CN117094576A - Method for quantitatively evaluating stability degree of blast furnace condition - Google Patents
Method for quantitatively evaluating stability degree of blast furnace condition Download PDFInfo
- Publication number
- CN117094576A CN117094576A CN202210542614.7A CN202210542614A CN117094576A CN 117094576 A CN117094576 A CN 117094576A CN 202210542614 A CN202210542614 A CN 202210542614A CN 117094576 A CN117094576 A CN 117094576A
- Authority
- CN
- China
- Prior art keywords
- stability
- index
- blast furnace
- sub
- condition
- 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 67
- 238000004364 calculation method Methods 0.000 claims abstract description 66
- 238000011156 evaluation Methods 0.000 claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000012512 characterization method Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 235000019580 granularity Nutrition 0.000 claims description 44
- 230000008859 change Effects 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 11
- 238000005096 rolling process Methods 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000003723 Smelting Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 239000002245 particle Substances 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000033228 biological regulation Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 description 16
- 238000003745 diagnosis Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- 229910052742 iron Inorganic materials 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 239000000725 suspension Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000004171 remote diagnosis Methods 0.000 description 2
- 238000009628 steelmaking Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Abstract
A method for quantitatively evaluating the stability of blast furnace conditions belongs to the field of process management. Selecting core key parameters capable of representing the running condition of the blast furnace, determining evaluation dimensions capable of macroscopically representing the stability degree of the blast furnace, and taking each dimension as a sub-index of total stability; constructing a calculation formula of a stability index of the blast furnace, and realizing quantitative characterization of the stability of the furnace condition; quantitatively calculating and tracking the running state and the stability of the blast furnace from different dimension time-sharing granularity; quantitative calculation is carried out on the overall stability of the blast furnace from different time granularity, and quantitative calculation of different time granularity is realized; through quantitative measurement and calculation of the stability of the furnace condition, operators are helped to evaluate the furnace condition in real time and quickly, and corresponding measures are taken to improve indexes or avoid production process disorder. The quantitative representation and real-time display of the stability of the furnace condition realize the conversion from qualitative to quantitative of the stability degree of the furnace condition of the blast furnace, and provide a basis for continuous on-line monitoring and tracking of the stability trend of the furnace condition.
Description
Technical Field
The invention belongs to the field of process management, and particularly relates to a quantitative evaluation method for evaluating the stability of a blast furnace condition.
Background
The blast furnace condition refers to a certain running state of main production technical indexes and running characterization parameters of the blast furnace under a certain smelting condition; the stable operation of the blast furnace refers to the production state that main production technical indexes and operation characterization parameters of the blast furnace are in a reasonable fluctuation range under certain smelting conditions.
The blast furnace is stable and smooth, and is the basis for obtaining good technical and economic indexes, reducing the cost and prolonging the service life, so that the method has important significance in timely diagnosing and evaluating the stability of the blast furnace, improving the indexes of the blast furnace, reducing the cost of molten iron and prolonging the service life of the blast furnace.
1. The state of the art regarding the evaluation of the degree of stability of the furnace conditions of a blast furnace:
at present, related data and documents for quantitatively evaluating the stability of the blast furnace are not found out in detail abroad; some domestic manufacturers quantitatively evaluate the running condition of the blast furnace, and representative companies and adopted technologies are as follows:
1) The forward running condition of the blast furnace is analyzed by forward running index:
the idea is that Liu Yuncai was proposed in 1998, 12 months in the release paper of iron making 6, the proposal of analyzing the blast furnace forward running state by forward running index. The method is characterized in that the running state of the furnace is estimated by using the times of sliding, material collapse and material suspension, a certain weight is set, and the running index is calculated to calculate the running degree of the blast furnace:
wherein: s is S x -an antegrade index;
T L counting the number of material collapse times (the stock rod suddenly descends by more than 0.5 m) in a calendar day; the furnace condition weight impact is defined as 1;
X L counting the number of suspensions in calendar days (the rod is drawn across more than 1/4 of a batch); for furnace conditions, the weight impact is defined as 3;
n is the number of blast furnace seats;
d-calculating calendar days.
Description: the measuring device for blast furnace is a measuring element for measuring the depth of the top material surface of the blast furnace and controlling the feeding time, and has the modes of machinery, microwaves and the like, and 2-3 measuring rods are uniformly distributed in the circumferential direction. When the blast furnace is in normal production, the stock rod is placed on the material surface to track the descending depth of the furnace burden, when the depth reaches a control target, the control system sends out a stock rod lifting signal, and after the stock rod is lifted, the blast furnace starts to charge; after the loading is completed, the trial rod is lowered again, the material level is tracked, and the circulation is performed, and a section of material is generally loaded for about 9-13 minutes. If the detection depth of any one of the trial rods suddenly drops by more than 0.5m in the process of detecting the material level of the trial rod, or the blast furnace just finishes charging materials, the detection depth of the trial rod exceeds the depth of more than 0.5m when the trial rod is lifted up last time, and the trial rod is considered to have material collapse; if the depth of all the trial rods is kept unchanged (i.e. the depth is displayed to be 'crossed') during the process of checking the material level by the trial rods, the time reaches about 1/4 of the feeding time (about 2-3 minutes), namely the suspension (the material level is not lowered and does not move).
2) Establishing an antegrade index and applying the antegrade index to guide actual production:
cheng Wangsheng et al, 12.6.A paper for applying the forward index to a horse steel blast furnace was published in the 6 th period of iron making, and the concept of the forward index is proposed in 2014 by the horse steel, and the core idea and method are that various parameters of the blast furnace running in real time are compared with normal values thereof and scored by classification (according to importance), then the total score is calculated, and states are judged according to different scores and countermeasures are formulated.
2. The technology and the method adopted by the Bao steel at present are as follows:
the steel is currently subjected to qualitative evaluation on the condition of the blast furnace by an operating society by using five major elements capable of representing the running state of the blast furnace, different parameters contained in the five major elements and different levels of the parameters based on expert experience.
3. The prior technology for evaluating the stability degree of the blast furnace condition has the following problems:
1) The forward running condition of the blast furnace is analyzed by forward running index: the method can reflect the forward running condition of the blast furnace to a certain extent, but has obvious limitation, and the forward running condition judgment is far from enough to comprise the elements of pressure relation, gas utilization, furnace temperature, forward operation and the like because the forward running condition judgment only uses collapsed materials and suspended materials as forward running judgment elements of the blast furnace, and the forward running index can not be comprehensively and objectively judged by simply calculating the forward running index through the collapsed materials and the suspended materials.
2) Establishing an antegrade index and applying the antegrade index to guide actual production: the technology has systematic and scientific aspects, but does not quantitatively calculate the influence degree of different parameters and does not distinguish the essential difference between the blast furnace process parameters and the result parameters, and strictly speaking, the method is a technical management measure of a blast furnace running state 'detail check list' and then calculates the score according to a certain rule.
3) The current judging method of the treasures comprises the following steps: there is also a limit to the evaluation of long-term steady-state operation: (1) Not quantitatively evaluated, and is difficult to continuously and digitally analyze and judge; (2) Is a short-term state evaluation, and does not contain parameters which can represent a long-term state; (3) The representation capability (weight) of each representation furnace condition running state parameter to the furnace condition is not classified and classified, and the index data for comprehensively measuring the stability degree of the furnace condition is not available. (4) The technical and management countermeasures after the characterization parameters are out of control range are not indicated.
The patent of China with the grant bulletin number of CN 109685289B discloses a method, a device and a system for predicting the forward running of a blast furnace condition, which comprises the steps of collecting the current production condition and the current running data of the blast furnace; screening historical production conditions matched with the current production conditions and a corresponding reference furnace condition characterization parameter metering table from an operation historical database; searching a current grade value range to which a current running value belongs in a reference furnace condition characterization parameter value table, and current evaluation score value and current weight index; accumulating the score values obtained by multiplying the plurality of current evaluation score values and the current weight index to obtain the current furnace condition forward score value, and further predicting the current furnace condition forward condition of the blast furnace. The accuracy of the current blast furnace prediction is improved by taking the reference furnace condition representation parameter value table corresponding to the historical production condition as the current judgment reference. According to the technical scheme, the current data and the historical data are compared to obtain the furnace condition sequence data, but the historical furnace condition cannot be objectively evaluated, and the method cannot be used for transverse operation between different blast furnaces.
The Chinese patent with the authorized bulletin number of CN 101881955B discloses a blast furnace condition evaluation method, which is characterized in that each main aspect representing the working state of a blast furnace in a certain period is evaluated by adopting two different types of production parameters related to the main aspects or adopting historical data of various similar parameters related to the main aspects; and determining a first limit and a second limit according to the historical data distribution condition by taking the historical data mean value of each parameter as a reference, wherein a normal region is arranged in the first limit, a warning region is arranged between the first limit and the second limit, and a deterioration region is arranged outside the second limit. The operation state of this aspect is described by the largest one of the ratios of the number of data falling in each area to the total number of data. The technical scheme adopts weighted average to process to describe the whole working condition of the blast furnace. The concept of the patent for evaluating the furnace conditions is similar to that of the patent, and the same problem exists in evaluating the stability of the furnace conditions of the blast furnace.
Disclosure of Invention
The invention aims to provide a method for quantitatively evaluating the stability of a blast furnace condition. The method selects core key parameters capable of representing the running condition of the blast furnace, and constructs a blast furnace stability index calculation formula by using a big data analysis method, so that quantitative representation of the stability of the furnace condition is realized, the conversion from qualitative to quantitative of the stability degree of the blast furnace condition is realized, and a foundation is provided for continuous on-line monitoring and tracking of the stability trend of the furnace condition. The method comprises the steps of quantitatively calculating and tracking the running state and the stability of the blast furnace from different dimension time-sharing granularity; quantitative calculation is carried out on the overall stability of the blast furnace from different time granularity, and quantitative calculation of different time granularity is realized; through quantitative measurement and calculation of the stability of the furnace condition, operators are helped to evaluate the furnace condition in real time and quickly, and corresponding measures are taken to improve indexes or avoid production process disorder.
The technical scheme of the invention is as follows: the method for quantitatively evaluating the stability of the blast furnace condition is characterized by comprising the following steps of:
1) Selecting core key parameters capable of representing the running condition of the blast furnace, determining evaluation dimensions capable of macroscopically representing the stability degree of the blast furnace, and taking each dimension as a sub-index of total stability;
2) Constructing a calculation formula of the stability index of the blast furnace, realizing quantitative characterization of the stability of the furnace condition,
3) Quantitatively calculating and tracking the running state and the stability of the blast furnace from different dimension time-sharing granularity;
4) Quantitative calculation is carried out on the overall stability of the blast furnace from different time granularity, and quantitative calculation of different time granularity is realized;
5) Through quantitative measurement and calculation of the stability of the furnace condition, operators are helped to evaluate the furnace condition in real time and quickly, and corresponding measures are taken to improve indexes or avoid production process disorder.
Specifically, the method for quantitatively evaluating the stability degree of the blast furnace condition uses a big data analysis method to calculate and compare data including the stability evaluation dimension and stability sub-index, the stability sub-index and calculation, the overall stability index and calculation in real time, and outputs the calculation comparison result in real time, thereby realizing the conversion from qualitative to quantitative of the stability degree of the blast furnace condition and providing a basis for continuously monitoring and tracking the stability trend of the blast furnace condition on line.
Specifically, the core key parameters comprise blanking conditions, pressure relationships, hearth working conditions, gas flow distribution and operation furnace types; the evaluation dimension comprises a blanking state sub-index, a pressure relation sub-index, a hearth working condition sub-index, a gas flow distribution sub-index and an operation furnace sub-index.
Specifically, when calculating the stability sub-index parameter, the stability sub-index parameter is divided into sub-index parameter and score calculation and different time granularity sub-index calculation.
Further, when sub-index parameters and scores thereof are calculated, key parameters which can microscopically represent each dimension, namely sub-index, are selected according to the experience of blast furnace operating specialists and by combining big data analysis; determining the characterization capacity, namely the weight, of each parameter in each dimension according to the smelting principle and the operation experience of the blast furnace; two methods are set for each parameter weight, namely, a multiple linear regression method is based, and the weight is set by combining expert experience; secondly, after the model system operates on line, self-learning mining is carried out through the design of expert rules, and weights are dynamically and intelligently selected; then, calculating the score of each key parameter according to the distribution range of each parameter value; and finally, calculating the index score of each dimension according to the parameter item, the weight of each parameter and the score. I.e. sub-index = Σ (weight) 1 * Parameters (parameters) 1 Weight of + & n * Parameters (parameters) n )。
Further, when calculating the sub-indexes of different time granularities, the stability sub-indexes are divided into five time granularities according to the operation characteristics of the blast furnace and the daily monitoring parameter acquisition and calculation period: minute-level subindex, hour-level subindex, shift-level subindex, day-level subindex, and week-level subindex; the minute sub-index takes a 10 minute parameter mean value and a fluctuation amplitude as judgment basis; the hour sub-index takes an hour parameter mean value and a fluctuation amplitude as judgment basis; the class average sub-index takes a rolling 12-hour parameter mean value and an hour fluctuation amplitude as a judgment basis; the day-average sub-index takes the average value and the fluctuation amplitude of the 24-hour rolling parameter as the judgment basis; the Zhou Junji sub-index is based on the average value and fluctuation amplitude of the rolling parameter for 72 hours.
Specifically, the quantitative measurement and calculation of the stability of the furnace condition comprises the following steps:
(1) Calculation of the overall stability index:
firstly, according to the influence degree of sub-indexes of five dimensions on furnace conditions and indexes, namely the representation capability of a certain sub-index on the stability degree of the furnace conditions, determining the weight of each sub-index; then weighting and calculating the total stability index by the sub-index items and the weight of each sub-index, namely the stability index=Σ (weight) 1 * Sub-index 1 Weight of + & n * Sub-index n )；
(2) Different time particle size stability index:
the stability index is divided into five time granularities according to sub-indices of different time granularities: minute stability index, shift stability index, day stability index, week stability index.
Specifically, the method for quantitatively evaluating the stability of the blast furnace condition is adopted to calculate the running state of the blast furnace, and a prompt picture is displayed according to the calculation result to early warn in time:
(1) According to calculation rules and ideas of the stability indexes, a model system is constructed, and relevant data acquisition, weight setting, score calculation and the like are placed in the background; the foreground makes visual monitoring pictures to respectively display the total stability index, the instant value of the stability sub-index and the trend graph of different time granularities; stability sub-index key parameter trend graph.
(2) In the continuous detection process of the evaluation model, presetting a furnace condition display rule through background definition; when the stability index or the sub-index is abnormal, the pop-up picture is early-warned in time, and indicates which key parameter is abnormal, and the reasons for causing the parameter abnormality and the adjustment operation guiding suggestion are provided.
Further, the preset furnace condition display rule includes:
the overall stability index is above 80 minutes, which indicates that the stability of the furnace condition is excellent, and the furnace condition can be tracked and observed without adjustment;
the score is 60-80, which shows that the stability is general and the follow-up development change is required to be concerned;
below 60 points, it is shown that the furnace conditions are unstable and may be abnormal, and countermeasures need to be taken.
Furthermore, the method for quantitatively evaluating the stability degree of the blast furnace condition, disclosed by the invention, adopts the stability index to guide the operation of the blast furnace, displays the stability index and the sub-index of the blast furnace condition in real time on line and visually, and evaluates the stability condition of the blast furnace:
1) Tracking and judging the change trend of the furnace conditions:
through continuous calculation and monitoring of stability, an operator can know the stability degree and the change trend of 10 minutes, 1 hour, 12 hours, 24 hours and 72 hours in the past and can be assisted by the stability change trend of different dimensions at any moment, and the operator can be guided to take a dispensing measure in a targeted manner due to the fact that the stability is poor and the operation parameters are changed;
2) When the parameters fall in the abnormal range, namely, an early warning picture is popped up, and meanwhile, an operation suggestion is popped up, so that an operator is guided to refer to analysis reasons, measures are taken as soon as possible, and the long-time abnormality of the furnace condition is prevented;
3) The method helps operators to diagnose and evaluate the blast furnace conditions rapidly and quantitatively from different dimensions and different time granularities so as to take regulation measures in time, thereby achieving the purposes of improving the stability of the furnace conditions, improving the operation index of the blast furnace production or avoiding production process abnormality.
Compared with the prior art, the invention has the advantages that:
1. according to the technical scheme, quantitative, rapid and time-interval modes are adopted to carry out omnibearing intelligent diagnosis on the blast furnace condition, and compared with manual operation meeting, the blast furnace condition diagnosis is carried out according to expert experience, and innovation and conversion from qualitative to quantitative on the stability of the blast furnace condition are realized; meanwhile, quantification also provides a basis for continuously and online monitoring and tracking stability trend of the furnace condition; the time granularity is ten minutes at the shortest, so that the diagnosis efficiency is greatly improved; the furnace condition can be evaluated from different time granularity of short term, medium term, long term and the like; multidimensional evaluation, namely avoiding deviation of single dimension to furnace condition diagnosis and evaluation;
2. according to the technical scheme, the method and the device for diagnosing the furnace conditions are scientific and objective in unified evaluation criteria. The calculation method of the invention combines the blast furnace smelting principle and the blast furnace operation technology, and combines expert rules to uniformly adopt related key parameters, set weights and evaluation dimensions, thereby avoiding the one-sided and non-objective diagnosis and evaluation of the stability degree of the furnace condition caused by the difference of skill level and operation experience of different operators;
3. the technical scheme of the invention is suitable for blast furnaces with different volumes and supports remote diagnosis of the blast furnace conditions. According to the basic technical architecture of the invention, the blast furnaces with different furnace capacities can perform stability index calculation to realize intelligent diagnosis of the furnace conditions as long as relevant data are obtained or partial parameters are deleted or replaced; therefore, when the related parameter data can be transmitted remotely, the remote diagnosis of the furnace condition can be realized.
Drawings
FIG. 1 is a schematic diagram of a method for quantitatively evaluating the stability of a blast furnace condition according to the present invention;
FIG. 2 is a schematic view of a general diagnostic screen for the stability of the blast furnace of the present invention;
FIG. 3a is a schematic diagram of the overall stability index of a certain blast furnace for a certain time granularity;
FIG. 3b is a schematic diagram of the overall index of stability of a certain blast furnace in different dimensions;
FIG. 3c is a schematic diagram of sub-index trend of different dimensions of a certain blast furnace.
Detailed Description
The invention is further described below with reference to the drawings and examples.
According to the technical scheme, core key parameters capable of representing the running condition of the blast furnace are selected based on the operation experience of the steel-making blast furnace, and a big data analysis method is used for constructing a blast furnace stability index calculation formula so as to realize quantitative representation of the stability of the furnace condition. The method consists of a blast furnace stability evaluation dimension, a stability sub-index, a calculation method, an overall stability index, a calculation method and a method for applying the stability index on site.
1. Calculation of stability index:
1. dimension and sub-index of blast furnace stability evaluation:
according to the experience of blast furnace operation expert, combining big data analysis, determining evaluation dimension capable of macroscopically representing the stability degree of the blast furnace, and taking each dimension as a sub-index of total stability.
According to the method, the stability degree of the blast furnace condition is evaluated from 5 dimensions of the blanking condition, the pressure relation, the hearth working condition, the gas flow distribution, the operation furnace type and the like, and each dimension is taken as one sub-index, and five sub-indexes are used, namely the blanking condition sub-index, the pressure relation sub-index, the hearth working condition sub-index, the gas flow distribution sub-index and the operation furnace type sub-index.
2. Stability sub-index parameters and calculation:
(1) Sub-index parameters and score calculation:
and selecting key parameters capable of microscopically representing each dimension, namely sub-indexes according to the experience of blast furnace operation specialists and by combining big data analysis. Determining the characterization capacity, namely the weight, of each parameter in each dimension according to the smelting principle and the operation experience of the blast furnace; the invention sets two methods for each parameter weight, namely, the weight is set based on a multiple linear regression method and combined with expert experience; secondly, after the model system operates on line, self-learning mining is carried out through the design of expert rules, and weights are dynamically and intelligently selected. And calculating the score of each key parameter according to the distribution range of the parameter values. And finally, calculating the index score of each dimension according to the parameter item, the weight of each parameter and the score. I.e. sub-index = Σ (weight) 1 * Parameters (parameters) 1 Weight of + & n * Parameters (parameters) n )。
(2) Different time granularity sub-index calculation:
according to the operation characteristics of the blast furnace and the daily monitoring parameter acquisition and calculation period, dividing the stability subindex into five time granularities: minute sub-indices (based on 10 minute parameter mean and fluctuation amplitude), hour sub-indices (based on one hour parameter mean and fluctuation amplitude), class average sub-indices (based on 12 hour parameter mean and hour fluctuation amplitude), day average sub-indices (based on 24 hour parameter mean and fluctuation amplitude), zhou Junji sub-indices (based on 72 hour parameter day mean and fluctuation amplitude).
3. Overall stability index:
(1) Calculation of the overall stability index:
firstly, according to the influence degree of sub-indexes of five dimensions on furnace conditions and indexes, namely the representation capability of a certain sub-index on the stability degree of the furnace conditions, the weight of each sub-index is established. Then weighting and calculating the total stability index by the sub-index items and the weight of each sub-index, namely the stability index=Σ (weight) 1 * Sub-index 1 Weight of + & n * Sub-index n )。
(2) Different time particle size stability index:
the stability index is divided into five time granularities according to sub-indices of different time granularities: a minute-level stability index (taking a 10 minute parameter mean value and a fluctuation amplitude as a judgment basis), an hour-level stability index (taking an hour parameter mean value and a fluctuation amplitude as a judgment basis), a shift stability index (taking a 12 hour parameter mean value and an hour fluctuation amplitude as a judgment basis), a day stability index (taking a 24 hour parameter hour mean value and a fluctuation amplitude as a judgment basis), and a week stability index (taking a 72 hour parameter day mean value and a fluctuation amplitude as a judgment basis).
4. The application method of the stability index in the field comprises the following steps:
(3) According to calculation rules and ideas of the stability indexes, a model system is constructed, and relevant data acquisition, weight setting, score calculation and the like are placed in the background; the foreground makes visual monitoring pictures to respectively display the total stability index, the instant value of the stability sub-index and the trend graph of different time granularities; stability sub-index key parameter trend graph.
(4) In the continuous detection process of the evaluation model, through background definition, design rules: the overall stability index is above 80 minutes, which indicates that the stability of the furnace condition is excellent, and the furnace condition can be tracked and observed without adjustment; the score is 60-80, which shows that the stability is general and the follow-up development change is required to be concerned; below 60 points, it is shown that the furnace conditions are unstable and may be abnormal, and countermeasures need to be taken. When the stability index or the sub-index is abnormal, the pop-up picture is early-warned in time, and indicates which key parameter is abnormal, and the reasons for causing the parameter abnormality and the adjustment operation guiding suggestion are provided. 2. The principle and logic flow chart of the invention:
according to the basic principle of blast furnace smelting, the operation technology of the blast furnace and experience, 5 dimensions capable of comprehensively evaluating the furnace conditions are determined, so that 5 sub-indexes forming the total stable index are determined; calculating the granularity stability sub-indexes according to the key parameters of the granularity sub-indexes, the state division of different values of the key parameters, the score calculation of different values and the score weights of different parameters; then calculating the stability indexes of different time granularities according to the values of the sub-indexes of different time granularities and the weights of the sub-indexes of different dimensions. The principle and logic flow diagram are shown in figure 1.
1. A method related operation control technology for quantitatively evaluating the stability of blast furnace conditions comprises the following steps:
(1) And (3) comprehensively evaluating the stability of the blast furnace condition. Firstly, "blast furnace stability" is a comprehensive concept that must be examined and evaluated from different dimensions; secondly, the 'blast furnace stability' is an operation state index parameter, and is not an input or output index parameter; thirdly, the blast furnace production is continuously carried out, and the same parameter has a time granularity concept, so that the state judgment also needs to be carried out at different times. The invention selects the composition parameters of the model formula of the 'blast furnace stability index', comprehensively considers the three properties, and should not contain basic condition type parameters and result type parameters.
(2) The key parameter different value ranges are defined and the continuous score calculation technology is adopted. In the production process of the blast furnace, key parameters fluctuate within a certain range. According to different values of key parameters, six states of stability, instability, general instability, abnormality and the like are defined; wherein the score is 100 points when the parameter instant value is within the steady state definition range; and for other states, taking the stable state as a reference, and then realizing continuous score calculation of each parameter according to a normal distribution principle and a piecewise function mode.
(3) The key parameters and the different dimension are used for representing the capacity of the blast furnace. The invention sets two methods for key parameters and each sub-index weight, firstly, sets the weight based on a multiple linear regression method and combines expert experience; secondly, after the model system operates on line, self-learning mining is carried out through the design of expert rules, and weights are dynamically and intelligently selected.
(4) And constructing an intelligent diagnosis blast furnace condition model system technology. The calculation method of the invention needs to construct a model to achieve the functions of on-line and continuous monitoring, collect key parameters of different time granularity, perform related operation, display operation result pictures, push information and the like, and manage background data and the like.
Examples
(1) Specific blast furnace application examples:
taking Baoshan four blast furnace as an example, the invention is applied to the specific operation guidance process.
1) And determining stability evaluation dimension, sub-index and sub-index weight through data induction and statistics, and constructing a stability index calculation formula. The following table shows the dimensions and the weight of each dimension of the hour-level overall stability index of the Baoshan four-blast furnace; each dimension contains a key parameter, and the key parameter is weighted in the sub-index; each key parameter defines and judges rules and methods:
table 1 table of the stability index parameters and weight composition of four blast furnaces at hour level
Table 2 is a continuous score calculation table for each key parameter:
table 2 Baoshan four-blast furnace hour-level stability index score calculation formula
/>
/>
Through the two tables, the total stability index of the four blast furnaces per hour and the sub-stability index of each dimension can be calculated according to the calculation formula of the invention.
1) Different time granularity stability calculation:
the method of calculating rule analogies in 1 hour can calculate stability indexes of 10 minutes, class average, day average and week level, and continuously track the change of the stability indexes; it should be noted that:
(1) the total index of different time granularity contains dimensions, or sub-index terms are the same; however, the periods and meanings which can be represented by different parameters are different, for example, some parameters have evaluation significance only in long-time granularity, and the parameters have no significance in evaluating the furnace condition in short-time granularity, so that the parameter options (numbers) in the same latitude and different time periods are different, and accordingly, the weight of the key parameters is also adjusted;
(2) the parameter values and the decision criteria used in the calculation of the granularity stability at different times are the average value and the decision criteria of the corresponding time periods. For example, in ten minutes, the average value of a certain parameter is rolled for ten minutes, and the fluctuation range allowed by the parameter is within 10 minutes; the hour level is the average value of a certain parameter rolled for 1 hour and the fluctuation range allowed by the parameter within 1 hour; class average is the fluctuation range allowed by a certain parameter when the parameter rolls for 12 hours; the average level of the day is the average value of a certain parameter rolled for 24 hours and the fluctuation range allowed by the parameter within 24 hours; zhou Jun it is the mean value of a certain parameter rolled for 72 hours and the fluctuation range allowed by the parameter within 72 hours (with 72 hours instead of 7 days mean value, from the aspect of the operation of the blast furnace, the parameter has been excessively averaged over the period of time, the sensitivity to the evaluation of the furnace condition has been passivated, the meaning of the evaluation of the furnace condition has been lost.)
2) Stability index guidance of blast furnace operation:
(1) and (5) tracking and judging the change trend of the furnace condition. Through continuous calculation and monitoring of stability, an operator can know the stability degree and the change trend of the past 10 minutes, the rolling time of 1 hour, the rolling time of 12 hours, the rolling time of 24 hours and the rolling time of 72 hours at any moment, and meanwhile, the stability change trend of different dimensions is assisted, so that the operator can be guided to take a regulating measure in a targeted manner due to the fact that the stability is poor and the operation parameters are changed.
(2) Through table 2, early warning decision rules are also defined, as shown in table 3. When the parameters fall in the abnormal range, the early warning picture is popped up, and meanwhile, the operation advice is popped up, so that an operator is guided to refer to analysis reasons, measures are taken as soon as possible, and the long-time abnormality of the furnace condition is prevented.
Table 3 gives the decision rule and operation guidance advice for the hour-level stability index pop-up warning:
table 3 determination rules and operation instruction advice for the hour-level stability index popup early warning
/>
The following table 4 shows the comparison of the effects before and after the practice of the present invention:
TABLE 4 comparison of effects before and after the implementation of the invention
4) The popularization and application conditions are as follows:
according to the technical scheme, the method is tried for a plurality of blast furnaces of Bao-steel stock, the stability index and the sub-index of the furnace condition can be displayed in real time, on line and visually, the stability condition of the blast furnace is evaluated, and the degree of coincidence of the evaluation and the actual condition of the blast furnace is more than 90%.
In fig. 2, a diagnostic overview of all blast furnace stability of the Bao Steel stock is shown. The leftmost side is the total stability index value of all 15 blast furnace hours, and the side-by-side names are automatically ordered according to the score (only 6 blast furnace access systems are currently used, and after other blast furnace data are accessed, calculation and ranking can be performed by referring to the same evaluation method); the middle is a transition diagram of the overall stability index of each blast furnace of each base; the rightmost is a base overall stability index histogram.
FIG. 3a is a view of instantaneous values of a stability index of a blast furnace, wherein the top of the view is a diagnosis granularity button, the granularity of time can be arbitrarily selected, and the total stability index and five dimensional stability sub-indexes corresponding to the granularity of time are displayed below; fig. 3b and 3c are overall stability index and sub-index trend graphs, where the sub-index may vary with time-granularity switching.
According to the technical scheme, based on a blast furnace smelting principle, a steel-making blast furnace expert rule and operation experience, core key parameters capable of representing the running condition of the blast furnace are selected, a blast furnace stability index calculation formula is constructed by a big data analysis method, and the rapid and quantitative diagnosis and evaluation of the blast furnace condition from different dimensions and different time granularities are helped by operators, so that regulation and control measures are timely taken, the stability of the furnace condition is improved, and the purposes of improving the production operation index of the blast furnace or avoiding production process abnormality are achieved. The invention is composed of a stability evaluation dimension and stability sub-index of a blast furnace, a stability sub-index and a calculating method, and an overall stability index and a calculating method. The method can scientifically and rapidly quantitatively diagnose and evaluate the stability of the blast furnace condition and comprehensively evaluate the stability of the blast furnace condition.
The invention can be widely applied to the field of process management of blast furnaces.
Claims (10)
1. A method for quantitatively evaluating the stability of a blast furnace condition is characterized by comprising the following steps:
1) Selecting core key parameters capable of representing the running condition of the blast furnace, determining evaluation dimensions capable of macroscopically representing the stability degree of the blast furnace, and taking each dimension as a sub-index of total stability;
2) Constructing a calculation formula of a stability index of the blast furnace, and realizing quantitative characterization of the stability of the furnace condition;
3) Quantitatively calculating and tracking the running state and the stability of the blast furnace from different dimension time-sharing granularity;
4) Quantitative calculation is carried out on the overall stability of the blast furnace from different time granularity, and quantitative calculation of different time granularity is realized;
5) Through quantitative measurement and calculation of the stability of the furnace condition, a quantitative characterization and real-time display mode of the stability of the furnace condition is adopted, an operator is helped to evaluate the furnace condition in real time and rapidly, corresponding measures are taken, and indexes are improved or production process abnormality is avoided.
2. The method for quantitatively evaluating the stability of the blast furnace condition according to claim 1, which is characterized in that the method for quantitatively evaluating the stability of the blast furnace condition uses a big data analysis method to calculate and compare data comprising a stability evaluation dimension and a stability sub-index of the blast furnace, a stability sub-index and calculation, a total stability index and calculation in real time, and outputs a calculation comparison result in real time, thereby realizing the conversion of the stability of the blast furnace condition from qualitative to quantitative, and providing a basis for continuously monitoring and tracking the stability trend on line of the furnace condition.
3. The method for quantitatively evaluating the stability of the blast furnace condition according to claim 1, wherein the core key parameters comprise blanking condition, pressure relation, hearth working condition, gas flow distribution and operation furnace type;
the evaluation dimension comprises a blanking state sub-index, a pressure relation sub-index, a hearth working condition sub-index, a gas flow distribution sub-index and an operation furnace sub-index.
4. The method for quantitatively evaluating the stability of the blast furnace conditions according to claim 1, wherein the stability sub-index parameters are calculated by dividing the stability sub-index parameters into sub-index parameters and score calculation thereof and different time granularity sub-index calculation.
5. The method for quantitatively evaluating the stability of the blast furnace condition according to claim 4, which is characterized in that when sub-index parameters and scores thereof are calculated, key parameters which can microscopically represent each dimension, namely sub-index, are selected according to the experience of blast furnace operating specialists and by combining big data analysis; determining the characterization capacity, namely the weight, of each parameter in each dimension according to the smelting principle and the operation experience of the blast furnace;
two methods are set for each parameter weight, namely, a multiple linear regression method is based, and the weight is set by combining expert experience; secondly, after the model system operates on line, self-learning mining is carried out through the design of expert rules, and weights are dynamically and intelligently selected;
then, calculating the score of each key parameter according to the distribution range of each parameter value;
and finally, calculating the index score of each dimension according to the parameter item, the weight of each parameter and the score. I.e. sub-index = Σ (weight) 1 * Parameters (parameters) 1 Weight of + & n * Parameters (parameters) n )。
6. The method for quantitatively evaluating the stability of the blast furnace condition according to claim 4, wherein when the calculation of the particle size sub-indexes is carried out at different time intervals, the particle size sub-indexes are divided into five time intervals according to the operation characteristics of the blast furnace, the daily monitoring parameter acquisition and calculation period: minute-level subindex, hour-level subindex, shift-level subindex, day-level subindex, and week-level subindex;
the minute sub-index takes a 10 minute parameter mean value and a fluctuation amplitude as judgment basis;
the hour sub-index takes an hour parameter mean value and a fluctuation amplitude as judgment basis;
the class average sub-index takes a rolling 12-hour parameter mean value and an hour fluctuation amplitude as a judgment basis;
the day-average sub-index takes the average value and the fluctuation amplitude of the 24-hour rolling parameter as the judgment basis;
the Zhou Junji sub-index is based on the average value and fluctuation amplitude of the rolling parameter for 72 hours.
7. The method for quantitatively evaluating the stability of the blast furnace conditions according to claim 1, wherein the quantitative measurement of the stability of the furnace conditions comprises:
(1) Calculation of the overall stability index:
firstly, according to the influence degree of sub-indexes of five dimensions on furnace conditions and indexes, namely the representation capability of a certain sub-index on the stability degree of the furnace conditions, determining the weight of each sub-index; then weighting and calculating the total stability index by the sub-index items and the weight of each sub-index, namely the stability index=Σ (weight) 1 * Sub-index 1 Weight of + & n * Sub-index n )；
(2) Different time particle size stability index:
the stability index is divided into five time granularities according to sub-indices of different time granularities: minute stability index, shift stability index, day stability index, week stability index.
8. The method for quantitatively evaluating the stability of the blast furnace condition according to claim 1, which is characterized in that the method for quantitatively evaluating the stability of the blast furnace condition is adopted to calculate the running state of the blast furnace, and a prompt picture is displayed according to the calculation result to early warn in time:
(1) According to calculation rules and ideas of the stability indexes, a model system is constructed, and relevant data acquisition, weight setting, score calculation and the like are placed in the background; the foreground makes visual monitoring pictures to respectively display the total stability index, the instant value of the stability sub-index and the trend graph of different time granularities; stability sub-index key parameter trend graph.
(2) In the continuous detection process of the evaluation model, presetting a furnace condition display rule through background definition; when the stability index or the sub-index is abnormal, the pop-up picture is early-warned in time, and indicates which key parameter is abnormal, and the reasons for causing the parameter abnormality and the adjustment operation guiding suggestion are provided.
9. The method for quantitatively evaluating the stability of a blast furnace condition according to claim 8, wherein said preset furnace condition display rule comprises:
the overall stability index is above 80 minutes, which indicates that the stability of the furnace condition is excellent, and the furnace condition can be tracked and observed without adjustment;
the score is 60-80, which shows that the stability is general and the follow-up development change is required to be concerned;
below 60 points, it is shown that the furnace conditions are unstable and may be abnormal, and countermeasures need to be taken.
10. The method for quantitatively evaluating the stability degree of the blast furnace condition according to claim 1, wherein the stability index is used for guiding the operation of the blast furnace, the stability index and the sub-index of the blast furnace condition are displayed in real time, on line and visually, and the stability condition of the blast furnace is evaluated:
1) Tracking and judging the change trend of the furnace conditions:
through continuous calculation and monitoring of stability, an operator can know the stability degree and the change trend of 10 minutes, 1 hour, 12 hours, 24 hours and 72 hours in the past and can be assisted by the stability change trend of different dimensions at any moment, and the operator can be guided to take a dispensing measure in a targeted manner due to the fact that the stability is poor and the operation parameters are changed;
2) When the parameters fall in the abnormal range, namely, an early warning picture is popped up, and meanwhile, an operation suggestion is popped up, so that an operator is guided to refer to analysis reasons, measures are taken as soon as possible, and the long-time abnormality of the furnace condition is prevented;
3) The method helps operators to diagnose and evaluate the blast furnace conditions rapidly and quantitatively from different dimensions and different time granularities so as to take regulation measures in time, thereby achieving the purposes of improving the stability of the furnace conditions, improving the operation index of the blast furnace production or avoiding production process abnormality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210542614.7A CN117094576A (en) | 2022-05-10 | 2022-05-10 | Method for quantitatively evaluating stability degree of blast furnace condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210542614.7A CN117094576A (en) | 2022-05-10 | 2022-05-10 | Method for quantitatively evaluating stability degree of blast furnace condition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117094576A true CN117094576A (en) | 2023-11-21 |
Family
ID=88781796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210542614.7A Pending CN117094576A (en) | 2022-05-10 | 2022-05-10 | Method for quantitatively evaluating stability degree of blast furnace condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094576A (en) |
-
2022
- 2022-05-10 CN CN202210542614.7A patent/CN117094576A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100485047C (en) | Intelligent diagnosis and determination support system for blast furnace | |
| CN109685289B (en) | Method, device and system for forward prediction of blast furnace conditions | |
| CN109063358B (en) | Novel blast furnace forward evaluation method | |
| CN1224720C (en) | Blast furnace smelt controlling method with intelligent control system | |
| CN109935280B (en) | Blast furnace molten iron quality prediction system and method based on ensemble learning | |
| CN107368125B (en) | A kind of blast furnace temperature control system and method based on CBR Yu the parallel mixed inference of RBR | |
| CN106345823B (en) | The method of online real-time estimate mechanical performance based on coils of hot-rolled steel production procedure | |
| CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
| CN111639801B (en) | Scoring method and scoring system for blast furnace conditions | |
| CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
| CN109252009A (en) | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine | |
| CN1207399C (en) | Intelligent blast furnace smelt controlling system | |
| CN110989510A (en) | Hot galvanizing product full-process quality control and grade automatic judgment system | |
| CN117094576A (en) | Method for quantitatively evaluating stability degree of blast furnace condition | |
| US20220390928A1 (en) | Production facilities monitoring method, production facilities monitoring device, and operation method for production facilities | |
| CN113065222B (en) | Method and device for evaluating state of hearth | |
| EP4060056A1 (en) | Method and system for operating production facility | |
| CN114185976A (en) | Visual intelligent perception platform of blast furnace | |
| Trofimov | Automated expert systems in blast-furnace process control | |
| Bouché et al. | AMELIOS Suite or the Fives Digital Package for Carbon 4.0 | |
| RU2209837C2 (en) | Method for controlling of processing power unit - blast furnace | |
| CN113061683B (en) | Automatic matching method for converter end point oxygen and converter end point reblowing times quality factor | |
| CN1763523B (en) | Soft measurement method for recovery rate of magnetic separation tube of shaft furnace roasting system | |
| JP6944393B2 (en) | Plant condition evaluation system, plant condition evaluation method, and program | |
| Sun et al. | A hot metal temperature predictor based on hybrid decision tree techniques |
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 |