CN116579654A - Online intelligent quality monitoring method and system for IF steel - Google Patents
Online intelligent quality monitoring method and system for IF steel Download PDFInfo
- Publication number
- CN116579654A CN116579654A CN202310544921.3A CN202310544921A CN116579654A CN 116579654 A CN116579654 A CN 116579654A CN 202310544921 A CN202310544921 A CN 202310544921A CN 116579654 A CN116579654 A CN 116579654A
- Authority
- CN
- China
- Prior art keywords
- quality
- steel
- online
- sample set
- hypersphere
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 150
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 59
- 239000010959 steel Substances 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 230000008569 process Effects 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000004519 manufacturing process Methods 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 238000004140 cleaning Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 17
- 230000032683 aging Effects 0.000 claims description 13
- 238000010438 heat treatment Methods 0.000 claims description 13
- 238000001816 cooling Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000002791 soaking Methods 0.000 claims description 8
- 229910052799 carbon Inorganic materials 0.000 claims description 7
- 238000010583 slow cooling Methods 0.000 claims description 7
- 238000005096 rolling process Methods 0.000 claims description 6
- 238000005098 hot rolling Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000003723 Smelting Methods 0.000 claims description 3
- 238000009628 steelmaking Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 abstract description 8
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 229910052742 iron Inorganic materials 0.000 abstract description 4
- 230000009466 transformation Effects 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- General Factory Administration (AREA)
Abstract
The application provides a quality online intelligent monitoring method and system for IF steel, wherein the method comprises the following steps: data acquisition and cleaning, and establishing a training sample set; training the training sample set by adopting a soft hypersphere method; carrying out online optimization on the product quality by adopting a local main manifold evolution algorithm; and (5) generating the technological specifications of the various working procedures of the IF steel. The application utilizes industrial big data analysis and machine learning methods to determine the range of the quality controllable region of the IF steel product so as to realize quality on-line intelligent monitoring. Aiming at the problems of iron and steel enterprises in online monitoring of product quality, the application provides a soft hypersphere algorithm-based online identification and abnormality cause diagnosis method of quality abnormal points and a manifold learning and adjacent point local projection transformation-based online optimization method of process parameters, so as to formulate quality design and process specification and improve production quality stability.
Description
Technical Field
The application relates to the technical field of automatic control, in particular to an online intelligent quality monitoring method and system for IF steel.
Background
The steel industry is a typical process industry, and the product involves multiple successive joining steps in the manufacturing process. At present, the main means for managing and controlling the product quality of enterprises is to make reasonable process specifications and judge the product quality by adopting a 'post' sampling detection mode. Such a process specification and "post-hoc" spot check, which rely on production experience, is prone to mass product quality outages or to claims and returns due to quality objections. The economic loss caused by quality waste judgment and quality objection is nearly one hundred billion yuan each year for iron and steel enterprises in China, and how to utilize an artificial intelligence method of big data analysis and machine learning to realize online monitoring and online optimization of product quality and to formulate scientific process specifications and quality designs is a key technology for the iron and steel enterprises to be solved urgently.
In actual industrial production, it is necessary to determine the control ranges of process parameters of different procedures, i.e. to formulate quality designs and process specifications of different products. When the process parameters (including the raw material parameters) are within this range, the set process parameters are considered to meet the product quality requirements, otherwise quality anomalies may occur. Currently, steel enterprises mainly rely on small-batch industrial trial production and production experience of technicians to formulate corresponding specifications in quality design and process specification formulation processes.
Disclosure of Invention
In view of the above, the application aims to provide an online intelligent quality monitoring method and system for IF steel, which can solve the existing problems in a targeted manner.
Based on the above purpose, the application provides an online intelligent quality monitoring method for IF steel, which comprises the following steps:
data acquisition and cleaning, and establishing a training sample set;
training the training sample set by adopting a soft hypersphere method;
carrying out online optimization on the product quality by adopting a local main manifold evolution algorithm;
and (5) generating the technological specifications of the various working procedures of the IF steel.
Further, the data acquisition and cleaning, creating a training sample set, includes:
the process parameters and quality index values of 12 different brands of IF steel of which the production line relates to material properties are collected, and the process parameters and quality index values comprise:
the main components in the steel during the smelting process of the steelmaking process are as follows: mass fraction of C, mn, P and S elements;
hot rolling: the outlet temperature of the heating furnace, the inlet temperature of the finish rolling, the outlet temperature of the finish rolling and the coiling temperature;
and (3) a heat treatment procedure: soaking average temperature, quick cooling outlet temperature, aging outlet temperature and slow cooling outlet temperature.
Further, the training sample set by using the soft hypersphere method comprises the following steps:
judging whether the technological parameters can cause abnormal product quality according to a preset super-ellipsoid boundary, randomly selecting 160 samples from an acquired training sample set as training samples, and determining the boundary of the training sample set by taking a soft super-sphere value as a control limit, namely solving the minimum closed super-sphere containing the training sample set.
Further, in the trained soft hypersphere model, 36 support vectors exist, and the support vectors and the corresponding weight coefficients monitor the product quality on line by the following formula:
wherein x represents the point to be measured, q represents the number of support vectors, gamma represents the relaxation coefficient,representing support vector +_>The weight coefficient corresponding to the support vector is represented, κ (,) represents the inner product of the variables, and R represents the radius of the smallest hypersphere.
Further, the product quality online optimization is performed by adopting a local main manifold evolution algorithm, which comprises the following steps:
the square of the distance from the sample x to be detected to the sphere center of the nonlinear hypersphere is calculated as follows:
the j-th variable of the sample x to be measured has a contribution value of deviation of
Wherein S is j Is the variance of variable j;
and determining the reason of the quality abnormality through the contribution value.
Further, the sample process parameters corresponding to the variables with the contribution values exceeding the preset range are determined as main reasons of quality abnormality.
Further, the process specification of each working procedure of generating the IF steel comprises the following steps: the process specifications for the various steps of IF steel are generated by a method that seeks the largest inscribed cuboid in the soft hypersphere.
Based on the above purpose, the application also provides an online intelligent quality monitoring system for the IF steel, which comprises:
the sample set module is used for collecting and cleaning data and establishing a training sample set;
the training module is used for training the training sample set by adopting a soft super sphere method;
the online optimization module is used for carrying out online optimization on the product quality by adopting a local main manifold evolution algorithm;
and the specification generation module is used for generating the process specification of each working procedure of the IF steel.
Overall, the advantages of the application and the experience brought to the user are:
aiming at the problems of iron and steel enterprises in online monitoring of product quality, the application provides a soft hypersphere algorithm-based online identification and abnormality cause diagnosis method of quality abnormal points and a manifold learning and adjacent point local projection transformation-based online optimization method of process parameters, so as to formulate quality design and process specification and improve production quality stability.
Drawings
In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the disclosure and are not therefore to be considered limiting of its scope.
Fig. 1 shows a flow chart of an online intelligent monitoring method for the quality of IF steel according to an embodiment of the application.
Fig. 2 shows a schematic diagram of a linear ellipsoid judging an outlier as an outlier.
Fig. 3 shows a schematic representation of the mapping of sample points from the original space to the feature space.
FIG. 4 shows a control limit R of a training set according to an embodiment of the application 2 Schematic diagram.
Fig. 5 shows a schematic of a minimum closed hypersphere.
Fig. 6 shows a schematic diagram of the on-line monitoring result of the training set.
Fig. 7 shows a contribution graph of 12 process parameters (sample 25).
Fig. 8 shows a contribution graph of 12 process parameters (sample 57).
Fig. 9 shows upper and lower limits of the process parameters of the heat treatment process.
Fig. 10 shows upper and lower limits of aging temperature and rapid cooling temperature.
Fig. 11 shows a constitution diagram of an on-line intelligent monitoring system for quality of IF steel according to an embodiment of the present application.
Fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 13 is a schematic diagram of a storage medium according to an embodiment of the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
The application aims to solve the technical problem of providing an online intelligent monitoring method for the quality of IF steel, and provides an online identification and abnormality cause diagnosis method for the quality abnormality of a product based on a soft super sphere algorithm aiming at the characteristics of high dimension, strong coupling and nonlinearity of industrial production data. And mapping sample points of the original space to a high-dimensional feature space by adopting a nonlinear Gaussian kernel function, determining a quality control limit by solving a soft hypersphere boundary in the feature space, and realizing product quality on-line monitoring and abnormality cause on-line diagnosis by utilizing a contribution graph of support vectors and abnormal points. The method for formulating the process specification by searching the maximum inscribed rectangle of the soft super sphere meets the requirement of personalized customization of the product. As shown in fig. 1, the online intelligent monitoring method for the quality of the IF steel provided by the application comprises the following steps:
step S1: data acquisition and cleaning, and establishing a training sample set: the process parameters and quality index values of 12 IF steels with different brands related to material performance are collected. The main components in the steel in the smelting process of the steelmaking process are as follows: mass fraction of C, mn, P and S elements; hot rolling: outlet temperature of the heating furnace, inlet temperature of finish rolling, outlet temperature of finish rolling, coiling temperature and the like; and (3) a heat treatment procedure: soaking average temperature, quick cooling outlet temperature, aging outlet temperature and slow cooling outlet temperature.
Step S2: training the collected data set by adopting a soft hypersphere method from the collected data set as a training sample: in actual production data, multiple coupling often exists between process parameters, and complex nonlinear characteristics exist between variables, so that the assumption of multivariate normal distribution is not satisfied between the process parameters. When nonlinear and non-normal distribution exists in the data set, the boundary of the super-ellipsoid in the linear form is easy to cause misjudgment, as shown in fig. 2.
The nonlinear mode analysis method based on the kernel function is adopted, and the kernel method is used for representing the inherent complex structural characteristics of the data through the nonlinear kernel function and determining the boundary of the nonlinear soft hypersphere. The nonlinear kernel functions map the data set on the original euclidean space into the high-dimensional feature space, and solve for the closed hypersphere in the nonlinear case by the inner product (dual form) of the mapping points phi (x) and phi (z), as shown in figure 3. As can be seen from fig. 3, the sample points of the original space (left image) are distributed in a complex enclosure, and after transformation by the nonlinear kernel function, the points phi (x) of the original sample points x mapped into the feature space are distributed in the enclosure sphere (right half of fig. 3).
For a stable production process, normal sample points are distributed in a certain super-ellipsoid in a high-dimensional space; once the sample points exceed the boundaries of the spheroid, the production process is considered abnormal. The position of the hyper-ellipsoid depends on the mean size of the variables and the correlation between the variables, while the size of the hyper-ellipsoid depends on the variance of the variables. The quality abnormal point identification method is to judge whether the set process parameters can cause abnormal product quality according to the determined ultra-ellipsoidal boundary, randomly selecting 160 samples from the collected data set as training samples, setting a relaxation coefficient=0.02, and taking the soft ultra-spherical value determined by the formula (1-4) as a control limit, wherein x is as follows i For a data vector of dimension p, n is the number of samples, the boundary of the data set is determined, i.e., the minimum closed hypersphere containing the data set is solved. Each sample point in the dataset should be less than the radius R of the sphere from the center C of the spheroid, as shown in fig. 5.
The minimum closed hypersphere can be expressed as the following optimization problem
And (3) optimizing solution:
constraint conditions: ||x i -C|| 2 ＝(x i -C) T (x i -C)≤R 2 ,i＝1,2,...n
Adding Lagrangian multiplier alpha to constraint conditions i Not less than 0, the corresponding Lagrange function is
C and R partial derivatives are calculated, and the derivative value is 0, so that the optimized solution of the hypersphere can be calculated
Wherein kappa (x) i ,x j ) Representing the inner product of the variables. Order theFrom the formula (3), the radius R and the center C of the minimum hypersphere can be obtained
Wherein alpha is i The optimal solution is obtained by the formula (3).
The training results are shown in fig. 4. As can be seen from fig. 4, most of the samples are below the control limit, which are all inside the soft hypersphere (normal samples), but 3 samples are at or beyond the control limit, and there may be quality anomalies. After examining the raw data, it was found that samples 28, 58 were in the normal range, but near the threshold, except that the quality index of sample 46 was slightly out of the standard. The reason for this is that the relaxation coefficient=0.02 is set in the training phase, i.e. the individual normal samples are allowed to be judged abnormal (outside the soft hypersphere boundary). The relaxation coefficient affects the soft supersphere value, so that the control limit can be moderately reduced for a product with high quality requirements for a strict monitoring of the production process.
In the trained soft hypersphere model, 36 support vectors are provided, and the support vectors and the corresponding weight coefficients monitor the product quality on line through the formula (5).
Wherein x represents a substance to be treatedThe measurement points q are the number of support vectors, gamma represents the relaxation coefficient,representing support vector +_>And the weight coefficient corresponding to the support vector is represented. In fact, in discriminant (5), D is a constant obtained by learning samples during the training phase, and no online calculation is required, and κ (x, x) is also a constant according to the definition of the kernel function. The only items related to the point x to be detected are
Therefore, when a sample to be identified is judged online, the equation (6) is only needed, and whether the quality is abnormal or not is judged by the equation (5), the calculation time is only needed to be a few milliseconds, and the real-time requirement of online monitoring of the quality is completely met.
Step S3: the local main manifold evolution algorithm is used for optimizing the product quality on line: if the process parameters of the previous process deviate, the process parameters need to be dynamically adjusted in the subsequent process, and the quality deviation caused by the previous process is corrected. 120 additional sample data were collected from the production line to verify the effectiveness of the method, and the results of the on-line monitoring are shown in fig. 6. As can be seen from fig. 6, sample No. 25 has exceeded the control limit, indicating that an abnormality occurs in the process parameters; sample number 57 is near the control limit and anomalies may occur.
In industrial application, once the set technological parameters deviate from the hypersphere, the process and the technological parameters are timely and accurately diagnosed, so that the technological parameters can be adjusted in subsequent production, and quality abnormality of batches is avoided. The quality abnormality diagnosis model has the function of searching for a contribution value of each process parameter causing deviation from the boundary of the controllable region from the set process parameters, wherein the process parameter with the large contribution value is a main cause of the deviation from the controllable region.
The square of the distance from the sample x to be detected to the sphere center of a nonlinear hypersphere (soft hypersphere) is:
as can be seen from formula (9), R is caused 2 (x) The reason for the enlargement is the second term to the right of the above equation. If a Gaussian kernel function is used, there are
Where σ is the coefficient term of the gaussian kernel function. It can be seen that ifThe larger the value of formula (8) is, the smaller is, so that R in formula (7) 2 (x) The greater the value. It can be seen that the change in the distance from the sample to be measured to the center of the sphere in the formula (7) is mainly determined by
Thus, the j-th variable of the sample x to be measured contributes to the deviation by a value of
In order to eliminate the influence of the variable dimension on the contribution value, the above formula is standardized, and the contribution value of the standardized variable j to the deviation is standardized
Wherein S is j For variance of variable j, concr (x j ) Those variables whose contribution values are the greatest are the main causes of the quality deviations.
In order to find the cause of the abnormality, the contribution value of the sample point process parameter (fig. 7 and 8) was calculated using equation (11), and it was found that the carbon mass fraction and the hot-rolling furnace outlet temperature contribution value were the largest. The data of the online monitoring system shows that the mass fraction of carbon at the No. 25 sample point is 0.0029 percent, which exceeds the maximum value of 0.0027 percent, the outlet temperature of the heating furnace is 1249 ℃ and is close to the minimum value 1247 ℃; the mass fraction of carbon at the sample point 57 is 0.0027%, the outlet temperature of the heating furnace is 1247 ℃, all the carbon are critical values, and other process parameters are all within the control limit range.
Because the technological parameters are closely related to the quality indexes, the product quality can be monitored on line through the on-line monitoring and diagnosis of the technological parameters. Essentially, a digital twin model is established between a physical object (process equipment and products) and a digital object (process parameters and product quality), and the behavior of the physical object under the set process parameters is predicted by the twin model. Through the analysis of the industrial application cases, the control limit determined by the soft hypersphere method can effectively realize the quality on-line monitoring, and the abnormal cause can be rapidly and accurately diagnosed.
Step S4: process specifications of various working procedures for producing the IF steel: the quality design according to the individual needs of the user is generated from the determined key process parameters, and the process parameter ranges for different yield strengths are given in table 1. Because of the quality indexes, such as tensile strength, elongation, plastic strain ratio and the like, can basically meet the product quality requirement in actual industrial production, while the yield strength is related to the forming performance of the IF steel and is difficult to control accurately in the production process, only the quality design for the yield strength is given in Table 1. Other quality indexes can also be used for preparing corresponding technological parameter ranges according to the requirements of users, and carrying out optimization combination with technological parameters prepared according to the yield strength, and finally determining technological parameter values so as to meet the personalized customization of users.
Table 1 mass design of yield strength
The heat treatment sequence is the last key procedure in the IF steel manufacturing process, the setting of the technological parameters determines the final performance of the material, and the main technological parameters comprise: soaking average temperature, quick cooling outlet temperature, aging outlet temperature, slow cooling outlet temperature, etc. The correlation coefficients between the process parameters are given in table 2, and the correlation coefficient of 4 pairs of variables is less than 0.5, so that only the upper and lower limits of the soft hypersphere in two-dimensional projection under the 4 conditions are concerned. Fig. 7 shows upper and lower limits of these 4 pairs of variables in the heat treatment process.
TABLE 2 correlation coefficient of heat treatment process parameters
In fig. 9a, the upper and lower limits of the maximum inscribed rectangle: soaking at 840-814 deg.c and fast cooling at 456-396 deg.c; in FIG. 9b, soaking temperature is 840-807 ℃, aging temperature is 392-356 ℃; in FIG. 9c, soaking temperature is 839-809 deg.C, slow cooling temperature is 662-618 deg.C; in FIG. 9d, the ageing temperature is 392-357℃and the slow cooling temperature is 662-620 ℃. Seeking the minimum set (union) of all variables, upper and lower limits of the process parameters of the heat treatment process: soaking temperature 839-814 ℃, quick cooling temperature 456-396 ℃, aging temperature 392-357 ℃ and slow cooling temperature 662-620 ℃.
Since there is strong coupling (correlation coefficient of 0.72) between the aging temperature and the rapid cooling temperature, the boundary problem of the correlation process parameters in the case of strong coupling needs to be discussed. The projection of the soft super sphere on two-dimensional variables of aging temperature and quick cooling temperature is shown in fig. 10, and the two-dimensional projection can be found to be an inclined complex boundary (the inclination angle is a tangent function of a correlation coefficient) from the graph, and the maximum inscribed rectangle becomes a parallelogram, and the upper limit and the lower limit are determined from the boundary of two points A, B. Boundary of parallel body: ageing temperature is 396-347 ℃, and quick cooling temperature is 451-398 ℃; and upper and lower limits determined by the maximum inscribed rectangle: ageing temperature 392-357 ℃, quick cooling temperature 456-396 ℃, obtaining the union of two sets, and finally obtaining upper and lower limits: ageing temperature is 392-357 deg.C, quick cooling temperature is 451-398 deg.C.
With reference to the same method, upper and lower limits of the process parameters of other steps are determined, and the setting ranges of the process parameters of each step are shown in table 3. In order to compare the upper and lower limit differences determined by the different methods, the upper and lower limits determined by the maximum and minimum values and the 6σ method are also given in table 3. It can be seen that the upper and lower limit regions of the process parameters determined by the soft hypersphere boundaries are stricter, more reasonable and more accurate than those determined by other methods.
TABLE 3 preset values of process parameters
The application embodiment provides an online intelligent monitoring system for quality of IF steel, which is used for executing the online intelligent monitoring method for quality of IF steel described in the above embodiment, as shown in fig. 11, and the system comprises:
the sample set module 901 is used for data acquisition and cleaning and establishing a training sample set;
a training module 902, configured to train the training sample set by using a soft super sphere method;
the online optimization module 903 is configured to perform online optimization on product quality by using a local main manifold evolution algorithm;
and the specification generation module 904 is used for generating the process specification of each working procedure of the IF steel.
The online intelligent monitoring system for the quality of the IF steel provided by the embodiment of the application and the online intelligent monitoring method for the quality of the IF steel provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the application program stored in the online intelligent monitoring system for the quality of the IF steel due to the same inventive concept.
The embodiment of the application also provides electronic equipment corresponding to the online intelligent monitoring method for the quality of the IF steel provided by the embodiment of the application, so as to execute the online intelligent monitoring method for the quality of the IF steel. The embodiment of the application is not limited.
Referring to fig. 12, a schematic diagram of an electronic device according to some embodiments of the present application is shown. As shown in fig. 12, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, the processor 200, the communication interface 203 and the memory 201 being connected by the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, the online intelligent monitoring method for the quality of the IF steel provided by any one of the foregoing embodiments of the present application is executed.
The memory 201 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 203 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 202 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. The memory 201 is configured to store a program, and the processor 200 executes the program after receiving an execution instruction, and the method for online intelligent monitoring of quality of IF steel disclosed in any of the foregoing embodiments of the present application may be applied to the processor 200 or implemented by the processor 200.
The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 200 or by instructions in the form of software. The processor 200 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201, and in combination with its hardware, performs the steps of the above method.
The electronic equipment provided by the embodiment of the application and the online intelligent monitoring method for the quality of the IF steel provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the electronic equipment and the online intelligent monitoring method for the quality of the IF steel.
The embodiment of the present application further provides a computer readable storage medium corresponding to the method for online intelligent monitoring of quality of IF steel provided in the foregoing embodiment, referring to fig. 13, the computer readable storage medium is shown as an optical disc 30, on which a computer program (i.e. a program product) is stored, where the computer program, when executed by a processor, performs the method for online intelligent monitoring of quality of IF steel provided in any of the foregoing embodiments.
It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.
The computer readable storage medium provided by the embodiment of the application has the same beneficial effects as the method adopted, operated or realized by the application program stored by the computer readable storage medium for the online intelligent monitoring method for the quality of the IF steel provided by the embodiment of the application due to the same inventive concept.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present application is not directed to any particular programming language. It will be appreciated that the teachings of the present application described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present application.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a virtual machine creation system according to embodiments of the application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application can also be implemented as an apparatus or system program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that various changes and substitutions are possible within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An online intelligent quality monitoring method for IF steel is characterized by comprising the following steps:
data acquisition and cleaning, and establishing a training sample set;
training the training sample set by adopting a soft hypersphere method;
carrying out online optimization on the product quality by adopting a local main manifold evolution algorithm;
and (5) generating the technological specifications of the various working procedures of the IF steel.
2. The online intelligent monitoring method for the quality of IF steel according to claim 1, wherein,
the data acquisition and cleaning establish a training sample set comprising:
the process parameters and quality index values of 12 different brands of IF steel of which the production line relates to material properties are collected, and the process parameters and quality index values comprise:
the main components in the steel during the smelting process of the steelmaking process are as follows: mass fraction of C, mn, P and S elements;
hot rolling: the outlet temperature of the heating furnace, the inlet temperature of the finish rolling, the outlet temperature of the finish rolling and the coiling temperature;
and (3) a heat treatment procedure: soaking average temperature, quick cooling outlet temperature, aging outlet temperature and slow cooling outlet temperature.
3. The online intelligent monitoring method for the quality of the IF steel according to claim 2, wherein,
the training sample set by adopting the soft hypersphere method comprises the following steps:
judging whether the technological parameters can cause abnormal product quality according to a preset super-ellipsoid boundary, randomly selecting 160 samples from an acquired training sample set as training samples, and determining the boundary of the training sample set by taking a soft super-sphere value as a control limit, namely solving the minimum closed super-sphere containing the training sample set.
4. The online intelligent monitoring method for the quality of IF steel according to claim 3, wherein,
in the trained soft super sphere model, 36 support vectors exist, and the support vectors and the corresponding weight coefficients monitor the product quality on line by the following formula:
wherein x represents the point to be measured, q represents the number of support vectors, gamma represents the relaxation coefficient,representing support vector +_>The weight coefficient corresponding to the support vector is represented, κ (,) represents the inner product of the variables, and R represents the radius of the smallest hypersphere.
5. The online intelligent monitoring method for the quality of IF steel according to claim 4, wherein,
the adoption of the local main manifold evolution algorithm for carrying out the online optimization of the product quality comprises the following steps:
the square of the distance from the sample x to be detected to the sphere center of the nonlinear hypersphere is calculated as follows:
the j-th variable of the sample x to be measured has a contribution value of deviation of
Wherein S is j Is the variance of variable j;
and determining the reason of the quality abnormality through the contribution value.
6. The online intelligent monitoring method for the quality of IF steel according to claim 5, wherein,
and determining the sample process parameters corresponding to the variables with the contribution values exceeding the preset range as main reasons of quality abnormality.
7. The online intelligent monitoring method for the quality of IF steel according to claim 1, wherein,
the technological specifications of the various working procedures for producing the IF steel comprise the following steps: the process specifications for the various steps of IF steel are generated by a method that seeks the largest inscribed cuboid in the soft hypersphere.
8. An online intelligent quality monitoring system for IF steel, comprising:
the sample set module is used for collecting and cleaning data and establishing a training sample set;
the training module is used for training the training sample set by adopting a soft super sphere method;
the online optimization module is used for carrying out online optimization on the product quality by adopting a local main manifold evolution algorithm;
and the specification generation module is used for generating the process specification of each working procedure of the IF steel.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor runs the computer program to implement the method of any one of claims 1-7.
10. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310544921.3A CN116579654A (en) | 2023-05-15 | 2023-05-15 | Online intelligent quality monitoring method and system for IF steel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310544921.3A CN116579654A (en) | 2023-05-15 | 2023-05-15 | Online intelligent quality monitoring method and system for IF steel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116579654A true CN116579654A (en) | 2023-08-11 |
Family
ID=87537211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310544921.3A Withdrawn CN116579654A (en) | 2023-05-15 | 2023-05-15 | Online intelligent quality monitoring method and system for IF steel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116579654A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117831659A (en) * | 2024-03-04 | 2024-04-05 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008042739A2 (en) * | 2006-09-29 | 2008-04-10 | Fisher-Rosemount Systems, Inc. | On-line monitoring and diagnostics of a process using multivariate statistical analysis |
| CN106054840A (en) * | 2016-06-29 | 2016-10-26 | 北京科技大学 | Whole process product quality online control system |
| CN111079832A (en) * | 2019-12-13 | 2020-04-28 | 辽宁科技大学 | Steel plate surface defect classification method with characteristic noise resistance |
| CN112207245A (en) * | 2020-09-27 | 2021-01-12 | 安徽工业大学 | Method for matching high-frequency and low-frequency data with cut casting blank number in continuous casting process |
| CN115049260A (en) * | 2022-06-15 | 2022-09-13 | 华院计算技术(上海)股份有限公司 | Application method and system of cognitive intelligent continuous casting ladle quality pre-judgment model |
| CN115081232A (en) * | 2022-06-30 | 2022-09-20 | 武汉钢铁有限公司 | Construction method and construction device of digital steel coil |
-
2023
- 2023-05-15 CN CN202310544921.3A patent/CN116579654A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008042739A2 (en) * | 2006-09-29 | 2008-04-10 | Fisher-Rosemount Systems, Inc. | On-line monitoring and diagnostics of a process using multivariate statistical analysis |
| CN106054840A (en) * | 2016-06-29 | 2016-10-26 | 北京科技大学 | Whole process product quality online control system |
| CN111079832A (en) * | 2019-12-13 | 2020-04-28 | 辽宁科技大学 | Steel plate surface defect classification method with characteristic noise resistance |
| CN112207245A (en) * | 2020-09-27 | 2021-01-12 | 安徽工业大学 | Method for matching high-frequency and low-frequency data with cut casting blank number in continuous casting process |
| CN115049260A (en) * | 2022-06-15 | 2022-09-13 | 华院计算技术(上海)股份有限公司 | Application method and system of cognitive intelligent continuous casting ladle quality pre-judgment model |
| CN115081232A (en) * | 2022-06-30 | 2022-09-20 | 武汉钢铁有限公司 | Construction method and construction device of digital steel coil |
Non-Patent Citations (2)
| Title |
|---|
| 徐钢;张晓彤;黎敏;徐金梧;: "基于统计过程控制的流程工业工艺规范制定方法", 机械工程学报, no. 08, pages 222 - 229 * |
| 徐钢;张晓彤;黎敏;徐金梧;: "基于软超球体的高维非线性数据异常点识别算法", 工程科学学报, no. 10, pages 93 - 99 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117831659A (en) * | 2024-03-04 | 2024-04-05 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
| CN117831659B (en) * | 2024-03-04 | 2024-05-03 | 山东钢铁股份有限公司 | Method and device for online detection of quality of wide and thick plates, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | A novel hierarchical detection and isolation framework for quality-related multiple faults in large-scale processes | |
| US20210342244A1 (en) | Distributed architecture for fault monitoring | |
| CN116579654A (en) | Online intelligent quality monitoring method and system for IF steel | |
| JP2019074969A (en) | Quality predicting device and quality predicting method | |
| Li et al. | Interpretation of convolutional neural network-based building HVAC fault diagnosis model using improved layer-wise relevance propagation | |
| CN108376264A (en) | A kind of handpiece Water Chilling Units method for diagnosing faults based on support vector machines incremental learning | |
| Wang et al. | Multiscale neighborhood normalization-based multiple dynamic PCA monitoring method for batch processes with frequent operations | |
| TWI737497B (en) | Quality designing method and electrical device | |
| CN109345143B (en) | Intelligent fan running state evaluation method and device and wind turbine generator | |
| CN104899425A (en) | Variable selection and forecast method of silicon content in molten iron of blast furnace | |
| CN107679089A (en) | A kind of cleaning method for electric power sensing data, device and system | |
| CN116432091A (en) | Equipment fault diagnosis method based on small sample, construction method and device of model | |
| Johnson et al. | Data preprocessing and mortality prediction: the Physionet/CinC 2012 challenge revisited | |
| Shi et al. | Intelligent fault diagnosis of rolling mills based on dual attention-guided deep learning method under imbalanced data conditions | |
| Mehta et al. | Collaborative Intelligence in AgriTech: Federated Learning CNN for Bean Leaf Disease Classification | |
| Lesany et al. | Recognition and classification of single and concurrent unnatural patterns in control charts via neural networks and fitted line of samples | |
| Jiao et al. | Collaborative multiple rank regression for temperature prediction of blast furnace | |
| CN107111643A (en) | Time series data retrieves device and time series data search program | |
| Shi et al. | An imbalanced data augmentation and assessment method for industrial process fault classification with application in air compressors | |
| TWI708128B (en) | Method and electrical device for adjusting process parameter | |
| CN109376080B (en) | Time-adaptive automatic defect positioning method and device | |
| CN112629659A (en) | Automated model training apparatus and automated model training method for training pipelines for different spectrometers | |
| CN115270861A (en) | Product composition data monitoring method and device, electronic equipment and storage medium | |
| Han et al. | Employing deep learning in non‐parametric inverse visualization of elastic–plastic mechanisms in dual‐phase steels | |
| CN116596376A (en) | Online automatic grade judging method and system for deep drawing steel quality |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230811 |