CN116433108A

CN116433108A - Raw material management method and system for smelting special steel

Info

Publication number: CN116433108A
Application number: CN202310669118.2A
Authority: CN
Inventors: 罗晓芳
Original assignee: Zhangjiagang Guangda Special Material Co ltd
Current assignee: Zhangjiagang Guangda Special Material Co ltd
Priority date: 2023-06-07
Filing date: 2023-06-07
Publication date: 2023-07-14
Anticipated expiration: 2043-06-07
Also published as: CN116433108B

Abstract

The invention discloses a raw material management method and a system for smelting special steel, and relates to the field of data processing, wherein the method comprises the following steps: classifying target batches of special steel smelting raw materials based on raw material type data to obtain N groups of special steel smelting raw materials; traversing N groups of special steel smelting raw materials to perform multi-dimensional quality inspection to obtain N groups of raw material quality inspection results; judging whether the quality inspection results of the N groups of raw materials meet N quality inspection qualification constraint conditions or not to obtain N quality inspection judgment results; obtaining a quality inspection qualification instruction and sending the quality inspection qualification instruction to an intelligent steel smelting raw material management platform; based on the warehouse area information and the smelting steel raw material list, a raw material warehouse management scheme is obtained according to a warehouse Chu Yunwei model, and warehouse management of target batches of special steel smelting raw materials is executed according to the raw material warehouse management scheme. Solves the technical problems of poor management effect of smelting raw materials aiming at special steels and the like in the prior art. The technical effects of improving the quality of the smelting raw materials of the special steel and the like are achieved.

Description

Raw material management method and system for smelting special steel

Technical Field

The invention relates to the field of data processing, in particular to a raw material management method and system for smelting special steels.

Background

The steel materials are classified into general steel materials and special steel materials. The special steel is the main steel in the industries of machinery, automobiles, military industry, chemical industry, household appliances and the like. The raw material management is one of the smelting production nodes of the special steel. In the prior art, the technical problems of insufficient quality inspection accuracy of smelting raw materials for special steels and low storage management adaptability, and poor management effect of the smelting raw materials for the special steels are caused.

Disclosure of Invention

The application provides a raw material management method and system for smelting special steel. Solves the technical problems of the prior art that the quality inspection accuracy of the smelting raw materials for the special steel is not enough and the storage management adaptability is low, thereby causing the poor management effect of the smelting raw materials for the special steel. The technical effects of improving the quality inspection accuracy and the storage management adaptability of the smelting raw materials of the special steel and improving the management quality of the smelting raw materials of the special steel are achieved.

In view of the above problems, the present application provides a raw material management method and system for smelting special steels.

In a first aspect, the present application provides a method for raw material management for specialty steel smelting, wherein the method is applied to a raw material management system for specialty steel smelting, the system including an intelligent metallurgical steel raw material management platform, the method comprising: constructing a raw material information acquisition table, traversing target batches of special steel smelting raw materials based on the raw material information acquisition table, and acquiring basic information to obtain a steel smelting raw material list; obtaining raw material type data based on the steel smelting raw material list, and classifying the target batch of special steel smelting raw materials based on the raw material type data to obtain N groups of special steel smelting raw materials, wherein N is a positive integer greater than 1; traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results; based on the raw material type data, N quality inspection qualification constraint conditions are obtained, whether the N groups of raw material quality inspection results meet the N quality inspection qualification constraint conditions is judged, and N quality inspection judgment results are obtained; based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to the intelligent steel smelting raw material management platform; the intelligent steel smelting raw material management platform comprises a bin Chu Yunwei model, and based on storage area information and the steel smelting raw material list, storage configuration analysis is carried out according to the storage operation and maintenance model to obtain a raw material storage management scheme; and executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.

In a second aspect, the present application also provides a raw material management system for special steel smelting, wherein the system includes an intelligent steel smelting raw material management platform, the system includes: the raw material information acquisition module is used for constructing a raw material information acquisition table, traversing the target batch of special steel smelting raw materials based on the raw material information acquisition table to acquire basic information, and obtaining a smelting steel raw material list; the raw material classification module is used for obtaining raw material type data based on the smelting steel raw material list, classifying the target batch of special steel smelting raw materials based on the raw material type data, and obtaining N groups of special steel smelting raw materials, wherein N is a positive integer greater than 1; the raw material quality inspection module is used for traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results; the judging module is used for obtaining N quality inspection qualified constraint conditions based on the raw material type data, judging whether the N groups of raw material quality inspection results meet the N quality inspection qualified constraint conditions or not and obtaining N quality inspection judging results; the instruction sending module is used for obtaining quality inspection qualified instructions based on the N quality inspection judging results and sending the quality inspection qualified instructions to the intelligent steel smelting raw material management platform; the warehouse configuration analysis module is used for the intelligent steel smelting raw material management platform and comprises a warehouse Chu Yunwei model, and based on warehouse area information and the steel smelting raw material list, warehouse configuration analysis is carried out according to the warehouse operation and maintenance model to obtain a raw material warehouse management scheme; and the warehouse management module is used for executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.

One or more technical solutions provided in the present application have at least the following technical effects or advantages:

traversing the target batch of special steel smelting raw materials through a raw material information acquisition table to acquire basic information, and obtaining a smelting steel raw material list; classifying target batches of special steel smelting raw materials based on raw material type data to obtain N groups of special steel smelting raw materials; the quality inspection results of N groups of raw materials are obtained by carrying out multi-dimensional quality inspection on N groups of special steel smelting raw materials; judging whether the quality inspection results of the N groups of raw materials meet N quality inspection qualification constraint conditions or not to obtain N quality inspection judgment results; based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to an intelligent steel smelting raw material management platform; based on the storage area information and the steel smelting raw material list, carrying out storage configuration analysis through a storage operation and maintenance model in the intelligent steel smelting raw material management platform to obtain a raw material storage management scheme, and executing storage management of target batch special steel smelting raw materials according to the raw material storage management scheme. The technical effects of improving the quality inspection accuracy and the storage management adaptability of the smelting raw materials of the special steel and improving the management quality of the smelting raw materials of the special steel are achieved.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

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 managing raw materials for smelting special steels;

FIG. 2 is a schematic flow chart of N groups of raw material quality inspection results obtained in a raw material management method for smelting special steels;

FIG. 3 is a schematic diagram of a material management system for special steel smelting.

Reference numerals illustrate: a raw material information acquisition module 11, a raw material classification module 12, a raw material quality inspection module 13, a judgment module 14, an instruction sending module 15, a storage configuration analysis module 16,

a warehouse management module 17.

Detailed Description

The application provides a raw material management method and system for smelting special steels. Solves the technical problems of the prior art that the quality inspection accuracy of the smelting raw materials for the special steel is not enough and the storage management adaptability is low, thereby causing the poor management effect of the smelting raw materials for the special steel. The technical effects of improving the quality inspection accuracy and the storage management adaptability of the smelting raw materials of the special steel and improving the management quality of the smelting raw materials of the special steel are achieved.

Example 1

Referring to fig. 1, the present application provides a raw material management method for smelting special steel, wherein the method is applied to a raw material management system for smelting special steel, the system comprises an intelligent steel smelting raw material management platform, and the method specifically comprises the following steps:

step S100: constructing a raw material information acquisition table, traversing target batches of special steel smelting raw materials based on the raw material information acquisition table, and acquiring basic information to obtain a steel smelting raw material list;

step S200: obtaining raw material type data based on the steel smelting raw material list, and classifying the target batch of special steel smelting raw materials based on the raw material type data to obtain N groups of special steel smelting raw materials, wherein N is a positive integer greater than 1;

Specifically, a raw material information collection table is constructed. The raw material information acquisition table comprises a plurality of information acquisition indexes. The plurality of information acquisition indexes comprise a plurality of raw material basic indexes such as raw material type, raw material price, raw material quantity, raw material weight, raw material manufacturer, raw material production date and the like, and a plurality of raw material storage environment indexes such as raw material storage environment temperature, raw material storage environment humidity, raw material storage ventilation requirement and the like. And then, based on the raw material information acquisition table, basic information acquisition is carried out on the target batch of special steel smelting raw materials, and a steel smelting raw material list is obtained. Raw material type data are extracted from the steel smelting raw material list, and target batches of special steel smelting raw materials are classified according to the raw material type data, so that N groups of special steel smelting raw materials are obtained.

The target batch of special steel smelting raw materials can be any batch of special steel smelting raw materials which are intelligently subjected to raw material management by using the raw material management system for special steel smelting. The steel smelting raw material list comprises raw material type data corresponding to target batch special steel smelting raw materials, raw material price information, raw material quantity information, raw material weight information, raw material manufacturer information, raw material production date information, raw material storage environment temperature information, raw material storage environment humidity information, raw material storage ventilation requirement information and other raw material basic information and raw material storage environment information corresponding to the raw material type data. The raw material type data comprise N raw material type parameters corresponding to the target batch of special steel smelting raw materials. N is a positive integer greater than 1. The N raw material type parameters comprise a plurality of raw material type parameters such as iron fine powder, coke, sintered ore, pellet, deoxidizer, carburant and the like. Each group of special steel smelting raw materials comprises smelting raw materials corresponding to each raw material type parameter in target batch special steel smelting raw materials. The technical effects that basic information acquisition is carried out on target batch special steel smelting raw materials through a raw material information acquisition table, a comprehensive smelting steel raw material list is obtained, the target batch special steel smelting raw materials are classified according to raw material type data in the smelting steel raw material list, N groups of special steel smelting raw materials are obtained, and a foundation is laid for carrying out raw material management on the target batch special steel smelting raw materials in the follow-up process are achieved.

Step S300: traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results;

further, as shown in fig. 2, step S300 of the present application further includes:

step S310: traversing the N groups of special steel smelting raw materials to obtain a first group of special steel smelting raw materials;

step S320: randomly sampling the first group of special steel smelting raw materials based on sampling constraint characteristics to obtain a first group of sampling raw materials;

step S330: performing external characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of raw material external characteristic quality inspection result;

step S340: performing internal characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of internal characteristic quality inspection result;

step S350: and obtaining a first group of raw material quality inspection results based on the first group of raw material external characteristic quality inspection results and the first group of raw material internal characteristic quality inspection results, and adding the first group of raw material quality inspection results to the N groups of raw material quality inspection results.

Specifically, each group of special steel smelting raw materials in the N groups of special steel smelting raw materials is set as a first group of special steel smelting raw materials in sequence, and the first group of special steel smelting raw materials are randomly sampled according to sampling constraint characteristics to obtain a first group of sampling raw materials. The sampling constraint characteristic includes a predetermined raw material sampling number/raw material sampling weight. The first set of sampled raw materials includes a random portion of the raw materials in the first set of specialty steel smelting raw materials. And, the first set of sampled raw materials satisfies a sampling constraint characteristic.

Further, the first group of sampling raw materials are subjected to external characteristic quality inspection and internal characteristic quality inspection respectively, and a first group of raw material external characteristic quality inspection result and a first group of internal characteristic quality inspection result are obtained. And setting the first group of raw material external characteristic quality inspection results and the first group of raw material internal characteristic quality inspection results as first group of raw material quality inspection results, and adding the first group of raw material quality inspection results to the N groups of raw material quality inspection results. Wherein, the external feature quality inspection includes performing color inspection, smell inspection, foreign matter inspection on the first group of sampling raw materials. The foreign matter inspection refers to an inspection of the first set of sampled materials for the presence of macroscopic impurities. The first group of raw material external characteristic quality inspection results comprise color information and smell information corresponding to the first group of sampling raw materials, and whether macroscopic impurities exist in the first group of sampling raw materials. The internal feature quality inspection includes physical and chemical index inspection of the first set of sampled raw materials. Illustratively, when performing the internal feature quality inspection on the first set of sampled raw materials, the first set of sampled raw materials is matched according to the raw material type data to obtain first raw material type information. The first raw material type information is a raw material type parameter corresponding to the first group of sampling raw materials. And carrying out historical data query based on the first raw material type information to obtain a plurality of historical raw material type information and a plurality of historical raw material physicochemical index inspection schemes. Each historical raw material physical and chemical index inspection scheme comprises a historical physical and chemical inspection index corresponding to each historical raw material type information and a historical inspection scheme corresponding to the historical physical and chemical inspection index. For example, when the historical feedstock type information is a carburant, the historical feedstock physicochemical index testing scheme includes a fixed carbon content test, an absorbance test, on the carburant. And analyzing the corresponding relation between the plurality of historical raw material type information and the plurality of historical raw material physicochemical index inspection schemes, and arranging the plurality of historical raw material type information and the plurality of historical raw material physicochemical index inspection schemes according to the corresponding relation to obtain a raw material internal characteristic quality inspection analysis database. Inputting the first raw material type information into a raw material internal feature quality inspection analysis database, matching physical and chemical inspection indexes and inspection schemes of the first raw material type information through the raw material internal feature quality inspection analysis database to obtain physical and chemical index inspection schemes corresponding to a first group of sampling raw materials, and carrying out physical and chemical inspection on the first group of sampling raw materials according to the physical and chemical index inspection schemes to obtain a first group internal feature quality inspection result. The N sets of feedstock quality inspection results include a first set of feedstock quality inspection results.

The method achieves the technical effects of traversing N groups of special steel smelting raw materials to perform external characteristic quality inspection and internal characteristic quality inspection, obtaining accurate and reliable N groups of raw material quality inspection results, and improving the comprehensiveness of the special steel smelting raw material management.

Further, step S330 of the present application further includes:

step S331: judging whether the first group of special steel smelting raw materials are shaping raw materials or not;

step S332: when the first group of special steel smelting raw materials are shaping raw materials, performing appearance size quality inspection index matching on the first group of special steel smelting raw materials to obtain matching size quality inspection indexes;

step S333: and carrying out quality inspection on the first group of sampling raw materials based on the quality inspection indexes of the matched sizes to obtain quality inspection results of the appearance sizes of the first group of raw materials, and adding the quality inspection results of the appearance sizes of the first group of raw materials to the quality inspection results of the external characteristics of the first group of raw materials.

Specifically, whether the first group of special steel smelting raw materials are shaping raw materials or not is judged, namely whether the first group of special steel smelting raw materials have fixed shapes or not is judged. When the first group of special steel smelting raw materials are shaping raw materials, performing appearance size quality inspection index matching on the first group of special steel smelting raw materials to obtain matching size quality inspection indexes, performing quality inspection on the first group of sampling raw materials according to the matching size quality inspection indexes to obtain a first group of raw material appearance size quality inspection results, and adding the first group of raw material appearance size quality inspection results to the first group of raw material external characteristic quality inspection results. The matched size quality inspection indexes comprise a plurality of size quality inspection indexes corresponding to the first group of special steel smelting raw materials. Illustratively, when appearance size quality inspection index matching is performed on the first group of special steel smelting raw materials, historical data query is performed based on the first raw material type information, and an appearance quality inspection index matching list is constructed. The appearance quality inspection index matching list comprises a plurality of historical raw material type parameters and a plurality of historical size quality inspection indexes corresponding to each historical raw material type parameter. And taking the first raw material type information as input information, inputting the input information into an appearance quality inspection index matching list, and performing appearance size quality inspection index matching on the first raw material type information through the appearance quality inspection index matching list to obtain matching size quality inspection indexes. Illustratively, when the first set of sampled raw materials is a carburant, the matched size quality index includes particle uniformity, particle porosity. The first group of raw material appearance size quality inspection results comprise particle uniformity parameters and particle porosity parameters corresponding to the first group of sampling raw materials. When the first group of special steel smelting raw materials are the shaping raw materials, the appearance size quality inspection is carried out on the first group of sampling raw materials, so that the comprehensive technical effect of quality inspection on the N groups of special steel smelting raw materials is improved.

Further, step S350 of the present application further includes:

step S351: acquiring quality inspection flow record data corresponding to the quality inspection result of the first group of raw materials;

step S352: performing quality inspection interference analysis based on the quality inspection flow record data to obtain a quality inspection interference index;

step S353: and when the quality inspection interference index meets the quality inspection interference constraint condition, acquiring quality inspection adjustment data based on the quality inspection interference index, and optimally updating the quality inspection result of the first group of raw materials based on the quality inspection adjustment data.

Specifically, the quality inspection process corresponding to the quality inspection result of the first group of raw materials is monitored in real time to obtain quality inspection flow record data, and quality inspection interference analysis is performed on the quality inspection flow record data to obtain a quality inspection interference index. The quality inspection flow record data comprises quality inspection step information, quality inspection instrument type, quality inspection instrument control parameters and quality inspection environment information corresponding to the quality inspection result of the first group of raw materials. The quality inspection interference index is parameter information for representing the accuracy of the quality inspection flow corresponding to the quality inspection result of the first group of raw materials. The greater the quality inspection interference index, the lower the accuracy of the quality inspection flow of the corresponding first group of raw material quality inspection results. Illustratively, when quality inspection interference analysis is performed on quality inspection flow record data, a quality inspection interference assessment set is constructed based on big data. The quality inspection interference evaluation set comprises a plurality of quality inspection interference indexes and a plurality of quality inspection interference index values which are preset and determined. And the quality inspection interference indexes have corresponding relations with the quality inspection interference index values. The larger the quality inspection interference index value is, the stronger the quality inspection interference of the corresponding quality inspection interference index is. For example, the quality inspection interference assessment set includes that the odor inspection environment has the stimulative gas, the fixed carbon content inspection environment has the excessive humidity, and the quality inspection interference index value corresponding to the odor inspection environment has the stimulative gas, the fixed carbon content inspection environment has the excessive humidity is 2 and 1. And inputting the quality inspection flow record data into a quality inspection interference evaluation set, and carrying out quality inspection interference identification on the quality inspection flow record data through the quality inspection interference evaluation set to obtain a quality inspection interference index. The quality inspection interference index is the sum of a plurality of quality inspection interference index values corresponding to the quality inspection flow record data.

Further, judging whether the quality inspection interference index meets the quality inspection interference constraint condition, obtaining quality inspection adjustment data when the quality inspection interference index meets the quality inspection interference constraint condition, and optimizing and updating the quality inspection result of the first group of raw materials according to the quality inspection adjustment data. The quality inspection interference constraint condition comprises a preset and determined quality inspection interference index threshold value. The quality control adjustment data includes a plurality of quality control adjustment parameters. The quality inspection adjusting parameters are a plurality of quality inspection interference index values corresponding to the quality inspection interference indexes meeting the quality inspection interference constraint conditions. When the quality inspection results of the first group of raw materials are optimized and updated according to the quality inspection adjustment data, multiple quality inspection information in the quality inspection results of the first group of raw materials corresponding to the quality inspection adjustment parameters is multiplied by the quality inspection adjustment parameters to obtain a first group of optimized quality inspection results, and the original first group of raw material quality inspection results are updated according to the first group of optimized quality inspection results. The technical effects of optimizing and updating the quality inspection results of the first group of raw materials by performing quality inspection interference analysis on quality inspection flow record data and improving the quality inspection accuracy of smelting raw materials of special steels are achieved.

Step S400: based on the raw material type data, N quality inspection qualification constraint conditions are obtained, whether the N groups of raw material quality inspection results meet the N quality inspection qualification constraint conditions is judged, and N quality inspection judgment results are obtained;

step S500: based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to the intelligent steel smelting raw material management platform;

specifically, N quality inspection pass constraints are set based on the raw material type data. Each quality inspection qualification constraint condition comprises a plurality of quality inspection index qualification range information corresponding to each raw material type parameter which is preset and determined. And then, judging whether the quality inspection results of the N groups of raw materials meet the corresponding N quality inspection qualification constraint conditions or not, and obtaining N quality inspection judgment results. Each quality inspection judging result comprises whether the quality inspection result of each group of raw materials meets the corresponding quality inspection qualification constraint condition. When the quality inspection results of the raw materials all meet the corresponding quality inspection qualification constraint conditions, the obtained quality inspection judgment result is that the quality inspection results of the raw materials meet the corresponding quality inspection qualification constraint conditions. Otherwise, the quality inspection judging result is that the quality inspection result of the raw material does not meet the corresponding quality inspection qualification constraint condition. Further, when the N quality inspection judging results are all that the raw material quality inspection results meet the corresponding quality inspection qualification constraint conditions, the raw material management system for special steel smelting automatically generates quality inspection qualification instructions and sends the quality inspection qualification instructions to the intelligent steel smelting raw material management platform. And when the raw material quality inspection results in the N quality inspection judgment results do not meet the corresponding quality inspection qualification constraint conditions, carrying out raw material quality early warning on the target batch of special steel smelting raw materials. The quality inspection qualification instructions are instruction information used for representing that all the N quality inspection judging results are that the raw material quality inspection results meet the corresponding quality inspection qualification constraint conditions, all the raw material qualities of the target batch of special steel smelting raw materials are qualified, and storage management can be carried out on the target batch of special steel smelting raw materials. The intelligent steel smelting raw material management platform is in communication connection with the raw material management system for smelting special steel. The intelligent steel smelting raw material management platform has the function of carrying out bin Chu Yunwei analysis and storage management on target batch special steel smelting raw materials. The technical effect of adaptively generating quality inspection qualification instructions by judging whether N groups of raw material quality inspection results meet N quality inspection qualification constraint conditions is achieved, so that the smelting raw material management quality of special steels is improved.

Further, step S400 of the present application further includes:

step S410: obtaining a production record of unqualified special steel raw materials in a preset history time zone;

step S420: performing raw material influence evaluation based on the raw material unqualified special steel production record to obtain a plurality of raw material type-influence indexes;

step S430: obtaining raw material influence data satisfying raw material influence constraint characteristics based on the plurality of raw material type-influence indexes;

step S440: obtaining production feedback quality inspection characteristics based on the raw material influence data;

step S450: and adjusting the N quality inspection qualification constraint conditions based on the production feedback quality inspection characteristics.

Specifically, raw material unqualified special steel production information is collected based on a preset history time zone, raw material unqualified special steel production records are obtained, raw material influence evaluation is carried out on the raw material unqualified special steel production records, and a plurality of raw material type-influence indexes are obtained. Wherein the preset historical time zone comprises preset determined historical time range information. The production record of the raw material unqualified special steel comprises a plurality of raw material unqualified special steels corresponding to a preset history time zone. The special steel with unqualified raw materials refers to special steel with unqualified production quality caused by the quality problem of the raw materials. For example, when evaluating the raw material influence of the raw material reject special steel production record, a plurality of raw material reject special steels in the raw material reject special steel production record are subjected to cluster analysis based on the N raw material type parameters, namely, a plurality of raw material reject special steels corresponding to the same raw material type parameters are classified into one type, and a plurality of types of raw material reject special steel records are obtained. Each type of raw material off-grade steel record includes a plurality of raw material off-grade grades corresponding to each raw material type parameter. And respectively counting the unqualified special steel records of the raw materials of the multiple types to obtain the number of the unqualified special steels of the multiple types. The number of off-grade steel of each type includes a sum of corresponding numbers of the plurality of off-grade steel of raw material in the raw material off-grade steel record of each type. And adding and calculating the number of the plurality of types of unqualified special steel to obtain the total number. And respectively calculating the ratio of the number of the unqualified special steels of the plurality of types to the total number of the unqualified special steels of the plurality of types to obtain a plurality of raw material type-influence indexes. The plurality of feedstock type-impact indices include a plurality of ratios between the number of the plurality of types of off-grade steel and the total number.

Further, it is determined whether the plurality of feedstock type-impact indices satisfy the feedstock impact constraint characteristic, respectively. When the feedstock type-impact index meets the feedstock impact constraint feature, the feedstock type-impact index is added to the feedstock impact data. And outputting the raw material influence data as production feedback quality inspection characteristics, and adjusting N quality inspection qualification constraint conditions according to the production feedback quality inspection characteristics. Wherein the feedstock impact constraint characteristic comprises a preset determined feedstock type-impact index threshold. The feedstock impact data includes a plurality of feedstock type-impact indices that satisfy a feedstock impact constraint characteristic. Illustratively, when the N quality inspection pass constraints are adjusted according to the production feedback quality inspection features, the production feedback quality inspection features are set to a reduction factor, and the N quality inspection pass constraints are reduced according to the reduction factor. Therefore, the N quality inspection qualification constraint conditions are stricter, and the accuracy and the instantaneity of the N quality inspection qualification constraint conditions are improved.

Step S600: the intelligent steel smelting raw material management platform comprises a bin Chu Yunwei model, and based on storage area information and the steel smelting raw material list, storage configuration analysis is carried out according to the storage operation and maintenance model to obtain a raw material storage management scheme;

Step S700: and executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.

Specifically, warehouse area information is collected, the warehouse area information and a smelting steel raw material list are used as input information, the input information is input into a warehouse storage and transportation maintenance model, a raw material warehouse management scheme is obtained, and warehouse management is carried out on target batch special steel smelting raw materials according to the raw material warehouse management scheme. The warehouse area information comprises a plurality of warehouse areas, and data information such as warehouse space structures, area layout information, area environment humidity, area environment temperature and the like corresponding to each warehouse area. The raw material warehouse management scheme comprises warehouse positions corresponding to target batch special steel smelting raw materials. Illustratively, when the warehouse operation model is constructed, historical data query is performed based on warehouse area information and a smelting steel raw material list, so that a plurality of pieces of construction data information are obtained. Each piece of construction data information comprises historical storage area information, a historical smelting steel raw material list and a historical raw material storage management scheme. A random 70% of the plurality of build data information is partitioned into training data sets. A random 30% of the plurality of build data information is partitioned into test data sets. Based on the BP neural network, cross-monitoring training is carried out on the training data set, and a bin Chu Yunwei model is obtained. And taking the test data set as input information, inputting the input information into the warehouse storage and transportation model, and updating parameters of the warehouse storage and transportation model through the test data set. And embedding the bin Chu Yunwei model into an intelligent smelting steel raw material management platform. The BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network comprises an input layer, a plurality of layers of neurons and an output layer. The BP neural network can perform forward calculation and backward calculation. When calculating in the forward direction, the input information is processed layer by layer from the input layer through a plurality of layers of neurons and is turned to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output cannot be obtained at the output layer, the reverse calculation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal. The storage, transportation and maintenance model comprises an input layer, an implicit layer and an output layer. The warehousing operation and maintenance model has the function of intelligently analyzing the input warehousing region information and the smelting steel raw material list and matching the warehousing management scheme. The technical effect of carrying out warehouse configuration analysis on warehouse area information and a smelting steel raw material list through a warehouse Chu Yunwei model and improving warehouse management quality of target batch special steel smelting raw materials is achieved.

Further, step S600 of the present application further includes:

step S610: obtaining environment forecast data in a forecast time zone, and analyzing the quality influence of raw materials based on the environment forecast data to obtain an analysis result of the quality influence of the environmental raw materials;

specifically, environmental forecast query is conducted on the warehouse area information based on the forecast time zone, and environmental forecast data are obtained. Further, raw material storage environment information corresponding to each raw material type parameter is extracted from the metallurgical steel raw material list, and a plurality of raw material storage environment data are obtained. And comparing the environmental forecast data with the storage environmental data of the raw materials to obtain a plurality of environmental impact indexes. And carrying out raw material quality influence analysis based on the plurality of environmental influence indexes to obtain a predicted environmental raw material quality influence index, and generating an environmental raw material quality influence analysis result by combining the plurality of environmental influence indexes. Illustratively, when obtaining the predicted environmental feedstock quality impact index, a historical data query is conducted based on a plurality of environmental impact indexes to obtain a feedstock quality impact analysis list. The feedstock quality impact analysis list includes a plurality of sets of feedstock quality impact analysis data. Each set of feedstock quality impact analysis data includes a plurality of historical environmental impact indicators, and a historical environmental feedstock quality impact index corresponding to the plurality of historical environmental impact indicators. Inputting a plurality of environmental impact indexes into a raw material quality impact analysis list to generate a predicted environmental raw material quality impact index. The larger the predicted environmental raw material quality influence index is, the higher the quality influence degree of the corresponding environmental forecast data on the target batch special steel smelting raw material is. Wherein the predicted time zone includes a plurality of predicted time points that are preset to be determined. The environment forecast data comprises a plurality of forecast temperatures, a plurality of forecast humidity, a plurality of forecast rainfall and other weather forecast information corresponding to the storage area information in the forecast time zone. The plurality of environmental impact indicators includes environmental forecast data that does not satisfy the plurality of raw material warehouse environmental data. The environmental raw material quality impact analysis result comprises a plurality of environmental impact indexes and a predicted environmental raw material quality impact index. The method achieves the technical effects of obtaining accurate analysis results of the quality influence of the environmental raw materials by analyzing the quality influence of the raw materials on the environmental forecast data, thereby improving the adaptability of the raw material warehouse management scheme.

Step S620: when the environmental raw material quality influence analysis result meets the environmental raw material quality influence constraint condition, carrying out storage intervention analysis based on the environmental raw material quality influence analysis result to obtain a storage intervention analysis result;

further, step S620 of the present application further includes:

step S621: extracting environmental impact factors based on the environmental raw material quality impact analysis result to obtain a plurality of environmental impact factors;

step S622: constructing a warehouse management knowledge base, and carrying out warehouse adjustment parameter configuration on the plurality of environmental impact factors based on the warehouse management knowledge base to obtain a plurality of groups of warehouse adjustment parameters;

step S623: based on the multiple groups of warehouse adjustment parameters, warehouse intervention effect prediction and warehouse intervention cost prediction are carried out, and warehouse adjustment prediction results are obtained;

step S624: carrying out weighted fusion based on the storage adjustment prediction result to obtain a weighted storage adjustment prediction result;

step S625: and screening a plurality of groups of storage adjustment parameters based on the weighted storage adjustment prediction result to obtain a storage intervention analysis result.

Step S630: and adjusting the raw material warehouse management scheme based on the warehouse intervention analysis result.

Specifically, the environmental feedstock quality impact constraint includes a preset determined predicted environmental feedstock quality impact index threshold. And judging whether the predicted environmental raw material quality influence index in the environmental raw material quality influence analysis result meets the environmental raw material quality influence constraint condition. And setting a plurality of environmental impact indexes in the environmental raw material quality impact analysis result as a plurality of environmental impact factors when the predicted environmental raw material quality impact index in the environmental raw material quality impact analysis result meets the environmental raw material quality impact constraint condition. And taking a plurality of environmental impact factors as input information, inputting the input information into a warehouse management knowledge base, and obtaining a plurality of groups of warehouse adjustment parameters. Each group of warehouse adjustment parameters comprises a plurality of adjustment parameters corresponding to a plurality of environmental impact factors. Illustratively, when constructing the warehouse management knowledge base, historical data queries are performed based on a plurality of environmental impact factors to obtain the warehouse management knowledge base. The warehouse management knowledge base comprises a plurality of warehouse management knowledge sequences. Each warehouse management knowledge sequence comprises a plurality of historical environment influence factors and a plurality of historical adjustment parameters corresponding to the historical environment influence factors. For example, when the historical environmental impact factor is that the storage environment temperature is too high, the corresponding historical adjustment parameter includes cooling control of the storage environment according to the historical cooling control parameter.

Further, warehouse intervention effect prediction and warehouse intervention cost prediction are respectively carried out on a plurality of groups of warehouse adjustment parameters, so that warehouse adjustment prediction results are obtained. The storage adjustment prediction result comprises a plurality of prediction storage intervention effect indexes and a plurality of prediction storage intervention cost indexes, wherein the prediction storage intervention effect indexes and the prediction storage intervention cost indexes correspond to a plurality of storage adjustment parameters. Illustratively, when the warehouse adjustment prediction result is obtained, historical data query is performed according to multiple groups of warehouse adjustment parameters, so as to obtain multiple training data sequences. Each training data sequence comprises a plurality of groups of historical storage adjustment parameters, a plurality of historical storage intervention effect indexes and a plurality of historical storage intervention cost indexes, wherein the historical storage intervention effect indexes and the historical storage intervention cost indexes correspond to the plurality of groups of historical storage adjustment parameters. And (3) continuously self-training and learning the plurality of training data sequences to a convergence state, so that the storage intervention prediction model can be obtained. The storage intervention prediction model comprises an input layer, an implicit layer and an output layer. And taking the multiple groups of storage adjustment parameters as input information, inputting the input information into a storage intervention prediction model, and predicting storage intervention effect and storage intervention cost for the multiple groups of storage adjustment parameters through the storage intervention prediction model to obtain multiple predicted storage intervention effect indexes and multiple predicted storage intervention cost indexes.

And further, carrying out weighted fusion on the warehouse adjustment prediction result to obtain a weighted warehouse adjustment prediction result. The weighted warehouse adjustment prediction result comprises a plurality of prediction warehouse intervention coefficients. Illustratively, when the weighted warehouse adjustment prediction result is obtained, the warehouse adjustment prediction result is calculated according to a preset weighted fusion formula, so as to obtain the weighted warehouse adjustment prediction result. The preset weighted fusion formula comprises

. Wherein (1)>

For the output predictive warehouse intervention factor, +.>

For the input index of predicted warehouse intervention effect, Y is the input index of predicted warehouse intervention cost,/-for the index of predicted warehouse intervention effect>

And setting a determined intervention effect weight value and an intervention cost weight value for the preset intervention effect. Further, multiple groups of storage adjustment parameters are screened based on the weighted storage adjustment prediction results, a group of storage adjustment parameters corresponding to the largest prediction storage intervention coefficient is output as storage intervention analysis results, and the storage intervention analysis results are added into the raw material storage management scheme, so that the raw material storage management scheme is adaptively adjusted, and the storage management comprehensiveness and accuracy of the target batch of special steel smelting raw materials are improved.

In summary, the raw material management method for smelting special steel provided by the application has the following technical effects:

1. Traversing the target batch of special steel smelting raw materials through a raw material information acquisition table to acquire basic information, and obtaining a smelting steel raw material list; classifying target batches of special steel smelting raw materials based on raw material type data to obtain N groups of special steel smelting raw materials; the quality inspection results of N groups of raw materials are obtained by carrying out multi-dimensional quality inspection on N groups of special steel smelting raw materials; judging whether the quality inspection results of the N groups of raw materials meet N quality inspection qualification constraint conditions or not to obtain N quality inspection judgment results; based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to an intelligent steel smelting raw material management platform; based on the storage area information and the steel smelting raw material list, carrying out storage configuration analysis through a storage operation and maintenance model in the intelligent steel smelting raw material management platform to obtain a raw material storage management scheme, and executing storage management of target batch special steel smelting raw materials according to the raw material storage management scheme. The technical effects of improving the quality inspection accuracy and the storage management adaptability of the smelting raw materials of the special steel and improving the management quality of the smelting raw materials of the special steel are achieved.

2. And traversing N groups of special steel smelting raw materials to perform external characteristic quality inspection and internal characteristic quality inspection to obtain accurate and reliable N groups of raw material quality inspection results, thereby improving the comprehensiveness of the smelting raw material management of the special steel.

3. By analyzing the quality influence of the raw materials on the environmental forecast data, an accurate analysis result of the quality influence of the environmental raw materials is obtained, so that the adaptability of adjusting the raw material warehouse management scheme is improved.

Examples

Based on the same inventive concept as the raw material management method for smelting special steel in the foregoing embodiment, the present invention also provides a raw material management system for smelting special steel, where the system includes an intelligent steel smelting raw material management platform, please refer to fig. 3, and the system includes:

the raw material information acquisition module 11 is used for constructing a raw material information acquisition table, traversing target batch of special steel smelting raw materials based on the raw material information acquisition table to acquire basic information, and obtaining a steel smelting raw material list;

the raw material classification module 12 is configured to obtain raw material type data based on the steel smelting raw material list, and classify the target batch of special steel smelting raw materials based on the raw material type data to obtain N groups of special steel smelting raw materials, where N is a positive integer greater than 1;

the raw material quality inspection module 13 is used for traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results;

The judging module 14 is configured to obtain N quality inspection qualification constraint conditions based on the raw material type data, and judge whether the N groups of raw material quality inspection results meet the N quality inspection qualification constraint conditions, so as to obtain N quality inspection judging results;

the instruction sending module 15 is used for obtaining quality inspection qualified instructions based on the N quality inspection judging results and sending the quality inspection qualified instructions to the intelligent steel smelting raw material management platform;

the warehouse configuration analysis module 16 is used for the intelligent steel smelting raw material management platform to comprise a warehouse Chu Yunwei model, and based on warehouse area information and the steel smelting raw material list, warehouse configuration analysis is carried out according to the warehouse operation and maintenance model to obtain a raw material warehouse management scheme;

and the warehouse management module 17 is used for executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.

Further, the system further comprises:

the first execution module is used for traversing the N groups of special steel smelting raw materials to obtain a first group of special steel smelting raw materials;

the random sampling module is used for randomly sampling the first group of special steel smelting raw materials based on sampling constraint characteristics to obtain a first group of sampling raw materials;

The external characteristic quality inspection module is used for performing external characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of raw material external characteristic quality inspection result;

the internal characteristic quality inspection module is used for performing internal characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of internal characteristic quality inspection results;

the second execution module is used for obtaining a first group of raw material quality inspection results based on the first group of raw material external characteristic quality inspection results and the first group of internal characteristic quality inspection results, and adding the first group of raw material quality inspection results to the N groups of raw material quality inspection results.

Further, the system further comprises:

the shaping judging module is used for judging whether the first group of special steel smelting raw materials are shaping raw materials or not;

the size quality inspection index matching module is used for carrying out appearance size quality inspection index matching on the first group of special steel smelting raw materials to obtain matching size quality inspection indexes when the first group of special steel smelting raw materials are shaping raw materials;

and the third execution module is used for carrying out quality inspection on the first group of sampling raw materials based on the quality inspection indexes of the matching size to obtain a quality inspection result of the appearance size of the first group of raw materials, and adding the quality inspection result of the appearance size of the first group of raw materials to the quality inspection result of the external characteristics of the first group of raw materials.

Further, the system further comprises:

the quality inspection flow record obtaining module is used for obtaining quality inspection flow record data corresponding to the quality inspection results of the first group of raw materials;

the quality inspection interference analysis module is used for carrying out quality inspection interference analysis based on the quality inspection flow record data to obtain a quality inspection interference index;

and the quality inspection result updating module is used for acquiring quality inspection adjustment data based on the quality inspection interference index when the quality inspection interference index meets the quality inspection interference constraint condition, and optimally updating the quality inspection result of the first group of raw materials based on the quality inspection adjustment data.

Further, the system further comprises:

the unqualified record obtaining module is used for obtaining a raw material unqualified special steel production record in a preset history time zone;

the raw material influence evaluation module is used for carrying out raw material influence evaluation based on the raw material unqualified special steel production record to obtain a plurality of raw material type-influence indexes;

a fourth execution module for obtaining raw material impact data satisfying raw material impact constraint characteristics based on the plurality of raw material type-impact indices;

The fifth execution module is used for obtaining production feedback quality inspection characteristics based on the raw material influence data;

and the constraint adjustment module is used for adjusting the N quality inspection qualification constraint conditions based on the production feedback quality inspection characteristics.

Further, the system further comprises:

the raw material quality influence analysis module is used for obtaining environment forecast data in a forecast time zone, and carrying out raw material quality influence analysis based on the environment forecast data to obtain an environmental raw material quality influence analysis result;

the storage intervention analysis module is used for carrying out storage intervention analysis based on the environmental raw material quality influence analysis result when the environmental raw material quality influence analysis result meets the environmental raw material quality influence constraint condition, so as to obtain a storage intervention analysis result;

the scheme adjusting module is used for adjusting the raw material warehouse management scheme based on the warehouse intervention analysis result.

Further, the system further comprises:

the environment influence factor obtaining module is used for extracting environment influence factors based on the analysis result of the quality influence of the environment raw materials to obtain a plurality of environment influence factors;

The warehouse adjustment parameter configuration module is used for constructing a warehouse management knowledge base, and carrying out warehouse adjustment parameter configuration on the plurality of environmental impact factors based on the warehouse management knowledge base to obtain a plurality of groups of warehouse adjustment parameters;

the storage prediction module is used for predicting storage intervention effect and storage intervention cost based on the plurality of groups of storage adjustment parameters to obtain storage adjustment prediction results;

the weighted fusion module is used for carrying out weighted fusion on the basis of the storage adjustment prediction result to obtain a weighted storage adjustment prediction result;

and the parameter screening module is used for screening a plurality of groups of storage adjustment parameters based on the weighted storage adjustment prediction result to obtain a storage intervention analysis result.

The raw material management system for special steel smelting provided by the embodiment of the invention can execute the raw material management method for special steel smelting provided by any embodiment of the invention, 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 invention.

The application provides a raw material management method for special steel smelting, wherein the method is applied to a raw material management system for special steel smelting, and the method comprises the following steps: traversing the target batch of special steel smelting raw materials through a raw material information acquisition table to acquire basic information, and obtaining a smelting steel raw material list; classifying target batches of special steel smelting raw materials based on raw material type data to obtain N groups of special steel smelting raw materials; the quality inspection results of N groups of raw materials are obtained by carrying out multi-dimensional quality inspection on N groups of special steel smelting raw materials; judging whether the quality inspection results of the N groups of raw materials meet N quality inspection qualification constraint conditions or not to obtain N quality inspection judgment results; based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to an intelligent steel smelting raw material management platform; based on the storage area information and the steel smelting raw material list, carrying out storage configuration analysis through a storage operation and maintenance model in the intelligent steel smelting raw material management platform to obtain a raw material storage management scheme, and executing storage management of target batch special steel smelting raw materials according to the raw material storage management scheme. Solves the technical problems of the prior art that the quality inspection accuracy of the smelting raw materials for the special steel is not enough and the storage management adaptability is low, thereby causing the poor management effect of the smelting raw materials for the special steel. The technical effects of improving the quality inspection accuracy and the storage management adaptability of the smelting raw materials of the special steel and improving the management quality of the smelting raw materials of the special steel are achieved.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention 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 invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A method for raw material management for special steel smelting, characterized in that the method is applied to a raw material management system for special steel smelting, the system comprises an intelligent steel smelting raw material management platform, and the method comprises:

constructing a raw material information acquisition table, traversing target batches of special steel smelting raw materials based on the raw material information acquisition table, and acquiring basic information to obtain a steel smelting raw material list;

obtaining raw material type data based on the steel smelting raw material list, and classifying the target batch of special steel smelting raw materials based on the raw material type data to obtain N groups of special steel smelting raw materials, wherein N is a positive integer greater than 1;

Traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results;

based on the raw material type data, N quality inspection qualification constraint conditions are obtained, whether the N groups of raw material quality inspection results meet the N quality inspection qualification constraint conditions is judged, and N quality inspection judgment results are obtained;

based on the N quality inspection judging results, obtaining a quality inspection qualified instruction, and sending the quality inspection qualified instruction to the intelligent steel smelting raw material management platform;

the intelligent steel smelting raw material management platform comprises a bin Chu Yunwei model, and based on storage area information and the steel smelting raw material list, storage configuration analysis is carried out according to the storage operation and maintenance model to obtain a raw material storage management scheme;

and executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.

2. The method of claim 1, wherein the method comprises:

traversing the N groups of special steel smelting raw materials to obtain a first group of special steel smelting raw materials;

randomly sampling the first group of special steel smelting raw materials based on sampling constraint characteristics to obtain a first group of sampling raw materials;

performing external characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of raw material external characteristic quality inspection result;

Performing internal characteristic quality inspection based on the first group of sampling raw materials to obtain a first group of internal characteristic quality inspection result;

and obtaining a first group of raw material quality inspection results based on the first group of raw material external characteristic quality inspection results and the first group of raw material internal characteristic quality inspection results, and adding the first group of raw material quality inspection results to the N groups of raw material quality inspection results.

3. The method according to claim 2, wherein the method comprises:

judging whether the first group of special steel smelting raw materials are shaping raw materials or not;

when the first group of special steel smelting raw materials are shaping raw materials, performing appearance size quality inspection index matching on the first group of special steel smelting raw materials to obtain matching size quality inspection indexes;

and carrying out quality inspection on the first group of sampling raw materials based on the quality inspection indexes of the matched sizes to obtain quality inspection results of the appearance sizes of the first group of raw materials, and adding the quality inspection results of the appearance sizes of the first group of raw materials to the quality inspection results of the external characteristics of the first group of raw materials.

4. The method of claim 2, wherein after obtaining the first set of feedstock quality inspection results, comprising:

acquiring quality inspection flow record data corresponding to the quality inspection result of the first group of raw materials;

Performing quality inspection interference analysis based on the quality inspection flow record data to obtain a quality inspection interference index;

and when the quality inspection interference index meets the quality inspection interference constraint condition, acquiring quality inspection adjustment data based on the quality inspection interference index, and optimally updating the quality inspection result of the first group of raw materials based on the quality inspection adjustment data.

5. The method of claim 1, after obtaining N quality check eligibility constraints, comprising:

obtaining a production record of unqualified special steel raw materials in a preset history time zone;

performing raw material influence evaluation based on the raw material unqualified special steel production record to obtain a plurality of raw material type-influence indexes;

obtaining raw material influence data satisfying raw material influence constraint characteristics based on the plurality of raw material type-influence indexes;

obtaining production feedback quality inspection characteristics based on the raw material influence data;

and adjusting the N quality inspection qualification constraint conditions based on the production feedback quality inspection characteristics.

6. The method of claim 1, wherein after obtaining the feedstock inventory management scheme, the method comprises:

obtaining environment forecast data in a forecast time zone, and analyzing the quality influence of raw materials based on the environment forecast data to obtain an analysis result of the quality influence of the environmental raw materials;

When the environmental raw material quality influence analysis result meets the environmental raw material quality influence constraint condition, carrying out storage intervention analysis based on the environmental raw material quality influence analysis result to obtain a storage intervention analysis result;

and adjusting the raw material warehouse management scheme based on the warehouse intervention analysis result.

7. The method of claim 6, wherein obtaining a warehouse intervention analysis result comprises:

extracting environmental impact factors based on the environmental raw material quality impact analysis result to obtain a plurality of environmental impact factors;

constructing a warehouse management knowledge base, and carrying out warehouse adjustment parameter configuration on the plurality of environmental impact factors based on the warehouse management knowledge base to obtain a plurality of groups of warehouse adjustment parameters;

based on the multiple groups of warehouse adjustment parameters, warehouse intervention effect prediction and warehouse intervention cost prediction are carried out, and warehouse adjustment prediction results are obtained;

carrying out weighted fusion based on the storage adjustment prediction result to obtain a weighted storage adjustment prediction result;

and screening a plurality of groups of storage adjustment parameters based on the weighted storage adjustment prediction result to obtain a storage intervention analysis result.

8. A raw material management system for special steel smelting, the system comprising an intelligent steel smelting raw material management platform, the system comprising:

The raw material information acquisition module is used for constructing a raw material information acquisition table, traversing the target batch of special steel smelting raw materials based on the raw material information acquisition table to acquire basic information, and obtaining a smelting steel raw material list;

the raw material classification module is used for obtaining raw material type data based on the smelting steel raw material list, classifying the target batch of special steel smelting raw materials based on the raw material type data, and obtaining N groups of special steel smelting raw materials, wherein N is a positive integer greater than 1;

the raw material quality inspection module is used for traversing the N groups of special steel smelting raw materials to carry out multi-dimensional quality inspection to obtain N groups of raw material quality inspection results;

the judging module is used for obtaining N quality inspection qualified constraint conditions based on the raw material type data, judging whether the N groups of raw material quality inspection results meet the N quality inspection qualified constraint conditions or not and obtaining N quality inspection judging results;

the instruction sending module is used for obtaining quality inspection qualified instructions based on the N quality inspection judging results and sending the quality inspection qualified instructions to the intelligent steel smelting raw material management platform;

The warehouse configuration analysis module is used for the intelligent steel smelting raw material management platform and comprises a warehouse Chu Yunwei model, and based on warehouse area information and the steel smelting raw material list, warehouse configuration analysis is carried out according to the warehouse operation and maintenance model to obtain a raw material warehouse management scheme;

and the warehouse management module is used for executing warehouse management of the target batch of special steel smelting raw materials based on the raw material warehouse management scheme.