CN117273432A - Converter splash risk prediction method and device - Google Patents
Converter splash risk prediction method and device Download PDFInfo
- Publication number
- CN117273432A CN117273432A CN202310842721.6A CN202310842721A CN117273432A CN 117273432 A CN117273432 A CN 117273432A CN 202310842721 A CN202310842721 A CN 202310842721A CN 117273432 A CN117273432 A CN 117273432A
- Authority
- CN
- China
- Prior art keywords
- oxygen lance
- vibration acceleration
- splash
- risk
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 131
- 239000001301 oxygen Substances 0.000 claims abstract description 131
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 131
- 230000001133 acceleration Effects 0.000 claims abstract description 110
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 239000002893 slag Substances 0.000 claims description 72
- 230000005587 bubbling Effects 0.000 claims description 45
- 238000005070 sampling Methods 0.000 claims description 16
- 239000006260 foam Substances 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000007664 blowing Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000005507 spraying Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 7
- 238000003860 storage Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 239000007789 gas Substances 0.000 description 4
- 238000012954 risk control Methods 0.000 description 4
- 238000009628 steelmaking Methods 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000002844 melting Methods 0.000 description 3
- 230000008018 melting Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010309 melting process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000012149 noodles Nutrition 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000004544 sputter deposition Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C5/00—Manufacture of carbon-steel, e.g. plain mild steel, medium carbon steel or cast steel or stainless steel
- C21C5/28—Manufacture of steel in the converter
- C21C5/30—Regulating or controlling the blowing
- C21C5/32—Blowing from above
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C2300/00—Process aspects
- C21C2300/06—Modeling of the process, e.g. for control purposes; CII
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Materials Engineering (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The invention relates to a method and a device for predicting splashing risk of a converter, wherein the method comprises the following steps: monitoring X, Y, Z triaxial oxygen lance vibration acceleration data; determining the splashing risk probability of the converter according to the probability; judging whether the splash risk probability is larger than a set threshold value; if yes, predicting the splash risk; if not, no splash risk is predicted. The method provides a brand new splash risk prediction mode, takes X, Y, Z triaxial oxygen lance vibration acceleration data as a monitoring object, and determines the splash risk probability of the converter; compared with parameters such as unidirectional oxygen lance amplitude, sound intensity change, converter surface image and the like, the X, Y, Z triaxial oxygen lance vibration acceleration can reflect the real situation in the furnace in an omnibearing manner, particularly the characteristic of oxygen lance vibration acceleration, can reflect the furnace pressure more truly, and can further improve the prediction accuracy and timeliness of the splash risk probability.
Description
Technical Field
The invention relates to the field of converter steelmaking, in particular to a splashing risk prediction method of a converter.
Background
The oxygen top-blown converter has the characteristics of high production efficiency and low cost, and is currently becoming a main steelmaking device. Slag melting is a key process in converter steelmaking, whether the slag melting process is stable or not directly influences the quality and steelmaking efficiency of steel, and if splashing occurs during slag melting, serious waste of raw materials can be caused, and accidents such as casualties, equipment damage and the like can be caused.
Therefore, in order to ensure that the slag melting can be stably carried out and avoid splash accidents, the method is firstly observed manually in the prior art, but is limited by experience, proficiency and other factors, so that the stability and the accuracy of a detection result are easy to cause, the efficiency is low, and the time is delayed; secondly, the splash risk is predicted by monitoring the amplitude, the sound intensity change, the image analysis, the buoyancy force borne by the oxygen lance and the like of the oxygen lance, but the predicted splash risk reflects the slag thickness state of the converter, so that the predicted effect is poor and needs to be improved.
Disclosure of Invention
In order to solve one of the above technical problems, the present invention provides a method for predicting splashing risk of a converter, including:
s1: monitoring X, Y, Z triaxial oxygen lance vibration acceleration data;
s2: determining the splashing risk probability of the converter according to the X, Y, Z triaxial oxygen lance vibration acceleration data;
s3: judging whether the splash risk probability is larger than a set threshold value;
s4: if yes, predicting the splash risk;
s5: if not, no splash risk is predicted.
Further, before step S1, step S0 is further included: determining sampling frequencies of monitoring X, Y, Z triaxial azimuth oxygen lance vibration acceleration data, comprising:
1a: acquiring the current oxygen lance vibration acceleration;
1b: calculating the current vibration frequency of slag foam according to the current vibration acceleration of the oxygen lance;
1c: and setting the sampling frequency for monitoring the vibration acceleration data of the oxygen lance according to the current vibration frequency of the slag foam.
Further, the step of determining the sampling frequency further includes:
setting a sampling frequency determination period T, and after one period T is finished, recursively executing steps 1a-1c to redetermine the sampling frequency according to the current oxygen lance vibration acceleration.
Further, step S2 includes:
according to the oxygen lance vibration acceleration data of the triaxial directions at each moment X, Y, Z, vector synthesis is carried out to determine the total oxygen lance vibration acceleration at each moment;
and calculating the ratio of the current value of the total vibration acceleration of the oxygen lance to the trend value at each moment, and taking the ratio as the splashing risk probability of the converter.
Further, step S2 includes:
constructing and training a prediction model, wherein the prediction model comprises a correlation relation between X, Y, Z triaxial oxygen lance vibration acceleration data and furnace pressure and slag bubbling degree;
inputting currently monitored X, Y, Z triaxial oxygen lance vibration acceleration data into a prediction model, and outputting current furnace pressure and current slag bubbling degree;
and determining the splash risk probability in the furnace according to the pressure in the furnace and the current slag bubbling degree.
Further, the predictive model includes:
the input module is used for inputting X, Y, Z triaxial oxygen lance vibration acceleration data;
the total extraction module is used for extracting the characteristics of the pressure in the furnace and the bubbling degree of slag according to the vibration acceleration data of the oxygen lance in the XYZ direction;
the output module is used for outputting the current furnace pressure and the slag bubbling degree according to the characteristics of the furnace pressure and the slag bubbling degree;
the splash risk probability is calculated according to equation (1).
P=f(at)/f(Ft)(1)
Wherein at is the current vibration acceleration value; ft is the predicted value of the pressure in the furnace and the slag bubbling degree at the next time; p is the splash risk probability.
Further, the predictive model includes:
the input module is used for inputting X, Y, Z triaxial oxygen lance vibration acceleration data;
the first extraction module is used for extracting the pressure characteristics of the furnace according to the oxygen lance vibration acceleration data in the XY direction; the second extraction module is used for extracting the slag bubbling degree characteristics according to the vibration acceleration data of the oxygen lance in the Z direction;
the output module is used for outputting the current furnace pressure according to the furnace pressure characteristics; outputting the slag bubbling degree according to the slag bubbling degree characteristics;
calculating a splash risk probability according to formula (2);
P=K1C1+K2C2(2)
wherein K1 and K2 are respectively weighting coefficients of the current furnace pressure and the current slag bubbling degree, C1 and C2 are respectively the current furnace pressure and the current slag bubbling degree, and P is the splash risk probability.
Further, the method further comprises the following steps: s6: and a shielding step, when the splash risk is predicted, judging whether events such as feeding, oxygen lance lifting and the like occur, and if so, shielding the splash risk judging result.
Further, the method further comprises the following steps: s7, automatic control: and according to the splash risk prediction result, if the splash risk is predicted, adopting one or more of pressurizing and spraying, reducing oxygen blowing flow of the oxygen lance and reducing the height operation of the oxygen lance.
On the other hand, the invention also provides a splashing risk prediction device of the converter, which is used for executing any splashing risk prediction method, and comprises the following steps: the monitoring module is used for monitoring X, Y, Z triaxial oxygen lance vibration acceleration data; the determining module is used for determining the splashing risk probability of the converter according to the X, Y, Z triaxial-azimuth oxygen lance vibration acceleration data; the judging module is used for judging whether the splash risk probability is larger than a set threshold value or not and the predicting module is used for predicting whether the splash risk occurs or not.
The invention provides a method and a device for predicting the splashing risk of a converter, which provide a brand-new splashing risk prediction mode, take X, Y, Z triaxial oxygen lance vibration acceleration data as a monitoring object and determine the prediction result of the splashing risk probability of the converter; compared with parameters such as unidirectional oxygen lance amplitude, sound intensity change, converter surface image and the like, the X, Y, Z triaxial oxygen lance vibration acceleration can reflect the real situation in the furnace in an omnibearing manner, particularly the characteristic of oxygen lance vibration acceleration, can reflect the furnace pressure more truly, and can further improve the prediction accuracy and timeliness of the splash risk probability.
Drawings
FIG. 1 is a flow chart of one embodiment of a method of predicting the risk of splashing in a converter in accordance with the present invention;
FIG. 2 is a front view of the rotary kiln of the present invention;
FIG. 3 is a top view of the rotary kiln of the present invention;
FIG. 4 is an enlarged view of the sensor assembly of the rotary kiln of the present invention;
FIG. 5 is a test chart of one embodiment of a method of predicting the risk of splashing in a converter in accordance with the present invention;
fig. 6 is a schematic diagram showing an embodiment of an automatic control procedure of the method for predicting a risk of splashing in a converter according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, in the embodiment of the present invention, directional indications such as up, down, left, right, front, and rear … … are referred to, and the directional indications are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture, and if the specific posture is changed, the directional indications are correspondingly changed. In addition, if there are descriptions of "first, second", "S1, S2", "step one, step two", etc. in the embodiments of the present invention, the descriptions are only for descriptive purposes, and are not to be construed as indicating or implying relative importance or implying that the number of technical features indicated or indicating the execution sequence of the method, etc. it will be understood by those skilled in the art that all matters in the technical concept of the present invention are included in the scope of this invention without departing from the gist of the present invention.
As shown in fig. 1, the present invention provides a method for predicting a splashing risk of a converter, comprising:
s1: monitoring X, Y, Z triaxial oxygen lance vibration acceleration data;
s2: determining the splashing risk probability of the converter according to the X, Y, Z triaxial oxygen lance vibration acceleration data;
s3: judging whether the splash risk probability is larger than a set threshold value;
s4: if yes, predicting the splash risk;
s5: if not, no splash risk is predicted.
In the embodiment, a method for predicting the splashing risk of the converter is provided, a brand new splashing risk prediction mode is provided, oxygen lance vibration acceleration data in a X, Y, Z triaxial direction is used as a monitoring object, and a prediction result of the splashing risk probability of the converter is determined; optionally, but not exclusively, a sensor such as a crystal oscillation accelerometer is arranged on the oxygen lance bracket to detect the three-dimensional vibration acceleration of the oxygen lance. Compared with parameters such as unidirectional oxygen lance amplitude, sound intensity change, converter surface image and the like, the X, Y, Z triaxial oxygen lance vibration acceleration can reflect the real situation in the furnace in an omnibearing manner, particularly the characteristic of the oxygen lance vibration acceleration, can reflect the furnace pressure more truly, and researches show that the oxygen lance vibration acceleration is positively related to the furnace pressure, so that the prediction precision and timeliness of the splash risk probability can be further improved.
Specific:
in step S1, preferably, as shown in fig. 2, in order to avoid the influence of the production operations such as replacement of the oxygen lance, maintenance of equipment, etc. on the detection of the oxygen lance vibration acceleration data, one or more acceleration sensors may be optionally but not limited to be installed on the oxygen lance lifting trolley, so that the oxygen lance vibration acceleration data in the X, Y, Z triaxial direction can be continuously and stably detected. Specifically, as shown in fig. 2-4, the oxygen lance vibration acceleration is optionally but not limited to be detected by an online vibration test sensor 1, and is optionally but not limited to be mounted on an oxygen lance lifting trolley platform 4 through a protective cover 2 and a welding plate 3. More preferably, the data is collected and then optionally but not exclusively subjected to a data preprocessing step such as filtering.
More preferably, in order to ensure the true accuracy of the oxygen lance vibration acceleration data and avoid the interference of the noise wave, thereby analyzing the internal condition of the converter in real time, further improving the accuracy and timeliness of the early warning function that the subsequent process may splash, the monitoring oxygen lance vibration acceleration data is also optionally but not limited to setting the proper sampling frequency, that is, before step S1, the method further comprises step S0: the sampling frequency of the oxygen lance vibration acceleration data monitoring X, Y, Z triaxial orientation is determined. Specifically, the step of determining the sampling frequency may optionally include, but is not limited to:
1a: acquiring the current oxygen lance vibration acceleration; for example, at the time t, collecting the current oxygen lance vibration acceleration through a vibration acceleration sensor; more specifically, for the convenience of calculation, the current oxygen lance vibration acceleration can be oxygen lance vibration acceleration data of a certain azimuth or vector sum of X, Y, Z triaxial oxygen lance vibration acceleration data.
1b: calculating the current vibration frequency of slag foam according to the current vibration acceleration of the oxygen lance; for example, the frequency analysis is carried out on the vibration acceleration signal by applying Fourier transformation on the vibration acceleration of the current oxygen lance, the vibration frequency related to the pressure in the furnace and the slag bubbling degree is determined according to a spectrogram, and a time-frequency diagram is made through inverse transformation to obtain the current vibration frequency of slag foam;
1c: setting the sampling frequency of monitoring oxygen lance vibration acceleration data according to the current vibration frequency of slag foam; illustratively, to avoid clutter interference, the sampling frequency of the lance vibration acceleration data is optionally, but not limited to, set to 4-5 times the current vibration frequency of the slag foam.
In step S2, two preferred embodiments are given below, but not limited to, the invention is based on theoretical research that the vibration acceleration of the oxygen lance is positively correlated to the splash risk probability of the converter, and the technical proposal under the guidance of the technical idea should be included in the protection scope of the invention.
In a first embodiment, optionally but not limited to, including:
2a, according to the oxygen lance vibration acceleration data of the triaxial directions at each moment X, Y, Z, vector synthesis is carried out to determine the total oxygen lance vibration acceleration at each moment;
2b, calculating the ratio of the current value of the total vibration acceleration of the oxygen lance to the trend value at each moment, wherein the ratio is taken as the splashing risk probability of the converter; specifically, for the current value, at any time t, vector summation is carried out on the monitored vibration acceleration data of the XYZ three-axis azimuth oxygen lance at the time to obtain the current value; for trend values, the trend values within a period of time are determined by adopting any one method of an extended time interval method, a moving average method or a least square method, 10 points are defined and calculated every sampling in order to characterize the severity of a splashing event and the relation of vibration acceleration, a current value curve (real-time line) of the total vibration acceleration of the oxygen lance and a trend value curve (trend line) are obtained as shown in fig. 5, and then the ratio of the current value curve (real-time line) to the trend value curve (trend line) at the moment t is calculated to reflect the splashing risk index, so that the splashing risk probability of the converter is determined. By way of example, the deviation of the measurement from the normal range is determined by the ratio of the current value of the vibration acceleration of the oxygen lance to the trend value at each time, and optionally, but not exclusively, the vibration in the upper line and the lower line of the trend value is set to be larger as the ratio of the current value to the trend value is larger, that is, the larger the splash risk index is, the larger the probability of occurrence of splash is, and a splash risk probability model is established. By way of example, and optionally but not limited to, setting to 40% from normal range, then the risk of splash is predicted to occur.
In a second embodiment, optionally but not limited to, includes:
2a', constructing and training a prediction model, wherein the prediction model comprises a correlation relation between X, Y, Z triaxial oxygen lance vibration acceleration data and furnace internal pressure and slag bubbling degree; more specifically, the prediction model comprises a correlation relation between oxygen lance vibration acceleration in an XY direction and pressure in the furnace, and a correlation relation between oxygen lance vibration acceleration data in a Z direction and the overgun degree of slag in the furnace; according to the mode, the oxygen lance vibration acceleration data in the XYZ three-axis directions are decoupled, the horizontal oxygen lance vibration acceleration in the XY two directions is reflected to the furnace pressure in the horizontal direction, the vertical oxygen lance vibration acceleration in the Z direction is reflected to the slag bubbling degree in the vertical direction, the real situation of the converter can be accurately reflected, and the prediction accuracy and timeliness of splashing risks are further improved.
Specifically, the correlation relation of each data in the prediction model is optionally but not limited to fitting and determining based on smelting data of 100 heats, preferably based on any form of neural network model.
Illustratively, a predictive model is first constructed, optionally in any form, but not limited to, using prior art neural network models, the structure comprising:
the input module is used for inputting X, Y, Z triaxial oxygen lance vibration acceleration data;
and the extraction module is used for extracting the pressure characteristic in the furnace and the slag bubbling degree characteristic according to the vibration acceleration of the oxygen lance in the XYZ three-axis direction. In particular, a smaller 18-layer ResNet network is used, optionally but not limited to, a preferably lightweight backbone network, such as ResNet, mobileNet, shuffleNet, etc., for example a ResNet18 (0.5). More specifically, it may also optionally but not be limited to include: specifically, the optional but not limited to include: the first extraction module is used for extracting the pressure characteristics of the furnace according to the oxygen lance vibration acceleration data in the XY direction; the second extraction module is used for extracting the slag bubbling degree characteristics according to the vibration acceleration data of the oxygen lance in the Z direction;
and the output module is used for outputting the current furnace pressure and slag bubbling degree values according to the furnace pressure characteristics and the slag bubbling degree characteristics.
And then, smelting data of 100 heats is selected, 80 heats are selected as a training sample set, 20 heats are selected as a verification sample set, the prediction model based on the neural network is sequentially input, a loss function is reduced in an iteration mode, various parameters of the prediction model are optimized and corrected, and a trained neural network model, namely a prediction model, is obtained, and the correlation relation between oxygen lance vibration acceleration data of X, Y, Z triaxial directions, furnace pressure and slag bubbling degree is reflected.
2b', inputting currently monitored X, Y, Z triaxial oxygen lance vibration acceleration data into a prediction model, and outputting current furnace pressure and current slag bubbling degree;
2c', determining the probability of splash risk in the furnace according to the pressure in the furnace and the current slag bubbling degree.
Specifically, if the pressure characteristic and the slag bubbling degree characteristic of the furnace are integrally extracted according to the vibration acceleration of the oxygen lance in the XYZ three-axis direction, the splash risk probability is calculated according to the formula (1).
P=f(at)/f(Ft)(1)
Wherein at is the current vibration acceleration value; ft is the predicted value of the pressure in the furnace and the slag bubbling degree at the next time; p is the splash risk probability.
Extracting pressure characteristics in the furnace according to the oxygen lance vibration acceleration data of the XY direction; when the characteristics of the slag bubbling degree are extracted according to the vibration acceleration data of the oxygen lance in the Z direction, the splash risk probability is calculated according to a formula (2) by adopting a weighting coefficient summation mode optionally but not exclusively.
P=K1C1+K2C2(2)
Wherein K1 and K2 are weighting coefficients, C1 and C2 are the current furnace pressure and the current slag bubbling degree, and P is the splash risk probability. Specifically, the weighting coefficients K1 and K2 may be arbitrarily set by those skilled in the art according to the actual converter conditions.
In the above preferred embodiment, a specific implementation manner of the method for predicting the splashing risk of the converter is provided, which takes the data of the oxygen lance vibration acceleration in the X, Y, Z triaxial directions as a whole, synthesizes the total radial vector of the oxygen lance vibration acceleration, comprehensively reflects the three-dimensional space state in the converter, takes the ratio of the current value of the oxygen lance vibration acceleration to the trend value at each moment as an evaluation standard, namely the splashing risk probability, instead of simply taking the current value of the oxygen lance vibration acceleration as a direct evaluation standard, can fully reflect the extremely rapid change process of the state in the converter, such as the change process of the pressure in the converter and the slag bubbling degree, judges whether the splashing risk probability is larger than a set threshold value on the basis of the data, predicts that the splashing risk occurs if the splashing risk is not predicted, predicts the splashing phenomenon in advance, and gives an early warning in advance, and the prediction accuracy is higher.
More preferably, in smelting data of a plurality of times, the oxygen lance vibration acceleration signal is found to be positively correlated with the furnace internal pressure and the slag bubbling degree, and a correlation relation model between the oxygen lance vibration acceleration signal and the furnace internal pressure and the slag bubbling degree is optionally but not exclusively constructed so as to truly reflect the furnace internal pressure and the slag bubbling degree, and the root cause of the splashing phenomenon can be more fully reflected compared with the modes of oxygen lance amplitude, converter surface images and the like. Specifically, the root cause of the splash is that the expansion speed of the gas in the furnace is larger than the discharge speed, the pressure in the furnace continuously rises to push the slag to rise, and the phenomenon is that: slag rises rapidly, the height exceeds the furnace mouth height, and splashing occurs. If the expansion speed and the discharge speed of the gas in the furnace are equal, the pressure in the furnace and the slag height are in an equilibrium state, and no splashing occurs even if the slag height is increased, so that the slag height is increased to cause splashing (the slag thickness is large in damping, the sound intensity is small, the amplitude is small, the buoyancy is large) in the prior art, and the slag thickness, namely the slag height, is taken as a detection object by a method for detecting the sound intensity, the amplitude and the buoyancy, so that the splashing is predicted to be practically biased. In practice, the slag is not necessarily splashed, just like a household noodles, and gas is generated after the pot is opened, so that foam rises. If the gas flame is suitable, the bubble speed and the exhaust speed are equal, the foam can not fall out even if reaching the edge of the pot after the pot is opened, the slag is thin and not necessarily not sprayed, the pot is just like a household cooking surface, if the flame is not well controlled, a large amount of bubbles are generated after the pot is opened, and the foam falls out at the moment of opening the pot. Therefore, the slag height is taken as a detection object, only the alarm can be given, the early forecast can not be carried out, and the control measures can not be taken in time to prevent splashing. The invention is innovative in that the oxygen lance vibration acceleration is taken as a monitoring object, the pressure in the furnace and the bubbling degree of slag are reflected on the side surface, and the splashing risk probability is reflected for the root cause of the splashing, in the preferred scheme, the actual value of the oxygen lance vibration acceleration is compared with the trend value, more preferably, the splashing risk probability is taken as an evaluation index, the law of positive correlation between the vibration acceleration and the pressure in the furnace and the bubbling degree of slag is constructed, the variation trend of the pressure in the furnace and the bubbling degree of slag is predicted by a method of detecting and calculating the vibration acceleration, and the splashing risk can be predicted 15 to 60 seconds in advance, so that a user has enough time to take measures to suppress the splashing.
More preferably, in the steps S3 to S5, it is determined whether the splash risk probability is greater than a set threshold; specifically, the set threshold value can be determined according to the size, model, slag quantity in the converter and the like, and if yes, the splashing risk is predicted; if not, no splash risk is predicted.
More preferably, the method for predicting splashing risk of the converter according to the present invention further optionally includes, but is not limited to, step S6: and a shielding step, when the splash risk is predicted, judging whether events such as feeding, oxygen lance lifting and the like occur, and if so, shielding the splash risk judging result.
In the embodiment, the method for predicting the splashing risk of the converter is provided, the influence of events such as molten steel slag quantity change, oxygen lance lifting and charging on the detection result of vibration acceleration data of the oxygen lance is considered, and the monitoring on the oxygen lance vibration and speed data on the basis is inaccurate, so that the obtained splashing risk prediction result on the basis is possibly inaccurate, the shielding step is additionally provided, and when the events such as charging and oxygen lance lifting occur, even if the splashing risk is predicted, the shielding step is shielded, so that the false early warning is avoided, the subsequent false operation is caused, the accuracy of the method for predicting the splashing risk is further improved, and the early warning of the splashing is realized 15-50 seconds in advance.
More preferably, the method for predicting the splashing risk of the converter according to the present invention may further optionally, but not exclusively, include: s7, automatic control: and according to the splash risk prediction result, if the splash risk is predicted, adopting any one or more of operations such as pressurizing the spray, reducing the oxygen blowing flow of the oxygen lance, reducing the height of the oxygen lance and the like.
Specifically, optionally but not limited to, setting a control level according to the splash risk probability, and dynamically adjusting the processes of the oxygen lance, the charging and the like so as to dynamically adjust the processes of the oxygen lance and the charging, thereby relieving the splash risk and avoiding the occurrence of splashing of the converter. By way of example, as shown in fig. 6, a preferred embodiment of automatic control is provided, whether a splash early warning occurs is judged, if not, everything is done normally, and monitoring and judgment are continued; if splash early warning occurs, the method is optional but not limited to low risk early warning, wherein the oxygen lance descends xx mm, during medium risk early warning, xx kg of material is added simultaneously when xx mm descends, and during high risk early warning, xx% descends, and the specific value can be set arbitrarily by a person skilled in the art according to the actual condition of the converter; and continuously monitoring and judging whether the early warning value is normal, if not, continuing to adjust, and if so, adjusting the gun position back to the original position.
On the other hand, the invention also provides a splashing risk prediction device of the converter, so as to execute the splashing prediction method, which comprises the following steps: the monitoring module is used for monitoring X, Y, Z triaxial oxygen lance vibration acceleration data; the determining module is used for determining the splashing risk probability of the converter according to the X, Y, Z triaxial-azimuth oxygen lance vibration acceleration data; the judging module is used for judging whether the splash risk probability is larger than a set threshold value or not and the predicting module is used for predicting whether the splash risk occurs or not. Preferably, the monitoring module is optionally but not limited to a vibration acceleration sensor, preferably arranged on the oxygen lance lifting trolley, and has longer service life and higher monitoring precision compared with the sensor arranged below the oxygen lance or the bracket without being influenced by replacing the oxygen lance.
Specifically, the prediction device is created based on the above prediction method, and the technical effects and the combination of technical features are not described herein.
On the other hand, the invention also provides a converter, which adopts any splashing risk control method or comprises any splashing risk control device.
In another aspect, the present invention also provides a computer storage medium storing executable program code; the executable program code is configured to perform any of the sputtering risk control methods described above.
In another aspect, the present invention further provides a terminal device, including a memory and a processor; the memory stores program code executable by the processor; the program code is for performing any of the splash risk control methods described above.
For example, the program code may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to perform the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments describe the execution of the program code in the terminal device.
The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the terminal devices may also include input-output devices, network access devices, buses, and the like.
The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage may be an internal storage unit of the terminal device, such as a hard disk or a memory. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used for storing the program codes and other programs and data required by the terminal equipment. The memory may also be used to temporarily store data that has been output or is to be output.
The above splash risk prediction apparatus, the computer storage medium, and the terminal device are created based on the above splash risk prediction method, and the technical effects and advantages thereof are not repeated herein, and each technical feature of the above embodiment may be arbitrarily combined, so that the description is concise, and all possible combinations of each technical feature in the above embodiment are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope described in the present specification.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A method for predicting the risk of splashing in a converter, comprising:
s1: monitoring X, Y, Z triaxial oxygen lance vibration acceleration data;
s2: determining the splashing risk probability of the converter according to the X, Y, Z triaxial oxygen lance vibration acceleration data;
s3: judging whether the splash risk probability is larger than a set threshold value;
s4: if yes, predicting the splash risk;
s5: if not, no splash risk is predicted.
2. The splash risk prediction method according to claim 1, characterized in that before step S1, further comprising step S0: determining sampling frequencies of monitoring X, Y, Z triaxial azimuth oxygen lance vibration acceleration data, comprising:
1a: acquiring the current oxygen lance vibration acceleration;
1b: calculating the current vibration frequency of slag foam according to the current vibration acceleration of the oxygen lance;
1c: and setting the sampling frequency for monitoring the vibration acceleration data of the oxygen lance according to the current vibration frequency of the slag foam.
3. The splash risk prediction method according to claim 2, characterized in that the step of determining the sampling frequency further comprises:
setting a sampling frequency determination period T, and after one period T is finished, recursively executing steps 1a-1c to redetermine the sampling frequency according to the current oxygen lance vibration acceleration.
4. The splash risk prediction method according to claim 1, characterized in that step S2 comprises:
according to the oxygen lance vibration acceleration data of the triaxial directions at each moment X, Y, Z, vector synthesis is carried out to determine the total oxygen lance vibration acceleration at each moment;
and calculating the ratio of the current value of the total vibration acceleration of the oxygen lance to the trend value at each moment, and taking the ratio as the splashing risk probability of the converter.
5. The splash risk prediction method according to claim 1, characterized in that step S2 comprises:
constructing and training a prediction model, wherein the prediction model comprises a correlation relation between X, Y, Z triaxial oxygen lance vibration acceleration data and furnace pressure and slag bubbling degree;
inputting currently monitored X, Y, Z triaxial oxygen lance vibration acceleration data into a prediction model, and outputting current furnace pressure and current slag bubbling degree;
and determining the splash risk probability in the furnace according to the pressure in the furnace and the current slag bubbling degree.
6. The splash risk prediction method according to claim 5, wherein the prediction model comprises:
the input module is used for inputting X, Y, Z triaxial oxygen lance vibration acceleration data;
the total extraction module is used for extracting the characteristics of the pressure in the furnace and the bubbling degree of slag according to the vibration acceleration data of the oxygen lance in the XYZ direction;
the output module is used for outputting the current furnace pressure and the slag bubbling degree according to the characteristics of the furnace pressure and the slag bubbling degree;
the splash risk probability is calculated according to equation (1).
P=f(at)/ f(Ft) (1)
Wherein at is the current vibration acceleration value; ft is the predicted value of the pressure in the furnace and the slag bubbling degree at the next time; p is the splash risk probability.
7. The splash risk prediction method according to claim 5, wherein the prediction model comprises:
the input module is used for inputting X, Y, Z triaxial oxygen lance vibration acceleration data;
the first extraction module is used for extracting the pressure characteristics of the furnace according to the oxygen lance vibration acceleration data in the XY direction;
the second extraction module is used for extracting the slag bubbling degree characteristics according to the vibration acceleration data of the oxygen lance in the Z direction;
the output module is used for outputting the current furnace pressure according to the furnace pressure characteristics; outputting the slag bubbling degree according to the slag bubbling degree characteristics;
calculating a splash risk probability according to formula (2);
P=K1C1+K2C2(2)
wherein K1 and K2 are respectively weighting coefficients of the current furnace pressure and the current slag bubbling degree, C1 and C2 are respectively the current furnace pressure and the current slag bubbling degree, and P is the splash risk probability.
8. The splash risk prediction method according to claim 1, characterized by further comprising: s6: and a shielding step, when the splash risk is predicted, judging whether events such as feeding, oxygen lance lifting and the like occur, and if so, shielding the splash risk judging result.
9. The splash risk prediction method according to claims 1 to 8, characterized by further comprising: s7, automatic control: and according to the splash risk prediction result, if the splash risk is predicted, adopting one or more of pressurizing and spraying, reducing oxygen blowing flow of the oxygen lance and reducing the height operation of the oxygen lance.
10. A splashing risk prediction apparatus of a converter, characterized by being configured to perform the splashing risk prediction method according to any one of claims 1-9, comprising: the monitoring module is used for monitoring X, Y, Z triaxial oxygen lance vibration acceleration data; the determining module is used for determining the splashing risk probability of the converter according to the X, Y, Z triaxial-azimuth oxygen lance vibration acceleration data; the judging module is used for judging whether the splash risk probability is larger than a set threshold value or not and the predicting module is used for predicting whether the splash risk occurs or not.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310842721.6A CN117273432A (en) | 2023-07-10 | 2023-07-10 | Converter splash risk prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310842721.6A CN117273432A (en) | 2023-07-10 | 2023-07-10 | Converter splash risk prediction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117273432A true CN117273432A (en) | 2023-12-22 |
Family
ID=89214886
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310842721.6A Pending CN117273432A (en) | 2023-07-10 | 2023-07-10 | Converter splash risk prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117273432A (en) |
-
2023
- 2023-07-10 CN CN202310842721.6A patent/CN117273432A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10379001B2 (en) | Detecting apparatus, detection method, and program | |
CN111486893A (en) | Bridge structure health monitoring and early warning system and early warning method | |
US10228994B2 (en) | Information processing system, information processing method, and program | |
EP3147902B1 (en) | Sound processing apparatus, sound processing method, and computer program | |
JP2018009906A (en) | Hammering sound diagnosis device and diagnosis method | |
CN110796305A (en) | Hearth safety early warning method, system, equipment and storage medium | |
CN111832813A (en) | Method and system for predicting fault activation water inrush of submarine tunnel | |
CN115239070A (en) | Watershed water environment organic pollutant monitoring overall process quality control index evaluation system | |
US20050102116A1 (en) | High-resolution intelligent rotor machine diagnostic system and method | |
US20150094622A1 (en) | System and method for measuring reaction time of a subject | |
KR102216306B1 (en) | System and method for predicting fatigue life of ship | |
CN115937504A (en) | Bridge structure damage identification method and system | |
CN117273432A (en) | Converter splash risk prediction method and device | |
CN109359803B (en) | Reliability evaluation method and device | |
JP5133276B2 (en) | Defect detection method for structures | |
JP2002131291A (en) | Method and device for inspecting structure | |
CN116258087B (en) | Matte grade soft measurement method and device, electronic equipment and storage medium | |
CN115034276A (en) | Method, device and system for detecting droplet distribution of high-flow spray head | |
CN112857419B (en) | Data testing method and device based on vehicle multi-sensor | |
JP6471632B2 (en) | Mold level estimation method, level level control method and apparatus in mold | |
CN112577403B (en) | Method and system for evaluating capacitor calibration effect | |
JP2000144229A (en) | Method for predicting slopping in converter and device therefor | |
JP6160283B2 (en) | Slapping prediction method in converter blowing. | |
CN111947730A (en) | Continuous casting molten pool liquid level detection system and continuous casting molten pool liquid level control method | |
JP7207118B2 (en) | Charging method determination method, charging method determination device, and charging method determination program |
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 |