CN116205543B - Method and system for detecting quality of metallurgical steel by combining feedback - Google Patents
Method and system for detecting quality of metallurgical steel by combining feedback Download PDFInfo
- Publication number
- CN116205543B CN116205543B CN202310486731.0A CN202310486731A CN116205543B CN 116205543 B CN116205543 B CN 116205543B CN 202310486731 A CN202310486731 A CN 202310486731A CN 116205543 B CN116205543 B CN 116205543B
- Authority
- CN
- China
- Prior art keywords
- pieces
- detection
- information
- failure
- association degree
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 124
- 239000010959 steel Substances 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 400
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000013507 mapping Methods 0.000 claims description 23
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 27
- 230000006978 adaptation Effects 0.000 abstract description 12
- 238000012545 processing Methods 0.000 abstract description 2
- 238000003723 Smelting Methods 0.000 description 20
- 238000007689 inspection Methods 0.000 description 6
- 238000012797 qualification Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000005489 elastic deformation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
The application discloses a method and a system for detecting the quality of metallurgical steel by combining feedback, and relates to the field of data processing, wherein the method comprises the following steps: according to the M pieces of failure detection data, N pieces of first association degree information are calculated; calculating Q pieces of second association degree information according to the P pieces of unqualified detection results; based on the above, Q pieces of comprehensive association degree information are obtained through calculation, the largest first K pieces of comprehensive association degree information and K pieces of key quality detection items are determined, the largest first K pieces of comprehensive association degree information are input into a detection requirement analysis model, K detection requirement adjustment coefficients are obtained, and detection quality requirements of the K pieces of key quality detection items are adjusted. The technical problems that in the prior art, the adaptation degree is low and the accuracy is insufficient aiming at the quality detection requirement of the metallurgical steel, and then the quality detection effect of the metallurgical steel is poor are solved. The technical effects of improving the adaptation degree and accuracy of the quality detection requirements of the metallurgical steel and improving the quality detection effect of the metallurgical steel are achieved.
Description
Technical Field
The application relates to the field of data processing, in particular to a method and a system for detecting the quality of steel smelting by combining feedback.
Background
Along with the modernization progress of cities, the metallurgical steel industry is rapidly developed. Meanwhile, the steel smelting quality is uneven, and unexpected failure in the steel use process caused by steel smelting quality problems sometimes occurs. Quality detection of metallurgical steel is receiving a great deal of attention.
At present, the quality detection of the steel is limited to fixed detection items and detection standards, and the steel is not detected in a targeted manner according to the conditions in the use process of the steel. In the prior art, the technical problems of low adaptation degree and insufficient accuracy required for the quality detection of the metallurgical steel, and poor quality detection effect of the metallurgical steel are caused.
Disclosure of Invention
The application provides a method and a system for detecting the quality of metallurgical steel by combining feedback. The technical problems that in the prior art, the adaptation degree is low and the accuracy is insufficient aiming at the quality detection requirement of the metallurgical steel, and then the quality detection effect of the metallurgical steel is poor are solved. The technical effects of analyzing the multidimensional quality detection requirements of steel according to the use requirements, improving the adaptation degree and accuracy of the quality detection requirements of steel smelting and improving the quality detection effect of steel smelting are achieved.
In view of the above problems, the present application provides a method and a system for detecting the quality of metallurgical steel by combining feedback.
In a first aspect, the present application provides a method of detecting the quality of steel using feedback in combination, wherein the method is applied to a system for detecting the quality of steel using feedback in combination, the method comprising: acquiring detection data of failure of target steel in a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers; collecting P unqualified detection results which are unqualified in the quality detection of the target steel within the preset time range in the past, wherein each unqualified detection result comprises detection data of whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relation with N failure reasons; according to the M failure detection data, N pieces of first association degree information of the N failure reasons and the failure of the target steel are calculated; according to the P unqualified detection results, Q pieces of second association degree information of the Q quality detection items and the unqualified quality detection of the target steel are calculated; according to the N pieces of first association degree information, the Q pieces of second association degree information and the mapping relation, Q pieces of comprehensive association degree information of the Q pieces of quality detection items are obtained through calculation, the quality detection items corresponding to the largest first K pieces of comprehensive association degree information are used as K pieces of key quality detection items, and K is a positive integer smaller than Q; inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of the K key quality detection items.
In a second aspect, the application also provides a metallurgical grade detection system incorporating feedback, wherein the system comprises: the detection data acquisition module is used for acquiring detection data of failure of the target steel in the use process within a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers; the unqualified detection result acquisition module is used for acquiring P unqualified detection results which appear in the quality detection of the target steel in the past preset time range, wherein each unqualified detection result comprises detection data of whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relation with N failure reasons; the first relevance calculating module is used for calculating N pieces of first relevance information of the N failure reasons and the failure of the target steel according to the M pieces of failure detection data; the second association degree calculation module is used for calculating Q pieces of second association degree information of the Q quality detection items and the quality detection failure of the target steel according to the P pieces of failure detection results; the key quality detection item determining module is used for calculating Q comprehensive association degree information of the Q quality detection items according to the N pieces of first association degree information, the Q pieces of second association degree information and the mapping relation, taking the quality detection item corresponding to the largest first K pieces of comprehensive association degree information as K key quality detection items, wherein K is a positive integer smaller than Q; the detection requirement adjustment module is used for inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of the K key quality detection items.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
acquiring failure detection data and failure detection results of target steel within a past preset time range to obtain M pieces of failure detection data and P pieces of failure detection results; calculating N first association degree information of N failure reasons and failures of the target steel material through M failure detection data; q pieces of second association degree information of Q quality detection items and unqualified quality detection of target steel products are obtained through calculation according to the P unqualified detection results; calculating to obtain Q comprehensive association degree information through N pieces of first association degree information, Q pieces of second association degree information and a mapping relation, and taking quality detection items corresponding to the first K largest comprehensive association degree information as K key quality detection items; inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of K key quality detection items according to the K detection requirement adjustment coefficients. The technical effects of improving the adaptation degree and accuracy of the quality detection requirements of the metallurgical steel and improving the quality detection effect of the metallurgical steel by carrying out multidimensional quality detection requirement analysis on the steel are achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of a method for detecting quality of steel by combining feedback according to the present application;
FIG. 2 is a schematic flow chart of K key quality detection items obtained in a method for detecting the quality of metallurgical steel by combining feedback according to the present application;
FIG. 3 is a schematic diagram of a steel quality inspection system incorporating feedback according to the present application.
Reference numerals illustrate: the system comprises a detection data acquisition module 11, a disqualification detection result acquisition module 12, a first association degree calculation module 13, a second association degree calculation module 14, a key quality detection item determination module 15 and a detection requirement adjustment module 16.
Detailed Description
The application provides a method and a system for detecting the quality of steel smelting by combining feedback. The technical problems that in the prior art, the adaptation degree is low and the accuracy is insufficient aiming at the quality detection requirement of the metallurgical steel, and then the quality detection effect of the metallurgical steel is poor are solved. The technical effects of improving the adaptation degree and accuracy of the quality detection requirements of the metallurgical steel and improving the quality detection effect of the metallurgical steel by carrying out multidimensional quality detection requirement analysis on the steel are achieved.
Example 1
Referring to fig. 1, the present application provides a method for detecting the quality of steel by combining feedback, wherein the method is applied to a system for detecting the quality of steel by combining feedback, and the method specifically comprises the following steps:
step S100: acquiring detection data of failure of target steel in a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers;
step S200: collecting P unqualified detection results which are unqualified in the quality detection of the target steel within the preset time range in the past, wherein each unqualified detection result comprises detection data of whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relation with N failure reasons;
specifically, based on a past preset time range, failure detection data and failure detection results of the target steel are acquired, and M pieces of failure detection data and P pieces of failure detection results are obtained. Wherein the past preset time range includes a preset determined historical time range, for example, the past year. The target steel is any steel which is subjected to intelligent quality detection by using the steel smelting quality detection system combined with feedback. Each failure detection data comprises detection data of whether N failure reasons appear or not, M is the number of times that the target steel fails, and M and N are positive integers. Each disqualified detection result comprises detection data of whether Q quality detection items are qualified or not, and Q is a positive integer. And, Q quality detection items have a mapping relationship with N failure reasons. And one failure cause can correspond to a plurality of quality detection items.
The N failure reasons include deformation failure, abrasion failure, corrosion failure, fracture failure and other failure reasons. The Q quality detection items comprise a plurality of quality detection items such as elastic modulus detection, density detection, hardness detection, oxidation resistance detection, ultrasonic flaw detection and the like. The method achieves the technical effects that M pieces of failure detection data and P pieces of unqualified detection results are obtained by data acquisition of the target steel, and a foundation is laid for subsequent quality detection requirement analysis of the target steel.
Step S300: according to the M failure detection data, N pieces of first association degree information of the N failure reasons and the failure of the target steel are calculated;
further, the step S300 of the present application further includes:
step S310: calculating the occurrence times of the N failure reasons in the M failure detection data to obtain N occurrence times;
step S320: and calculating the ratio of the N occurrence times to M to obtain the N pieces of first association degree information.
Specifically, in general, when a steel fails, only one failure cause will generally occur, and the number of occurrences of N failure causes in M failure detection data is counted separately, to obtain N occurrence numbers. And respectively carrying out ratio calculation on the N occurrence times and M to obtain N pieces of first association degree information. Wherein each occurrence number includes a total number of occurrences of each failure cause within the M failure detection data. The N first degree of association information includes a plurality of ratios between N number of occurrences and M. The technical effect of calculating N first association degree information of N failure reasons and failure of target steel through M failure detection data and providing data support for subsequent determination of K key quality detection items is achieved.
Step S400: according to the P unqualified detection results, Q pieces of second association degree information of the Q quality detection items and the unqualified quality detection of the target steel are calculated;
further, the step S400 of the present application further includes:
step S410: according to the P unqualified detection results, calculating the total times information of unqualified occurrence quality of the Q quality detection items and the Q times information of unqualified occurrence quality times of the Q quality detection items;
specifically, a failure detection result may include a plurality of failure quality detection items, and the number of quality failures of Q quality detection items in P failure detection results is counted to obtain Q number of times information, and the Q number of times information is summed up to obtain total number of times information. Wherein each of the number of times information includes the number of times of quality failure of each of the quality inspection items occurring in the P failure inspection results. The total number of times information is the sum of the Q number of times information.
Step S420: and calculating and obtaining the Q pieces of second association degree information according to the total frequency information and the Q pieces of frequency information.
Further, step S420 of the present application further includes:
step S421: calculating the ratio of the Q times information to the total times information to obtain Q pieces of support degree information;
step S422: calculating the ratio of the Q times information to P to obtain Q credibility information;
step S423: and carrying out weighted calculation on the Q pieces of support degree information and the Q pieces of credibility information to obtain the Q pieces of second association degree information.
Specifically, ratio calculation is performed on the Q number of times information and the total number of times information, respectively, to obtain Q support degree information. And respectively carrying out ratio calculation on the Q times information and P to obtain Q credibility information. And then, carrying out weighted calculation on the Q pieces of support degree information and the Q pieces of credibility information to obtain Q pieces of second association degree information. Wherein the Q pieces of support degree information include a plurality of ratios between the Q pieces of number of times information and the total number of times information. The Q pieces of reliability information include a plurality of ratios between the Q pieces of frequency information and P, so that the probability of occurrence of failure in all of the failure times of each quality inspection item and the probability of occurrence of failure in each quality inspection item when the failure inspection result occurs can be reflected.
Illustratively, when Q pieces of second association degree information are obtained, a certain support degree weight value and a certain credibility weight value are preset by the steel smelting quality detection system using feedback in combination. And multiplying the Q pieces of support degree information and the support degree weight value respectively to obtain Q pieces of weighted support degree information. And multiplying the Q pieces of credibility information and the credibility weight value respectively to obtain Q pieces of weighted credibility information. And respectively carrying out addition calculation on the Q weighted support degree information and the corresponding Q weighted credibility information to obtain Q second association degree information. For example, the support weight value and the credibility weight value are respectively 0.4 and 0.6.
The technical effect that accurate Q pieces of second association degree information are obtained by carrying out multidimensional association degree calculation on P unqualified detection results and Q quality detection items is achieved, and therefore analysis accuracy is required for quality detection of metallurgical steel is improved.
Step S500: according to the N pieces of first association degree information, the Q pieces of second association degree information and the mapping relation, Q pieces of comprehensive association degree information of the Q pieces of quality detection items are obtained through calculation, the quality detection items corresponding to the largest first K pieces of comprehensive association degree information are used as K pieces of key quality detection items, and K is a positive integer smaller than Q;
further, as shown in fig. 2, step S500 of the present application further includes:
step S510: according to the mapping relation, converting the N pieces of first association degree information into Q pieces of first association degree information;
step S520: weighting and calculating the Q pieces of first association degree information and the Q pieces of second association degree information to obtain the Q pieces of comprehensive association degree information;
step S530: and sequencing the Q pieces of comprehensive relevance information according to the sequence from large to small, and outputting quality detection items corresponding to the first K pieces of comprehensive relevance information in the sequencing as K pieces of key quality detection items.
Specifically, Q quality detection items have a mapping relationship with N failure causes, i.e., each failure cause corresponds to one/more quality detection items. The N failure reasons include deformation failure, abrasion failure, corrosion failure, fracture failure and other failure reasons. And, each of the N failure causes includes a finer failure cause. For example, when the failure cause is a deformation failure, the deformation failure includes an elastic deformation failure, a plastic deformation failure, a creep failure, and the like. Based on confirmation by a person skilled in the art, quality detection items corresponding to refined elastic deformation failure, plastic deformation failure and creep failure comprise elastic modulus detection, plastic deformation amount detection, creep strength detection and the like. In this way, a failure cause corresponds to one or more quality detection items, and a mapping relationship between Q quality detection items and N failure causes is formed.
And converting the N pieces of first association degree information according to the mapping relation between the Q quality detection items and the N failure reasons based on the Q quality detection items to obtain Q pieces of first association degree information. And then, carrying out weighted calculation on the Q pieces of first association degree information and the Q pieces of second association degree information to obtain Q pieces of comprehensive association degree information. Illustratively, the first association weight coefficient and the second association weight coefficient are preset and determined by the steel smelting quality detection system using feedback. And multiplying the Q pieces of first association degree information with the first association degree weight coefficients to obtain Q pieces of weighted first association degree information. And similarly, multiplying the Q pieces of second association degree information by the second association degree weight coefficients to obtain Q pieces of weighted second association degree information. And respectively carrying out addition calculation on the Q weighted first association degree information and the corresponding Q weighted second association degree information to obtain Q comprehensive association degree information. The first association weight coefficient and the second association weight coefficient may be both 0.5, and in another possible embodiment, the first association weight coefficient and the second association weight coefficient may be 0.7 and 0.3, respectively.
Further, the Q pieces of comprehensive relevance information are ordered in the order from large to small, and quality detection items corresponding to the first K pieces of comprehensive relevance information in the order are output as K pieces of key quality detection items. Wherein the K value may be determined by an adaptive setting, for example, may be 5. The K key quality detection items are quality detection items corresponding to the first K comprehensive relevance information in the Q comprehensive relevance information which are sequenced from big to small. The method achieves the technical effects that Q comprehensive relevance information of Q quality detection items is obtained by calculating N pieces of first relevance information and Q pieces of second relevance information, and Q quality detection items are screened according to the Q comprehensive relevance information to obtain K key quality detection items, so that the adaptation degree and the accuracy of the quality detection requirements of smelting steel are improved.
Step S600: inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of the K key quality detection items.
Further, the step S600 of the present application further includes:
step S610: according to failure detection data and quality detection data of steel in the past time, calculating to obtain a history comprehensive association degree information set;
step S620: according to the historical comprehensive relevance information in the historical comprehensive relevance information set, carrying out detection requirement evaluation adjustment to obtain a sample detection requirement adjustment coefficient set;
specifically, the steel smelting quality detection system combined with feedback is connected, failure data and detection data of steel in a plurality of preset time ranges in the past time are collected by the steel smelting quality detection system combined with feedback, analysis and calculation of comprehensive relevance information are carried out, and a history comprehensive relevance information set is obtained. And calibrating the sample detection requirement adjustment coefficient according to the historical comprehensive association degree information set by a technician in the field of steel quality detection analysis to obtain a sample detection requirement adjustment coefficient set. Wherein the past time includes a previously set historical time range parameter. And, the elapsed time is greater than the elapsed preset time range. The steel includes a plurality of similar steels as the target steel. The set of historical integrated relevance information includes a plurality of historical integrated relevance information. The sample detection requirement adjustment coefficient set comprises a plurality of sample detection requirement adjustment coefficients corresponding to a plurality of pieces of historical comprehensive relevance information. The sample detection requirement adjustment coefficient comprises amplitude information which corresponds to the historical comprehensive association degree information and is used for adjusting the detection qualification range of the quality detection item. The greater the historical comprehensive association degree information is, the greater the sample detection requirement adjustment coefficient is, the smaller the detection qualification range corresponding to the adjusted quality detection item is, and the more strict the quality detection corresponding to the quality detection item is. For example, if the sample detection requirement adjustment coefficient may be 0.5, the detection qualification range of the corresponding quality detection item needs to be reduced by 50%, for example, the original qualification range of the quality detection item is within 5% of error, and after the sample detection requirement adjustment coefficient is adjusted, the qualification range is within 2.5% of error. The technical effects of constructing a historical comprehensive association degree information set and a sample detection requirement adjustment coefficient set and tamping a foundation for a subsequent construction detection requirement analysis model are achieved.
Step S630: the historical comprehensive association degree information set and the sample detection requirement adjustment coefficient set are used as construction data, and the detection requirement analysis model is constructed;
further, step S630 of the present application further includes:
step S631: constructing a plurality of layers of division decision nodes in the detection requirement analysis model based on decision trees according to a plurality of pieces of history comprehensive relevance information in the history comprehensive relevance information set, wherein each layer of division decision nodes can conduct classification division decision on the input comprehensive relevance information, and input division results into an upper layer of division decision nodes;
step S632: obtaining a plurality of final division results of the multi-layer division decision node;
step S633: and marking the final division results by adopting a plurality of sample detection requirement adjustment coefficients in the sample detection requirement adjustment coefficient set as a plurality of decision results to obtain the detection requirement analysis model.
Step S640: inputting the maximum first K pieces of comprehensive association degree information into the detection requirement analysis model to obtain K detection requirement adjustment coefficients.
Specifically, the embodiment of the application builds a detection requirement analysis model based on the idea of a decision tree algorithm. Setting the historical comprehensive association degree information as a decision feature, and randomly selecting a plurality of pieces of historical comprehensive association degree information in the historical comprehensive association degree information set according to the decision feature to obtain a plurality of first division thresholds. The plurality of first partitioning thresholds includes a plurality of history integrated relevancy information randomly selected. A plurality of first partitioning thresholds is set as a multi-layered partitioning decision node within the detection requirement analysis model. Each layer of division decision nodes can carry out division decision on the input comprehensive association degree information, and the division result is input into an upper layer of division decision nodes.
Further, the multi-layer division decision nodes are connected, and a plurality of final division results of division decisions performed by the multi-layer division decision nodes are obtained, wherein each final division result comprises a section integrating the relevance information. And setting a plurality of sample detection requirement adjustment coefficients in the sample detection requirement adjustment coefficient set as a plurality of decision results. And marking a plurality of final dividing results according to the plurality of decision results to obtain a detection requirement analysis model. And then, inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of K key quality detection items according to the K detection requirement adjustment coefficients. The detection requirement analysis model comprises a multi-layer division decision node and a plurality of final division results marked according to a plurality of decision results. Each detection requirement adjustment coefficient comprises detection qualification range adjustment information of quality detection items corresponding to each comprehensive association degree information in the first K maximum comprehensive association degree information. The detection quality requirement comprises detection qualified ranges corresponding to K predetermined key quality detection items. The method achieves the technical effects that the adjustment coefficient matching is carried out on the maximum first K pieces of comprehensive association degree information through the detection requirement analysis model, and the K detection requirement adjustment coefficients are obtained, so that the accuracy of the detection quality requirements of K key quality detection items is improved, and the quality detection effect of smelting steel is improved.
In summary, the method for detecting the quality of the steel smelting by combining feedback provided by the application has the following technical effects:
1. acquiring failure detection data and failure detection results of target steel within a past preset time range to obtain M pieces of failure detection data and P pieces of failure detection results; calculating N first association degree information of N failure reasons and failures of the target steel material through M failure detection data; q pieces of second association degree information of Q quality detection items and unqualified quality detection of target steel products are obtained through calculation according to the P unqualified detection results; calculating to obtain Q comprehensive association degree information through N pieces of first association degree information, Q pieces of second association degree information and a mapping relation, and taking quality detection items corresponding to the first K largest comprehensive association degree information as K key quality detection items; inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of K key quality detection items according to the K detection requirement adjustment coefficients. The technical effects of improving the adaptation degree and accuracy of the quality detection requirements of the metallurgical steel and improving the quality detection effect of the metallurgical steel by carrying out multidimensional quality detection requirement analysis on the steel are achieved.
2. Through multidimensional association calculation of the P unqualified detection results and the Q quality detection items, accurate Q pieces of second association information are obtained, and therefore analysis accuracy of quality detection requirements of smelting steel is improved.
3. And carrying out adjustment coefficient matching on the maximum first K pieces of comprehensive association degree information through a detection requirement analysis model to obtain K detection requirement adjustment coefficients which are adapted, so that the accuracy of the detection quality requirements of K key quality detection items is improved, and the quality detection effect of smelting steel is improved.
Example 2
Based on the same inventive concept as the method for detecting the quality of steel by using feedback in combination with the above embodiment, the present application further provides a system for detecting the quality of steel by using feedback in combination, referring to fig. 3, the system includes:
the detection data acquisition module 11 is used for acquiring detection data of failure of the target steel in the use process within a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers;
the unqualified detection result collection module 12 is configured to collect P unqualified detection results that appear in quality detection of the target steel within the preset time range in the past, where each unqualified detection result includes detection data that whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relationship with N failure reasons;
a first association calculation module 13, where the first association calculation module 13 is configured to calculate N pieces of first association information of the N failure reasons and failure occurring in the target steel according to the M pieces of failure detection data;
the second association degree calculating module 14, where the second association degree calculating module 14 is configured to calculate Q second association degree information that the Q quality detection items and the target steel quality detection are not qualified according to the P failure detection results;
the key quality detection item determining module 15 is configured to calculate Q pieces of comprehensive relevance information of the Q quality detection items according to the N pieces of first relevance information, the Q pieces of second relevance information, and the mapping relation, and use quality detection items corresponding to the first K pieces of comprehensive relevance information that are the largest as K key quality detection items, where K is a positive integer smaller than Q;
the detection requirement adjustment module 16 is configured to input the first K maximum comprehensive association degree information into a detection requirement analysis model, obtain K detection requirement adjustment coefficients, and adjust detection quality requirements of the K key quality detection items.
Further, the system further comprises:
the frequency calculation module is used for calculating the frequency of occurrence of the N failure reasons in the M failure detection data to obtain N occurrence frequencies;
the first association degree obtaining module is used for calculating the ratio of the N occurrence times to M to obtain the N first association degree information.
Further, the system further comprises:
the first execution module is used for calculating the total number of times of occurrence of quality failure of the Q quality detection items and the Q number of times of occurrence of quality failure of the Q quality detection items according to the P failure detection results;
and the second association degree obtaining module is used for calculating and obtaining the Q second association degree information according to the total frequency information and the Q frequency information.
Further, the system further comprises:
the support degree calculating module is used for calculating the ratio of the Q times information to the total times information to obtain Q support degree information;
the reliability calculation module is used for calculating the ratio of the Q times information to P to obtain Q reliability information;
the first execution module is used for carrying out weighted calculation on the Q pieces of support degree information and the Q pieces of credibility information to obtain the Q pieces of second association degree information.
Further, the system further comprises:
the information conversion module is used for converting the N pieces of first association degree information into Q pieces of first association degree information according to the mapping relation;
the comprehensive relevance determining module is used for carrying out weighted calculation on the Q pieces of first relevance information and the Q pieces of second relevance information to obtain the Q pieces of comprehensive relevance information;
and the second execution module is used for sequencing the Q pieces of comprehensive relevance information according to the sequence from big to small, and outputting quality detection items corresponding to the first K pieces of comprehensive relevance information in the sequencing as K pieces of key quality detection items.
Further, the system further comprises:
the third execution module is used for calculating according to failure detection data and quality detection data of the steel in the past time to obtain a history comprehensive association degree information set;
the sample acquisition module is used for carrying out detection requirement evaluation adjustment according to the historical comprehensive relevance information in the historical comprehensive relevance information set to acquire a sample detection requirement adjustment coefficient set;
the fourth execution module is used for constructing the detection requirement analysis model by adopting the historical comprehensive association degree information set and the sample detection requirement adjustment coefficient set as construction data;
and the detection requirement adjustment coefficient determining module is used for inputting the maximum first K pieces of comprehensive association degree information into the detection requirement analysis model to obtain the K detection requirement adjustment coefficients.
Further, the system further comprises:
the fifth execution module is used for constructing a plurality of layers of division decision nodes in the detection requirement analysis model based on a decision tree according to a plurality of pieces of history comprehensive relevance information in the history comprehensive relevance information set, and each layer of division decision nodes can conduct classification division decision on the input comprehensive relevance information and input division results into an upper layer of division decision nodes;
the sixth execution module is used for acquiring a plurality of final division results of the multi-layer division decision node;
the marking module is used for marking the plurality of final division results by adopting a plurality of sample detection requirement adjustment coefficients in the sample detection requirement adjustment coefficient set as a plurality of decision results to obtain the detection requirement analysis model.
The steel smelting quality detection system combined with feedback provided by the embodiment of the application can execute the steel smelting quality detection method combined with feedback provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application.
The application provides a steel smelting quality detection method combined with feedback, wherein the method is applied to a steel smelting quality detection system combined with feedback, and the method comprises the following steps: acquiring failure detection data and failure detection results of target steel within a past preset time range to obtain M pieces of failure detection data and P pieces of failure detection results; calculating N first association degree information of N failure reasons and failures of the target steel material through M failure detection data; q pieces of second association degree information of Q quality detection items and unqualified quality detection of target steel products are obtained through calculation according to the P unqualified detection results; calculating to obtain Q comprehensive association degree information through N pieces of first association degree information, Q pieces of second association degree information and a mapping relation, and taking quality detection items corresponding to the first K largest comprehensive association degree information as K key quality detection items; inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of K key quality detection items according to the K detection requirement adjustment coefficients. The technical problems that in the prior art, the adaptation degree is low and the accuracy is insufficient aiming at the quality detection requirement of the metallurgical steel, and then the quality detection effect of the metallurgical steel is poor are solved. The technical effects of improving the adaptation degree and accuracy of the quality detection requirements of the metallurgical steel and improving the quality detection effect of the metallurgical steel by carrying out multidimensional quality detection requirement analysis on the steel are achieved.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, while the application has been described in connection with the above embodiments, the application is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the application, which is set forth in the following claims.
Claims (8)
1. A method of detecting quality of steel using feedback in combination, the method comprising:
acquiring detection data of failure of target steel in a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers;
collecting P unqualified detection results which are unqualified in the quality detection of the target steel within the preset time range in the past, wherein each unqualified detection result comprises detection data of whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relation with N failure reasons;
according to the M failure detection data, N pieces of first association degree information of the N failure reasons and the failure of the target steel are calculated;
according to the P unqualified detection results, Q pieces of second association degree information of the Q quality detection items and the unqualified quality detection of the target steel are calculated;
according to the N pieces of first association degree information, the Q pieces of second association degree information and the mapping relation, Q pieces of comprehensive association degree information of the Q pieces of quality detection items are obtained through calculation, the quality detection items corresponding to the largest first K pieces of comprehensive association degree information are used as K pieces of key quality detection items, and K is a positive integer smaller than Q;
inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of the K key quality detection items.
2. The method of claim 1, wherein calculating N pieces of first association information of the N failure causes with the occurrence of the failure of the target steel based on the M pieces of failure detection data, comprises:
calculating the occurrence times of the N failure reasons in the M failure detection data to obtain N occurrence times;
and calculating the ratio of the N occurrence times to M to obtain the N pieces of first association degree information.
3. The method of claim 1, wherein calculating Q second association information of the Q quality detection items with the target steel quality detection failure based on the P failure detection results, comprises:
according to the P unqualified detection results, calculating the total times information of unqualified occurrence quality of the Q quality detection items and the Q times information of unqualified occurrence quality times of the Q quality detection items;
and calculating and obtaining the Q pieces of second association degree information according to the total frequency information and the Q pieces of frequency information.
4. The method of claim 3, wherein computing the Q second association degree information based on the total number of times information and the Q number of times information comprises:
calculating the ratio of the Q times information to the total times information to obtain Q pieces of support degree information;
calculating the ratio of the Q times information to P to obtain Q credibility information;
and carrying out weighted calculation on the Q pieces of support degree information and the Q pieces of credibility information to obtain the Q pieces of second association degree information.
5. The method of claim 1, wherein calculating Q pieces of integrated relevance information for the Q quality-check items based on the N pieces of first relevance information, the Q pieces of second relevance information, and the mapping relation, includes:
according to the mapping relation, converting the N pieces of first association degree information into Q pieces of first association degree information;
weighting and calculating the Q pieces of first association degree information and the Q pieces of second association degree information to obtain the Q pieces of comprehensive association degree information;
and sequencing the Q pieces of comprehensive relevance information according to the sequence from large to small, and outputting quality detection items corresponding to the first K pieces of comprehensive relevance information in the sequencing as K pieces of key quality detection items.
6. The method of claim 1, wherein inputting the first K largest pieces of integrated association information into the detection requirement analysis model to obtain K detection requirement adjustment coefficients, comprises:
according to failure detection data and quality detection data of steel in the past time, calculating to obtain a history comprehensive association degree information set;
according to the historical comprehensive relevance information in the historical comprehensive relevance information set, carrying out detection requirement evaluation adjustment to obtain a sample detection requirement adjustment coefficient set;
the historical comprehensive association degree information set and the sample detection requirement adjustment coefficient set are used as construction data, and the detection requirement analysis model is constructed;
inputting the maximum first K pieces of comprehensive association degree information into the detection requirement analysis model to obtain K detection requirement adjustment coefficients.
7. The method of claim 6, wherein constructing the test requirement analysis model using the set of historical integrated relevance information and the set of sample test requirement adjustment coefficients as construction data comprises:
constructing a plurality of layers of division decision nodes in the detection requirement analysis model based on decision trees according to a plurality of pieces of history comprehensive relevance information in the history comprehensive relevance information set, wherein each layer of division decision nodes can conduct classification division decision on the input comprehensive relevance information, and input division results into an upper layer of division decision nodes;
obtaining a plurality of final division results of the multi-layer division decision node;
and marking the final division results by adopting a plurality of sample detection requirement adjustment coefficients in the sample detection requirement adjustment coefficient set as a plurality of decision results to obtain the detection requirement analysis model.
8. A metallurgical grade quality detection system incorporating the use of feedback, wherein the system is for performing the method of any one of claims 1 to 7, the system comprising:
the detection data acquisition module is used for acquiring detection data of failure of the target steel in the use process within a past preset time range, and obtaining M pieces of failure detection data, wherein each piece of failure detection data comprises detection data of whether N failure reasons occur or not, M is the number of times of failure of the target steel, and M and N are positive integers;
the unqualified detection result acquisition module is used for acquiring P unqualified detection results which appear in the quality detection of the target steel in the past preset time range, wherein each unqualified detection result comprises detection data of whether Q quality detection items are qualified or not, Q is a positive integer, and the Q quality detection items have a mapping relation with N failure reasons;
the first relevance calculating module is used for calculating N pieces of first relevance information of the N failure reasons and the failure of the target steel according to the M pieces of failure detection data;
the second association degree calculation module is used for calculating Q pieces of second association degree information of the Q quality detection items and the quality detection failure of the target steel according to the P pieces of failure detection results;
the key quality detection item determining module is used for calculating Q comprehensive association degree information of the Q quality detection items according to the N pieces of first association degree information, the Q pieces of second association degree information and the mapping relation, taking the quality detection item corresponding to the largest first K pieces of comprehensive association degree information as K key quality detection items, wherein K is a positive integer smaller than Q;
the detection requirement adjustment module is used for inputting the maximum first K pieces of comprehensive association degree information into a detection requirement analysis model to obtain K detection requirement adjustment coefficients, and adjusting the detection quality requirements of the K key quality detection items.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310486731.0A CN116205543B (en) | 2023-05-04 | 2023-05-04 | Method and system for detecting quality of metallurgical steel by combining feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310486731.0A CN116205543B (en) | 2023-05-04 | 2023-05-04 | Method and system for detecting quality of metallurgical steel by combining feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116205543A CN116205543A (en) | 2023-06-02 |
| CN116205543B true CN116205543B (en) | 2023-10-31 |
Family
ID=86515050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310486731.0A Active CN116205543B (en) | 2023-05-04 | 2023-05-04 | Method and system for detecting quality of metallurgical steel by combining feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116205543B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433108B (en) * | 2023-06-07 | 2023-10-27 | 张家港广大特材股份有限公司 | Raw material management method and system for smelting special steel |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009282740A (en) * | 2008-05-22 | 2009-12-03 | Sumitomo Metal Ind Ltd | Product quality prediction and control method |
| JP2013084057A (en) * | 2011-10-06 | 2013-05-09 | Nippon Steel & Sumitomo Metal | Management method for product quality and management device for product quality |
| CN106408166A (en) * | 2016-08-30 | 2017-02-15 | 内蒙古蒙牛乳业（集团）股份有限公司 | Detection data processing method and system |
| WO2018084180A1 (en) * | 2016-11-04 | 2018-05-11 | 株式会社Kmc | Production management system and production management method |
| CN111445103A (en) * | 2020-02-25 | 2020-07-24 | 国网河南省电力公司电力科学研究院 | Power transmission cable production quality management feedback system based on industrial internet |
| CN112434923A (en) * | 2020-11-16 | 2021-03-02 | 太原科技大学 | Mechanical product quality analysis method based on subspace clustering |
| CN113205278A (en) * | 2021-05-26 | 2021-08-03 | 深圳大尚网络技术有限公司 | Intelligent inspection system for building engineering quality |
| CN114994289A (en) * | 2022-08-01 | 2022-09-02 | 江苏卓鹏智能机电有限公司 | Spinning product quality detection method and system |
| CN115541601A (en) * | 2022-11-30 | 2022-12-30 | 江苏永钢集团有限公司 | Steel low-power digital detection method based on machine vision |
| CN115841359A (en) * | 2022-09-30 | 2023-03-24 | 浙江西图盟数字科技有限公司 | Object generation method, device, equipment and storage medium |
| CN115980531A (en) * | 2023-03-16 | 2023-04-18 | 江苏大全长江电器股份有限公司 | GIS switch cabinet quality detection method and system under specific environment |
| CN115993344A (en) * | 2023-03-23 | 2023-04-21 | 苏州斌智科技有限公司 | Quality monitoring and analyzing system and method for near infrared spectrum analyzer |
-
2023
- 2023-05-04 CN CN202310486731.0A patent/CN116205543B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009282740A (en) * | 2008-05-22 | 2009-12-03 | Sumitomo Metal Ind Ltd | Product quality prediction and control method |
| JP2013084057A (en) * | 2011-10-06 | 2013-05-09 | Nippon Steel & Sumitomo Metal | Management method for product quality and management device for product quality |
| CN106408166A (en) * | 2016-08-30 | 2017-02-15 | 内蒙古蒙牛乳业（集团）股份有限公司 | Detection data processing method and system |
| WO2018084180A1 (en) * | 2016-11-04 | 2018-05-11 | 株式会社Kmc | Production management system and production management method |
| CN111445103A (en) * | 2020-02-25 | 2020-07-24 | 国网河南省电力公司电力科学研究院 | Power transmission cable production quality management feedback system based on industrial internet |
| CN112434923A (en) * | 2020-11-16 | 2021-03-02 | 太原科技大学 | Mechanical product quality analysis method based on subspace clustering |
| CN113205278A (en) * | 2021-05-26 | 2021-08-03 | 深圳大尚网络技术有限公司 | Intelligent inspection system for building engineering quality |
| CN114994289A (en) * | 2022-08-01 | 2022-09-02 | 江苏卓鹏智能机电有限公司 | Spinning product quality detection method and system |
| CN115841359A (en) * | 2022-09-30 | 2023-03-24 | 浙江西图盟数字科技有限公司 | Object generation method, device, equipment and storage medium |
| CN115541601A (en) * | 2022-11-30 | 2022-12-30 | 江苏永钢集团有限公司 | Steel low-power digital detection method based on machine vision |
| CN115980531A (en) * | 2023-03-16 | 2023-04-18 | 江苏大全长江电器股份有限公司 | GIS switch cabinet quality detection method and system under specific environment |
| CN115993344A (en) * | 2023-03-23 | 2023-04-21 | 苏州斌智科技有限公司 | Quality monitoring and analyzing system and method for near infrared spectrum analyzer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116205543A (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116205543B (en) | Method and system for detecting quality of metallurgical steel by combining feedback | |
| CN109214581B (en) | Railway line wind speed prediction method considering wind direction and confidence interval | |
| CN115577018B (en) | Intelligent processing method and system for water quality monitoring data | |
| CN110619691B (en) | Prediction method and device for slab surface cracks | |
| CN110196814A (en) | A kind of method for evaluating software quality | |
| CN111080356A (en) | Method for calculating residence price influence factors by using machine learning regression model | |
| CN115586256B (en) | Method, device, equipment and storage medium for detecting cleaning grade of experimental equipment | |
| CN116823172B (en) | Model optimization-based engineering cost assessment method and system | |
| CN107679756B (en) | Soil suitability evaluation method and device | |
| CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN116415931A (en) | Big data-based power equipment operation state monitoring method and system | |
| CN113935535A (en) | Principal component analysis method for medium-and-long-term prediction model | |
| CN109902752B (en) | Bridge regular inspection classification method, device and equipment based on disease information big data | |
| Mayer et al. | Prediction of natural dry-snow avalanche activity using physics-based snowpack simulations | |
| CN107145995A (en) | Production environment safety prediction methods, devices and systems | |
| CN113283768A (en) | Food detection item extraction method, device, equipment and storage medium | |
| CN113505980A (en) | Reliability evaluation method, device and system for intelligent traffic management system | |
| CN111881800A (en) | Concrete filled steel tube void defect detection method based on AR model and self-service inspection | |
| CN115206528B (en) | Psychological health assessment system and method based on software data analysis | |
| CN116665482A (en) | Parking space recommending method and device based on intelligent parking | |
| CN113592090B (en) | Building quality prediction method and device based on deep learning and storage medium | |
| CN114418410A (en) | Army main battle sub-unit equipment combat effectiveness evaluation analysis method | |
| Petrocchi | Automatic detection of hail by radar | |
| Omar et al. | Mat-713: evaluation of ndt techniques for concrete bridge decks using fuzzy analytical hierarchy process | |
| CN112949977A (en) | Intelligent supervision management system for periodic acceptance check of engineering project quality based on big data and artificial intelligence |
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 |