources controlling | |
| CN105199973B (en) | A kind of Yeast Cultivation online adaptive control method based on differential evolution algorithm | |
| CN104531978A (en) | Non-oriented silicon steel heating method and modeling control method of non-oriented silicon steel heating method | |
| CN206328336U (en) | The system of nitrogen oxides in a kind of coke oven exhaust gas from Sources controlling | |
| CN114317859B (en) | Air supply strategy correction method for hot blast stove | |
| CN117286295A (en) | Hot blast stove gas consumption prediction method based on hot blast stove cooling and heating judgment | |
| CN103937957B (en) | Pulse-combustion formula furnace pressure feedforward optimizing and controlling method | |
| JPS63226524A (en) | Combustion control in hot blast furnace |
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 |