A method and system for optimizing the feeding of steel bars by intelligent screening

Abstract

The present invention discloses an intelligent steel bar screening optimization unloading method and system, which relates to the field of construction engineering technology, including collecting attribute information of all steel bars to be unloaded and performing preprocessing; constructing a multidimensional feature matrix based on the preprocessed steel bar attribute information; measuring the similarity between steel bars according to the multidimensional feature matrix to form an initial candidate combination list; performing optimization combination according to the initial candidate combination list to generate an optimal combination scheme; constructing an intelligent inventory prediction model based on the optimal combination scheme to predict the number of steel bars that need to be replenished; dynamically adjusting the inventory plan according to the prediction result in combination with the current inventory level and safety inventory setting; the present invention combines the intelligent inventory prediction model with the dynamic adjustment mechanism to accurately predict the demand for steel bars in a future period of time, and flexibly adjusts the procurement plan according to the actual situation, thereby reducing the inventory holding cost and avoiding the risks caused by insufficient or excessive supply.

Description

Technical Field

[0001] The invention relates to the technical field of construction engineering, and in particular to an intelligent screening steel bar optimized feeding method and system. Background Art

[0002] In the field of construction engineering, steel bar cutting is an indispensable part of structural construction. The traditional steel bar cutting method mainly relies on manual measurement and cutting, which is not only inefficient, but also prone to a large amount of waste, increasing project costs. In recent years, with the development of information technology, some automation systems have been introduced into the steel bar cutting process. For example, the application of RFID tags makes the tracking and management of steel bars more convenient; at the same time, rule-based algorithms are also used to optimize steel bar combinations to reduce surplus materials. However, these existing technologies still have limitations, especially in the comprehensive consideration of multi-dimensional features, similarity evaluation and intelligent inventory forecasting.

[0003] A significant shortcoming of existing technologies is that they usually only consider the basic properties of steel bars (such as length), while ignoring the impact of other important characteristics (such as diameter, strength grade, etc.) on the combination effect. In addition, traditional methods lack an integrated platform to coordinate the whole process management from information collection to inventory adjustment, which leads to serious data silos and cannot achieve true intelligent and efficient operation. Therefore, how to build an intelligent system that can comprehensively consider the multiple properties of steel bars, accurately measure the similarity between steel bars, and dynamically adjust inventory plans has become an urgent problem to be solved. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent screening steel bar optimization cutting method to solve the problems of the traditional steel bar cutting and inventory management system failing to fully integrate multi-dimensional steel bar attribute information and lacking a dynamic inventory adjustment mechanism.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent screening steel bar optimization feeding method, which comprises:

[0008] Collect the attribute information of all the steel bars to be cut and perform pre-processing;

[0009] Based on the pre-processed attribute information of the steel bars to be cut, a multi-dimensional feature matrix is ​​constructed;

[0010] According to the multi-dimensional feature matrix, the similarities between the steel bars to be cut are measured to form an initial candidate combination list;

[0011] Based on the initial candidate combination list, optimize the combination and generate the best combination solution;

[0012] Based on the best combination plan, an intelligent inventory forecasting model is built to predict the number of steel bars to be replenished;

[0013] Based on the forecast results, combined with the current inventory level and safety stock settings, the inventory plan is dynamically adjusted.

[0014] As a preferred solution of the intelligent screening steel bar optimization cutting method of the present invention, wherein: collecting the attribute information of all steel bars to be cut and pre-processing includes the following steps:

[0015] Attach a passive RFID tag containing a unique serial number to each steel bar to be cut;

[0016] When the steel bar to be cut passes through the reader area, the UID on the tag is automatically read and the attribute information including the length, diameter, grade strength and bending radius of the steel bar to be cut is input;

[0017] Design a multi-table associated database architecture to store the attribute information of the steel bars to be cut;

[0018] The attribute information of the steel bars to be cut stored in the multi-table associated database is preliminarily cleaned and standardized.

[0019] As a preferred solution of the intelligent steel bar optimization cutting method of the present invention, the multi-dimensional feature matrix is ​​constructed based on the pre-processed steel bar attribute information, including the following steps:

[0020] Extract the attribute information of all the steel bars to be cut from the multi-table associated database and export them as temporary files;

[0021] According to the characteristics of the steel bars to be cut, the attribute information of each steel bar to be cut is obtained, and the attribute dimension of the steel bars to be cut is clarified;

[0022] Based on the total number of steel bars to be cut and the attribute dimensions, create an empty matrix, set indexes for the rows of the empty matrix, and set labels for the columns;

[0023] The attribute data of the steel bars to be cut in the temporary file are read line by line and filled into the empty matrix for real-time verification to form a multi-dimensional feature matrix.

[0024] As a preferred solution of the intelligent steel bar optimization cutting method of the present invention, the similarity between the steel bars to be cut is measured according to the multidimensional feature matrix, and the initial candidate combination list is formed, which includes the following steps:

[0025] According to the constructed multidimensional feature matrix, all the combinations of steel bars to be cut are traversed, and the Euclidean distance is selected as the measure of the similarity between the steel bars to be cut. The expression is:

[0026] ;

[0027] in, Indicates Based on the steel bar attribute value and the Based on the similarity scores between the attribute values ​​of the steel bars to be cut, and Indicates the index of the steel bars to be cut. Indicates the attribute index of each steel bar to be cut. The dimension representing the properties of the steel bars to be cut. Indicates The weight factor of the properties of the steel bars to be cut, Indicates Waiting for the steel bar to be cut The attribute value of the steel bar to be cut. Indicates Waiting for the steel bar to be cut Property values ​​of the steel bars to be cut;

[0028] According to the actual construction requirements, clarify the required specifications of the steel bar combination to be cut;

[0029] From the calculated similarity scores of the steel bars to be cut, select the steel bars to be cut that meet the conditions according to the required specifications, and sort them from high to low according to the similarity scores;

[0030] The steel bar combinations to be cut are selected in sequence from the sorted steel bar combinations to form an initial candidate combination list.

[0031] As a preferred solution of the intelligent steel bar optimization cutting method of the present invention, wherein: according to the initial candidate combination list, optimizing the combination and generating the best combination solution includes the following steps:

[0032] Randomly select a certain number of steel bar combinations to be cut from the initial candidate combination list to form an initial population;

[0033] For each candidate combination, calculate the total length and remaining length of the steel bar combination to be cut;

[0034] According to the total length of the steel bar combination to be cut and the length of the remaining material, the fitness function is defined to evaluate the quality of each individual. The expression is:

[0035] ;

[0036] in, Indicates the fitness value of the steel bar combination to be cut. Indicates the code representation of the steel bar combination to be cut. Indicates the total length of the steel bar combination to be cut. Indicates the length of raw steel bars. A positive weight factor indicating the effect of adjusting the residual length on fitness, Indicates the length of the remaining material;

[0037] According to the fitness value, the roulette wheel selection method is used to perform crossover operation on the steel bar combinations to be cut in the initial population to generate new offspring, and mutation operation is performed on some of the steel bar combinations to be cut;

[0038] Repeat the selection, crossover and mutation operations until the fitness value no longer increases, and output the best combination solution.

[0039] As a preferred solution of the intelligent sieve steel bar optimization cutting method of the present invention, wherein:

[0040] Based on the best combination solution, an intelligent inventory forecasting model is constructed to predict the number of steel bars to be replenished, including the following steps:

[0041] Extract the attribute information of all used steel bars to be cut from the best combination scheme, define the endogenous and exogenous variables that affect the demand for steel bars, and propose preliminary causal hypothesis;

[0042] Use statistical methods to evaluate whether there are significant correlations and causal relationships between different variables, test whether the proposed causal hypothesis is valid, and integrate all verified causal relationships into a causal relationship map;

[0043] By calculating the centrality of each variable in the causal relationship graph in the network, we can find the variables in the core position for sensitivity analysis, identify the key factors affecting the demand for steel bars, define scenario assumptions, and adjust the corresponding key factor values;

[0044] According to the impact of the adjusted key factor values ​​on the demand for steel bars, combined with the best combination plan, an intelligent inventory forecasting model is constructed to predict the number of steel bars to be replenished in the future. The expression is:

[0045] ;

[0046] in, Indicates the prediction at time The number of steel bars to be cut that need to be added. represents the best combination solution index, represents the number of optimal combination solutions, Indicates The total length of the steel bars to be cut in the best combination scheme is Indicates The length of raw steel bars in the best combination scheme is The adjustment factor represents the influence of the change of residual material on the prediction result. Indicates The change of the remaining length of the best combination solution, represents the average residual length of all optimal combination solutions, Indicates The impact value of the key factors, represents the key factor index, Indicates the number of key factors.

[0047] As a preferred solution of the intelligent steel bar optimization cutting method of the present invention, the following steps are included: according to the prediction results, combined with the current inventory level and the safety inventory setting, the inventory plan is dynamically adjusted.

[0048] Obtain inventory records of all uncut steel bars from the inventory management system and set safety stock levels for each specification of uncut steel bars based on historical usage records;

[0049] According to the forecast results, combined with the current inventory level and the safety stock level setting, the actual number of steel bars to be replenished is calculated. The expression is:

[0050] ;

[0051] in, Indicates at time The actual number of steel bars to be cut that needs to be added. Indicates at time The current inventory level at Indicates the safety stock level;

[0052] Adjust purchase orders based on calculated actual replenishment needs;

[0053] when When , a new purchase request is generated and the purchase process is started; when When there is a shortage of inventory, there is no need to replenish it immediately, and the inventory level should be monitored continuously.

[0054] In a second aspect, the present invention provides an intelligent screening steel bar optimization feeding system, comprising:

[0055] The information collection module collects the attribute information of all the steel bars to be cut and performs pre-processing;

[0056] The feature matrix module constructs a multi-dimensional feature matrix based on the pre-processed attribute information of the steel bars to be cut;

[0057] The similarity assessment module measures the similarity between the steel bars to be cut according to the multi-dimensional feature matrix and forms an initial candidate combination list;

[0058] The optimization combination module performs optimization combination based on the initial candidate combination list to generate the best combination solution;

[0059] The inventory forecasting module builds an intelligent inventory forecasting model based on the best combination solution to predict the number of steel bars to be replenished;

[0060] The inventory adjustment module dynamically adjusts the inventory plan based on the forecast results, combined with the current inventory level and safety stock settings.

[0061] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent screening steel bar optimization cutting method as described in the first aspect of the present invention is implemented.

[0062] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the intelligent screening steel bar optimization cutting method as described in the first aspect of the present invention is implemented.

[0063] The beneficial effects of the present invention are as follows: by comprehensively pre-processing all the steel bars to be cut and assigning them a unique RFID identification, the accuracy and traceability of the information of each steel bar to be cut is ensured; based on the constructed multi-dimensional feature matrix, the similarity between the steel bars to be cut is evaluated to form an initial candidate combination list, which effectively improves the quality of the combination scheme of the steel bars to be cut and reduces unnecessary waste generation; the best combination scheme is screened out by optimization means such as genetic algorithms, further improving resource utilization; combined with the intelligent inventory prediction model and the dynamic adjustment mechanism, the present invention can accurately predict the demand for steel bars to be cut in a certain period of time in the future, and flexibly adjust the procurement plan according to the actual situation, thereby reducing the inventory holding cost and avoiding the risks caused by insufficient or excessive supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0065] Figure 1 This is a flow chart of the intelligent steel bar optimization cutting method in Example 1.

[0066] Figure 2 This is a module diagram of the intelligent steel bar screening optimization feeding system in Example 1. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0069] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0070] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an intelligent screening steel bar optimization cutting method, comprising the following steps:

[0071] S1. Collect the attribute information of all the steel bars to be cut and perform pre-processing.

[0072] S1.1. Attach a passive RFID tag containing a unique serial number to each steel bar to be cut.

[0073] Specifically, the selection of tags should be high-frequency (HF) or ultra-high-frequency (UHF) passive RFID tags with good reading and writing performance and long working distance; the installation of tags should be in the production stage of the steel bars to be cut, that is, before the steel bars to be cut leave the factory, an RFID tag should be fixed on one end of each steel bar to be cut. The tag can be embedded in the protective layer of the steel bars to be cut, or fastened to the surface of the steel bars to be cut by a special fixing device to ensure that the tag is not easy to fall off and does not affect the normal use of the steel bars to be cut.

[0074] The unique serial number is created using a method based on a combination of timestamp and random number generator, ensuring that each tag is unique, which not only helps to track the life cycle of each steel bar to be cut, but also prevents security risks caused by tag duplication.

[0075] It should be noted that through the unique serial number, each steel bar to be cut can be tracked throughout the entire supply chain, from the manufacturer to the construction site, ensuring the reliable source of the material.

[0076] S1.2. When the steel bar to be cut passes through the reader area, the UID on the tag is automatically read, and the attribute information including the length, diameter, grade strength and bending radius of the steel bar to be cut is input; a multi-table associated database architecture is designed to store the attribute information of the steel bar to be cut.

[0077] Specifically, the database architecture with multiple table associations follows the third normal form (3NF) to design the database table structure, creating multiple interrelated tables, such as "basic information table of steel bars to be cut", "attribute value table", "history record table", etc. The primary key-foreign key relationship between the tables is used to achieve efficient query, and the fields and their types in each table are clarified, such as the steel bar ID (integer), UID (string), length (floating point), diameter (floating point), grade strength (integer), bending radius (floating point), etc. At the same time, reserved extension fields are used to add new attribute information in the future; indexes are established for frequently queried fields, such as UID, steel bar ID to be cut, etc., to speed up the query speed; composite indexes are created for combined query conditions to improve retrieval efficiency.

[0078] S1.3. Perform preliminary cleaning and standardization on the attribute information of the steel bars to be cut stored in the multi-table associated database.

[0079] Specifically, preliminary cleaning includes removing duplicate records, correcting erroneous values, filling missing values, etc. For abnormal data points, they can be screened and marked; standardization is to convert data from different sources or formats into a standard format, such as unit unification (all lengths are converted to meters, diameters are converted to millimeters, etc.). In addition, some continuous variables (such as length and diameter) are discretized and grouped according to specific intervals to facilitate subsequent analysis.

[0080] S2. Construct a multi-dimensional feature matrix based on the pre-processed attribute information of the steel bars to be cut.

[0081] S2.1. Extract the attribute information of all the steel bars to be cut from the multi-table associated database and export it as a temporary file; according to the characteristics of the steel bars to be cut, obtain the attribute information of each steel bar to be cut, and clarify the attribute dimensions of the steel bars to be cut.

[0082] Specifically, the physical and mechanical properties of the steel bars to be cut are comprehensively analyzed to determine which properties are most important for the optimal combination. In addition to the basic length, diameter, grade strength and bending radius, other factors that may affect the combination effect can also be considered, such as surface treatment methods (galvanizing, painting, etc.) and chemical composition ratios (such as carbon content, silicon content, etc.). According to actual construction needs and technical specifications, expert scoring methods, hierarchical analysis methods (AHP) or other quantitative methods are used to determine which properties are most important for the optimal combination. For example, if the project is located in a corrosive environment, the importance of the surface treatment method may increase; assign a reasonable weight factor to each selected attribute, which can be automatically calculated through expert review and historical data analysis. The weight setting needs to consider the balance between the importance of the attribute and the complexity of the calculation. The attribute dimension refers to the attribute type of the steel bars to be cut, that is, how many attributes there are, including but not limited to the length, diameter, grade strength and bending radius of the steel bars to be cut. For different steel bars to be cut, the same attribute dimension has different attribute dimension values; the order of their arrangement in the multidimensional feature matrix is ​​determined according to the number of steel bars to be cut corresponding to the attribute dimension values ​​of different attribute dimensions. Usually, the attributes of the steel bars to be cut with a larger number are placed in the front row, which can improve the calculation efficiency to a certain extent and reduce unnecessary calculation overhead.

[0083] It should be noted that through careful attribute selection and weight setting, it is ensured that the feature vector of each steel bar to be cut can fully and accurately reflect its characteristics, thereby improving the accuracy of similarity evaluation; reasonable attribute arrangement helps to accelerate matrix operations, reduce algorithm complexity, and improve overall processing speed.

[0084] S2.2. Based on the total number of steel bars to be cut and the attribute dimensions, create an empty matrix and set a unique index for the empty matrix row, corresponding to the UID of each steel bar to be cut, add a descriptive label to each column to identify the specific attribute name; read the attribute data of the steel bars to be cut in the temporary file row by row and fill it into the empty matrix for real-time verification to form a multi-dimensional feature matrix.

[0085] Specifically, the empty matrix can be selected as a sparse matrix or a dense matrix according to the actual situation. The sparse matrix is ​​suitable for the case where most values ​​are zero and can save memory space; while the dense matrix is ​​suitable for the case where the data distribution is relatively uniform.

[0086] It should be noted that a unique index is set for each row of the empty matrix, corresponding to the UID of each steel bar to be cut; a descriptive label is added to each column to identify the specific attribute name in order to make the empty matrix structure more intuitive and easy to understand, and to facilitate subsequent analysis and interpretation.

[0087] S3. According to the multi-dimensional feature matrix, the similarities between the steel bars to be cut are measured to form an initial candidate combination list.

[0088] S3.1. Based on the constructed multidimensional feature matrix, all combinations of steel bars to be cut are traversed, and the Euclidean distance is selected as the measure of the similarity between the steel bars to be cut. The expression is:

[0089] ;

[0090] in, Indicates Based on the steel bar attribute value and the Based on the similarity scores between the attribute values ​​of the steel bars to be cut, and Indicates the index of the steel bars to be cut. Indicates the attribute index of each steel bar to be cut. The dimension representing the properties of the steel bars to be cut. Indicates The weight factor of the properties of the steel bars to be cut, Indicates Waiting for the steel bar to be cut The attribute value of the steel bar to be cut. Indicates Waiting for the steel bar to be cut The attribute values ​​of the steel bars to be cut.

[0091] It should be noted that the Euclidean distance is selected as the standard for measuring the similarity between the steel bars to be cut because the Euclidean distance can intuitively reflect the straight-line distance between two points in a multidimensional space, and is suitable for the comparison of the steel bars to be cut based on geometric and mechanical properties in the present invention; the Euclidean distance provides an intuitive and mathematically rigorous method to quantify the similarity between the steel bars to be cut, thereby ensuring the accuracy of the evaluation results.

[0092] S3.2. According to the actual construction requirements, clarify the required specifications of the steel bar combination to be cut.

[0093] Specifically, the definition of required specifications is to determine the specific specifications of the steel bar combination to be cut in combination with the drawings and technical requirements of the specific construction project, including but not limited to the total length, diameter range, strength grade, etc. of the steel bars to be cut. In addition, special conditions of the construction site, such as the height and span of the building, must also be considered.

[0094] S3.3. From the calculated similarity scores of the steel bars to be cut, select the steel bars to be cut that meet the conditions according to the required specifications, and sort them from high to low according to the similarity scores.

[0095] It should be noted that the selected steel bar combinations to be cut are sorted again according to the similarity scores from high to low. For the same similarity scores, they can be further sorted according to other secondary criteria (such as price, supply speed, etc.). This not only ensures that the selected steel bar combinations to be cut have high similarity, but also improves the combination efficiency and engineering quality. The sorting mechanism helps to quickly locate the best combination, simplify the decision-making process, and save time.

[0096] S3.4. Select the steel bar combinations to be cut from the sorted steel bar combinations to be cut in turn to form an initial candidate combination list.

[0097] Specifically, each time a selection is made, it is necessary to check whether the newly added steel bar combination to be cut will conflict with the existing combination (such as reusing the same steel bar to be cut). If there is a conflict, the current steel bar combination to be cut is skipped and the next one is selected. As the selection process progresses, the similarity scores and ranking positions of the remaining steel bar combinations to be cut are continuously updated. If a new steel bar combination to be cut is found to be more suitable for the current combination, it can be replaced to maintain the quality of the candidate list.

[0098] S4. Optimize the combination based on the initial candidate combination list to generate the best combination solution.

[0099] S4.1. Randomly select a certain number of steel bar combinations to be cut from the initial candidate combination list to form an initial population; for each candidate combination, calculate the total length and remaining length of the steel bar combination to be cut.

[0100] Specifically, the initial population is determined by setting the initial population size based on the number of steel bars to be cut and the availability of computing resources. For example, if computing resources are limited, a smaller initial population can be selected to save computing time; conversely, if resources are sufficient, the initial population size can be appropriately increased to explore more possibilities, and a random number generator is used to extract a certain number of combinations from the unsorted list of initial candidate combinations as members of the initial population; for each selected candidate combination, its total length (i.e., the sum of the lengths of all steel bars in the combination) and the remaining length (the length of the raw steel bar minus the total length of the combination) are calculated. It should be noted here that when the total length is greater than or equal to the length of the raw steel bar, the combination is feasible; otherwise, the combination should be considered infeasible and removed from the initial population.

[0101] S4.2. According to the total length of the steel bar combination to be cut and the length of the remaining material, define the fitness function to evaluate the quality of each individual, and the expression is:

[0102] ;

[0103] in, Indicates the fitness value of the steel bar combination to be cut. Indicates the code representation of the steel bar combination to be cut. Indicates the total length of the steel bar combination to be cut. Indicates the length of raw steel bars. A positive weight factor indicating the effect of adjusting the residual length on fitness, Indicates the remaining material length.

[0104] Specifically, the purpose of the fitness function is to quantify the quality or fitness of the combination of steel bars to be cut, which can reflect the relationship between the total length of the combination and the length of the raw steel bars, as well as the impact of the remaining length on the combination efficiency.

[0105] It should be noted that by carefully defining the various components of the fitness function, we can not only accurately evaluate the quality of each steel bar combination to be cut, but also provide a solid foundation for subsequent optimization, which helps to achieve effective use of materials, reduce costs, improve engineering efficiency, and be more in line with the principles of sustainable development.

[0106] S4.3. According to the fitness value, the roulette wheel selection method is used to perform a crossover operation on the combinations of steel bars to be cut in the initial population to generate new offspring, and a mutation operation is performed on some of the combinations of steel bars to be cut; the selection, crossover and mutation operations are repeated until the fitness value no longer increases, and the best combination solution is output.

[0107] Specifically, the roulette selection method constructs a probability distribution model based on the fitness value of each combination of steel bars to be cut, which is similar to the mechanism of "roulette". The individuals with higher fitness values ​​have a greater probability of being selected, but individuals with low fitness also have a certain chance of being selected to maintain the diversity of the population.

[0108] Crossover operation: For a selected pair of steel bar combinations to be cut, randomly select a crossover point and exchange their coding parts after the crossover point. For example, if the codes of the two steel bar combinations to be cut are "0101" and "1010" respectively, the second position can be selected as the crossover point to generate new offspring "0110" and "1001". The crossover operation helps to introduce new gene combinations and improve search efficiency.

[0109] Mutation operation: Mutate the newly generated offspring, that is, randomly change the values ​​of certain coding bits with a certain probability. The mutation probability is generally low (such as 0.01) to avoid destroying the excellent combination that has been formed. The mutation operation can prevent the algorithm from falling into the local optimal solution and increase the global search capability.

[0110] It should be noted that the roulette wheel selection method ensures that individuals with high fitness have more opportunities to reproduce, while also retaining a certain proportion of individuals with low fitness, promoting the genetic diversity and stability of the population; the crossover operation introduces new gene combinations, improves the coverage of the search space, and increases the possibility of finding the global optimal solution; the mutation operation maintains the diversity of the population, prevents the algorithm from converging prematurely, and ensures long-term exploration capabilities and innovation potential.

[0111] S5. Based on the best combination plan, build an intelligent inventory forecasting model to predict the number of steel bars that need to be replenished.

[0112] S5.1. Extract the attribute information of all used steel bars to be cut from the best combination solution.

[0113] Specifically, the attribute information includes but is not limited to UID, length, diameter, strength grade, bending radius, etc.; ensure that the extracted information can accurately match the information such as the incoming quantity, outgoing quantity and current inventory level in the historical inventory records, so as to calculate the change in the remaining length and other related indicators.

[0114] S5.2. Based on the extracted attribute information of all used steel bars to be cut, define the endogenous and exogenous variables that affect the demand for steel bars.

[0115] Specifically, endogenous variables include but are not limited to project progress, construction phase, changes in the length of remaining materials, etc., which are affected by internal management and construction arrangements; exogenous variables include but are not limited to weather conditions, market price fluctuations, changes in policies and regulations, etc., which come from the outside and are not directly controlled by internal management.

[0116] S5.3. Propose preliminary causal hypotheses based on the endogenous and exogenous variables that affect the demand for steel.

[0117] Specifically, the preliminary causal hypothesis includes but is not limited to the following:

[0118] The impact of exogenous variables on exogenous variables: For example, weather changes may affect market prices.

[0119] The impact of exogenous variables on endogenous variables: For example, an increase in market prices may lead to a decrease in steel bar purchases.

[0120] The impact of endogenous variables on endogenous variables: For example, faster project progress may increase the demand for steel bars in the short term.

[0121] Effect of endogenous variables on exogenous variables: This relationship is less common but may exist in some cases, such as the start of a large-scale construction project which may affect supply and prices in the local market.

[0122] S5.4. Use statistical methods to assess whether there are significant correlations and causal relationships between different variables, and to test whether the proposed causal relationship hypothesis is valid.

[0123] Specifically, statistical methods include regression analysis, path analysis or structural equation modeling, Granger causality test and instrumental variable method.

[0124] For simple linear relationships, regression analysis can be used to assess the impact of the independent variable on the dependent variable.

[0125] If there are complex causal chains, consider using path analysis or structural equation modeling (SEM).

[0126] For time series data, Granger causality test can be applied.

[0127] If endogeneity is suspected, try using instrumental variables (IV).

[0128] S5.5. According to the test results, the preliminary causal relationship hypothesis is adjusted, insignificant relationships are removed, and new potential causal paths are added, and all verified causal relationships are integrated into a causal relationship map; by calculating the centrality of each variable in the causal relationship map in the network, the variables in the core position are found; sensitivity analysis is performed on the variables in the core position, simulating the response of other variables when the variables in the core position are changed, and identifying the key factors affecting the demand for steel bars; based on the identified key factors affecting the demand for steel bars, scenario assumptions are defined, and for each defined scenario, the corresponding key factor values ​​are adjusted; according to the impact of the adjusted key factor values ​​on the demand for steel bars, combined with the best combination plan, an intelligent inventory forecasting model is constructed to predict the number of steel bars to be replenished in the future, and the expression is:

[0129] ;

[0130] in, Indicates the prediction at time The number of steel bars to be cut that need to be added. represents the best combination solution index, represents the number of optimal combination solutions, Indicates The total length of the steel bars to be cut in the best combination scheme is Indicates The length of raw steel bars in the best combination scheme is The adjustment factor represents the influence of the change of residual material on the prediction result. Indicates The change of the remaining length of the best combination solution, represents the average residual length of all optimal combination solutions, Indicates The impact value of the key factors, represents the key factor index, Indicates the number of key factors.

[0131] Specifically, centrality includes degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality.

[0132] Degree centrality is the simplest centrality indicator, measuring the number of direct connections between nodes; betweenness centrality measures the importance of a node as a bridge between other nodes, that is, how many shortest paths pass through the node; closeness centrality measures the inverse of the average distance from a node to all other nodes, reflecting the accessibility of the node in the network; eigenvector centrality considers not only the number of connections of the node itself, but also the importance of its neighboring nodes; for steel demand forecasting, betweenness centrality may be particularly important because it reflects the bridge role of the variable in the network, and the expression is:

[0133] ;

[0134] in, Representation Node The betweenness centrality of Represents a slave node To Node The number of shortest paths, Represents a slave node To Node The shortest path through the node The number of paths.

[0135] It should be noted that the identified key factors are important inputs for future scenario simulations, making forecasts more targeted and practical. Through scenario simulations, we can understand in advance the changing trends in steel bar demand under different circumstances, help decision makers formulate response strategies, and make accurate forecasts of steel bar demand in the future, thereby optimizing inventory management and improving supply chain efficiency.

[0136] S6. Dynamically adjust inventory plans based on forecast results, combined with current inventory levels and safety stock settings.

[0137] S6.1. Obtain inventory records of all uncut steel bars from the inventory management system and set safety stock levels for each specification of uncut steel bars based on historical usage records.

[0138] Specifically, the usage records of steel bars to be cut over the past period of time are collected, their usage frequency, periodic changes and emergency demand situations are analyzed, the demand patterns and fluctuation trends of steel bars to be cut of different specifications are identified, and the safety stock level is set according to experience to ensure that the demand is met with a certain probability.

[0139] S6.2. According to the forecast results, combined with the current inventory level and the safety stock level setting, the actual number of steel bars to be replenished is calculated. The expression is:

[0140] ;

[0141] in, Indicates at time The actual number of steel bars to be cut that needs to be added. Indicates at time The current inventory level at Indicates the safety stock level;

[0142] Adjust purchase orders based on calculated actual replenishment needs;

[0143] when When , a new purchase request is generated and the purchase process is started; when When there is a shortage of inventory, there is no need to replenish it immediately, and the inventory level should be monitored continuously.

[0144] It should be noted that the urgency and importance of actual replenishment needs are determined and different order priorities are set based on the urgency of demand (according to the construction schedule, some steel bar specifications may be urgently needed in the short term, while other specifications can be obtained in a longer time frame), project criticality (some steel bar specifications may be used in the most critical parts of the project or in locations where structural safety is critical, so they are more important), substitution possibilities (if a certain steel bar specification cannot be in place in time, are there other specifications that can be temporarily replaced without affecting the progress and quality of the project) and supply chain stability (considering the supplier's delivery cycle, reliability and market supply). For steel bar specifications that need to be replenished urgently, they can be marked as high-priority orders to speed up approval and execution. When adjusting purchase orders, the most economical procurement plan should be selected by comprehensively considering factors such as procurement cost, transportation cost, and warehousing cost. The overall cost can be reduced through bulk procurement and centralized distribution.

[0145] This embodiment also provides an intelligent screening steel bar optimization feeding system, including:

[0146] The information collection module collects the attribute information of all the steel bars to be cut and performs preprocessing; the feature matrix module constructs a multidimensional feature matrix based on the preprocessed attribute information of the steel bars to be cut; the similarity evaluation module measures the similarity between the steel bars to be cut according to the multidimensional feature matrix to form an initial candidate combination list; the optimization combination module performs optimization combination based on the initial candidate combination list to generate the best combination plan; the inventory forecasting module builds an intelligent inventory forecasting model based on the best combination plan to predict the number of steel bars to be cut that need to be replenished; the inventory adjustment module dynamically adjusts the inventory plan according to the forecast results, combined with the current inventory level and safety stock settings.

[0147] This embodiment also provides a computer device, which is suitable for the case of an intelligent screening steel bar optimization cutting method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent screening steel bar optimization cutting method proposed in the above embodiment.

[0148] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0149] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the method for optimizing the cutting of steel bars for intelligent screening is implemented as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0150] In summary, the present invention ensures the accuracy and traceability of the information of each steel bar to be cut by comprehensively preprocessing all the steel bars to be cut and assigning a unique RFID tag; based on the constructed multi-dimensional feature matrix, the similarity between the steel bars to be cut is evaluated to form an initial candidate combination list, which effectively improves the quality of the combination scheme of the steel bars to be cut and reduces unnecessary waste generation; the best combination scheme is screened out by optimization means such as genetic algorithms, further improving resource utilization; combined with the intelligent inventory forecasting model and the dynamic adjustment mechanism, the present invention can accurately predict the demand for steel bars to be cut in the future, and flexibly adjust the procurement plan according to the actual situation, thereby reducing the inventory holding cost and avoiding the risks caused by insufficient or excessive supply.

[0151] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent steel bar optimization feeding method, characterized in that: include, Collect the attribute information of all the steel bars to be cut and perform pre-processing; Based on the pre-processed attribute information of the steel bars to be cut, a multi-dimensional feature matrix is ​​constructed; According to the multi-dimensional feature matrix, the similarities between the steel bars to be cut are measured to form an initial candidate combination list; Based on the initial candidate combination list, optimize the combination and generate the best combination solution; Based on the best combination plan, an intelligent inventory forecasting model is built to predict the number of steel bars to be replenished; Dynamically adjust inventory plans based on forecast results, combined with current inventory levels and safety stock settings; Based on the best combination solution, an intelligent inventory forecasting model is built to predict the number of steel bars to be replenished. The following steps are included: Extract the attribute information of all used steel bars to be cut from the best combination scheme, define the endogenous and exogenous variables that affect the demand for steel bars, and propose preliminary causal hypothesis; Use statistical methods to evaluate whether there are significant correlations and causal relationships between different variables, test whether the proposed causal hypothesis is valid, and integrate all verified causal relationships into a causal relationship map; By calculating the centrality of each variable in the causal relationship graph in the network, we can find the variables in the core position for sensitivity analysis, identify the key factors affecting the demand for steel bars, define scenario assumptions, and adjust the corresponding key factor values; According to the impact of the adjusted key factor values ​​on the demand for steel bars, combined with the best combination plan, an intelligent inventory forecasting model is constructed to predict the number of steel bars to be replenished in the future. The expression is: ； in, Indicates the prediction at time The number of steel bars to be cut that need to be added. represents the best combination solution index, represents the number of optimal combination solutions, Indicates The total length of the steel bars to be cut in the best combination scheme is Indicates The length of raw steel bars in the best combination scheme is The adjustment factor represents the influence of the change of residual material on the prediction result. Indicates The change of the remaining length of the best combination solution, represents the average residual length of all optimal combination solutions, Indicates The impact value of the key factors, represents the key factor index, Indicates the number of key factors; Based on the forecast results, combined with the current inventory level and safety stock setting, the dynamic adjustment of inventory plan includes the following steps: Obtain inventory records of all uncut steel bars from the inventory management system and set safety stock levels for each specification of uncut steel bars based on historical usage records; According to the forecast results, combined with the current inventory level and the safety stock level setting, the actual number of steel bars to be replenished is calculated. The expression is: ； in, Indicates at time The actual number of steel bars to be cut that needs to be added. Indicates at time The current inventory level at Indicates the safety stock level; Adjust the purchase order based on the calculated actual replenishment needs; When , a new purchase request is generated and the purchase process is started; when When the inventory is sufficient, no replenishment is needed and the inventory level is continuously monitored.

2. The intelligent sieve steel bar optimization cutting method according to claim 1, characterized in that: Collecting the attribute information of all the steel bars to be cut and preprocessing them includes the following steps: Attach a passive RFID tag containing a unique serial number to each steel bar to be cut; When the steel bar passes through the reader area, the UID on the tag is automatically read and the attribute information including the length, diameter, grade strength and bending radius of the steel bar to be cut is input; Design a multi-table associated database architecture to store the attribute information of the steel bars to be cut; The attribute information of the steel bars to be cut stored in the multi-table associated database is preliminarily cleaned and standardized.

3. The intelligent sieve steel bar optimization cutting method according to claim 2, characterized in that: Based on the preprocessed steel bar attribute information, a multidimensional feature matrix is ​​constructed The following steps are included: Extract the attribute information of all the steel bars to be cut from the multi-table associated database and export them as temporary files; According to the characteristics of the steel bars to be cut, the attribute information of each steel bar to be cut is obtained, and the attribute dimension of the steel bars to be cut is clarified; Based on the total number of steel bars to be cut and the attribute dimensions, create an empty matrix, set indexes for the rows of the empty matrix, and set labels for the columns; The attribute data of the steel bars to be cut in the temporary file are read line by line and filled into the empty matrix for real-time verification to form a multi-dimensional feature matrix.

4. The intelligent sieve steel bar optimization cutting method according to claim 3 is characterized in that: According to the multidimensional feature matrix, the similarity between the steel bars to be cut is measured, and the initial candidate combination list is formed, which includes the following steps: According to the constructed multidimensional feature matrix, all the combinations of steel bars to be cut are traversed, and the Euclidean distance is selected as the measure of the similarity between the steel bars to be cut. The expression is: ； in, Indicates Based on the steel bar attribute value and the Based on the similarity scores between the attribute values ​​of the steel bars to be cut, and Indicates the index of the steel bars to be cut. Indicates the attribute index of each steel bar to be cut. The dimension representing the properties of the steel bars to be cut. Indicates The weight factor of the properties of the steel bars to be cut, Indicates Waiting for the steel bar to be cut The attribute value of the steel bar to be cut. Indicates Waiting for the steel bar to be cut reinforcement property values; According to the actual construction requirements, clarify the required specifications of the steel bar combination to be cut; From the calculated similarity scores of the steel bars to be cut, select the steel bars to be cut that meet the conditions according to the required specifications, and sort them from high to low according to the similarity scores; Steel bar combinations are selected in sequence from the sorted steel bar combinations to form an initial candidate combination list.

5. The intelligent sieve steel bar optimization cutting method according to claim 4, characterized in that: Based on the initial candidate combination list, the optimization combination is performed to generate the best combination solution, including the following steps: Randomly select a certain number of steel bar combinations to be cut from the initial candidate combination list to form an initial population; For each candidate combination, calculate the total length and remaining length of the steel bar combination to be cut; According to the total length of the steel bar combination to be cut and the length of the remaining material, the fitness function is defined to evaluate the quality of each individual. The expression is: ； in, Indicates the fitness value of the steel bar combination to be cut. Indicates the code representation of the steel bar combination to be cut. Indicates the total length of the steel bar combination to be cut. Indicates the length of raw steel bars. A positive weight factor indicating the effect of adjusting the residual length on fitness, Indicates the length of the remaining material; According to the fitness value, the roulette wheel selection method is used to perform crossover operation on the steel bar combinations to be cut in the initial population to generate new offspring, and mutation operation is performed on some of the steel bar combinations to be cut; Repeat the selection, crossover and mutation operations, and when the fitness value no longer increases, output the best combination solution.

6. An intelligent steel bar optimization feeding system, based on the intelligent steel bar optimization feeding method according to any one of claims 1 to 5, characterized in that: include, The information collection module collects the attribute information of all the steel bars to be cut and performs pre-processing; The feature matrix module constructs a multi-dimensional feature matrix based on the pre-processed attribute information of the steel bars to be cut; The similarity assessment module measures the similarity between the steel bars to be cut according to the multi-dimensional feature matrix and forms an initial candidate combination list; The optimization combination module performs optimization combination based on the initial candidate combination list to generate the best combination solution; The inventory forecasting module builds an intelligent inventory forecasting model based on the best combination solution to predict the number of steel bars to be replenished; The inventory adjustment module dynamically adjusts the inventory plan based on the forecast results, combined with the current inventory level and safety stock settings.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent screening steel bar optimization cutting method described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent screening steel bar optimization cutting method according to any one of claims 1 to 5 are implemented.

Images