Multi-decision fusion type pickling and rolling intelligent scheduling method and system

Abstract

The invention discloses a multi-decision fusion type acid rolling intelligent scheduling method and system, and relates to the technical field of production scheduling, and the method comprises the steps: obtaining initial raw material information data of an acid rolling production line, and carrying out the preprocessing of the initial raw material information data, and obtaining the feeding assignment information of each roll of acid rolling raw material, the preprocessing comprises beforehand analysis, parameter configuration and material identification; performing preliminary evaluation and decision on different set batch schemes based on the feeding score assignment information to obtain a plurality of sets of set batch schemes to be ranked; and obtaining a target pickling and rolling arrangement plan in combination with a preset operation plan arrangement constraint and an optimization target in the plurality of sets of set batch schemes to be arranged. According to the method and the device, the pickling and rolling planner can be helped to flexibly develop personalized operation plan scheduling decisions in combination with information such as the production rhythm of the production line and the individual scheduling tendency, the decision requirements in different scenes are met, and the scheduling quality and efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of production scheduling, and in particular to a multi-decision fusion pickling intelligent scheduling method and system. Background Art

[0002] The pickling process is the pre-process in the cold rolling process, responsible for providing raw materials for subsequent processes such as galvanizing and annealing. Due to the continuous operation of the production line, planners are required to arrange and issue pickling operation plans every day to guide the production of raw materials for the subsequent processes of the pickling production line to ensure the production continuity of the subsequent processes.

[0003] However, the orders for pickling raw materials come from multiple post-process production lines, with a large material base and multiple specifications. Manual scheduling often requires screening out nearly 100 rolls of materials from a material pool of thousands of rolls, and sorting them according to the production rules and connection constraints of the pickling production line. Not only is the scheduling efficiency low, but the manual scheduling method is also difficult to find the optimal material batching and sorting scheme from a huge data set. Therefore, the current scheduling of pickling operation plans is low in intelligence and efficiency, and is greatly affected by the subjectivity of the scheduling planners. There is also a lack of scientific tools for automated evaluation of historical operation plans afterwards. In addition, when scheduling pickling operation plans, it is also necessary to consider complex scheduling requirements such as the production rhythm of the post-process production line and the material supply requirements.

[0004] Therefore, it is necessary to propose a multi-decision fusion pickling intelligent scheduling method to solve the current problems of low intelligence level, low efficiency, and changeable and complex scheduling scenarios in pickling operation planning. Summary of the invention

[0005] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0006] This application specifically includes the following aspects:

[0007] In the first aspect, the present application proposes a multi-decision fusion pickling intelligent scheduling method, comprising:

[0008] Acquire initial raw material information data of the acid rolling production line, and pre-process the initial raw material information data to obtain the feeding score information of each roll of acid rolling raw material, wherein the initial raw material information data includes acid rolling raw material information and post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification. The pre-analysis performs subdivision statistics on scattered acid rolling raw material information and post-rolling warehouse raw material information according to subdivision fields, and the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendency. The material identification distinguishes the differentiated information of each roll of acid rolling raw material based on the basic decision parameter information, and generates the feeding score information of each roll of acid rolling raw material in combination with the feeding urgency of the subsequent process and the material differentiation information;

[0009] Based on the feed scoring information, different batching schemes are preliminarily evaluated and decided to obtain multiple batching schemes to be arranged;

[0010] The target pickling schedule is obtained by combining the preset operation schedule scheduling constraints and optimization targets in the multiple sets of batching schemes to be scheduled.

[0011] In a feasible implementation manner, the acid-rolled raw material information is obtained by performing detailed statistics based on the material category, material specification, and the warehouse node where the acid-rolled material is located; the post-rolling warehouse raw material information is obtained by performing detailed statistics based on the material post-process code and the warehouse node where the post-rolling warehouse material is located.

[0012] In a feasible implementation, the basic decision parameter information includes production line production decision parameter information and manual scheduling tendency decision parameter information. The production line production decision parameter information includes actual information of the rhythm of the post-process production line and current rhythm information of the pickling production line. The manual scheduling tendency decision parameter information is tendency scheduling information adapted to manual experience.

[0013] In a feasible implementation manner, the differentiated information of each roll of pickling raw material is differentiated based on the basic decision parameter information, and the feed scoring information of each roll of pickling raw material is generated in combination with the feed urgency and material differentiation information of the subsequent process, including:

[0014] Obtain the difference factors of different production schedules of pickling mill raw materials;

[0015] Based on the above-mentioned difference factors, formulate the mapping rules that adapt to the relationship between the production rhythm of the production line and the material supply priority, establish the production priority level mechanism and material supply scoring mechanism for different post-processes, and perform differentiated scoring for each roll of material;

[0016] Based on the basic decision parameter information and the production line production rhythm information, a basic material supply score is obtained for each roll of material;

[0017] The basic feed scoring is combined with the differentiated scoring to obtain the feed scoring information of each roll of acid-rolled raw material.

[0018] In a feasible implementation manner, the preliminary evaluation and decision-making of different batching schemes based on the feed scoring information to obtain multiple sets of batching schemes to be arranged include:

[0019] Formulate material batch division rules under different production scheduling trends;

[0020] Clustering and evaluating the pickling materials according to the material batch division rules, and predicting the production scheduling evaluation results of different batching schemes based on the material feeding score information of each roll of pickling raw materials;

[0021] A plurality of batching plans to be scheduled that meet the manual scheduling tendency are selected according to the scheduling scores.

[0022] In a feasible implementation manner, the preliminarily evaluating and deciding on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged further includes:

[0023] The batching strategy based on the main supply post-process is used to evaluate multiple batching plans to select three batching plans that meet the first preset results;

[0024] Evaluate multiple batching plans with a batching strategy that takes into account the main supply post-process and rolling period, and select three batching plans that meet the second preset results;

[0025] Evaluate multiple batching plans based on the limit scheduling strategy of the post-main supply process to select a batching plan that meets the third preset result;

[0026] Evaluate multiple batching schemes using the 2-day 4-roll model decision strategy to select a batching scheme that meets the fourth preset result;

[0027] A horizontal comparison is made among the different selected batching plans, duplicate batching plans are removed, and multiple batching plans to be scheduled that meet the manual scheduling tendency are selected from them according to the scheduling scores.

[0028] In a feasible implementation, the method of obtaining a target pickling schedule according to the obtained multiple sets of batching schemes to be arranged in combination with preset operation schedule scheduling constraints and optimization targets includes:

[0029] Based on the mixed integer programming model of the main scheduling stage, the mixed integer programming model of the rebound stage, the mixed integer programming model of the transition and the mixed integer programming model of the sorting optimization, the initial pickling schedule is automatically generated;

[0030] Based on the heuristic algorithm, the initial pickling schedule is post-processed to obtain the target pickling schedule whose plan sorting and scheduled material content meet the manual scheduling tendency and preset requirements; the post-processing operation includes material addition, material deletion and sequence adjustment.

[0031] In a feasible implementation, the initial pickling schedule is post-processed based on a heuristic algorithm to obtain the target pickling schedule whose schedule order and scheduled material content meet the manual scheduling tendency and preset requirements, including:

[0032] The initial materials are merged to obtain the initial material data to be arranged, and the redundant materials are generated into a material set to be inserted;

[0033] Inputting the initial material data to be arranged into the mixed integer programming model of the main arrangement stage and the mixed integer programming model of the sorting optimization in sequence, generating the initial pickling arrangement plan, and adjusting the order of individual materials in the initial pickling arrangement plan;

[0034] Performing a procedure constraint check on the initial pickling schedule and updating the initial pickling schedule;

[0035] The material set to be inserted is inserted into the initial pickling schedule coil by coil through a heuristic algorithm, and when the total rolling kilometers of the current initial pickling schedule does not reach the upper limit requirement of the rolling period, the restriction on the thickness group interval of the current batch is relaxed until the total rolling tons or kilometers of the current initial pickling schedule exceeds the rolling threshold of the rolling period, or there is no material in the pickling collection pool to be supplemented to the current initial pickling schedule, and the target initial pickling schedule is returned;

[0036] Identify the quantity of materials in the target initial pickling arrangement plan, and when the quantity exceeds the rolling life of the current working roll, remove the excess materials that exceed the rolling life of the roll;

[0037] Based on the first roll and the subsequent roll information in the target initial pickling schedule, a mixed integer programming model of the rebound stage is constructed to generate a rebound plan;

[0038] The target initial pickling schedule after removing the redundant materials is merged with the rebound schedule, and information notes are made to generate the target pickling schedule.

[0039] In a feasible implementation manner, the method further includes:

[0040] The initial pickling schedule is reviewed and adjusted according to the target pickling schedule, and after the review and adjustment is completed, the indicator statistical analysis and data storage are performed on the initial pickling schedule and the target pickling schedule to generate pickling scheduling results and business statistical reports according to a preset time period.

[0041] In a second aspect, the present application proposes a multi-decision fusion pickling intelligent scheduling system, which is applied to the multi-decision fusion pickling intelligent scheduling method described in any one of the above embodiments, including:

[0042] A data processing module, used for acquiring initial raw material information data of a pickling production line, and pre-processing the initial raw material information data to obtain the feeding score information of each roll of pickling raw material, wherein the initial raw material information data includes pickling raw material information and post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification, the pre-analysis performs subdivision statistics on scattered pickling raw material information and post-rolling warehouse raw material information according to subdivision fields, the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendency, the material identification distinguishes the differentiated information of each roll of pickling raw material based on the basic decision parameter information, and generates the feeding score information of each roll of pickling raw material in combination with the feeding urgency of the subsequent process and the material differentiation information;

[0043] A batching decision module is used to make a preliminary evaluation and decision on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged;

[0044] The planning module is used to obtain a target pickling scheduling plan by combining preset operation scheduling constraints and optimization targets in the multiple sets of batching plans to be scheduled.

[0045] In summary, the multi-decision fusion acid rolling intelligent scheduling method proposed in this application, compared with the traditional pure manual job planning, can help planners get rid of the traditional inefficient manual planning method, and efficiently and conveniently generate job plans that meet their expectations for planners. At the same time, it automatically evaluates indicators and accumulates data for each plan, and promotes the intelligent and digital development of cold rolling scheduling operations; this application opens up more basic decision parameter interface services in combination with the flexible production scheduling needs of acid rolling in parameter configuration, so that planners can flexibly combine production line production rhythm, temporary material feeding adjustment needs of post-process, personal expert experience expectations and other information to input accurate production scheduling tendencies into the acid rolling intelligent scheduling system, and design the underlying screening, sorting, insertion, deletion and other algorithm logics that are adapted to different parameter inputs, so that after the intelligent scheduling system obtains the parameters, the automatically decided job plan can adapt to different real-life scenarios. The low-code framework development model is realized by the production scheduling needs under the scene, without the need to continuously customize and develop corresponding business scheduling codes according to specific scenarios; compared with the limited evaluation of various production scheduling plans during manual scheduling, the present invention combines the expert experience of the pickling planner, evaluates and decides on different batch plans according to different strategies, and pushes multiple sets of recommended optimal batch plans to the planner in the system interface, thereby broadening the planner's thinking of scheduling the current node operation plan and avoiding the issued production schedule being overly affected by the planner's subjective judgment; compared with the "short-sighted" effect that exists in manual scheduling, the present invention constructs multiple customized mathematical models, considers material scheduling and connection transition from the perspective of global optimization, and matches the corresponding heuristic algorithm framework for efficient solution, so that the final material sorting is more compliant and the transition is smoother, which is more conducive to the smooth production of the production line.

[0046] The multi-decision fusion acid rolling intelligent scheduling method proposed in this application, and other advantages, objectives and features of this application will be reflected in part through the following description, and in part will also be understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0048] Figure 1 A schematic diagram of the process of a multi-decision fusion pickling intelligent scheduling method provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of the process of generating a multi-strategy set batch solution provided in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of functional modules of a multi-decision fusion pickling intelligent scheduling system provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the structure of a multi-decision fusion acid rolling intelligent scheduling electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0053] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0054] The present application provides a multi-decision-fusion acid rolling intelligent scheduling method and system, which can adapt to the decision-making needs in different scenarios, improve the quality and efficiency of scheduling, and solve the practical problems of low intelligence, slow efficiency and poor digitization level of manual scheduling of work plans in the current traditional steel manufacturing industry.

[0055] See also Figure 1 , which is a schematic diagram of the process of a multi-decision fusion pickling intelligent scheduling method provided in an embodiment of the present application, which may specifically include:

[0056] S110. Acquire initial raw material information data of the acid rolling production line, and pre-process the initial raw material information data to obtain feeding scoring information of each roll of acid rolling raw material, wherein the initial raw material information data includes acid rolling raw material information and post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification. The pre-analysis performs subdivision statistics on scattered acid rolling raw material information and post-rolling warehouse raw material information according to subdivision fields, and the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendencies. The material identification distinguishes differentiated information for each roll of acid rolling raw material based on the basic decision parameter information, and generates the feeding scoring information of each roll of acid rolling raw material in combination with the feeding urgency of the subsequent process and the material differentiation information.

[0057] For example, the pre-analysis classifies and counts the raw material data in the database according to the subdivision items of acid-rolled raw materials and the subdivision items of post-rolled warehouses, and displays the resource distribution of acid-rolled raw materials in different categories, specifications, and inventory locations at the current decision node; the resource inventory of post-rolled warehouse raw materials in different post-processes and inventory locations. Through the subdivision statistics of acid-rolled raw materials displayed in the pre-analysis, the acid-rolling planner can quickly understand the material distribution of the current acid-rolled raw materials in stock, and when scheduling different roll schedules (external plate roll schedule, high-strength roll schedule, ordinary roll schedule), the upper limit of the raw material weight supplied within a certain specification range for the corresponding post-process can be determined; and through the subdivision statistics of post-rolled warehouse raw materials, the maximum duration of continuous production of each post-process can be estimated according to the order subdivision (drawing strip material, external plate material, automobile plate, non-starting plate, etc.) and inventory location, thereby judging the supply priority of different post-processes.

[0058] It should be added that the information statistics displayed by the prior analysis are not only the basis for planners to obtain information and judge the supply direction, but also one of the decision-making information automatically sorted and collected by the intelligent scheduling system before making a decision, thereby providing a reference basis for subsequent material identification work.

[0059] Furthermore, parameter configuration, on the one hand, serves as the input port for the basic decision information parameters of the intelligent scheduling system, and on the other hand, provides a flexible information receiving port for adapting the planner's production scheduling tendency, production line production rhythm, and temporary material supply requirements of the subsequent process, thereby guiding the intelligent scheduling system to output the batch plan for materials to be scheduled to be more in line with the material supply requirements of the subsequent process or the production situation of the production line. Before starting the intelligent scheduling system for decision-making and scheduling, planners need to input the decision information of the day's plan to be scheduled through the parameter configuration system, which is equivalent to telling the intelligent scheduling algorithm the "demand" for the job plan scheduling, so that the final output plan results can adapt to the complex and changeable acid rolling scheduling scenario. The production line status parameter information that needs to be manually input mainly includes: the estimated start time of the current plan, the material preparation rhythm of the galvanizing production line (pulling strip / outer plate / inner plate stage), the resource availability of the galvanizing production line (whether automotive plates / non-automotive plates are available), etc., while the production scheduling tendency parameter information that needs to be input mainly includes: specifying the post-main scheduling process, specifying the operation plan roll period, working roll restriction, emergency contract number, emergency material number, etc. The above parameters all significantly affect the final production scheduling results.

[0060] It should be noted that the production scheduling tendency information itself will be obtained by the embedded algorithm of this application based on prior analysis, and this application, by expanding the parameter interface, can enable the intelligent scheduling method to be accompanied by the planner's long-term accumulated empirical judgment during daily use, thereby outputting better batch plans and operation plans.

[0061] Furthermore, based on the basic decision parameter information obtained through prior analysis and parameter configuration, the material identification will automatically identify, distinguish, label and assign values ​​to thousands of rolls of acid-rolled raw materials according to the underlying scoring mechanism, thereby providing a scheduling "handle" for subsequent batch decision-making and planning. When the supply score of a roll of material is lower than a certain threshold, the material will be identified as an "invalid inventory" material by the scheduling algorithm, and will not be actively scheduled into the production plan for the day, but will only be scheduled as a transition; conversely, when the supply score of a batch of materials belongs to the high water level value among all materials, the material will be identified as an "effective inventory" material by the scheduling algorithm, and will be scheduled into the production plan for the day as much as possible. Of course, different material supply scores are only meaningful for horizontal comparison and identification within the same roll period / working roll, and therefore different roll period plans will be generated, that is, the difference in the supply of different material batching plans.

[0062] S120, based on the basic decision parameter information and the material feeding scoring information, preliminary evaluation and decision making are performed on different batching schemes to obtain multiple sets of batching schemes to be arranged.

[0063] For example, after differentiating and identifying each roll of material based on the feed scoring information, the material batches are classified according to the categories, specifications and post-process codes of different materials in the pickling production line, and different batching strategies are used to classify the feed benefits of different plans. The higher the score of the plan, the more conducive it is to achieving the continuous production of the post-process and the resource balance goal of the production line. Finally, multiple sets of recommended plans are pushed to the planner for manual selection based on the production line situation and experience.

[0064] S130, obtaining a target pickling schedule by combining preset operation schedule scheduling constraints and optimization targets in the plurality of sets of batching plans to be scheduled.

[0065] Exemplarily, after the planner selects a set of batch material solutions in step S120, he or she embeds and develops multiple mathematical models based on operations research optimization theory, abstracts and transforms the input batch material information and pickling raw material information, and then uses the designed heuristic algorithm and general mathematical model solver to efficiently calculate and solve the problem, and finally outputs a complete pickling operation plan, including the material numbers included in the plan and the production order of each roll of material in the plan, which is used to guide production in the pickling operation area.

[0066] In summary, the multi-decision fusion acid rolling intelligent scheduling method proposed in the embodiment of the present application can automatically compile a complete process of acid rolling operation plan scheduling. If the planner needs to schedule multiple copies continuously, just repeat the above steps. The evaluation results of each operation plan will eventually be stored for quantitative statistics of periodic indicators.

[0067] In some examples, the acid-rolled raw material information is obtained by performing detailed statistics based on the material category, material specification, and the warehouse node where the acid-rolled material is located; the post-rolling warehouse raw material information is obtained by performing detailed statistics based on the material post-process code and the warehouse node where the post-rolling warehouse material is located.

[0068] For example, the scattered acid rolling raw material information and post-rolling warehouse raw material information are subdivided and counted according to the subdivided fields, which helps planners to clearly and directly understand the resource distribution of the current acid rolling production line and the supply urgency of the post-rolling warehouse resources. On the one hand, the acid rolling raw material information will be subdivided and counted according to the material scheduling category, scheduling subcategory, thickness group interval, and material node position fields, so that planners can understand the distribution of the current acid rolling resources in different batching plans; on the other hand, the post-rolling warehouse raw material information will be subdivided and counted according to the post-process production line code, the order subdivision of each post-process, and the material node position field, so that planners can understand the material demand of each post-process in the future.

[0069] In some examples, the basic decision parameter information includes production line production decision parameter information and manual scheduling tendency decision parameter information. The production line production decision parameter information includes actual information on the rhythm of the post-process production line and current rhythm information of the pickling production line. The manual scheduling tendency decision parameter information is tendency scheduling information adapted to manual experience.

[0070] For example, the basic decision parameter information includes the actual information of the rhythm of the post-process production line (such as whether the galvanized production line is in the outer plate production cycle or the inner plate production cycle of the sinking roller, the post-rolling warehouse resource data of the galvanized production line and the continuous annealing production line, etc.), and includes the rhythm information of the pickling production line itself (such as whether the current plan is to stop for maintenance, whether to start the machine, and the estimated start time of the current plan). On the other hand, the "parameter configuration layer" also opens some manual tendency parameter interfaces, so that planners can use the intelligent scheduling system with tendency guidance to output their expected plan.

[0071] In some examples, the differentiated information of each roll of pickling raw material is differentiated based on the basic decision parameter information, and the feed scoring information of each roll of pickling raw material is generated in combination with the feed urgency and material differentiation information of the subsequent process, including:

[0072] Obtain the difference factors of different production schedules of pickling mill raw materials;

[0073] Based on the above-mentioned difference factors, formulate the mapping rules that adapt to the relationship between the production rhythm of the production line and the material supply priority, establish the production priority level mechanism and material supply scoring mechanism for different post-processes, and perform differentiated scoring for each roll of material;

[0074] Based on the basic decision parameter information and the production line production rhythm information, a basic material supply score is obtained for each roll of material;

[0075] The basic feed scoring is combined with the differentiated scoring to obtain the feed scoring information of each roll of acid-rolled raw material.

[0076] Exemplarily, the material identification will identify differentiated information for each roll of material in the acid rolling pool database. The main process is divided into three aspects. First: according to the specification attributes of the material itself, the differential identification with manual scheduling tendency is identified, such as "order transfer priority", "retained material specification mark", "material emergency attribute", "feeding priority", etc.; second, based on the basic decision parameters provided by the parameter configuration, the basic feeding score of each roll of material is identified according to the material "post-process" attribute; third, based on the basic decision parameters provided by the parameter configuration, the feeding score of each roll of material is dynamically adjusted according to the fields such as "post-process scheduling category", "contract number", "material number", "sorting degree code", "contract nature", and "horizontal and vertical cutting identification" of the material, so as to adapt to the unified judgment logic of material scheduling tendency under different production line rhythms.

[0077] In some examples, the preliminary evaluation and decision-making of different batching schemes based on the feed scoring information to obtain multiple sets of batching schemes to be arranged include:

[0078] Formulate material batch division rules under different production scheduling trends;

[0079] Clustering and evaluating the pickling materials according to the material batch division rules, and predicting the production scheduling evaluation results of different batching schemes based on the material feeding score information of each roll of pickling raw materials;

[0080] A plurality of batching plans to be scheduled that meet the manual scheduling tendency are selected according to the scheduling scores.

[0081] Exemplarily, based on the material identification calculation of the material supply score for each roll of material, a preliminary evaluation and decision-making of different batch production plans are carried out, so as to provide planners with multiple sets of different batch production plan ideas and suggestions before the formal operation plan is arranged. Different batch production plans are mainly formed based on four types of strategies, and they are ranked according to the cumulative value of the supply score. Finally, the three plans with the highest supply scores are recommended for the pickling planner to choose. The four types of strategies are: the extreme scheduling strategy of the main supply post-process, the batch production strategy based on the main supply post-process, the batch production strategy that takes into account the main supply post-process and the roll period, and the 2-day 4-roll period model decision strategy.

[0082] In some examples, the performing preliminary evaluation and decision-making on different batching schemes based on the feed scoring information to obtain multiple sets of batching schemes to be arranged further includes:

[0083] S210, evaluating multiple batching schemes based on the batching strategy mainly for the post-main supply process, so as to select three batching schemes that meet the first preset result;

[0084] S220, evaluating multiple batching plans with a batching strategy that takes into account the post-main supply process and the rolling period, so as to select three batching plans that meet the second preset result;

[0085] S230, evaluating multiple batching schemes based on the limit scheduling strategy of the post-main supply process to select a batching scheme that meets the third preset result;

[0086] S240, evaluating multiple batching schemes using a 2-day 4-roll period model decision strategy to select a batching scheme that meets the fourth preset result;

[0087] S250. Perform a horizontal comparison of different selected batching plans, remove duplicate batching plans, and select multiple batching plans to be scheduled that meet the manual scheduling trend based on the scheduling scores.

[0088] Exemplarily, in step S210, the batching strategy based on the post-main supply process is used to select the best three batching schemes, and the first three batching schemes with the best supply scores of the batching schemes based on the post-main supply process are evaluated; in step S220, the best three batching schemes are selected with the batching strategy that takes into account the post-main supply process and the roll period, that is, all batching material schemes are directly evaluated, and the first three batching schemes with the best supply scores for all post-process batch scheduling are selected. At this time, the post-main supply process may not always account for the largest proportion in the selected optimal schemes, but at the same time, the total amount of this type of batching is relatively large, and the roll period utilization rate is guaranteed; the material batching scheme around the post-main supply process is obtained by the extreme scheduling strategy of the post-main supply process, and the scheme is evaluated.

[0089] In step S230, since the different batches initially classified are strictly distinguished according to thickness specifications, under this strategy, the original thickness specification range will be broken, and the original batch units will be merged to obtain an extreme scheduling batch plan around the main supply post-process. Furthermore, in the batch materials under this strategy, the material specifications of the main supply post-process may have both thin materials and thick materials, and may also have both wide materials and narrow materials. Therefore, after the scheduling is issued, the production plan may affect the operating stability of the pickling production line, making the production line operation more difficult, so it is an "extreme" scheduling, but the benefit is that it can concentrate the supply of materials for a certain post-process, alleviating its current problem of resource shortage.

[0090] In step S240, the 2-day 4-roll model decision strategy is used to obtain the batch material plan decided by the model, and the plan is evaluated. It should be noted that the mathematical model takes into account the material supply arrangement of the future 2-day 4-roll period and considers the current optimal batch material plan from a global perspective.

[0091] Step S250 compares different batching schemes horizontally, removes duplicate batching material schemes, and finally pushes three sets of recommended alternative batching material schemes to the batching decision layer. The process can be as follows: Figure 2 shown.

[0092] It should be noted that when the total number of any set of alternative batch materials obtained is small, a certain batch fusion is performed by breaking the thickness division requirements between different batches to generate the final batch material plan.

[0093] In some examples, the step of obtaining a target pickling schedule according to the obtained multiple sets of batching schemes to be arranged in combination with preset operation schedule scheduling constraints and optimization targets includes:

[0094] Based on the mixed integer programming model of the main scheduling stage, the mixed integer programming model of the rebound stage, the mixed integer programming model of the transition and the mixed integer programming model of the sorting optimization, the initial pickling schedule is automatically generated;

[0095] Based on the heuristic algorithm, the initial pickling schedule is post-processed to obtain the target pickling schedule whose plan sorting and scheduled material content meet the manual scheduling tendency and preset requirements; the post-processing operation includes material addition, material deletion and sequence adjustment.

[0096] Exemplarily, in order to complete the automatic scheduling of the pickling operation plan, the materials in the designated batch plan are first formed into a main stage material production plan sorted from wide to narrow according to the basic constraint rules of pickling production, and then a rebound stage material production plan sorted from narrow to wide is formed, wherein the first roll of the main stage material is the last roll of the rebound stage material. In order to achieve the above-mentioned operation plan scheduling requirements, combined with the basic rules of the pickling production line, the main mixed integer programming model of the main stage (production scheduling from wide to narrow), the mixed integer programming model of the rebound stage (production scheduling from narrow to wide), the mixed integer programming model of the transitional mixed integer programming model and the mixed integer programming model of the sorting optimization are mainly constructed. The optimization goal of the mixed integer programming model in the main scheduling stage focuses on the utilization rate of the working rolls, the cumulative value of the feeding points, and the satisfaction of the procedural constraints, aiming to arrange the materials urgently needed in the current post-process into the plan as much as possible while satisfying the specification connection constraints, and at the same time maximize the utilization rate of the working rolls; the optimization goal of the mixed integer programming model for sorting optimization focuses on smoother material connection transitions, which is specifically reflected in the fact that the specification fluctuations such as the inlet thickness fluctuation, the outlet thickness fluctuation, and the order width rebound fluctuation are as small as possible, so that the issued operation plan is more conducive to the smooth operation of the production line in the acid rolling operation area. The mixed integer programming model in the connection transition or rebound stage focuses on making decisions to use as few materials as possible from the original collection pool resources to complete the connection transition of two rolls of materials. In addition, in order to avoid the omission of materials in the post-process of the main scheduling, the over-roll period of the initial operation plan, the omission of material sorting optimization, etc., this application has also developed corresponding heuristic strategies for inserting materials, deleting materials, and local micro-adjustments to post-process the initial plan.

[0097] In some examples, the post-processing operation on the initial pickling schedule based on the heuristic algorithm to obtain the target pickling schedule whose plan sorting and scheduled material content meet the manual scheduling tendency and preset requirements includes:

[0098] S310, merging the initial materials to obtain initial material data to be arranged, and generating a material set to be inserted for the redundant materials;

[0099] S320, inputting the initial material data to be arranged into the mixed integer programming model of the main arrangement stage and the mixed integer programming model of the sorting optimization in sequence, generating the initial pickling arrangement plan, and adjusting the front and back order of individual materials in the initial pickling arrangement plan;

[0100] S330, performing a procedure constraint check on the initial pickling schedule, and updating the initial pickling schedule;

[0101] S340, inserting the material set to be inserted into the initial pickling schedule coil by coil through a heuristic algorithm, and when the total rolling kilometers of the current initial pickling schedule does not reach the upper limit requirement of the rolling period, relaxing the restriction on the thickness group spacing of the current batch, until the total rolling tons or kilometers of the current initial pickling schedule exceeds the rolling threshold of the rolling period, or there is no material in the pickling collection pool to be supplemented to the current initial pickling schedule, and returning to the target initial pickling schedule;

[0102] S350, identifying the quantity of materials in the target initial pickling arrangement plan, and when the quantity exceeds the rolling life of the current working roll, removing the excess materials exceeding the rolling life of the roll;

[0103] S360, based on the first roll and the subsequent roll information in the target initial pickling arrangement plan, construct a mixed integer programming model of the rebound stage to generate a rebound plan;

[0104] S370, merging the target initial pickling schedule after removing excess materials with the rebound schedule, and making information notes to generate the target pickling schedule.

[0105] Exemplarily, in step S310, in order to optimize the time for solving the model, the original materials are merged, that is, materials with similar specifications in terms of entrance thickness, order thickness, welding grouping, and order width are merged. Before the materials with similar specifications are input into the mathematical model, only 2 rolls of materials are left, and the remaining materials are included in the set of materials to be inserted. After the above operations, the number of initial raw materials in the set of materials to be inserted can be reduced.

[0106] In step S320, a mixed integer programming model for the main row stage (entrance width is sorted from wide to narrow) is constructed, and the optimization objectives focus on the utilization rate of working rolls, the cumulative value of feeding points, and the satisfaction of procedural constraints. A mixed integer programming model for sorting optimization is constructed, and the optimization objectives focus on smoother material transitions, which is specifically reflected in the fact that specification fluctuations such as entrance thickness fluctuations, exit thickness fluctuations, and order width rebound fluctuations are as small as possible. The initial data of materials to be rowed is used as model input, and after the above two models are solved, the initial job plan for pickling is generated. Next, the initial job plan is input into the local sequence micro-adjustment module in the algorithm to adjust the order of individual materials in a job plan, so that the transition between materials of different specifications is smoother, and batch production of materials of similar specifications is achieved as much as possible.

[0107] In step S330, the initial operation plan is checked for procedural constraints. When the system recognizes that the connection between two rolls of material in the initial operation plan violates the procedural constraints, the mixed integer programming model of the connection transition is called to query suitable materials from the acid-rolled raw materials, decide to use the least material, complete the connection transition of the two rolls of material, and update the initial operation plan.

[0108] In step S340, the material set to be inserted is used as the input of the material insertion heuristic algorithm module, and each roll is inserted into the most appropriate position in the initial operation plan. It should be noted that before each roll of material is formally inserted, its optimal insertion position in the entire plan will be determined based on the transition score between the previous and next rolls.

[0109] After step S340 is completed, if the total rolling kilometers of the current operation plan has not reached the upper limit requirement of the rolling period, the restriction on the thickness group interval of the current batch is relaxed, and suitable materials are found from the original pickling pool, and placed in the material set to be inserted to re-execute the insertion operation. The above steps will be performed multiple times until the total rolling tons or kilometers of the current operation plan have exceeded the rolling threshold of the rolling period, or there is no suitable material in the pickling pool to be added to the current plan.

[0110] It can be understood that step S340 converts traditional manual operations such as manual material query, material insertion position evaluation, and material insertion order marking into a computer calculation process, which greatly improves the efficiency and calculation accuracy of planning.

[0111] In step S350, the material quantity of the operation plan finally returned by S340 is identified. When the material quantity exceeds the rolling life of the working roll, the "material deletion" module is enabled to remove the excess material that exceeds the rolling life of the roll.

[0112] In step S360, based on the first volume of the S350 job plan and the subsequent volume information, a mixed integer programming model for the rebound stage (entry width is sorted from narrow to wide) is constructed. The model aims to decide to use as few materials as possible to complete the sorting connection from narrow to wide from the subsequent volume to the first volume of the job plan, and generate a rebound plan, which does not include the first volume of the main scheduling stage plan.

[0113] In step S370, the two copies returned by step S360 and step S350 are merged, and the information such as "production sequence" and "roller change" are annotated and marked to generate a complete pickling operation plan.

[0114] In some examples, the method further includes:

[0115] The initial pickling schedule is reviewed and adjusted according to the target pickling schedule, and after the review and adjustment is completed, the indicator statistical analysis and data storage are performed on the initial pickling schedule and the target pickling schedule to generate pickling scheduling results and business statistical reports according to a preset time period.

[0116] Exemplarily, after the pickling operation plan is generated in step S130, it will be automatically manually reviewed and evaluated for review, adjustment, and issuance by the production planner. After the plan is officially issued, the final issued plan and the algorithm-automatic scheduling plan will be automatically compared and statistically analyzed for relevant business indicators, and the data will be stored.

[0117] Furthermore, manual review and evaluation mainly involve the acid rolling planner reviewing and adjusting the automatic scheduling plan on the system interface, and automatically performing indicator statistics and data storage on the automatic scheduling plan of this application and the final schedule after the manual confirmation of the plan issuance, so as to provide underlying data for the weekly, monthly and annual statistics of the evaluation indicators of the acid rolling operation plan, and improve the digital level of the results of the acid rolling operation plan scheduling. In terms of indicator statistics, this embodiment focuses on the utilization rate of the working rolls of the acid rolling, the connection transition within a single operation plan, the fluctuation level and switching number of indicators of different specifications within a single operation plan, and the frequency of use of transition roll materials within a single operation plan.

[0118] It should be noted that the above embodiments are only the best examples and are not limitations on the implementation methods of the present application.

[0119] Furthermore, the present application also proposes a multi-decision fusion type pickling intelligent scheduling system, which is applied to any of the above-mentioned multi-decision fusion type pickling intelligent scheduling methods, specifically as follows: Figure 3 As shown, it is a functional module diagram of a multi-decision fusion pickling intelligent scheduling system proposed in this application, including:

[0120] The data processing module 21 is used to obtain the initial raw material information data of the acid rolling production line, and pre-process the initial raw material information data to obtain the feeding scoring information of each roll of acid rolling raw material, wherein the initial raw material information data includes the acid rolling raw material information and the post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification. The pre-analysis subdivides and counts the scattered acid rolling raw material information and the post-rolling warehouse raw material information according to the subdivided fields, and the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendencies. The material identification distinguishes the differentiated information of each roll of acid rolling raw material based on the basic decision parameter information, and combines the feeding urgency of the subsequent process and the material differentiation information to generate the feeding scoring information of each roll of acid rolling raw material.

[0121] Exemplarily, the acid-rolling raw material resource view and the post-process resource view are defined through prior analysis, and the acid-rolling raw material data and the post-process raw material data are classified and counted, wherein the acid-rolling raw material resource view is subdivided and counted according to the material category, material specification, and the material storage area node, and the post-process resource view is subdivided and counted according to the material post-process code and the material storage area node; through parameter configuration, basic decision parameters that change flexibly and dynamically with the production situation of the production line and the corresponding system interface input interface are defined, such as the sinking roll period of the galvanizing production line and the decision node, the estimated start time of the current job plan to be arranged, the production arrangement information of different acid-rolling raw materials, and other decision information that cannot be directly obtained from the steel plant database level. Expand the parameter interface with manual scheduling tendency to adapt the automatic scheduling tendency with manual experience, such as the specified feeding process, the specified material specifications, the specified material category, the specified scheduling strategy, etc., so that the manual combination of production line production conditions and expert experience can flexibly obtain the scheduling plan to deal with different scheduling decision scenarios; clarify the difference factors of different raw materials for pickling and rolling through material identification, such as the post-process category of the material supply, the supply specifications (thickness, width), the order month, the urgency of delivery, the storage time, etc. Formulate mapping rules to adapt to the relationship between the production rhythm of the production line and the priority of feeding, establish a scheduling priority level mechanism and a feeding scoring mechanism for different post-processes, and perform differentiated scoring for each roll of material. The corresponding feeding score of each roll of material represents the priority identification of the material in this scheduling process. The basic score of each roll of material identification is derived from the post-rolling warehouse resource situation and the production rhythm information of the production line at the current decision node. At the same time, combined with the formulated differentiated scoring rules, the final identification score of each roll of material is fitted.

[0122] The batching decision module 22 is used to make a preliminary evaluation and decision on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged.

[0123] Exemplarily, the batch decision module 22 is used to formulate material batch division rules under different production scheduling tendencies (such as a strategy that focuses on supplying the subsequent processes, a strategy that takes into account both the roll fullness and the feeding of the subsequent processes, an extreme scheduling strategy, and a 2-day 4-roll production scheduling rhythm strategy). The scattered and disordered acid-rolled materials are clustered and scored according to the corresponding batch division rules under different production scheduling tendencies, and the supply score of each roll of material identification is used to predict the production scheduling scores of different batching schemes, and multiple sets of batching schemes to be scheduled that best meet the manual production scheduling tendencies are selected.

[0124] The planning module 23 is used to obtain a target pickling scheduling plan by combining preset operation scheduling constraints and optimization targets in the multiple sets of batching plans to be scheduled.

[0125] Exemplarily, the planning module 23 is used to establish a mixed integer programming model for the main scheduling stage (scheduling from wide to narrow), a mixed integer programming model for the rebound stage (scheduling from narrow to wide), a mixed integer programming model for transition and a mixed integer programming model for sorting optimization, for automatically scheduling and generating a pickling schedule. Develop heuristic algorithms such as inserting materials, deleting materials, and local sequence adjustment, and perform post-processing operations such as adding materials, deleting materials, and adjusting the sequence on the generated initial pickling schedule, so that the automatically scheduled plan sorting and the content of the scheduled materials are more in line with the complete plan of the manual scheduling tendency and demand.

[0126] In some examples, the present application proposes a multi-decision fusion pickling intelligent scheduling system which may also include a manual review and plan evaluation module, which is used by the pickling production line planner to review the complete pickling operation plan automatically compiled and output in the system, and complete the issuance of the operation plan after appropriate material adjustments; develop an automated operation plan indicator evaluation interface to statistically evaluate the final issued operation plan and the initial plan generated by the scheduling system, and perform data storage and comparative analysis; based on the collected indicator data and difference factor records, iteratively optimize the underlying algorithm development logic of the pickling intelligent scheduling system.

[0127] like Figure 4 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and executable on the processor. When the processor 310 executes the computer program 321, the steps of any one of the above-mentioned multi-decision fusion acid rolling intelligent scheduling methods are implemented.

[0128] Since the electronic device introduced in this embodiment is a device used to implement a multi-decision fusion acid rolling intelligent scheduling method in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0129] In the specific implementation process, when the computer program 321 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0130] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of a multi-decision fusion pickling intelligent scheduling method.

[0136] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0142] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0143] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0144] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and variations of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and variations.

Claims

1. A multi-decision fusion pickling intelligent scheduling method, characterized in that: include: Acquire the initial raw material information data of the acid rolling production line, and pre-process the initial raw material information data to obtain the feeding score information of each roll of acid rolling raw material, wherein the initial raw material information data includes the acid rolling raw material information and the post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification. The pre-analysis performs subdivision statistics on the scattered acid rolling raw material information and the post-rolling warehouse raw material information according to the subdivision fields, and the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendency. The material identification distinguishes the differentiated information of each roll of acid rolling raw material based on the basic decision parameter information, and generates the feeding score information of each roll of acid rolling raw material in combination with the feeding urgency of the subsequent process and the material differentiation information; Based on the feed scoring information, different batching schemes are preliminarily evaluated and decided to obtain multiple batching schemes to be arranged; The target pickling schedule is obtained by combining the preset operation schedule constraints and optimization targets in the multiple sets of batching plans to be arranged.

2. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The acid-rolled raw material information is obtained by performing detailed statistics based on the material category, material specification, and the warehouse node where the acid-rolled material is located; the post-rolling warehouse raw material information is obtained by performing detailed statistics based on the material post-process code and the warehouse node where the post-rolling warehouse material is located.

3. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The basic decision parameter information includes production line production decision parameter information and manual scheduling tendency decision parameter information. The production line production decision parameter information includes the actual information of the rhythm of the post-process production line and the current rhythm information of the pickling production line. The manual scheduling tendency decision parameter information is a tendency scheduling information adapted to manual experience.

4. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The differentiated information of each roll of pickling raw material is distinguished based on the basic decision parameter information, and the feed scoring information of each roll of pickling raw material is generated in combination with the feed urgency and material differentiation information of the subsequent process, including: Obtain the difference factors of different production schedules of pickling mill raw materials; Based on the above-mentioned difference factors, formulate the mapping rules that adapt to the relationship between the production rhythm of the production line and the material supply priority, establish the production priority level mechanism and material supply scoring mechanism for different post-processes, and perform differentiated scoring for each roll of material; Based on the basic decision parameter information and the production line production rhythm information, a basic material supply score for each roll of material is obtained; The basic feed scoring is combined with the differentiated scoring to obtain the feed scoring information of each roll of acid-rolled raw material.

5. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The method of performing preliminary evaluation and decision making on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged includes: Formulate material batch division rules under different production scheduling trends; Clustering and evaluating the pickling materials according to the material batch division rules, and predicting the production scheduling evaluation results of different batching schemes based on the material feeding score information of each roll of pickling raw materials; According to the production scheduling scoring results, multiple sets of batching plans to be scheduled that meet the manual production scheduling tendency are selected.

6. The multi-decision fusion pickling intelligent scheduling method according to claim 5 is characterized in that: The method of performing preliminary evaluation and decision-making on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged also includes: The batching strategy based on the main supply post-process is used to evaluate multiple batching plans to select three batching plans that meet the first preset results; Evaluate multiple batching plans with a batching strategy that takes into account the main supply post-process and rolling period, and select three batching plans that meet the second preset results; Evaluate multiple batching plans based on the limit scheduling strategy of the post-main supply process to select a batching plan that meets the third preset result; Evaluate multiple batching schemes using the 2-day 4-roll model decision strategy to select a batching scheme that meets the fourth preset result; A horizontal comparison is made among the different selected batching plans, duplicate batching plans are removed, and multiple batching plans to be scheduled that meet the manual scheduling tendency are selected from them according to the scheduling scores.

7. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The method of obtaining a target pickling schedule according to the obtained multiple sets of batching schemes to be arranged in combination with preset operation schedule scheduling constraints and optimization targets includes: Based on the mixed integer programming model of the main scheduling stage, the mixed integer programming model of the rebound stage, the mixed integer programming model of the transition and the mixed integer programming model of the sorting optimization, the initial pickling schedule is automatically generated; Based on the heuristic algorithm, the initial pickling schedule is post-processed to obtain the target pickling schedule whose plan sorting and scheduled material content meet the manual scheduling tendency and preset requirements; the post-processing operation includes material addition, material deletion and sequence adjustment.

8. The multi-decision fusion pickling intelligent scheduling method according to claim 7 is characterized in that: The heuristic algorithm is used to post-process the initial pickling schedule to obtain the target pickling schedule whose schedule order and scheduled material content meet the manual scheduling tendency and preset requirements, including: The initial materials are merged to obtain the initial material data to be arranged, and the redundant materials are generated into a material set to be inserted; Inputting the initial material data to be arranged into the mixed integer programming model of the main arrangement stage and the mixed integer programming model of the sorting optimization in sequence, generating the initial pickling arrangement plan, and adjusting the order of individual materials in the initial pickling arrangement plan; Performing a procedure constraint check on the initial pickling schedule and updating the initial pickling schedule; The material set to be inserted is inserted into the initial pickling schedule coil by coil through a heuristic algorithm, and when the total rolling kilometers of the current initial pickling schedule does not reach the upper limit requirement of the rolling period, the restriction on the thickness group interval of the current batch is relaxed until the total rolling tons or kilometers of the current initial pickling schedule exceeds the rolling threshold of the rolling period, or there is no material in the pickling collection pool to be supplemented to the current initial pickling schedule, and the target initial pickling schedule is returned; Identify the quantity of materials in the target initial pickling arrangement plan, and when the quantity exceeds the rolling life of the current working roll, remove the excess materials that exceed the rolling life of the roll; Based on the first roll and the subsequent roll information in the target initial pickling schedule, a mixed integer programming model of the rebound stage is constructed to generate a rebound plan; The target initial pickling schedule after removing the redundant materials is merged with the rebound schedule, and information notes are made to generate the target pickling schedule.

9. The multi-decision fusion pickling intelligent scheduling method according to claim 1 is characterized in that: The method further comprises: The initial pickling schedule is reviewed and adjusted according to the target pickling schedule, and after the review and adjustment is completed, the indicator statistical analysis and data storage are performed on the initial pickling schedule and the target pickling schedule to generate pickling scheduling results and business statistical reports according to a preset time period.

10. A multi-decision fusion pickling mill intelligent scheduling system, applied to the multi-decision fusion pickling mill intelligent scheduling method according to any one of claims 1 to 9, characterized in that: include: A data processing module, used for acquiring initial raw material information data of a pickling production line, and pre-processing the initial raw material information data to obtain the feeding score information of each roll of pickling raw material, wherein the initial raw material information data includes pickling raw material information and post-rolling warehouse raw material information, and the pre-processing includes pre-analysis, parameter configuration and material identification, the pre-analysis performs subdivision statistics on scattered pickling raw material information and post-rolling warehouse raw material information according to subdivision fields, the parameter configuration provides basic decision parameter information for production line production and manual scheduling tendency, the material identification distinguishes the differentiated information of each roll of pickling raw material based on the basic decision parameter information, and generates the feeding score information of each roll of pickling raw material in combination with the feeding urgency of the subsequent process and the material differentiation information; A batching decision module is used to make a preliminary evaluation and decision on different batching schemes based on the feed scoring information to obtain multiple batching schemes to be arranged; The planning module is used to obtain a target pickling scheduling plan by combining preset operation scheduling constraints and optimization targets in the multiple sets of batching plans to be scheduled.

Images