CN112430727B - Furnace temperature early warning method and system for continuous annealing furnace - Google Patents
Furnace temperature early warning method and system for continuous annealing furnace Download PDFInfo
- Publication number
- CN112430727B CN112430727B CN202011101209.9A CN202011101209A CN112430727B CN 112430727 B CN112430727 B CN 112430727B CN 202011101209 A CN202011101209 A CN 202011101209A CN 112430727 B CN112430727 B CN 112430727B
- Authority
- CN
- China
- Prior art keywords
- furnace
- tension
- annealing furnace
- sample
- samples
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D11/00—Process control or regulation for heat treatments
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/26—Methods of annealing
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D9/00—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor
- C21D9/52—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor for wires; for strips ; for rods of unlimited length
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Mechanical Engineering (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Control Of Heat Treatment Processes (AREA)
- Heat Treatment Of Strip Materials And Filament Materials (AREA)
Abstract
The method comprises the steps of collecting data, generating samples according to different collection time periods, checking the data quality of all the samples to generate a sample set, extracting the characteristics of the sample set, judging the stability and the degradation trend of the sample set, and predicting the furnace temperature change condition of each furnace section in the annealing furnace based on a BP neural network algorithm. The method combines the traditional alarm mode with the SPC process control statistics and neural network prediction algorithm mode, can predict the health degree of the furnace while realizing the ultralimit alarm, and predicts the furnace temperature by adopting the BP neural network algorithm, thereby providing a brand-new temperature health monitoring and early warning method for the continuous annealing furnace of the hot galvanizing unit. The early warning system using the method can assist operators in giving an alarm in advance and finding fault points in time when problems occur, so as to strive for early finding and early intervention.
Description
Technical Field
The invention relates to the field of cold rolling processes, in particular to a method and a system for early warning the furnace temperature (annealing furnace temperature) of a continuous annealing furnace (hot galvanizing unit annealing furnace), which are suitable for automatically acquiring and storing furnace data of a horizontal continuous annealing furnace and early warning and monitoring the steady state of the furnace through a theoretical model based on a BP neural network algorithm and an SPC process control chart.
Background
Generally, a continuous annealing furnace is an apparatus in which a heat treatment process is performed to increase or decrease the temperature of a metal strip at a room temperature or a low temperature according to a preset temperature profile to obtain desired material characteristics. The continuous annealing furnace is mainly divided into a Heating Section and a Cooling Section, wherein the Heating Section is divided into a preheating Section (Pre Heating Section), a Heating Section (Heating Section) and a Soaking Section (absorbing Section), and the Cooling Section is divided into a Slow Cooling Section (Slow Cooling Section), a fast Cooling Section (Rapid Cooling Section), an overaging Section (OAS) and a Final Cooling Section (Final Cooling Section). The temperature of the annealing furnace is controlled by accurately controlling the temperature rise, the heat preservation and the temperature reduction of the strip steel according to the process requirements and a set curve, and the uniformity of the furnace temperature of the annealing furnace is required to be ensured in the process and directly determines the quality of products.
Chinese patent No. CN201710828269.2 in the prior art discloses an annealing furnace temperature control method and system, which respectively determine whether the actually required heating load of each of M heating control zones in an annealing furnace is smaller than a preset load threshold by obtaining the actually required heating load of each of the M heating control zones, and keep the gas flow controllers corresponding to each of the M heating control zones whose actually required heating load is smaller than the preset load threshold at a first constant flow, and control each burner in the same heating control zone to perform intermittent ignition at the same time.
In the prior art, a Chinese patent with a patent number of CN201310109424.7 discloses a temperature control method for a roller hearth annealing furnace, which comprises six steps, wherein in the first step, the target temperature of an outlet of a product heating section corresponding to a temperature rise curve given by a process is calculated; secondly, calculating the temperature of the steel billet; thirdly, calculating the residual heating time from the billet to the end of the heating section; fourthly, performing feedforward control on the heating temperature, taking the temperature of the steel billet calculated in the second step as a starting point, utilizing the residual heating time T of the steel billet calculated in the third step and taking a process curve as furnace temperature input, forecasting the temperature T of the steel billet reaching the end of a heating section according to a given time step delta T, and then calculating the deviation between the forecasted temperature and the target temperature so as to further calculate the feedforward temperature control quantity of the section where the steel billet is located; fifthly, determining the feedback control quantity of the heating temperature by utilizing the calculation result of the billet temperature tracking model at the outlet position of the heating section and the deviation of the billet temperature tracking model and the target temperature of the billet at the position; and sixthly, performing feedforward and feedback temperature setting control on the heating section of the roller hearth furnace.
In the prior art, the furnace temperature is monitored according to the process curve, only overrun alarm can be given, early warning and deterioration trend reminding cannot be achieved, and the prior art cannot meet the production line with high production requirements.
Disclosure of Invention
The invention aims to provide a furnace temperature early warning method and system for a continuous annealing furnace (a hot galvanizing unit annealing furnace), which combines a traditional alarm mode with an SPC process control statistic and neural network prediction algorithm mode and provides a brand-new temperature health monitoring and early warning method for the continuous annealing furnace of the hot galvanizing unit.
In order to achieve the purpose, the invention adopts the following technical scheme:
the application provides a continuous annealing furnace temperature early warning method in a first aspect, which comprises the following steps:
acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more, preferably at least two or more, of oxygen content, hydrogen content, dew point of the atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas;
the collected data are transmitted to an SPC system, the SPC system groups the collected data according to the category of the process point location, each group independently sets the sample collection time period, and the data in each sample collection time period are processed according to the preset sample collection method corresponding to the category of the process point location to form a single sample;
performing data quality inspection on all samples, only retaining data in a normal operation period of a unit, eliminating data in a fault period, and interpolating a few missing data in the normal operation period to form a sample set;
extracting characteristics of the sample set, and calculating the average value and the standard deviation of the samples in preset time;
carrying out statistical judgment on the sample set according to a first judgment rule, and triggering an overrun alarm if the judgment result is overrun abnormity; otherwise, carrying out statistical judgment on the sample set according to a second judgment rule, and if the judgment result is abnormal fluctuation, indicating that the annealing furnace has a degradation trend and an unstable condition appears, triggering degradation trend early warning;
and predicting the furnace temperature change condition of each furnace section in the annealing furnace based on a BP neural network algorithm.
Preferably, the preset sample collection method includes one or more of an average value of the sample collection time periods and a maximum value of the sample collection time periods.
Preferably, the roll shaft tension of each set process point comprises several or more of uncoiler tension, cleaning section tension, inlet loop tension, annealing furnace preheating section tension, annealing furnace heating section inlet tension, annealing furnace heating section outlet tension, annealing furnace soaking section tension, annealing furnace slow cooling section tension, annealing furnace fast cooling section tension, zinc pot section tension, central loop tension, temper mill inlet tension, temper mill outlet tension, withdrawal and straightening machine tension, post-processing section tension, outlet loop tension, circle shear section tension and coiler tension.
Preferably, the steel coil specification includes one or more of a thickness, a width, a coil number, and a steel type of the steel coil.
Preferably, the exhaust gas comprises particulate matter, SO2、NOX、O2And one or more of the temperature of the waste gas, wherein x is the atomic number ratio of O to N in the NOx.
Preferably, before the real-time collection of the process parameters in the fire, the early warning method further comprises: and setting a standard value of each process point location of each furnace section, wherein the standard value is a reference range of health degree evaluation of the corresponding process point location.
Preferably, the first rule includes: if the average value of the samples in the preset time exceeds a preset abnormal threshold value, judging the samples to be abnormal points; and if the number of the abnormal points in a preset time period before the current moment exceeds a preset value, judging that the overrun is abnormal.
More preferably, the preset abnormal threshold may be calculated according to respective distribution patterns of the operating state signal values of the equipment in the healthy state, for example, the motor torque signal generally follows a normal distribution, and the average value plus three times the standard deviation is taken as the abnormal threshold.
Preferably, the second rule includes: the method comprises the steps that self-defined control limit values are adopted and comprise a first control limit, a second control limit and a third control limit, the first control limit is 3 times of a standard deviation of a sample in preset time, the second control limit is 2 times of the standard deviation, and the third control limit is 1 time of the standard deviation; performing data trend analysis according to the following rules, and judging that the fluctuation is abnormal as long as any rule is met;
rule 1: one sample falls outside a preset first control limit;
rule 2: the continuous K samples fall on the same side of the center line;
criterion 3: consecutive K samples increment or decrement;
rule 4: adjacent samples in the continuous K samples alternate up and down;
criterion 5: k samples of the K +1 consecutive samples fall outside a second control limit on the same side of the centerline;
criterion 6: k samples of the K +1 consecutive samples fall outside a third control limit on the same side of the centerline;
criterion 7: the continuous K samples fall within third control limits on the same two sides of the center line;
criterion 8: the continuous K samples fall on two sides of the central line, and none of the continuous K samples is within a third control limit;
wherein K is a positive integer.
Preferably, the method for predicting the furnace temperature change condition of each furnace section in the annealing furnace based on the BP neural network algorithm comprises the following steps:
selecting a sample training set from the sample set;
constructing a BP neural network model, wherein the BP neural network model comprises an input layer, a hidden layer and an output layer, all neurons in adjacent layers are in full connection, and all neurons in each layer are not in connection; setting model parameters, including: setting selection of input signals of an input layer, setting the number of layers of a hidden layer and the number of nodes of each layer, and setting the number of nodes, learning rate, transfer function, momentum factor, maximum training times and minimum precision of an output layer;
training a BP neural network model by using the existing sample training set, comprising the following steps: proceeding according to a forward propagation direction, obtaining the output value of each neuron from the direction from the input layer to the hidden layer to the output layer until obtaining the output value of the final output layer, if the output value of the output layer is not consistent with the expected output value, proceeding according to the backward propagation direction, and adjusting the connection weight between the neurons according to the set learning rate and the error between the actual output and the expected output value of the output layer; alternately performing forward output calculation and reverse weight modification until the error of network output is smaller than the preset minimum precision or the preset maximum training times to determine a current furnace temperature change trend prediction model;
and inputting the sample set into an input layer of the BP neural network model according to the trained BP neural network model, and obtaining a predicted value of the current furnace temperature change trend through the processing of the neural network.
More preferably, the learning rate of the BP neural network model is selected in a range of 0.01-0.8, and the momentum factor is selected in a range of 0-1 and is larger than the learning rate.
Further, the learning rate of the BP neural network model is preferably 0.06, and the momentum factor is preferably 0.95.
More preferably, the transfer function of the BP neural network model is
The application provides in a second aspect a continuous annealing furnace temperature early warning system, includes:
the data acquisition module is used for acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more of oxygen content, hydrogen content, dew point of atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas; preferably at least two or more;
the sample generation module is used for grouping the acquired data according to the category of the process point location, setting the sample acquisition time period of each group independently, and processing the data of each sample acquisition time period according to a preset sample acquisition method corresponding to the category of the process point location to form a single sample;
the data quality inspection module is used for performing data quality inspection on all samples, only retaining data in a normal operation time period of the unit, eliminating data in a fault time period, and interpolating a few missing data in the normal operation time period to form a sample set;
the characteristic extraction module is used for extracting characteristics of the sample set and calculating the average value and the standard deviation of the samples in preset time;
the overrun judgment alarm module is used for carrying out statistical judgment on the sample set according to a first judgment rule, and triggering overrun alarm if the judgment result is overrun abnormity;
the degradation trend judgment and early warning module is used for carrying out statistical judgment on the sample set according to a second judgment rule under the condition that the sample set is not in overrun abnormality, and triggering degradation trend early warning if the judgment result is in fluctuation abnormality and indicates that the annealing furnace has a degradation trend and an unstable condition appears;
and the furnace temperature prediction module based on the BP neural network algorithm is used for predicting the furnace temperature change condition of each furnace section in the annealing furnace based on the BP neural network algorithm.
Preferably, the roll shaft tension of each set process point comprises several or more of uncoiler tension, cleaning section tension, inlet loop tension, annealing furnace preheating section tension, annealing furnace heating section inlet tension, annealing furnace heating section outlet tension, annealing furnace soaking section tension, annealing furnace slow cooling section tension, annealing furnace fast cooling section tension, zinc pot section tension, central loop tension, temper mill inlet tension, temper mill outlet tension, withdrawal and straightening machine tension, post-processing section tension, outlet loop tension, circle shear section tension and coiler tension.
Preferably, the steel coil specification includes one or more of a thickness, a width, a coil number, and a steel type of the steel coil.
Preferably, the exhaust gas comprises particulate matter, SO2、NOX、O2And one or more of the temperature of the waste gas, wherein x is the atomic number ratio of O to N in the NOx.
Preferably, the furnace temperature prediction module based on the BP neural network algorithm includes:
the BP neural network model building module is used for setting the selection of input signals of an input layer, setting the number of layers of a hidden layer and the number of nodes of each layer, and setting the number of nodes, the learning rate, the transfer function, the momentum factor, the maximum training times and the minimum precision of an output layer;
the BP neural network model training module is used for training the BP neural network model by utilizing the existing sample training set to obtain a prediction model of the current furnace temperature change trend;
and the furnace temperature change trend prediction module is used for inputting the sample set into an input layer of the BP neural network model according to the trained BP neural network model, and obtaining a predicted value of the current furnace temperature change trend through the processing of the neural network.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
the application provides a furnace temperature early warning method and system for a continuous annealing furnace, wherein a traditional warning mode is combined with an SPC process control statistic and a BP neural network prediction algorithm mode, and a set of brand-new early warning mode based on temperature prediction under a stable state of an SPC control theory is generated. According to the technical scheme, the furnace health degree can be subjected to trend prediction such as increasing, decreasing, chaos and regular fluctuation while the overrun alarm is achieved, and the furnace temperature is predicted by adopting a BP neural network algorithm. The early warning system using the method can assist an operator to give an alarm in advance and find fault points in time when problems occur, strive for early finding and early intervention, and avoid missing the optimal fault processing time due to finding the fault points.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
FIG. 1 is a schematic flow diagram of a method for pre-warning a furnace temperature of a continuous annealing furnace according to the present application;
FIG. 2 is a schematic diagram of an SPC model design of the present application;
FIG. 3 is a graph showing the variation of the annealing temperature 1 of the steel coil under the unsteady state degradation of the annealing furnace SPC according to the embodiment of the present application (target temperature 830 ℃);
FIG. 4 is a graph showing the variation of the annealing temperature 2 of the steel coil under the unsteady state degradation of the annealing furnace SPC according to the embodiment of the present application (target temperature 830 ℃);
FIG. 5 is a graph showing the variation of the annealing temperature of the steel coil in the steady state health of the annealing furnace SPC according to the embodiment of the present application (target temperature 810 ℃);
fig. 6 is a graph showing the variation of the annealing temperature of the steel coil under the steady state health of the annealing furnace SPC according to the embodiment of the present application (target temperature 835 ℃).
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order, it being understood that the data so used may be interchanged under appropriate circumstances. Furthermore, the terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, the method for warning the furnace temperature of the continuous annealing furnace includes:
acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more of oxygen content, hydrogen content, dew point of atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas; preferably at least two or more;
the collected data are transmitted to an SPC system, the SPC system groups the collected data according to the category of the process point location, each group independently sets the sample collection time period, and the data in each sample collection time period are processed according to the preset sample collection method corresponding to the category of the process point location to form a single sample;
performing data quality inspection on all samples, only retaining data in a normal operation period of a unit, eliminating data in a fault period, and interpolating a few missing data in the normal operation period to form a sample set;
extracting characteristics of the sample set, and calculating the average value and the standard deviation of the samples in preset time;
carrying out statistical judgment on the sample set according to a first judgment rule, and triggering an overrun alarm if the judgment result is overrun abnormity; otherwise, carrying out statistical judgment on the sample set according to a second judgment rule, and if the judgment result is abnormal fluctuation, indicating that the annealing furnace has a degradation trend and an unstable condition appears, triggering degradation trend early warning;
and predicting the furnace temperature change condition of each furnace section in the annealing furnace based on a BP neural network algorithm.
Example (b):
the nature of the early warning of the furnace health degree is the early warning of important indexes of each furnace section, so important parameters and reasonable ranges of each furnace section are firstly confirmed, the specific contents are shown in table 1, and the health degree evaluation scheme of each furnace section is designed mainly according to the judgment of relevant factors of process parameters and quality in table 1.
TABLE 1 evaluation scheme for health degree of each furnace section
The electrical control unit of the cold rolling annealing furnace comprises two parts, namely DCS and PLC. And confirming the data address of the required process point location and automatically collecting the part of the process point location. Referring to table 2, the part of the process points may include oxygen content, hydrogen content, dew point of the furnace atmosphere, furnace pressure, target plate temperature, roll shaft tension, coil number, furnace temperature, coil specification, unit speed, plate temperature and exhaust gas.
TABLE 2 important process points and their corresponding address tables
The SPC system is deployed on site, the collected data are transmitted to the SPC system, the main work of the SPC system is used as SPC sample interval adjustment, frequent false alarm is easily caused when the set sample interval is too short, and the promptness that early warning cannot be given out is brought into play when the set sample interval is too large. The SPC system groups the collected data according to the categories of the process point locations, each group independently sets the sample collection time periods, and the data in each sample collection time period are processed according to the preset sample collection method corresponding to the category of the process point locations to form a single sample. See table 3.
TABLE 3 SPC Collection Interval schematic Table
The data quality detection aims at detecting whether the data quality of input data meets the algorithm requirement, and the data quality detection comprises two aspects:
(1) checking whether the sample data has missing values or abnormal values, and detecting the abnormal values by adopting a rule-based method, such as whether the signals are in a certain numerical value range, a judgment rule of PLC signals and the like;
(2) and checking whether the working condition of the sample data meets the algorithm requirement, namely whether the sample data is data in the normal operation process of the unit, and judging by using a zone bit in the PLC data.
And then, carrying out feature extraction on the sample set, and calculating the average value and the standard deviation of the samples in preset time, wherein the average value is used for overrun abnormity judgment, and the standard deviation is used for fluctuation abnormity judgment.
And (4) overrun judgment and alarm:
the SPC system will automatically calculate the set anomaly threshold. The abnormal threshold may be calculated according to respective distribution patterns of the operating state signal values of the equipment in a healthy state, for example, the motor torque signal generally follows a normal distribution, and the average value plus three times the standard deviation is taken as the abnormal threshold. If the average value of the samples in the preset time exceeds a preset abnormal threshold value, judging the samples to be abnormal points; in order to reduce the false alarm rate, the number of abnormal points in a preset time period before the current moment exceeds a preset value, the overrun abnormality is judged, and overrun alarm is triggered.
Judging and early warning the degradation trend:
when the sample set is determined to be within the controllable range through the overrun determination, the deterioration tendency determination is performed, and the determination is based on the SPC rule.
SPC, statistical process control, is a widely used process control method and is a process control tool that relies on mathematical statistical methods. The method analyzes and evaluates the production process, timely discovers the sign of the systematic factors according to the feedback information, and takes measures to eliminate the influence, so that the process is maintained in a controlled state only influenced by the random factors, and the purpose of controlling the quality is achieved.
SPC rules (discriminant criteria) are as follows:
criterion 1: 1 dot falls outside the A zone (dot goes beyond the control limit)
Criterion 2: the continuous 9 points fall on the same side of the central line
Criterion 3: successive 6-point increments or decrements
Criterion 4: the adjacent points in the 14 continuous points are always alternated up and down
Criterion 5: 2 of the continuous 3 points fall outside the area B on the same side of the center line
Criterion 6: 4 of the continuous 5 points fall outside the C area on the same side of the center line
Criterion 7: the continuous 15 points fall in the C areas on the same two sides of the central line
Criterion 8: continuous 8 points on both sides of the center line and no 1 point in the C zone
The C area is a preset third control limit, and the size of the C area is 1 time of the standard deviation of the samples in the preset time; the area B is a preset second control limit, and the size of the area B is 2 times of the standard deviation of the sample in the preset time; the a region is a preset third control limit, and the size of the a region is 3 times of the standard deviation of the sample in the preset time.
Referring to fig. 2, data trend analysis is performed according to the above rules, and when the sample set meets any one of the above rules, which indicates that the health of the annealing furnace is degraded and an unsteady state occurs, it is determined that the fluctuation is abnormal, and degradation trend early warning is triggered.
The above-mentioned early warning method of this application improves traditional SPC, mainly has following two points:
the SPC control chart has the effect of reflecting the stability of the production process, but the stability cannot completely reflect the excellent data, and the stable output of error data is possible, so that the technical scheme of the application is additionally provided with an upper limit condition setting function and a lower limit condition setting function, and the trend of data is analyzed while the data are ensured to be in a controllable range.
Secondly, the number of samples can be adjusted, and the number of the collected single samples of the corresponding data needs to be adjusted according to the process condition because the field data change rates are different, so that the field trend can be better reflected. If the temperature difference of the furnace temperature plate is averaged once in 30 minutes to prepare a sample, the sample is analyzed by an SPC XBR chart, and if the temperature difference of the furnace temperature plate rises continuously at 6 points, the temperature difference of the furnace temperature plate within 3 hours has a rising trend. The true effect of SPC can be exerted by setting up a reasonable sample.
The method can also predict the furnace temperature change condition of each furnace section in the annealing furnace based on a BP neural network algorithm.
The BP neural network is a neural network learning algorithm. The hierarchical neural network is composed of an input layer, a hidden layer and an output layer, wherein the hidden layer can be expanded into multiple layers. All the neurons in adjacent layers are in full connection, and all the neurons in each layer are not in connection, so that the network learns in a mode of supervision of a teacher.
The learning process consists of two parts, namely signal forward propagation and error backward propagation; in forward propagation, input samples are transmitted from the input layer, processed layer by layer sequentially through hidden layers, and transmitted to the output layer, if outputIf the output of the output layer is not in accordance with the expectation, the error is used as an adjusting signal to reversely return layer by layer, and a connection weight matrix between the neurons is processed, so that the error is reduced. After repeated learning, the error is finally reduced to an acceptable range, and finally a transfer function is selected as
The learning rate is 0.06, the additional momentum factor is 0.95, and the specific steps are as follows:
firstly, a certain sample is taken out from the training sample set, and information is input into the network.
And processing the connection condition among the nodes layer by layer in the forward direction to obtain the actual output of the neural network.
And calculating the error between the actual output and the expected output of the network.
Fourthly, reversely transmitting the errors layer by layer back to the previous layers, and loading error signals to the connection weight according to a certain principle to convert the connection weight of the whole neural network to the direction of reducing the errors.
And fifthly, repeating the steps for each input-output sample pair in the training sample set until the error of the whole training sample set is smaller than the preset precision or the preset times.
And inputting the sample set into an input layer of the BP neural network model according to the trained BP neural network model, and obtaining a predicted value of the current furnace temperature change trend through the processing of the neural network.
Table 4 shows the prediction results of predicting the furnace temperature of the annealing furnace under the unsteady state degradation and the steady state health, respectively, using the BP neural network model obtained by the training.
TABLE 4 model Algorithm results Table
Note that the data in table 4 is the value of a sample, and the points in fig. 3 to 6 are the average value of the sample at a certain time because the number of samples is large.
Fig. 3 is a graph showing the variation of the annealing temperature 1 of the steel coil under the unsteady degradation of the SPC in the annealing furnace, and fig. 4 is a graph showing the variation of the annealing temperature 2 of the steel coil under the unsteady degradation of the SPC in the annealing furnace, wherein the target temperature in fig. 3 is 830 ℃, and the target temperature in fig. 4 is 830 ℃. As can be seen from table 4 in conjunction with fig. 3, the trailing panel temperature is lower. As can be seen from table 4 in conjunction with fig. 4, the trailing panel temperature is lower by more than 10 ℃.
Fig. 5 is a graph showing the variation of the annealing temperature of the steel coil in the annealing furnace under the SPC steady state health, and fig. 6 is a graph showing the variation of the annealing temperature of the steel coil in the annealing furnace under the SPC steady state health, in which the target temperature in fig. 5 is 810 ℃ and the target temperature in fig. 6 is 835 ℃. As can be seen from table 4 in conjunction with fig. 5, the rear panel had large fluctuation, and the rear panel had good temperature. It can be seen from table 4 in conjunction with fig. 6 that the rear plate has large fluctuation and the rear plate has better plate temperature control.
As can be seen from the above legend and data, the predicted trend is substantially the same as the actual board temperature variation trend, and the fitting degree between the predicted value and the measured value is good.
Based on the same inventive concept of the above embodiment, in another preferred embodiment, the present application further provides a continuous annealing furnace temperature early warning system, including:
the data acquisition module is used for acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more of oxygen content, hydrogen content, dew point of atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas; preferably at least two or more;
the sample generation module is used for grouping the acquired data according to the category of the process point location, setting the sample acquisition time period of each group independently, and processing the data of each sample acquisition time period according to a preset sample acquisition method corresponding to the category of the process point location to form a single sample;
the data quality inspection module is used for performing data quality inspection on all samples, only retaining data in a normal operation time period of the unit, eliminating data in a fault time period, and interpolating a few missing data in the normal operation time period to form a sample set;
the characteristic extraction module is used for extracting characteristics of the sample set and calculating the average value and the standard deviation of the samples in preset time;
the overrun judgment alarm module is used for carrying out statistical judgment on the sample set according to a first judgment rule, and triggering overrun alarm if the judgment result is overrun abnormity;
the degradation trend judgment and early warning module is used for carrying out statistical judgment on the sample set according to a second judgment rule under the condition that the sample set is not in overrun abnormality, and triggering degradation trend early warning if the judgment result is in fluctuation abnormality and indicates that the annealing furnace has a degradation trend and an unstable condition appears;
and the furnace temperature prediction module based on the BP neural network algorithm is used for predicting the furnace temperature change condition of each furnace section in the annealing furnace based on the BP neural network algorithm.
In summary, the application provides a method and a system for early warning the furnace temperature of a continuous annealing furnace, wherein a traditional warning mode is combined with an SPC process control statistics and a BP neural network prediction algorithm mode, and a set of brand-new early warning modes based on temperature prediction under the stable state of an SPC control theory are generated. According to the technical scheme, the furnace health degree can be subjected to trend prediction such as increasing, decreasing, chaos and regular fluctuation while the overrun alarm is achieved, and the furnace temperature is predicted by adopting a BP neural network algorithm. The early warning system using the method can assist an operator to give an alarm in advance and find fault points in time when problems occur, strive for early finding and early intervention, and avoid missing the optimal fault processing time due to finding the fault points. The method is applied to the design of the cold rolling and hot galvanizing unit A08 continuous annealing furnace of the baby steel bus board, analyzes the trend of key process parameters of different furnace sections through the SPC judgment principle, judges the possible health hidden danger of the annealing furnace, predicts the furnace temperature change according to the BP neural network algorithm, assists managers in making decisions, avoids major faults, reduces the shutdown times and improves the production efficiency.
The embodiments of the present invention have been described in detail, but the embodiments are merely examples, and the present invention is not limited to the embodiments described above. Any equivalent modifications and substitutions to those skilled in the art are also within the scope of the present invention. Accordingly, equivalent changes and modifications made without departing from the spirit and scope of the present invention should be covered by the present invention.
Claims (8)
1. The method for early warning the furnace temperature of the continuous annealing furnace is characterized by comprising the following steps of:
acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more of oxygen content, hydrogen content, dew point of atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas;
the collected data are transmitted to an SPC system, the SPC system groups the collected data according to the category of the process point location, each group independently sets the sample collection time period, and the data in each sample collection time period are processed according to the preset sample collection method corresponding to the category of the process point location to form a single sample;
performing data quality inspection on all samples, only retaining data in a normal operation period of a unit, eliminating data in a fault period, and interpolating a few missing data in the normal operation period to form a sample set;
extracting characteristics of the sample set, and calculating the average value and the standard deviation of the samples in preset time;
carrying out statistical judgment on the sample set according to a first judgment rule, and triggering an overrun alarm if the judgment result is overrun abnormity; otherwise, carrying out statistical judgment on the sample set according to a second judgment rule, and if the judgment result is abnormal fluctuation, indicating that the annealing furnace has a degradation trend and an unstable condition appears, triggering degradation trend early warning;
predicting the furnace temperature change condition of each furnace section in the annealing furnace based on a BP neural network algorithm;
wherein the first discriminant rule includes: if the average value of the samples in the preset time exceeds a preset abnormal threshold value, judging the samples to be abnormal points; if the number of abnormal points in a preset time period before the current moment exceeds a preset value, judging that the overrun is abnormal;
the second rule includes: the method comprises the steps that self-defined control limit values are adopted and comprise a first control limit, a second control limit and a third control limit, the first control limit is 3 times of a standard deviation of a sample in preset time, the second control limit is 2 times of the standard deviation, and the third control limit is 1 time of the standard deviation; performing data trend analysis according to the following rules, and judging that the fluctuation is abnormal as long as any rule is met;
criterion 1: one sample falls outside a preset first control limit;
criterion 2: the continuous K samples fall on the same side of the center line;
criterion 3: consecutive K samples increment or decrement;
criterion 4: adjacent samples in the continuous K samples alternate up and down;
criterion 5: k samples of the K +1 consecutive samples fall outside a second control limit on the same side of the centerline;
criterion 6: k samples of the K +1 consecutive samples fall outside a third control limit on the same side of the centerline;
criterion 7: the continuous K samples fall within third control limits on the same two sides of the center line;
criterion 8: the continuous K samples fall on two sides of the central line, and none of the continuous K samples is within a third control limit;
wherein K is a positive integer.
2. The method for early warning the furnace temperature of the continuous annealing furnace according to claim 1, wherein the roll shaft tension of each set process point comprises several or more of uncoiler tension, cleaning section tension, inlet loop tension, annealing furnace preheating section tension, annealing furnace heating section inlet tension, annealing furnace heating section outlet tension, annealing furnace soaking section tension, annealing furnace slow cooling section tension, annealing furnace fast cooling section tension, zinc pot section tension, central loop tension, leveler inlet tension, leveler outlet tension, tension of a tension leveler, tension of a post-processing section, outlet loop tension, tension of a circle shear section and tension of a coiler.
3. The method for warning the furnace temperature of the continuous annealing furnace according to claim 1, wherein the steel coil specification comprises one or more of the thickness, the width, the coil number and the steel type of the steel coil.
4. The method for warning the temperature of the continuous annealing furnace according to claim 1, wherein the exhaust gas comprises particulate matters and SO2、NOX、O2And one or more of the temperature of the waste gas, wherein x is the atomic number ratio of O to N in the NOx.
5. The method for warning the furnace temperature of the continuous annealing furnace according to claim 1, wherein before the real-time collection of the process parameters in the furnace fire, the method for warning the furnace temperature further comprises: and setting a standard value of each process point location of each furnace section, wherein the standard value is a reference range of health degree evaluation of the corresponding process point location.
6. The method for warning the furnace temperature of the continuous annealing furnace according to claim 1, wherein the step of predicting the furnace temperature change of each furnace section in the annealing furnace based on a BP neural network algorithm comprises the following steps:
selecting a sample training set from the sample set;
constructing a BP neural network model, wherein the BP neural network model comprises an input layer, a hidden layer and an output layer, all neurons in adjacent layers are in full connection, and all neurons in each layer are not in connection; setting model parameters, including: setting selection of input signals of an input layer, setting the number of layers of a hidden layer and the number of nodes of each layer, and setting the number of nodes, learning rate, transfer function, momentum factor, maximum training times and minimum precision of an output layer;
training a BP neural network model by using the existing sample training set, comprising the following steps: proceeding according to a forward propagation direction, obtaining the output value of each neuron from the direction from the input layer to the hidden layer to the output layer until obtaining the output value of the final output layer, if the output value of the output layer is not consistent with the expected output value, proceeding according to the backward propagation direction, and adjusting the connection weight between the neurons according to the set learning rate and the error between the actual output and the expected output value of the output layer; alternately performing forward output calculation and reverse weight modification until the error of network output is smaller than the preset minimum precision or the preset maximum training times to determine a current furnace temperature change trend prediction model;
and inputting the sample set into an input layer of the BP neural network model according to the trained BP neural network model, and obtaining a predicted value of the current furnace temperature change trend through the processing of the neural network.
7. The furnace temperature early warning method of the continuous annealing furnace according to claim 6, wherein the learning rate of the BP neural network model is selected from a range of 0.01-0.8; the selection range of the momentum factor is between 0 and 1 and is larger than the learning rate; the transfer function is
8. The utility model provides a continuous annealing stove furnace temperature early warning system which characterized in that includes:
the data acquisition module is used for acquiring process parameters of process point locations set by each furnace section in the annealing furnace in real time, wherein the set process point locations comprise one or more of oxygen content, hydrogen content, dew point of atmosphere in the furnace, furnace pressure, target plate temperature, roller shaft tension, steel coil number, furnace temperature, steel coil specification, unit speed, plate temperature and waste gas;
the sample generation module is used for grouping the acquired data according to the type of the process point location, independently setting the sample acquisition time period of each group, and processing the data of each sample acquisition time period according to a preset sample acquisition method corresponding to the type of the process point location to form a single sample;
the data quality inspection module is used for performing data quality inspection on all samples, only retaining data in a normal operation time period of the unit, eliminating data in a fault time period, and interpolating a few missing data in the normal operation time period to form a sample set;
the characteristic extraction module is used for extracting characteristics of the sample set and calculating the average value and the standard deviation of the samples in preset time;
the overrun judgment alarm module is used for carrying out statistical judgment on the sample set according to a first judgment rule, and triggering overrun alarm if the judgment result is overrun abnormity;
the degradation trend judgment and early warning module is used for carrying out statistical judgment on the sample set according to a second judgment rule under the condition that the sample set is not in overrun abnormality, and triggering degradation trend early warning if the judgment result is in fluctuation abnormality and indicates that the annealing furnace has a degradation trend and an unstable condition appears;
and the furnace temperature prediction module based on the BP neural network algorithm is used for predicting the furnace temperature change condition of each furnace section in the annealing furnace based on the BP neural network algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101209.9A CN112430727B (en) | 2020-10-15 | 2020-10-15 | Furnace temperature early warning method and system for continuous annealing furnace |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101209.9A CN112430727B (en) | 2020-10-15 | 2020-10-15 | Furnace temperature early warning method and system for continuous annealing furnace |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112430727A CN112430727A (en) | 2021-03-02 |
| CN112430727B true CN112430727B (en) | 2022-05-20 |
Family
ID=74690036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011101209.9A Active CN112430727B (en) | 2020-10-15 | 2020-10-15 | Furnace temperature early warning method and system for continuous annealing furnace |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112430727B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113151666B (en) * | 2021-03-16 | 2022-07-22 | 沈阳广泰真空科技有限公司 | Operation control method, device and system for continuous vacuum heat treatment furnace |
| CN113325819B (en) * | 2021-04-22 | 2022-08-19 | 上海孟伯智能物联网科技有限公司 | Continuous annealing unit fault diagnosis method and system based on deep learning algorithm |
| CN113862436A (en) * | 2021-10-09 | 2021-12-31 | 河北工程大学 | High-entropy alloy heat treatment method based on artificial intelligence prediction system |
| CN114058833B (en) * | 2021-11-17 | 2023-12-22 | 上海途开者机械工程技术有限公司 | Automatic continuous annealing furnace control method and system, computer readable storage medium and computer program product |
| CN114681736B (en) * | 2022-03-30 | 2022-10-18 | 广东省医疗器械质量监督检验所 | Respirator abnormality detection method and respirator |
| TWI810000B (en) * | 2022-07-29 | 2023-07-21 | 中國鋼鐵股份有限公司 | Automatic temperature control method for steel strip continuous annealing process and computer program product |
| CN115563819B (en) * | 2022-12-06 | 2023-04-07 | 北京博数智源人工智能科技有限公司 | Thermal power station furnace tube loss evaluation method and system based on temperature change |
| CN115852289A (en) * | 2023-02-13 | 2023-03-28 | 惠博新材料股份有限公司 | Monitoring method and monitoring system for manufacturing and processing process of galvanized plate |
| CN118460840B (en) * | 2024-07-09 | 2024-10-15 | 辰信轴承科技(山东)有限公司 | Intelligent monitoring system of automatic continuous production line of hood-type spheroidizing annealing furnace |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102455135B (en) * | 2010-10-27 | 2013-11-20 | 宝山钢铁股份有限公司 | Furnace temperature control method and control equipment for open fire heating furnace |
| CN104962727B (en) * | 2015-07-29 | 2017-04-05 | 上海宝钢节能环保技术有限公司 | A kind of continuous annealing furnace bringing-up section Furnace Temperature Control System and method |
| CN106350657B (en) * | 2016-08-29 | 2018-06-22 | 首钢京唐钢铁联合有限责任公司 | Buckling-proof alarm system applied to continuous vertical annealing furnace |
| CN110042223B (en) * | 2018-01-16 | 2022-07-05 | 上海金艺检测技术有限公司 | On-line monitoring and diagnosing method for annealing furnace of cold rolling hot galvanizing unit |
| CN109492335B (en) * | 2018-12-12 | 2020-12-08 | 中国地质大学（武汉） | Method and system for predicting furnace temperature of annealing furnace |
| CN110607435B (en) * | 2019-09-05 | 2020-10-30 | 中国地质大学（武汉） | Annealing furnace plate temperature control system and method |
-
2020
- 2020-10-15 CN CN202011101209.9A patent/CN112430727B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112430727A (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112430727B (en) | Furnace temperature early warning method and system for continuous annealing furnace | |
| EP3928885A1 (en) | Rolling load predicting method, rolling load predicting device, and rolling control method | |
| CN106636610A (en) | Time-and-furnace-length-based double-dimensional stepping type heating curve optimizing setting method of heating furnace | |
| US6546310B1 (en) | Process and device for controlling a metallurgical plant | |
| CN113033974B (en) | Digital steel coil characteristic quality prediction and process parameter dynamic adjustment method and system based on improved LSTM network | |
| CN102319883A (en) | Method for controlling on-line prediction of continuous casting blank quality | |
| CN102540879A (en) | Multi-target evaluation optimization method based on group decision making retrieval strategy | |
| CN102147273A (en) | Data-based blast-furnace gas dynamic predication method for metallurgical enterprises | |
| Laurinen et al. | An adaptive neural network model for predicting the post roughing mill temperature of steel slabs in the reheating furnace | |
| JP7503150B2 (en) | System and method for controlling a production facility consisting of several facility parts, in particular for producing industrial products such as metal semi-finished products - Patents.com | |
| CN105181744B (en) | A kind of computational methods and the anti-spontaneous combustion monitoring system of coal yard of dump ignition phase | |
| CN111832215A (en) | Method for on-line predicting steel plate structure performance | |
| CN106845826B (en) | PCA-Cpk-based cold continuous rolling production line service quality state evaluation method | |
| CN106600076A (en) | Regenerative thermal oxidizer (RTO) waste gas treatment device monitoring data analysis and early warning method | |
| CN112718880A (en) | Tapping temperature control system of rod and wire heating furnace and operation method thereof | |
| CN117494531A (en) | Medium carbon steel decarburization depth prediction method based on finite element and XGBoost algorithm | |
| JP7135962B2 (en) | Steel plate finishing delivery side temperature control method, steel plate finishing delivery side temperature control device, and steel plate manufacturing method | |
| CN113325819B (en) | Continuous annealing unit fault diagnosis method and system based on deep learning algorithm | |
| CN111222627A (en) | Air knife distance data driving prediction method for plating control | |
| Lan et al. | Prediction of Microstructure and Mechanical Properties of Hot Rolled Steel Strip: Part I‐Description of Models | |
| JP7562707B2 (en) | System, method and computer program for controlling a manufacturing facility consisting of several facility parts, in particular a metal processing manufacturing facility for producing metal products such as metal semi-finished products and/or metal finished products | |
| KR100306140B1 (en) | Method for controlling cooling of wire rods by neural network | |
| JP2002236119A (en) | Material estimating device for steel product | |
| SHERBAF et al. | Multi-objective economic-statistical design of cumulative count of conforming control chart | |
| CN115392104A (en) | Method for predicting mechanical property of cold-rolled continuous annealing strip steel based on annealing process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |